[PATCH v10 19/61] target/riscv: vector integer divide instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 33 +++ target/riscv/insn32.decode | 8 +++ target/riscv/insn_trans/trans_rvv.inc.c | 10 target/riscv/vector_helper.c| 74 + 4 files changed, 125 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index c2de0d29ba..e14979e452 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -568,3 +568,36 @@ DEF_HELPER_6(vmulhsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmulhsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmulhsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmulhsu_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vdivu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdivu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdivu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdivu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdiv_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdiv_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdiv_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdiv_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vremu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vremu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vremu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vremu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrem_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrem_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrem_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrem_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdivu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdivu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdivu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdivu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdiv_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdiv_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdiv_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdiv_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vremu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vremu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vremu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vremu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrem_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrem_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrem_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrem_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 6b29aad4d2..cf58764308 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -373,6 +373,14 @@ vmulhu_vv 100100 . . . 010 . 1010111 @r_vm vmulhu_vx 100100 . . . 110 . 1010111 @r_vm vmulhsu_vv 100110 . . . 010 . 1010111 @r_vm vmulhsu_vx 100110 . . . 110 . 1010111 @r_vm +vdivu_vv10 . . . 010 . 1010111 @r_vm +vdivu_vx10 . . . 110 . 1010111 @r_vm +vdiv_vv 11 . . . 010 . 1010111 @r_vm +vdiv_vx 11 . . . 110 . 1010111 @r_vm +vremu_vv100010 . . . 010 . 1010111 @r_vm +vremu_vx100010 . . . 110 . 1010111 @r_vm +vrem_vv 100011 . . . 010 . 1010111 @r_vm +vrem_vx 100011 . . . 110 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index de5b8b7df6..4b4312fa99 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1581,3 +1581,13 @@ GEN_OPIVX_GVEC_TRANS(vmul_vx, muls) GEN_OPIVX_TRANS(vmulh_vx, opivx_check) GEN_OPIVX_TRANS(vmulhu_vx, opivx_check) GEN_OPIVX_TRANS(vmulhsu_vx, opivx_check) + +/* Vector Integer Divide Instructions */ +GEN_OPIVV_TRANS(vdivu_vv, opivv_check) +GEN_OPIVV_TRANS(vdiv_vv, opivv_check) +GEN_OPIVV_TRANS(vremu_vv, opivv_check) +GEN_OPIVV_TRANS(vrem_vv, opivv_check) +GEN_OPIVX_TRANS(vdivu_vx, opivx_check) +GEN_OPIVX_TRANS(vdiv_vx, opivx_check) +GEN_OPIVX_TRANS(vremu_vx, opivx_check) +GEN_OPIVX_TRANS(vrem_vx, opivx_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 3319370ae2..aee107a82e 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -1766,3 +1766,77 @@ GEN_VEXT_VX(vmulhsu_vx_b, 1, 1, clearb) GEN_VEXT_VX(vmulhsu_vx_h, 2, 2, clearh) GEN_VEXT_VX(vmulhsu_vx_w, 4, 4, clearl) GEN_VEXT_VX(vmulhsu_vx_d, 8, 8, clearq) + +/* Vector Integer Divide Instructions */ +#define DO_DIVU(N
[PATCH v10 18/61] target/riscv: vector single-width integer multiply instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Alistair Francis Reviewed-by: Richard Henderson --- target/riscv/helper.h | 33 + target/riscv/insn32.decode | 8 ++ target/riscv/insn_trans/trans_rvv.inc.c | 10 ++ target/riscv/vector_helper.c| 163 4 files changed, 214 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 9c576e1220..c2de0d29ba 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -535,3 +535,36 @@ DEF_HELPER_6(vmax_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmax_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmax_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmax_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vmul_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmul_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulh_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulh_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulh_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulh_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmul_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmul_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmul_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmul_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulh_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulh_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulh_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulh_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 3d8986c74d..6b29aad4d2 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -365,6 +365,14 @@ vmaxu_vv000110 . . . 000 . 1010111 @r_vm vmaxu_vx000110 . . . 100 . 1010111 @r_vm vmax_vv 000111 . . . 000 . 1010111 @r_vm vmax_vx 000111 . . . 100 . 1010111 @r_vm +vmul_vv 100101 . . . 010 . 1010111 @r_vm +vmul_vx 100101 . . . 110 . 1010111 @r_vm +vmulh_vv100111 . . . 010 . 1010111 @r_vm +vmulh_vx100111 . . . 110 . 1010111 @r_vm +vmulhu_vv 100100 . . . 010 . 1010111 @r_vm +vmulhu_vx 100100 . . . 110 . 1010111 @r_vm +vmulhsu_vv 100110 . . . 010 . 1010111 @r_vm +vmulhsu_vx 100110 . . . 110 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index cbcb40e682..de5b8b7df6 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1571,3 +1571,13 @@ GEN_OPIVX_TRANS(vminu_vx, opivx_check) GEN_OPIVX_TRANS(vmin_vx, opivx_check) GEN_OPIVX_TRANS(vmaxu_vx, opivx_check) GEN_OPIVX_TRANS(vmax_vx, opivx_check) + +/* Vector Single-Width Integer Multiply Instructions */ +GEN_OPIVV_GVEC_TRANS(vmul_vv, mul) +GEN_OPIVV_TRANS(vmulh_vv, opivv_check) +GEN_OPIVV_TRANS(vmulhu_vv, opivv_check) +GEN_OPIVV_TRANS(vmulhsu_vv, opivv_check) +GEN_OPIVX_GVEC_TRANS(vmul_vx, muls) +GEN_OPIVX_TRANS(vmulh_vx, opivx_check) +GEN_OPIVX_TRANS(vmulhu_vx, opivx_check) +GEN_OPIVX_TRANS(vmulhsu_vx, opivx_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index cb41daa3ac..3319370ae2 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -859,6 +859,10 @@ GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w, clearl) #define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t #define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
[PATCH v10 17/61] target/riscv: vector integer min/max instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 33 target/riscv/insn32.decode | 8 +++ target/riscv/insn_trans/trans_rvv.inc.c | 10 target/riscv/vector_helper.c| 71 + 4 files changed, 122 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 2bcb6c7889..9c576e1220 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -502,3 +502,36 @@ DEF_HELPER_6(vmsgt_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmsgt_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmsgt_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmsgt_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vminu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vminu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vminu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vminu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmin_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmin_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmin_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmin_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmaxu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmaxu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmaxu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmaxu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmax_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmax_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmax_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmax_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vminu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vminu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vminu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vminu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmin_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmin_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmin_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmin_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmaxu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmaxu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmaxu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmaxu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmax_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmax_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmax_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmax_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 5d022ff414..3d8986c74d 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -357,6 +357,14 @@ vmsgtu_vx 00 . . . 100 . 1010111 @r_vm vmsgtu_vi 00 . . . 011 . 1010111 @r_vm vmsgt_vx01 . . . 100 . 1010111 @r_vm vmsgt_vi01 . . . 011 . 1010111 @r_vm +vminu_vv000100 . . . 000 . 1010111 @r_vm +vminu_vx000100 . . . 100 . 1010111 @r_vm +vmin_vv 000101 . . . 000 . 1010111 @r_vm +vmin_vx 000101 . . . 100 . 1010111 @r_vm +vmaxu_vv000110 . . . 000 . 1010111 @r_vm +vmaxu_vx000110 . . . 100 . 1010111 @r_vm +vmax_vv 000111 . . . 000 . 1010111 @r_vm +vmax_vx 000111 . . . 100 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index 8fa3d5ecb0..cbcb40e682 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1561,3 +1561,13 @@ GEN_OPIVI_TRANS(vmsleu_vi, 1, vmsleu_vx, opivx_cmp_check) GEN_OPIVI_TRANS(vmsle_vi, 0, vmsle_vx, opivx_cmp_check) GEN_OPIVI_TRANS(vmsgtu_vi, 1, vmsgtu_vx, opivx_cmp_check) GEN_OPIVI_TRANS(vmsgt_vi, 0, vmsgt_vx, opivx_cmp_check) + +/* Vector Integer Min/Max Instructions */ +GEN_OPIVV_GVEC_TRANS(vminu_vv, umin) +GEN_OPIVV_GVEC_TRANS(vmin_vv, smin) +GEN_OPIVV_GVEC_TRANS(vmaxu_vv, umax) +GEN_OPIVV_GVEC_TRANS(vmax_vv, smax) +GEN_OPIVX_TRANS(vminu_vx, opivx_check) +GEN_OPIVX_TRANS(vmin_vx, opivx_check) +GEN_OPIVX_TRANS(vmaxu_vx, opivx_check) +GEN_OPIVX_TRANS(vmax_vx, opivx_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 07e474781c..cb41daa3ac 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -855,6 +855,10 @@ GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w, clearl) #define OP_SSS_H int16_t, int16_t, int16_t, int16_t, int16_t #define OP_SSS_W int32_t, int32_t, int32_t
[PATCH v10 16/61] target/riscv: vector integer comparison instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 57 +++ target/riscv/insn32.decode | 20 target/riscv/insn_trans/trans_rvv.inc.c | 46 + target/riscv/vector_helper.c| 123 4 files changed, 246 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 1ec2202814..2bcb6c7889 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -445,3 +445,60 @@ DEF_HELPER_6(vnsrl_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnsra_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnsra_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnsra_vx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vmseq_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmseq_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmseq_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmseq_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsne_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsne_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsne_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsne_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsltu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsltu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsltu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsltu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmslt_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmslt_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmslt_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmslt_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsleu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsleu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsleu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsleu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsle_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsle_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsle_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsle_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmseq_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmseq_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmseq_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmseq_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsne_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsne_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsne_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsne_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsltu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsltu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsltu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsltu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmslt_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmslt_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmslt_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmslt_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsleu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsleu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsleu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsleu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsle_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsle_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsle_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsle_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgtu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgtu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgtu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgtu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgt_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgt_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgt_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgt_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 435415f9f9..5d022ff414 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -337,6 +337,26 @@ vnsrl_vi101100 . . . 011 . 1010111 @r_vm vnsra_vv101101 . . . 000 . 1010111 @r_vm vnsra_vx101101 . . . 100 . 1010111 @r_vm vnsra_vi101101 . . . 011 . 1010111 @r_vm +vmseq_vv011000 . . . 000 . 1010111 @r_vm +vmseq_vx011000 . . . 100 . 1010111 @r_vm +vmseq_vi011000 . . . 011 . 1010111 @r_vm +vmsne_vv011001 . . . 000 . 1010111 @r_vm +vmsne_vx011001 . . . 100 . 1010111 @r_vm
[PATCH v10 15/61] target/riscv: vector narrowing integer right shift instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 13
target/riscv/insn32.decode | 6 ++
target/riscv/insn_trans/trans_rvv.inc.c | 90 +
target/riscv/vector_helper.c| 14
4 files changed, 123 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 6805bf7dbd..1ec2202814 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -432,3 +432,16 @@ DEF_HELPER_6(vsra_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsra_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vnsrl_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnsrl_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnsrl_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnsra_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnsra_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnsra_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnsrl_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnsrl_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnsrl_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnsra_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnsra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnsra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index e5334230df..435415f9f9 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -331,6 +331,12 @@ vsrl_vi 101000 . . . 011 . 1010111
@r_vm
vsra_vv 101001 . . . 000 . 1010111 @r_vm
vsra_vx 101001 . . . 100 . 1010111 @r_vm
vsra_vi 101001 . . . 011 . 1010111 @r_vm
+vnsrl_vv101100 . . . 000 . 1010111 @r_vm
+vnsrl_vx101100 . . . 100 . 1010111 @r_vm
+vnsrl_vi101100 . . . 011 . 1010111 @r_vm
+vnsra_vv101101 . . . 000 . 1010111 @r_vm
+vnsra_vx101101 . . . 100 . 1010111 @r_vm
+vnsra_vi101101 . . . 011 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 8ea7c437ee..87f9ee7f6c 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1425,3 +1425,93 @@ GEN_OPIVX_GVEC_SHIFT_TRANS(vsra_vx, sars)
GEN_OPIVI_GVEC_TRANS(vsll_vi, 1, vsll_vx, shli)
GEN_OPIVI_GVEC_TRANS(vsrl_vi, 1, vsrl_vx, shri)
GEN_OPIVI_GVEC_TRANS(vsra_vi, 1, vsra_vx, sari)
+
+/* Vector Narrowing Integer Right Shift Instructions */
+static bool opivv_narrow_check(DisasContext *s, arg_rmrr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, false) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs2, true) &&
+vext_check_reg(s, a->rs1, false) &&
+vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs2,
+2 << s->lmul) &&
+(s->lmul < 0x3) && (s->sew < 0x3));
+}
+
+/* OPIVV with NARROW */
+#define GEN_OPIVV_NARROW_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+if (opivv_narrow_check(s, a)) {\
+uint32_t data = 0; \
+static gen_helper_gvec_4_ptr * const fns[3] = {\
+gen_helper_##NAME##_b, \
+gen_helper_##NAME##_h, \
+gen_helper_##NAME##_w, \
+}; \
+TCGLabel *over = gen_new_label(); \
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ \
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \
+data = FIELD_DP32(data, VDATA, VM, a->vm); \
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
+ vreg_ofs(s, a->rs1),\
+ vreg_ofs(s, a->rs2), cpu_env, 0,\
+ s->v
[PATCH v10 14/61] target/riscv: vector single-width bit shift instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 25
target/riscv/insn32.decode | 9 +++
target/riscv/insn_trans/trans_rvv.inc.c | 52
target/riscv/vector_helper.c| 79 +
4 files changed, 165 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index f8b1c8a800..6805bf7dbd 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -407,3 +407,28 @@ DEF_HELPER_6(vxor_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vxor_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vxor_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vxor_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vsll_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsll_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsll_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsll_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsrl_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsrl_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsrl_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsrl_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsra_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsra_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsra_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsra_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsll_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsll_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsll_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsll_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsrl_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsrl_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsrl_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsrl_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsra_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsra_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 34d05a5917..e5334230df 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -322,6 +322,15 @@ vor_vi 001010 . . . 011 . 1010111
@r_vm
vxor_vv 001011 . . . 000 . 1010111 @r_vm
vxor_vx 001011 . . . 100 . 1010111 @r_vm
vxor_vi 001011 . . . 011 . 1010111 @r_vm
+vsll_vv 100101 . . . 000 . 1010111 @r_vm
+vsll_vx 100101 . . . 100 . 1010111 @r_vm
+vsll_vi 100101 . . . 011 . 1010111 @r_vm
+vsrl_vv 101000 . . . 000 . 1010111 @r_vm
+vsrl_vx 101000 . . . 100 . 1010111 @r_vm
+vsrl_vi 101000 . . . 011 . 1010111 @r_vm
+vsra_vv 101001 . . . 000 . 1010111 @r_vm
+vsra_vx 101001 . . . 100 . 1010111 @r_vm
+vsra_vi 101001 . . . 011 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 35c92986a6..8ea7c437ee 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1373,3 +1373,55 @@ GEN_OPIVX_GVEC_TRANS(vxor_vx, xors)
GEN_OPIVI_GVEC_TRANS(vand_vi, 0, vand_vx, andi)
GEN_OPIVI_GVEC_TRANS(vor_vi, 0, vor_vx, ori)
GEN_OPIVI_GVEC_TRANS(vxor_vi, 0, vxor_vx, xori)
+
+/* Vector Single-Width Bit Shift Instructions */
+GEN_OPIVV_GVEC_TRANS(vsll_vv, shlv)
+GEN_OPIVV_GVEC_TRANS(vsrl_vv, shrv)
+GEN_OPIVV_GVEC_TRANS(vsra_vv, sarv)
+
+typedef void GVecGen2sFn32(unsigned, uint32_t, uint32_t, TCGv_i32,
+ uint32_t, uint32_t);
+
+static inline bool
+do_opivx_gvec_shift(DisasContext *s, arg_rmrr *a, GVecGen2sFn32 *gvec_fn,
+gen_helper_opivx *fn)
+{
+if (!opivx_check(s, a)) {
+return false;
+}
+
+if (a->vm && s->vl_eq_vlmax) {
+TCGv_i32 src1 = tcg_temp_new_i32();
+TCGv tmp = tcg_temp_new();
+
+gen_get_gpr(tmp, a->rs1);
+tcg_gen_trunc_tl_i32(src1, tmp);
+tcg_gen_extract_i32(src1, src1, 0, s->sew + 3);
+gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
+src1, MAXSZ(s), MAXSZ(s));
+
+tcg_temp_free_i32(src1);
+tcg_temp_free(tmp);
+return true;
+}
+return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s);
+}
+
+#define GEN_OPIVX_GVEC_SHIFT_TRANS(NAME, SUF) \
+static bo
[PATCH v10 13/61] target/riscv: vector bitwise logical instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 25 target/riscv/insn32.decode | 9 + target/riscv/insn_trans/trans_rvv.inc.c | 11 ++ target/riscv/vector_helper.c| 51 + 4 files changed, 96 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 67a2e64c4a..f8b1c8a800 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -382,3 +382,28 @@ DEF_HELPER_6(vmsbc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmsbc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmsbc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmsbc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vand_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vand_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vand_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vand_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vor_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vor_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vor_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vor_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vxor_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vxor_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vxor_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vxor_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vand_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vand_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vand_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vand_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vor_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vor_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vor_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vor_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vxor_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vxor_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vxor_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vxor_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index be63e900c6..34d05a5917 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -313,6 +313,15 @@ vsbc_vvm010010 1 . . 000 . 1010111 @r_vm_1 vsbc_vxm010010 1 . . 100 . 1010111 @r_vm_1 vmsbc_vvm 010011 1 . . 000 . 1010111 @r_vm_1 vmsbc_vxm 010011 1 . . 100 . 1010111 @r_vm_1 +vand_vv 001001 . . . 000 . 1010111 @r_vm +vand_vx 001001 . . . 100 . 1010111 @r_vm +vand_vi 001001 . . . 011 . 1010111 @r_vm +vor_vv 001010 . . . 000 . 1010111 @r_vm +vor_vx 001010 . . . 100 . 1010111 @r_vm +vor_vi 001010 . . . 011 . 1010111 @r_vm +vxor_vv 001011 . . . 000 . 1010111 @r_vm +vxor_vx 001011 . . . 100 . 1010111 @r_vm +vxor_vi 001011 . . . 011 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index 6fe2f071e6..35c92986a6 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1362,3 +1362,14 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ GEN_OPIVI_TRANS(vadc_vim, 0, vadc_vxm, opivx_vadc_check) GEN_OPIVI_TRANS(vmadc_vim, 0, vmadc_vxm, opivx_vmadc_check) + +/* Vector Bitwise Logical Instructions */ +GEN_OPIVV_GVEC_TRANS(vand_vv, and) +GEN_OPIVV_GVEC_TRANS(vor_vv, or) +GEN_OPIVV_GVEC_TRANS(vxor_vv, xor) +GEN_OPIVX_GVEC_TRANS(vand_vx, ands) +GEN_OPIVX_GVEC_TRANS(vor_vx, ors) +GEN_OPIVX_GVEC_TRANS(vxor_vx, xors) +GEN_OPIVI_GVEC_TRANS(vand_vi, 0, vand_vx, andi) +GEN_OPIVI_GVEC_TRANS(vor_vi, 0, vor_vx, ori) +GEN_OPIVI_GVEC_TRANS(vxor_vi, 0, vxor_vx, xori) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index ad746175bd..6c53dc5796 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -1265,3 +1265,54 @@ GEN_VEXT_VMADC_VXM(vmsbc_vxm_b, uint8_t, H1, DO_MSBC) GEN_VEXT_VMADC_VXM(vmsbc_vxm_h, uint16_t, H2, DO_MSBC) GEN_VEXT_VMADC_VXM(vmsbc_vxm_w, uint32_t, H4, DO_MSBC) GEN_VEXT_VMADC_VXM(vmsbc_vxm_d, uint64_t, H8, DO_MSBC) + +/* Vector Bitwise Logical Instructions */ +RVVCALL(OPIVV2, vand_vv_b, OP_SSS_B, H1, H1, H1, DO_AND) +RVVCALL(OPIVV2, vand_vv_h, OP_SSS_H, H2, H2, H2, DO_AND) +RVVCALL(OPIVV2, vand_vv_w, OP_SSS_W, H4, H4, H4, DO_AND) +RVVCALL(OPIVV2, vand_vv_d, OP_SSS_D, H8, H8, H8, DO_AND) +RVVCALL(OPIVV2, vor_vv_b, OP_SSS_B, H1, H1, H1, DO_OR) +RVVCALL(OPIVV2, vor_vv_h
[PATCH v10 12/61] target/riscv: vector integer add-with-carry / subtract-with-borrow instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Alistair Francis Reviewed-by: Richard Henderson --- target/riscv/helper.h | 33 ++ target/riscv/insn32.decode | 11 ++ target/riscv/insn_trans/trans_rvv.inc.c | 113 +++ target/riscv/vector_helper.c| 137 4 files changed, 294 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index da6acc067b..67a2e64c4a 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -349,3 +349,36 @@ DEF_HELPER_6(vwadd_wx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vwsub_wx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vwsub_wx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vwsub_wx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vadc_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadc_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadc_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadc_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsbc_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsbc_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsbc_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsbc_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadc_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadc_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadc_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadc_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsbc_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsbc_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsbc_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsbc_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vadc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vadc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vadc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsbc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsbc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsbc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsbc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsbc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsbc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsbc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsbc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 6ec166d0ed..be63e900c6 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -70,6 +70,7 @@ @r2_nfvm ... ... vm:1 . . ... . ... %nf %rs1 %rd @r_nfvm ... ... vm:1 . . ... . ... %nf %rs2 %rs1 %rd @r_vm.. vm:1 . . ... . ... %rs2 %rs1 %rd +@r_vm_1 .. . . . ... . ... vm=1 %rs2 %rs1 %rd @r_wdvm . wd:1 vm:1 . . ... . ... %rs2 %rs1 %rd @r2_zimm . zimm:11 . ... . ... %rs1 %rd @@ -302,6 +303,16 @@ vwsubu_wv 110110 . . . 010 . 1010111 @r_vm vwsubu_wx 110110 . . . 110 . 1010111 @r_vm vwsub_wv110111 . . . 010 . 1010111 @r_vm vwsub_wx110111 . . . 110 . 1010111 @r_vm +vadc_vvm01 1 . . 000 . 1010111 @r_vm_1 +vadc_vxm01 1 . . 100 . 1010111 @r_vm_1 +vadc_vim01 1 . . 011 . 1010111 @r_vm_1 +vmadc_vvm 010001 1 . . 000 . 1010111 @r_vm_1 +vmadc_vxm 010001 1 . . 100 . 1010111 @r_vm_1 +vmadc_vim 010001 1 . . 011 . 1010111 @r_vm_1 +vsbc_vvm010010 1 . . 000 . 1010111 @r_vm_1 +vsbc_vxm010010 1 . . 100 . 1010111 @r_vm_1 +vmsbc_vvm 010011 1 . . 000 . 1010111 @r_vm_1 +vmsbc_vxm 010011 1 . . 100 . 1010111 @r_vm_1 vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index 7a14b64c3d..6fe2f071e6 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1249,3 +1249,116 @@ GEN_OPIWX_WIDEN_TRANS(vwaddu_wx) GEN_OPIWX_WIDEN_TRANS(vwadd_wx) GEN_OPIWX_WIDEN_TRANS(vwsubu_wx) GEN_OPIWX_WIDEN_TRANS(vwsub_wx) + +/* Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions */ +/* OPIVV without GVEC IR */ +#define GEN_OPIVV_TRANS(NAME, CHECK) \ +static bool trans_##NAME(DisasContext
[PATCH v10 11/61] target/riscv: vector widening integer add and subtract
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 49 +++ target/riscv/insn32.decode | 16 ++ target/riscv/insn_trans/trans_rvv.inc.c | 186 target/riscv/vector_helper.c| 111 ++ 4 files changed, 362 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 7660bec01f..da6acc067b 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -300,3 +300,52 @@ DEF_HELPER_FLAGS_4(vec_rsubs8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(vec_rsubs16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(vec_rsubs32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(vec_rsubs64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) + +DEF_HELPER_6(vwaddu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_wv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_wv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_wv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_wv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_wx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_wx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_wx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_wx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_wx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_wx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_wx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_wx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_wx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_wx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_wx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_wx_w, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index bb1e47a2be..6ec166d0ed 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -286,6 +286,22 @@ vsub_vv 10 . . . 000 . 1010111 @r_vm vsub_vx 10 . . . 100 . 1010111 @r_vm vrsub_vx11 . . . 100 . 1010111 @r_vm vrsub_vi11 . . . 011 . 1010111 @r_vm +vwaddu_vv 11 . . . 010 . 1010111 @r_vm +vwaddu_vx 11 . . . 110 . 1010111 @r_vm +vwadd_vv110001 . . . 010 . 1010111 @r_vm +vwadd_vx110001 . . . 110 . 1010111 @r_vm +vwsubu_vv 110010 . . . 010 . 1010111 @r_vm +vwsubu_vx 110010 . . . 110 . 1010111 @r_vm +vwsub_vv110011 . . . 010 . 1010111 @r_vm +vwsub_vx110011 . . . 110 . 1010111 @r_vm +vwaddu_wv 110100 . . . 010 . 1010111 @r_vm +vwaddu_wx 110100 . . . 110 . 1010111 @r_vm +vwadd_wv110101 . . . 010 . 1010111 @r_vm +vwadd_wx110101 . . . 110
[PATCH v10 10/61] target/riscv: vector single-width integer add and subtract
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 25 ++
target/riscv/insn32.decode | 10 +
target/riscv/insn_trans/trans_rvv.inc.c | 291
target/riscv/vector_helper.c| 183 +++
4 files changed, 509 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index c5f43b5b64..7660bec01f 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -275,3 +275,28 @@ DEF_HELPER_6(vamominw_v_w, void, ptr, ptr, tl, ptr, env,
i32)
DEF_HELPER_6(vamomaxw_v_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vamominuw_v_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vamomaxuw_v_w, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsub_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vadd_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vadd_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vadd_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vadd_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrsub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrsub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrsub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrsub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_FLAGS_4(vec_rsubs8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vec_rsubs16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vec_rsubs32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vec_rsubs64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 625914c85f..bb1e47a2be 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -44,6 +44,7 @@
imm rd
shamt rs1 rd
aq rl rs2 rs1 rd
+ vm rd rs1 rs2
vm wd rd rs1 rs2
vm rd rs1 nf
vm rd rs1 rs2 nf
@@ -68,6 +69,7 @@
@r2 ... . . ... . ... %rs1 %rd
@r2_nfvm ... ... vm:1 . . ... . ... %nf %rs1 %rd
@r_nfvm ... ... vm:1 . . ... . ... %nf %rs2 %rs1 %rd
+@r_vm.. vm:1 . . ... . ... %rs2 %rs1 %rd
@r_wdvm . wd:1 vm:1 . . ... . ... %rs2 %rs1 %rd
@r2_zimm . zimm:11 . ... . ... %rs1 %rd
@@ -277,5 +279,13 @@ vamominuw_v 11000 . . . . 110 . 010
@r_wdvm
vamomaxuw_v 11100 . . . . 110 . 010 @r_wdvm
# *** new major opcode OP-V ***
+vadd_vv 00 . . . 000 . 1010111 @r_vm
+vadd_vx 00 . . . 100 . 1010111 @r_vm
+vadd_vi 00 . . . 011 . 1010111 @r_vm
+vsub_vv 10 . . . 000 . 1010111 @r_vm
+vsub_vx 10 . . . 100 . 1010111 @r_vm
+vrsub_vx11 . . . 100 . 1010111 @r_vm
+vrsub_vi11 . . . 011 . 1010111 @r_vm
+
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index a551139207..79b6cd9b4a 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -772,3 +772,294 @@ GEN_VEXT_TRANS(vamomaxd_v, 15, rwdvm, amo_op, amo_check)
GEN_VEXT_TRANS(vamominud_v, 16, rwdvm, amo_op, amo_check)
GEN_VEXT_TRANS(vamomaxud_v, 17, rwdvm, amo_op, amo_check)
#endif
+
+/*
+ *** Vector Integer Arithmetic Instructions
+ */
+#define MAXSZ(s) (s->vlen >> (3 - s->lmul))
+
+static bool opivv_check(DisasContext *s, arg_rmrr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, false) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs2, false) &&
+vext_check_reg(s, a->rs1, false));
+}
+
+typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t,
+uint32_t, uint32_t, uint32_t);
+
+static inline bool
+do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
+ gen_helper_gvec_4_ptr *fn)
+{
+TCGLabel *over = gen_new_la
[PATCH v10 09/61] target/riscv: add vector amo operations
Vector AMOs operate as if aq and rl bits were zero on each element with regard to ordering relative to other instructions in the same hart. Vector AMOs provide no ordering guarantee between element operations in the same vector AMO instruction Signed-off-by: LIU Zhiwei Reviewed-by: Alistair Francis Reviewed-by: Richard Henderson --- target/riscv/helper.h | 29 + target/riscv/insn32-64.decode | 11 ++ target/riscv/insn32.decode | 13 +++ target/riscv/insn_trans/trans_rvv.inc.c | 138 ++ target/riscv/internals.h| 1 + target/riscv/vector_helper.c| 147 6 files changed, 339 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 5c97bc446e..c5f43b5b64 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -246,3 +246,32 @@ DEF_HELPER_5(vlhuff_v_w, void, ptr, ptr, tl, env, i32) DEF_HELPER_5(vlhuff_v_d, void, ptr, ptr, tl, env, i32) DEF_HELPER_5(vlwuff_v_w, void, ptr, ptr, tl, env, i32) DEF_HELPER_5(vlwuff_v_d, void, ptr, ptr, tl, env, i32) +#ifdef TARGET_RISCV64 +DEF_HELPER_6(vamoswapw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoswapd_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoaddw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoaddd_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoxorw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoxord_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoandw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoandd_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoorw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoord_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomind_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxd_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominuw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominud_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxuw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxud_v_d, void, ptr, ptr, tl, ptr, env, i32) +#endif +DEF_HELPER_6(vamoswapw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoaddw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoxorw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoandw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoorw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominuw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxuw_v_w, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32-64.decode b/target/riscv/insn32-64.decode index 380bf791bc..86153d93fa 100644 --- a/target/riscv/insn32-64.decode +++ b/target/riscv/insn32-64.decode @@ -57,6 +57,17 @@ amomax_d 10100 . . . . 011 . 010 @atom_st amominu_d 11000 . . . . 011 . 010 @atom_st amomaxu_d 11100 . . . . 011 . 010 @atom_st +#*** Vector AMO operations (in addition to Zvamo) *** +vamoswapd_v 1 . . . . 111 . 010 @r_wdvm +vamoaddd_v 0 . . . . 111 . 010 @r_wdvm +vamoxord_v 00100 . . . . 111 . 010 @r_wdvm +vamoandd_v 01100 . . . . 111 . 010 @r_wdvm +vamoord_v 01000 . . . . 111 . 010 @r_wdvm +vamomind_v 1 . . . . 111 . 010 @r_wdvm +vamomaxd_v 10100 . . . . 111 . 010 @r_wdvm +vamominud_v 11000 . . . . 111 . 010 @r_wdvm +vamomaxud_v 11100 . . . . 111 . 010 @r_wdvm + # *** RV64F Standard Extension (in addition to RV32F) *** fcvt_l_s 110 00010 . ... . 1010011 @r2_rm fcvt_lu_s 110 00011 . ... . 1010011 @r2_rm diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 7146aec22a..625914c85f 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -44,6 +44,7 @@ imm rd shamt rs1 rd aq rl rs2 rs1 rd + vm wd rd rs1 rs2 vm rd rs1 nf vm rd rs1 rs2 nf @@ -67,6 +68,7 @@ @r2 ... . . ... . ... %rs1 %rd @r2_nfvm ... ... vm:1 . . ... . ... %nf %rs1 %rd @r_nfvm ... ... vm:1 . . ... . ... %nf %rs2 %rs1 %rd +@r_wdvm . wd:1 vm:1 . . ... . ... %rs2 %rs1 %rd @r2_zimm . zimm:11 . ... . ... %rs1 %rd @hfence_gvma ... . . ... . ... %rs2 %rs1 @@ -263,6 +265,17 @@ vsxh_v ... -11 . . . 101 . 0100111 @r_nfvm vsxw_v ... -11 . . . 110 . 0100111 @r_nfvm vsxe_v ... -11 . . . 111 . 0100111 @r_nfvm
[PATCH v10 08/61] target/riscv: add fault-only-first unit stride load
The unit-stride fault-only-fault load instructions are used to
vectorize loops with data-dependent exit conditions(while loops).
These instructions execute as a regular load except that they
will only take a trap on element 0.
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 22 +
target/riscv/insn32.decode | 7 ++
target/riscv/insn_trans/trans_rvv.inc.c | 73
target/riscv/vector_helper.c| 110
4 files changed, 212 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index f3650f736e..5c97bc446e 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -224,3 +224,25 @@ DEF_HELPER_6(vsxe_v_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsxe_v_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsxe_v_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsxe_v_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_5(vlbff_v_b, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbff_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbff_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlhff_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlhff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlhff_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlwff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlwff_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vleff_v_b, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vleff_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vleff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vleff_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbuff_v_b, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbuff_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbuff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbuff_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlhuff_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlhuff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlhuff_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlwuff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlwuff_v_d, void, ptr, ptr, tl, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 287d52bcc9..7146aec22a 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -226,6 +226,13 @@ vle_v ... 000 . 0 . 111 . 111 @r2_nfvm
vlbu_v ... 000 . 0 . 000 . 111 @r2_nfvm
vlhu_v ... 000 . 0 . 101 . 111 @r2_nfvm
vlwu_v ... 000 . 0 . 110 . 111 @r2_nfvm
+vlbff_v... 100 . 1 . 000 . 111 @r2_nfvm
+vlhff_v... 100 . 1 . 101 . 111 @r2_nfvm
+vlwff_v... 100 . 1 . 110 . 111 @r2_nfvm
+vleff_v... 000 . 1 . 111 . 111 @r2_nfvm
+vlbuff_v ... 000 . 1 . 000 . 111 @r2_nfvm
+vlhuff_v ... 000 . 1 . 101 . 111 @r2_nfvm
+vlwuff_v ... 000 . 1 . 110 . 111 @r2_nfvm
vsb_v ... 000 . 0 . 000 . 0100111 @r2_nfvm
vsh_v ... 000 . 0 . 101 . 0100111 @r2_nfvm
vsw_v ... 000 . 0 . 110 . 0100111 @r2_nfvm
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index c3a79c5232..299b479ec1 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -561,3 +561,76 @@ GEN_VEXT_TRANS(vsxb_v, 0, rnfvm, st_index_op,
st_index_check)
GEN_VEXT_TRANS(vsxh_v, 1, rnfvm, st_index_op, st_index_check)
GEN_VEXT_TRANS(vsxw_v, 2, rnfvm, st_index_op, st_index_check)
GEN_VEXT_TRANS(vsxe_v, 3, rnfvm, st_index_op, st_index_check)
+
+/*
+ *** unit stride fault-only-first load
+ */
+static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data,
+ gen_helper_ldst_us *fn, DisasContext *s)
+{
+TCGv_ptr dest, mask;
+TCGv base;
+TCGv_i32 desc;
+
+TCGLabel *over = gen_new_label();
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+dest = tcg_temp_new_ptr();
+mask = tcg_temp_new_ptr();
+base = tcg_temp_new();
+desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
+
+gen_get_gpr(base, rs1);
+tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd));
+tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0));
+
+fn(dest, mask, base, cpu_env, desc);
+
+tcg_temp_free_ptr(dest);
+tcg_temp_free_ptr(mask);
+tcg_temp_free(base);
+tcg_temp_free_i32(desc);
+gen_set_label(over);
+return true;
+}
+
+static bool ldff_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq)
+{
+uint32_t data = 0;
+gen_helper_ldst_us *fn;
+static gen_helper_ldst_us * const fns[7][4] = {
+{ gen_helper_vlbff_v_b, gen_helper_vlbff_v_h,
+ gen_helper_vlbff_v_w, gen_helper_vlbff_v_d },
+{ NULL, gen_helper_vlhff_v_h,
+ gen_helper_vlhff_
[PATCH v10 07/61] target/riscv: add vector index load and store instructions
Vector indexed operations add the contents of each element of the vector offset operand specified by vs2 to the base effective address to give the effective address of each element. Signed-off-by: LIU Zhiwei Reviewed-by: Alistair Francis Reviewed-by: Richard Henderson --- target/riscv/helper.h | 35 +++ target/riscv/insn32.decode | 13 +++ target/riscv/insn_trans/trans_rvv.inc.c | 129 target/riscv/vector_helper.c| 116 + 4 files changed, 293 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index f03b3d52f5..f3650f736e 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -189,3 +189,38 @@ DEF_HELPER_6(vsse_v_b, void, ptr, ptr, tl, tl, env, i32) DEF_HELPER_6(vsse_v_h, void, ptr, ptr, tl, tl, env, i32) DEF_HELPER_6(vsse_v_w, void, ptr, ptr, tl, tl, env, i32) DEF_HELPER_6(vsse_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlxb_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxb_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxb_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxb_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxh_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxh_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxh_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxe_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxe_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxe_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxe_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxbu_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxbu_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxbu_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxbu_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxhu_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxhu_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxhu_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxwu_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxwu_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxb_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxb_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxb_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxb_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxh_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxh_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxh_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxe_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxe_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxe_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxe_v_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 58b95792e6..287d52bcc9 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -243,6 +243,19 @@ vssh_v ... 010 . . . 101 . 0100111 @r_nfvm vssw_v ... 010 . . . 110 . 0100111 @r_nfvm vsse_v ... 010 . . . 111 . 0100111 @r_nfvm +vlxb_v ... 111 . . . 000 . 111 @r_nfvm +vlxh_v ... 111 . . . 101 . 111 @r_nfvm +vlxw_v ... 111 . . . 110 . 111 @r_nfvm +vlxe_v ... 011 . . . 111 . 111 @r_nfvm +vlxbu_v... 011 . . . 000 . 111 @r_nfvm +vlxhu_v... 011 . . . 101 . 111 @r_nfvm +vlxwu_v... 011 . . . 110 . 111 @r_nfvm +# Vector ordered-indexed and unordered-indexed store insns. +vsxb_v ... -11 . . . 000 . 0100111 @r_nfvm +vsxh_v ... -11 . . . 101 . 0100111 @r_nfvm +vsxw_v ... -11 . . . 110 . 0100111 @r_nfvm +vsxe_v ... -11 . . . 111 . 0100111 @r_nfvm + # *** new major opcode OP-V *** vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index f9950ad5a0..c3a79c5232 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -432,3 +432,132 @@ GEN_VEXT_TRANS(vssb_v, 0, rnfvm, st_stride_op, st_stride_check) GEN_VEXT_TRANS(vssh_v, 1, rnfvm, st_stride_op, st_stride_check) GEN_VEXT_TRANS(vssw_v, 2, rnfvm, st_stride_op, st_stride_check) GEN_VEXT_TRANS(vsse_v, 3, rnfvm, st_stride_op, st_stride_check) + +/* + *** index load and store + */ +typedef void gen_helper_ldst_index(TCGv_ptr, TCGv_ptr, TCGv, + TCGv_ptr, TCGv_env, TCGv_i32); + +static bool ldst_index_trans
[PATCH v10 06/61] target/riscv: add vector stride load and store instructions
Vector strided operations access the first memory element at the base address, and then access subsequent elements at address increments given by the byte offset contained in the x register specified by rs2. Vector unit-stride operations access elements stored contiguously in memory starting from the base effective address. It can been seen as a special case of strided operations. Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 105 ++ target/riscv/insn32.decode | 32 ++ target/riscv/insn_trans/trans_rvv.inc.c | 355 target/riscv/internals.h| 5 + target/riscv/translate.c| 7 + target/riscv/vector_helper.c| 410 6 files changed, 914 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 8e81ff440b..f03b3d52f5 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -84,3 +84,108 @@ DEF_HELPER_1(hyp_tlb_flush, void, env) /* Vector functions */ DEF_HELPER_3(vsetvl, tl, env, tl, tl) +DEF_HELPER_5(vlb_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlw_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlw_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlw_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlw_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwu_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwu_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwu_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwu_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsw_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsw_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsw_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsw_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5
[PATCH v10 05/61] target/riscv: add an internals.h header
The internals.h keeps things that are not relevant to the actual architecture, only to the implementation, separate. Signed-off-by: LIU Zhiwei Reviewed-by: Alistair Francis Reviewed-by: Richard Henderson --- target/riscv/internals.h | 24 1 file changed, 24 insertions(+) create mode 100644 target/riscv/internals.h diff --git a/target/riscv/internals.h b/target/riscv/internals.h new file mode 100644 index 00..22a49af413 --- /dev/null +++ b/target/riscv/internals.h @@ -0,0 +1,24 @@ +/* + * QEMU RISC-V CPU -- internal functions and types + * + * Copyright (c) 2020 T-Head Semiconductor Co., Ltd. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef RISCV_CPU_INTERNALS_H +#define RISCV_CPU_INTERNALS_H + +#include "hw/registerfields.h" + +#endif -- 2.23.0
[PATCH v10 04/61] target/riscv: add vector configure instruction
vsetvl and vsetvli are two configure instructions for vl, vtype. TB flags
should update after configure instructions. The (ill, lmul, sew ) of vtype
and the bit of (VSTART == 0 && VL == VLMAX) will be placed within tb_flags.
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/Makefile.objs | 2 +-
target/riscv/cpu.h | 63 +---
target/riscv/helper.h | 3 +
target/riscv/insn32.decode | 5 ++
target/riscv/insn_trans/trans_rvv.inc.c | 79 +
target/riscv/translate.c| 17 +-
target/riscv/vector_helper.c| 53 +
7 files changed, 210 insertions(+), 12 deletions(-)
create mode 100644 target/riscv/insn_trans/trans_rvv.inc.c
create mode 100644 target/riscv/vector_helper.c
diff --git a/target/riscv/Makefile.objs b/target/riscv/Makefile.objs
index ff651f69f6..ff38df6219 100644
--- a/target/riscv/Makefile.objs
+++ b/target/riscv/Makefile.objs
@@ -1,4 +1,4 @@
-obj-y += translate.o op_helper.o cpu_helper.o cpu.o csr.o fpu_helper.o
gdbstub.o
+obj-y += translate.o op_helper.o cpu_helper.o cpu.o csr.o fpu_helper.o
vector_helper.o gdbstub.o
obj-$(CONFIG_SOFTMMU) += pmp.o
ifeq ($(CONFIG_SOFTMMU),y)
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index 302e0859a0..0ad51c6580 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -21,6 +21,7 @@
#define RISCV_CPU_H
#include "hw/core/cpu.h"
+#include "hw/registerfields.h"
#include "exec/cpu-defs.h"
#include "fpu/softfloat-types.h"
@@ -93,6 +94,12 @@ typedef struct CPURISCVState CPURISCVState;
#define RV_VLEN_MAX 512
+FIELD(VTYPE, VLMUL, 0, 2)
+FIELD(VTYPE, VSEW, 2, 3)
+FIELD(VTYPE, VEDIV, 5, 2)
+FIELD(VTYPE, RESERVED, 7, sizeof(target_ulong) * 8 - 9)
+FIELD(VTYPE, VILL, sizeof(target_ulong) * 8 - 2, 1)
+
struct CPURISCVState {
target_ulong gpr[32];
uint64_t fpr[32]; /* assume both F and D extensions */
@@ -352,19 +359,62 @@ void riscv_cpu_set_fflags(CPURISCVState *env,
target_ulong);
#define TB_FLAGS_MMU_MASK 3
#define TB_FLAGS_MSTATUS_FS MSTATUS_FS
+typedef CPURISCVState CPUArchState;
+typedef RISCVCPU ArchCPU;
+#include "exec/cpu-all.h"
+
+FIELD(TB_FLAGS, VL_EQ_VLMAX, 2, 1)
+FIELD(TB_FLAGS, LMUL, 3, 2)
+FIELD(TB_FLAGS, SEW, 5, 3)
+FIELD(TB_FLAGS, VILL, 8, 1)
+
+/*
+ * A simplification for VLMAX
+ * = (1 << LMUL) * VLEN / (8 * (1 << SEW))
+ * = (VLEN << LMUL) / (8 << SEW)
+ * = (VLEN << LMUL) >> (SEW + 3)
+ * = VLEN >> (SEW + 3 - LMUL)
+ */
+static inline uint32_t vext_get_vlmax(RISCVCPU *cpu, target_ulong vtype)
+{
+uint8_t sew, lmul;
+
+sew = FIELD_EX64(vtype, VTYPE, VSEW);
+lmul = FIELD_EX64(vtype, VTYPE, VLMUL);
+return cpu->cfg.vlen >> (sew + 3 - lmul);
+}
+
static inline void cpu_get_tb_cpu_state(CPURISCVState *env, target_ulong *pc,
-target_ulong *cs_base, uint32_t *flags)
+target_ulong *cs_base, uint32_t
*pflags)
{
+uint32_t flags = 0;
+
*pc = env->pc;
*cs_base = 0;
+
+if (riscv_has_ext(env, RVV)) {
+uint32_t vlmax = vext_get_vlmax(env_archcpu(env), env->vtype);
+bool vl_eq_vlmax = (env->vstart == 0) && (vlmax == env->vl);
+flags = FIELD_DP32(flags, TB_FLAGS, VILL,
+FIELD_EX64(env->vtype, VTYPE, VILL));
+flags = FIELD_DP32(flags, TB_FLAGS, SEW,
+FIELD_EX64(env->vtype, VTYPE, VSEW));
+flags = FIELD_DP32(flags, TB_FLAGS, LMUL,
+FIELD_EX64(env->vtype, VTYPE, VLMUL));
+flags = FIELD_DP32(flags, TB_FLAGS, VL_EQ_VLMAX, vl_eq_vlmax);
+} else {
+flags = FIELD_DP32(flags, TB_FLAGS, VILL, 1);
+}
+
#ifdef CONFIG_USER_ONLY
-*flags = TB_FLAGS_MSTATUS_FS;
+flags |= TB_FLAGS_MSTATUS_FS;
#else
-*flags = cpu_mmu_index(env, 0);
+flags |= cpu_mmu_index(env, 0);
if (riscv_cpu_fp_enabled(env)) {
-*flags |= env->mstatus & MSTATUS_FS;
+flags |= env->mstatus & MSTATUS_FS;
}
#endif
+*pflags = flags;
}
int riscv_csrrw(CPURISCVState *env, int csrno, target_ulong *ret_value,
@@ -405,9 +455,4 @@ void riscv_set_csr_ops(int csrno, riscv_csr_operations
*ops);
void riscv_cpu_register_gdb_regs_for_features(CPUState *cs);
-typedef CPURISCVState CPUArchState;
-typedef RISCVCPU ArchCPU;
-
-#include "exec/cpu-all.h"
-
#endif /* RISCV_CPU_H */
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index b36be978d5..8e81ff440b 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -81,3 +81,6 @@ DEF_HELPER_1(tlb_flush, void, env)
#ifndef CONFIG_USER_ONLY
DEF_HELPER_1(hyp_tlb_flush, void, env)
#endif
+
+/* Vector functions */
+DEF_HELPER_3(vsetvl, tl, env, tl, tl)
diff --git a/targ
[PATCH v10 03/61] target/riscv: support vector extension csr
The v0.7.1 specification does not define vector status within mstatus.
A future revision will define the privileged portion of the vector status.
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/cpu_bits.h | 15 +
target/riscv/csr.c | 75 -
2 files changed, 89 insertions(+), 1 deletion(-)
diff --git a/target/riscv/cpu_bits.h b/target/riscv/cpu_bits.h
index 7f64ee1174..8117e8b5a7 100644
--- a/target/riscv/cpu_bits.h
+++ b/target/riscv/cpu_bits.h
@@ -29,6 +29,14 @@
#define FSR_NXA (FPEXC_NX << FSR_AEXC_SHIFT)
#define FSR_AEXC(FSR_NVA | FSR_OFA | FSR_UFA | FSR_DZA | FSR_NXA)
+/* Vector Fixed-Point round model */
+#define FSR_VXRM_SHIFT 9
+#define FSR_VXRM(0x3 << FSR_VXRM_SHIFT)
+
+/* Vector Fixed-Point saturation flag */
+#define FSR_VXSAT_SHIFT 8
+#define FSR_VXSAT (0x1 << FSR_VXSAT_SHIFT)
+
/* Control and Status Registers */
/* User Trap Setup */
@@ -48,6 +56,13 @@
#define CSR_FRM 0x002
#define CSR_FCSR0x003
+/* User Vector CSRs */
+#define CSR_VSTART 0x008
+#define CSR_VXSAT 0x009
+#define CSR_VXRM0x00a
+#define CSR_VL 0xc20
+#define CSR_VTYPE 0xc21
+
/* User Timers and Counters */
#define CSR_CYCLE 0xc00
#define CSR_TIME0xc01
diff --git a/target/riscv/csr.c b/target/riscv/csr.c
index 383be0a955..ac01c835e1 100644
--- a/target/riscv/csr.c
+++ b/target/riscv/csr.c
@@ -46,6 +46,10 @@ void riscv_set_csr_ops(int csrno, riscv_csr_operations *ops)
static int fs(CPURISCVState *env, int csrno)
{
#if !defined(CONFIG_USER_ONLY)
+/* loose check condition for fcsr in vector extension */
+if ((csrno == CSR_FCSR) && (env->misa & RVV)) {
+return 0;
+}
if (!env->debugger && !riscv_cpu_fp_enabled(env)) {
return -1;
}
@@ -53,6 +57,14 @@ static int fs(CPURISCVState *env, int csrno)
return 0;
}
+static int vs(CPURISCVState *env, int csrno)
+{
+if (env->misa & RVV) {
+return 0;
+}
+return -1;
+}
+
static int ctr(CPURISCVState *env, int csrno)
{
#if !defined(CONFIG_USER_ONLY)
@@ -154,6 +166,10 @@ static int read_fcsr(CPURISCVState *env, int csrno,
target_ulong *val)
#endif
*val = (riscv_cpu_get_fflags(env) << FSR_AEXC_SHIFT)
| (env->frm << FSR_RD_SHIFT);
+if (vs(env, csrno) >= 0) {
+*val |= (env->vxrm << FSR_VXRM_SHIFT)
+| (env->vxsat << FSR_VXSAT_SHIFT);
+}
return 0;
}
@@ -166,10 +182,62 @@ static int write_fcsr(CPURISCVState *env, int csrno,
target_ulong val)
env->mstatus |= MSTATUS_FS;
#endif
env->frm = (val & FSR_RD) >> FSR_RD_SHIFT;
+if (vs(env, csrno) >= 0) {
+env->vxrm = (val & FSR_VXRM) >> FSR_VXRM_SHIFT;
+env->vxsat = (val & FSR_VXSAT) >> FSR_VXSAT_SHIFT;
+}
riscv_cpu_set_fflags(env, (val & FSR_AEXC) >> FSR_AEXC_SHIFT);
return 0;
}
+static int read_vtype(CPURISCVState *env, int csrno, target_ulong *val)
+{
+*val = env->vtype;
+return 0;
+}
+
+static int read_vl(CPURISCVState *env, int csrno, target_ulong *val)
+{
+*val = env->vl;
+return 0;
+}
+
+static int read_vxrm(CPURISCVState *env, int csrno, target_ulong *val)
+{
+*val = env->vxrm;
+return 0;
+}
+
+static int write_vxrm(CPURISCVState *env, int csrno, target_ulong val)
+{
+env->vxrm = val;
+return 0;
+}
+
+static int read_vxsat(CPURISCVState *env, int csrno, target_ulong *val)
+{
+*val = env->vxsat;
+return 0;
+}
+
+static int write_vxsat(CPURISCVState *env, int csrno, target_ulong val)
+{
+env->vxsat = val;
+return 0;
+}
+
+static int read_vstart(CPURISCVState *env, int csrno, target_ulong *val)
+{
+*val = env->vstart;
+return 0;
+}
+
+static int write_vstart(CPURISCVState *env, int csrno, target_ulong val)
+{
+env->vstart = val;
+return 0;
+}
+
/* User Timers and Counters */
static int read_instret(CPURISCVState *env, int csrno, target_ulong *val)
{
@@ -1183,7 +1251,12 @@ static riscv_csr_operations csr_ops[CSR_TABLE_SIZE] = {
[CSR_FFLAGS] = { fs, read_fflags, write_fflags },
[CSR_FRM] = { fs, read_frm, write_frm },
[CSR_FCSR] ={ fs, read_fcsr,write_fcsr},
-
+/* Vector CSRs */
+[CSR_VSTART] = { vs, read_vstart, write_vstart },
+[CSR_VXSAT] = { vs, read_vxsat, write_vxsat },
+[CSR_VXRM] ={ vs, read_vxrm,write_vxrm},
+[CSR_VL] = { vs, read_vl },
+[CSR_VTYPE] = { vs, read_vtype
[PATCH v10 02/61] target/riscv: implementation-defined constant parameters
vlen is the vector register length in bits.
elen is the max element size in bits.
vext_spec is the vector specification version, default value is v0.7.1.
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/cpu.c | 7 +++
target/riscv/cpu.h | 5 +
2 files changed, 12 insertions(+)
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index 391a0b9eec..d525cfb687 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -106,6 +106,11 @@ static void set_priv_version(CPURISCVState *env, int
priv_ver)
env->priv_ver = priv_ver;
}
+static void set_vext_version(CPURISCVState *env, int vext_ver)
+{
+env->vext_ver = vext_ver;
+}
+
static void set_feature(CPURISCVState *env, int feature)
{
env->features |= (1ULL << feature);
@@ -334,6 +339,7 @@ static void riscv_cpu_realize(DeviceState *dev, Error
**errp)
CPURISCVState *env = >env;
RISCVCPUClass *mcc = RISCV_CPU_GET_CLASS(dev);
int priv_version = PRIV_VERSION_1_11_0;
+int vext_version = VEXT_VERSION_0_07_1;
target_ulong target_misa = 0;
Error *local_err = NULL;
@@ -357,6 +363,7 @@ static void riscv_cpu_realize(DeviceState *dev, Error
**errp)
}
set_priv_version(env, priv_version);
+set_vext_version(env, vext_version);
if (cpu->cfg.mmu) {
set_feature(env, RISCV_FEATURE_MMU);
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index 0018a79fa3..302e0859a0 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -78,6 +78,8 @@ enum {
#define PRIV_VERSION_1_10_0 0x00011000
#define PRIV_VERSION_1_11_0 0x00011100
+#define VEXT_VERSION_0_07_1 0x0701
+
#define TRANSLATE_PMP_FAIL 2
#define TRANSLATE_FAIL 1
#define TRANSLATE_SUCCESS 0
@@ -113,6 +115,7 @@ struct CPURISCVState {
target_ulong guest_phys_fault_addr;
target_ulong priv_ver;
+target_ulong vext_ver;
target_ulong misa;
target_ulong misa_mask;
@@ -275,6 +278,8 @@ typedef struct RISCVCPU {
char *priv_spec;
char *user_spec;
+uint16_t vlen;
+uint16_t elen;
bool mmu;
bool pmp;
} cfg;
--
2.23.0
[PATCH v10 01/61] target/riscv: add vector extension field in CPURISCVState
The 32 vector registers will be viewed as a continuous memory block.
It avoids the convension between element index and (regno, offset).
Thus elements can be directly accessed by offset from the first vector
base address.
Signed-off-by: LIU Zhiwei
Acked-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/cpu.h | 12
target/riscv/translate.c | 3 ++-
2 files changed, 14 insertions(+), 1 deletion(-)
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index 80569f0d44..0018a79fa3 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -59,6 +59,7 @@
#define RVA RV('A')
#define RVF RV('F')
#define RVD RV('D')
+#define RVV RV('V')
#define RVC RV('C')
#define RVS RV('S')
#define RVU RV('U')
@@ -88,9 +89,20 @@ typedef struct CPURISCVState CPURISCVState;
#include "pmp.h"
+#define RV_VLEN_MAX 512
+
struct CPURISCVState {
target_ulong gpr[32];
uint64_t fpr[32]; /* assume both F and D extensions */
+
+/* vector coprocessor state. */
+uint64_t vreg[32 * RV_VLEN_MAX / 64] QEMU_ALIGNED(16);
+target_ulong vxrm;
+target_ulong vxsat;
+target_ulong vl;
+target_ulong vstart;
+target_ulong vtype;
+
target_ulong pc;
target_ulong load_res;
target_ulong load_val;
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index ce71ca7a92..b269f15920 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -32,7 +32,7 @@
#include "instmap.h"
/* global register indices */
-static TCGv cpu_gpr[32], cpu_pc;
+static TCGv cpu_gpr[32], cpu_pc, cpu_vl;
static TCGv_i64 cpu_fpr[32]; /* assume F and D extensions */
static TCGv load_res;
static TCGv load_val;
@@ -887,6 +887,7 @@ void riscv_translate_init(void)
}
cpu_pc = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, pc), "pc");
+cpu_vl = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, vl), "vl");
load_res = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, load_res),
"load_res");
load_val = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, load_val),
--
2.23.0
[PATCH v10 00/61] target/riscv: support vector extension v0.7.1
This patchset implements the vector extension for RISC-V on QEMU.
You can also find the patchset and all *test cases* in
my repo(https://github.com/romanheros/qemu.git branch:vector-upstream-v10).
All the test cases are in the directory qemu/tests/riscv/vector/. They are
riscv64 linux user mode programs.
You can test the patchset by the script qemu/tests/riscv/vector/runcase.sh.
Features:
* support specification
riscv-v-spec-0.7.1.(https://github.com/riscv/riscv-v-spec/releases/tag/0.7.1/)
* support basic vector extension.
* support Zvlsseg.
* support Zvamo.
* not support Zvediv as it is changing.
* SLEN always equals VLEN.
* element width support 8bit, 16bit, 32bit, 64bit.
Changelog:
v10
* rebase to https://github.com/alistair23/qemu/tree/riscv-to-apply.next.
* fix compile error in patch 57/61.
* fix review tag typo.
v9
* always set dynamic rounding mode for vector float insns.
* bug fix atomic implementation.
* bug fix first-only-fault.
* some small tidy up.
v8
* support different float rounding modes for vector instructions.
* use lastest released TCG GVEC DUP IR.
* set RV_VLEN_MAX to 256 bits, as GVEC IR uses simd_desc.
v7
* move vl == 0 check to translation time by add a global cpu_vl.
* implement vector element inline load and store function by TCG IR.
* based on vec_element_load(store), implement some permutation instructions.
* implement rsubs GVEC IR.
* fixup vsmul, vmfne, vfmerge, vslidedown.
* some other small bugs and indentation errors.
v6
* use gvec_dup Gvec IR to accellerate move and merge.
* a better way to implement fixed point instructions.
* a global check when vl == 0.
* limit some macros to only one inline function call.
* fixup sew error when use Gvec IR.
* fixup bugs for corner cases.
v5
* fixup a bug in tb flags.
v4
* no change
v3
* move check code from execution-time to translation-time
* use a continous memory block for vector register description.
* vector registers as direct fields in RISCVCPUState.
* support VLEN configure from qemu command line.
* support ELEN configure from qemu command line.
* support vector specification version configure from qemu command line.
* probe pages before real load or store access.
* use probe_page_check for no-fault operations in linux user mode.
* generation atomic exit exception when in parallel environment.
* fixup a lot of concrete bugs.
V2
* use float16_compare{_quiet}
* only use GETPC() in outer most helper
* add ctx.ext_v Property
LIU Zhiwei (61):
target/riscv: add vector extension field in CPURISCVState
target/riscv: implementation-defined constant parameters
target/riscv: support vector extension csr
target/riscv: add vector configure instruction
target/riscv: add an internals.h header
target/riscv: add vector stride load and store instructions
target/riscv: add vector index load and store instructions
target/riscv: add fault-only-first unit stride load
target/riscv: add vector amo operations
target/riscv: vector single-width integer add and subtract
target/riscv: vector widening integer add and subtract
target/riscv: vector integer add-with-carry / subtract-with-borrow
instructions
target/riscv: vector bitwise logical instructions
target/riscv: vector single-width bit shift instructions
target/riscv: vector narrowing integer right shift instructions
target/riscv: vector integer comparison instructions
target/riscv: vector integer min/max instructions
target/riscv: vector single-width integer multiply instructions
target/riscv: vector integer divide instructions
target/riscv: vector widening integer multiply instructions
target/riscv: vector single-width integer multiply-add instructions
target/riscv: vector widening integer multiply-add instructions
target/riscv: vector integer merge and move instructions
target/riscv: vector single-width saturating add and subtract
target/riscv: vector single-width averaging add and subtract
target/riscv: vector single-width fractional multiply with rounding
and saturation
target/riscv: vector widening saturating scaled multiply-add
target/riscv: vector single-width scaling shift instructions
target/riscv: vector narrowing fixed-point clip instructions
target/riscv: vector single-width floating-point add/subtract
instructions
target/riscv: vector widening floating-point add/subtract instructions
target/riscv: vector single-width floating-point multiply/divide
instructions
target/riscv: vector widening floating-point multiply
target/riscv: vector single-width floating-point fused multiply-add
instructions
target/riscv: vector widening floating-point fused multiply-add
instructions
target/riscv: vector floating-point square-root instruction
target/riscv: vector floating-point min/max instructions
target/riscv: vector floating-point sign-injection instructions
target/riscv: vector floating-point
[PATCH v10 37/61] target/riscv: vector floating-point min/max instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 13 target/riscv/insn32.decode | 4 target/riscv/insn_trans/trans_rvv.inc.c | 6 ++ target/riscv/vector_helper.c| 27 + 4 files changed, 50 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 8d44154ad2..a080f8358a 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -927,3 +927,16 @@ DEF_HELPER_6(vfwnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_5(vfsqrt_v_h, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfsqrt_v_w, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfsqrt_v_d, void, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vfmin_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmin_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmin_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmax_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmax_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmax_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmin_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmin_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmin_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmax_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmax_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmax_vf_d, void, ptr, ptr, i64, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 0d58c4c5e8..854ff9a38f 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -492,6 +492,10 @@ vfwmsac_vf 10 . . . 101 . 1010111 @r_vm vfwnmsac_vv 11 . . . 001 . 1010111 @r_vm vfwnmsac_vf 11 . . . 101 . 1010111 @r_vm vfsqrt_v100011 . . 0 001 . 1010111 @r2_vm +vfmin_vv000100 . . . 001 . 1010111 @r_vm +vfmin_vf000100 . . . 101 . 1010111 @r_vm +vfmax_vv000110 . . . 001 . 1010111 @r_vm +vfmax_vf000110 . . . 101 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index 35db704bbc..0c1e45123d 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -2132,3 +2132,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ } GEN_OPFV_TRANS(vfsqrt_v, opfv_check) + +/* Vector Floating-Point MIN/MAX Instructions */ +GEN_OPFVV_TRANS(vfmin_vv, opfvv_check) +GEN_OPFVV_TRANS(vfmax_vv, opfvv_check) +GEN_OPFVF_TRANS(vfmin_vf, opfvf_check) +GEN_OPFVF_TRANS(vfmax_vf, opfvf_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 7f527c95e0..82e570da4e 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -3817,3 +3817,30 @@ RVVCALL(OPFVV1, vfsqrt_v_d, OP_UU_D, H8, H8, float64_sqrt) GEN_VEXT_V_ENV(vfsqrt_v_h, 2, 2, clearh) GEN_VEXT_V_ENV(vfsqrt_v_w, 4, 4, clearl) GEN_VEXT_V_ENV(vfsqrt_v_d, 8, 8, clearq) + +/* Vector Floating-Point MIN/MAX Instructions */ +RVVCALL(OPFVV2, vfmin_vv_h, OP_UUU_H, H2, H2, H2, float16_minnum) +RVVCALL(OPFVV2, vfmin_vv_w, OP_UUU_W, H4, H4, H4, float32_minnum) +RVVCALL(OPFVV2, vfmin_vv_d, OP_UUU_D, H8, H8, H8, float64_minnum) +GEN_VEXT_VV_ENV(vfmin_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmin_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmin_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfmin_vf_h, OP_UUU_H, H2, H2, float16_minnum) +RVVCALL(OPFVF2, vfmin_vf_w, OP_UUU_W, H4, H4, float32_minnum) +RVVCALL(OPFVF2, vfmin_vf_d, OP_UUU_D, H8, H8, float64_minnum) +GEN_VEXT_VF(vfmin_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmin_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmin_vf_d, 8, 8, clearq) + +RVVCALL(OPFVV2, vfmax_vv_h, OP_UUU_H, H2, H2, H2, float16_maxnum) +RVVCALL(OPFVV2, vfmax_vv_w, OP_UUU_W, H4, H4, H4, float32_maxnum) +RVVCALL(OPFVV2, vfmax_vv_d, OP_UUU_D, H8, H8, H8, float64_maxnum) +GEN_VEXT_VV_ENV(vfmax_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmax_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmax_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfmax_vf_h, OP_UUU_H, H2, H2, float16_maxnum) +RVVCALL(OPFVF2, vfmax_vf_w, OP_UUU_W, H4, H4, float32_maxnum) +RVVCALL(OPFVF2, vfmax_vf_d, OP_UUU_D, H8, H8, float64_maxnum) +GEN_VEXT_VF(vfmax_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmax_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmax_vf_d, 8, 8, clearq) -- 2.23.0
[PATCH v10 36/61] target/riscv: vector floating-point square-root instruction
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 4 +++
target/riscv/insn32.decode | 3 ++
target/riscv/insn_trans/trans_rvv.inc.c | 43 +
target/riscv/vector_helper.c| 43 +
4 files changed, 93 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index b537030a11..8d44154ad2 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -923,3 +923,7 @@ DEF_HELPER_6(vfwmsac_vf_h, void, ptr, ptr, i64, ptr, env,
i32)
DEF_HELPER_6(vfwmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfwnmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfwnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_5(vfsqrt_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfsqrt_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfsqrt_v_d, void, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index c9d5078385..0d58c4c5e8 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -45,6 +45,7 @@
shamt rs1 rd
aq rl rs2 rs1 rd
vm rd rs1 rs2
+ vm rd rs2
vm wd rd rs1 rs2
vm rd rs1 nf
vm rd rs1 rs2 nf
@@ -68,6 +69,7 @@
@r2_rm ... . . ... . ... %rs1 %rm %rd
@r2 ... . . ... . ... %rs1 %rd
@r2_nfvm ... ... vm:1 . . ... . ... %nf %rs1 %rd
+@r2_vm .. vm:1 . . ... . ... %rs2 %rd
@r_nfvm ... ... vm:1 . . ... . ... %nf %rs2 %rs1 %rd
@r_vm.. vm:1 . . ... . ... %rs2 %rs1 %rd
@r_vm_1 .. . . . ... . ... vm=1 %rs2 %rs1 %rd
@@ -489,6 +491,7 @@ vfwmsac_vv 10 . . . 001 . 1010111 @r_vm
vfwmsac_vf 10 . . . 101 . 1010111 @r_vm
vfwnmsac_vv 11 . . . 001 . 1010111 @r_vm
vfwnmsac_vf 11 . . . 101 . 1010111 @r_vm
+vfsqrt_v100011 . . 0 001 . 1010111 @r2_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 945c9424ba..35db704bbc 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2089,3 +2089,46 @@ GEN_OPFVF_WIDEN_TRANS(vfwmacc_vf)
GEN_OPFVF_WIDEN_TRANS(vfwnmacc_vf)
GEN_OPFVF_WIDEN_TRANS(vfwmsac_vf)
GEN_OPFVF_WIDEN_TRANS(vfwnmsac_vf)
+
+/* Vector Floating-Point Square-Root Instruction */
+
+/*
+ * If the current SEW does not correspond to a supported IEEE floating-point
+ * type, an illegal instruction exception is raised
+ */
+static bool opfv_check(DisasContext *s, arg_rmr *a)
+{
+ return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, false) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs2, false) &&
+(s->sew != 0));
+}
+
+#define GEN_OPFV_TRANS(NAME, CHECK)\
+static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
+{ \
+if (CHECK(s, a)) { \
+uint32_t data = 0; \
+static gen_helper_gvec_3_ptr * const fns[3] = {\
+gen_helper_##NAME##_h, \
+gen_helper_##NAME##_w, \
+gen_helper_##NAME##_d, \
+}; \
+TCGLabel *over = gen_new_label(); \
+gen_set_rm(s, 7); \
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ \
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \
+data = FIELD_DP32(data, VDATA, VM, a->vm); \
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
+ vreg_ofs(s, a->rs2), cpu_env, 0,\
+ s->vlen / 8, data, fns[s->sew - 1]);\
+gen_set_label(over); \
+return true; \
+} \
+return false; \
+}
+
+GEN_OPFV_TRANS(vfsqrt_v, opfv_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 7abdc2b7d
[PATCH v10 35/61] target/riscv: vector widening floating-point fused multiply-add instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 17 +
target/riscv/insn32.decode | 8 +++
target/riscv/insn_trans/trans_rvv.inc.c | 10 +++
target/riscv/vector_helper.c| 91 +
4 files changed, 126 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 108a177f25..b537030a11 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -906,3 +906,20 @@ DEF_HELPER_6(vfmsub_vf_d, void, ptr, ptr, i64, ptr, env,
i32)
DEF_HELPER_6(vfnmsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfnmsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfnmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(vfwmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 9ca765d37f..c9d5078385 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -481,6 +481,14 @@ vfmsub_vv 101010 . . . 001 . 1010111
@r_vm
vfmsub_vf 101010 . . . 101 . 1010111 @r_vm
vfnmsub_vv 101011 . . . 001 . 1010111 @r_vm
vfnmsub_vf 101011 . . . 101 . 1010111 @r_vm
+vfwmacc_vv 00 . . . 001 . 1010111 @r_vm
+vfwmacc_vf 00 . . . 101 . 1010111 @r_vm
+vfwnmacc_vv 01 . . . 001 . 1010111 @r_vm
+vfwnmacc_vf 01 . . . 101 . 1010111 @r_vm
+vfwmsac_vv 10 . . . 001 . 1010111 @r_vm
+vfwmsac_vf 10 . . . 101 . 1010111 @r_vm
+vfwnmsac_vv 11 . . . 001 . 1010111 @r_vm
+vfwnmsac_vf 11 . . . 101 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 439bfc0469..945c9424ba 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2079,3 +2079,13 @@ GEN_OPFVF_TRANS(vfmadd_vf, opfvf_check)
GEN_OPFVF_TRANS(vfnmadd_vf, opfvf_check)
GEN_OPFVF_TRANS(vfmsub_vf, opfvf_check)
GEN_OPFVF_TRANS(vfnmsub_vf, opfvf_check)
+
+/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
+GEN_OPFVV_WIDEN_TRANS(vfwmacc_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwnmacc_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwmsac_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwnmsac_vv, opfvv_widen_check)
+GEN_OPFVF_WIDEN_TRANS(vfwmacc_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwnmacc_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwmsac_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwnmsac_vf)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d3ad4aa8f1..7abdc2b7d8 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3683,3 +3683,94 @@ RVVCALL(OPFVF3, vfnmsub_vf_d, OP_UUU_D, H8, H8, fnmsub64)
GEN_VEXT_VF(vfnmsub_vf_h, 2, 2, clearh)
GEN_VEXT_VF(vfnmsub_vf_w, 4, 4, clearl)
GEN_VEXT_VF(vfnmsub_vf_d, 8, 8, clearq)
+
+/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
+static uint32_t fwmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
+{
+return float32_muladd(float16_to_float32(a, true, s),
+float16_to_float32(b, true, s), d, 0, s);
+}
+
+static uint64_t fwmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
+{
+return float64_muladd(float32_to_float64(a, s),
+float32_to_float64(b, s), d, 0, s);
+}
+
+RVVCALL(OPFVV3, vfwmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwmacc16)
+RVVCALL(OPFVV3, vfwmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwmacc32)
+GEN_VEXT_VV_ENV(vfwmacc_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwmacc_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF3, vfwmacc_vf_h, WOP_UUU_H, H4, H2, fwmacc16)
+RVVCALL(OPFVF3, vfwmacc_vf_w, WOP_UUU_W, H8, H4, fwmacc32)
+GEN_VEXT_VF(vfwmacc_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwmacc_vf_w, 4
[PATCH v10 34/61] target/riscv: vector single-width floating-point fused multiply-add instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 49 + target/riscv/insn32.decode | 16 ++ target/riscv/insn_trans/trans_rvv.inc.c | 18 ++ target/riscv/vector_helper.c| 251 4 files changed, 334 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 9d7dcfeef9..108a177f25 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -857,3 +857,52 @@ DEF_HELPER_6(vfwmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfwmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfwmul_vf_h, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfwmul_vf_w, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_6(vfmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmacc_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsac_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmacc_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsac_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmadd_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmadd_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmadd_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index dd9bca7eeb..9ca765d37f 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -465,6 +465,22 @@ vfdiv_vf10 . . . 101 . 1010111 @r_vm vfrdiv_vf 11 . . . 101 . 1010111 @r_vm vfwmul_vv 111000 . . . 001 . 1010111 @r_vm vfwmul_vf 111000 . . . 101 . 1010111 @r_vm +vfmacc_vv 101100 . . . 001 . 1010111 @r_vm +vfnmacc_vv 101101 . . . 001 . 1010111 @r_vm +vfnmacc_vf 101101 . . . 101 . 1010111 @r_vm +vfmacc_vf 101100 . . . 101 . 1010111 @r_vm +vfmsac_vv 101110 . . . 001 . 1010111 @r_vm +vfmsac_vf 101110 . . . 101 . 1010111 @r_vm +vfnmsac_vv 10 . . . 001 . 1010111 @r_vm +vfnmsac_vf 10 . . . 101 . 1010111 @r_vm +vfmadd_vv 101000 . . . 001 . 1010111 @r_vm +vfmadd_vf 101000 . . . 101 . 1010111 @r_vm +vfnmadd_vv 101001 . . . 001 . 1010111 @r_vm +vfnmadd_vf 101001 . . . 101
[PATCH v10 33/61] target/riscv: vector widening floating-point multiply
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 5 +
target/riscv/insn32.decode | 2 ++
target/riscv/insn_trans/trans_rvv.inc.c | 4
target/riscv/vector_helper.c| 22 ++
4 files changed, 33 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 94305bd870..9d7dcfeef9 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -852,3 +852,8 @@ DEF_HELPER_6(vfdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfrdiv_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfrdiv_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfrdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(vfwmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmul_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmul_vf_w, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 5db02f0c0a..dd9bca7eeb 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -463,6 +463,8 @@ vfmul_vf100100 . . . 101 . 1010111 @r_vm
vfdiv_vv10 . . . 001 . 1010111 @r_vm
vfdiv_vf10 . . . 101 . 1010111 @r_vm
vfrdiv_vf 11 . . . 101 . 1010111 @r_vm
+vfwmul_vv 111000 . . . 001 . 1010111 @r_vm
+vfwmul_vf 111000 . . . 101 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index be60115801..7ff3af0c61 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2057,3 +2057,7 @@ GEN_OPFVV_TRANS(vfdiv_vv, opfvv_check)
GEN_OPFVF_TRANS(vfmul_vf, opfvf_check)
GEN_OPFVF_TRANS(vfdiv_vf, opfvf_check)
GEN_OPFVF_TRANS(vfrdiv_vf, opfvf_check)
+
+/* Vector Widening Floating-Point Multiply */
+GEN_OPFVV_WIDEN_TRANS(vfwmul_vv, opfvv_widen_check)
+GEN_OPFVF_WIDEN_TRANS(vfwmul_vf)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index ea807ef731..0dd94348e8 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3410,3 +3410,25 @@ RVVCALL(OPFVF2, vfrdiv_vf_d, OP_UUU_D, H8, H8,
float64_rdiv)
GEN_VEXT_VF(vfrdiv_vf_h, 2, 2, clearh)
GEN_VEXT_VF(vfrdiv_vf_w, 4, 4, clearl)
GEN_VEXT_VF(vfrdiv_vf_d, 8, 8, clearq)
+
+/* Vector Widening Floating-Point Multiply */
+static uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s)
+{
+return float32_mul(float16_to_float32(a, true, s),
+float16_to_float32(b, true, s), s);
+}
+
+static uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s)
+{
+return float64_mul(float32_to_float64(a, s),
+float32_to_float64(b, s), s);
+
+}
+RVVCALL(OPFVV2, vfwmul_vv_h, WOP_UUU_H, H4, H2, H2, vfwmul16)
+RVVCALL(OPFVV2, vfwmul_vv_w, WOP_UUU_W, H8, H4, H4, vfwmul32)
+GEN_VEXT_VV_ENV(vfwmul_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwmul_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF2, vfwmul_vf_h, WOP_UUU_H, H4, H2, vfwmul16)
+RVVCALL(OPFVF2, vfwmul_vf_w, WOP_UUU_W, H8, H4, vfwmul32)
+GEN_VEXT_VF(vfwmul_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwmul_vf_w, 4, 8, clearq)
--
2.23.0
[PATCH v10 32/61] target/riscv: vector single-width floating-point multiply/divide instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 16 target/riscv/insn32.decode | 5 +++ target/riscv/insn_trans/trans_rvv.inc.c | 7 target/riscv/vector_helper.c| 49 + 4 files changed, 77 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 828b145150..94305bd870 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -836,3 +836,19 @@ DEF_HELPER_6(vfwadd_wf_h, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfwadd_wf_w, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfwsub_wf_h, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfwsub_wf_w, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_6(vfmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmul_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfdiv_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfdiv_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfdiv_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmul_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmul_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmul_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfdiv_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfdiv_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrdiv_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrdiv_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 42d8a967d0..5db02f0c0a 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -458,6 +458,11 @@ vfwsub_vv 110010 . . . 001 . 1010111 @r_vm vfwsub_vf 110010 . . . 101 . 1010111 @r_vm vfwsub_wv 110110 . . . 001 . 1010111 @r_vm vfwsub_wf 110110 . . . 101 . 1010111 @r_vm +vfmul_vv100100 . . . 001 . 1010111 @r_vm +vfmul_vf100100 . . . 101 . 1010111 @r_vm +vfdiv_vv10 . . . 001 . 1010111 @r_vm +vfdiv_vf10 . . . 101 . 1010111 @r_vm +vfrdiv_vf 11 . . . 101 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index bee4d4cb76..be60115801 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -2050,3 +2050,10 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ GEN_OPFWF_WIDEN_TRANS(vfwadd_wf) GEN_OPFWF_WIDEN_TRANS(vfwsub_wf) + +/* Vector Single-Width Floating-Point Multiply/Divide Instructions */ +GEN_OPFVV_TRANS(vfmul_vv, opfvv_check) +GEN_OPFVV_TRANS(vfdiv_vv, opfvv_check) +GEN_OPFVF_TRANS(vfmul_vf, opfvf_check) +GEN_OPFVF_TRANS(vfdiv_vf, opfvf_check) +GEN_OPFVF_TRANS(vfrdiv_vf, opfvf_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index b65ef51116..ea807ef731 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -3361,3 +3361,52 @@ RVVCALL(OPFVF2, vfwsub_wf_h, WOP_WUUU_H, H4, H2, vfwsubw16) RVVCALL(OPFVF2, vfwsub_wf_w, WOP_WUUU_W, H8, H4, vfwsubw32) GEN_VEXT_VF(vfwsub_wf_h, 2, 4, clearl) GEN_VEXT_VF(vfwsub_wf_w, 4, 8, clearq) + +/* Vector Single-Width Floating-Point Multiply/Divide Instructions */ +RVVCALL(OPFVV2, vfmul_vv_h, OP_UUU_H, H2, H2, H2, float16_mul) +RVVCALL(OPFVV2, vfmul_vv_w, OP_UUU_W, H4, H4, H4, float32_mul) +RVVCALL(OPFVV2, vfmul_vv_d, OP_UUU_D, H8, H8, H8, float64_mul) +GEN_VEXT_VV_ENV(vfmul_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmul_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmul_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfmul_vf_h, OP_UUU_H, H2, H2, float16_mul) +RVVCALL(OPFVF2, vfmul_vf_w, OP_UUU_W, H4, H4, float32_mul) +RVVCALL(OPFVF2, vfmul_vf_d, OP_UUU_D, H8, H8, float64_mul) +GEN_VEXT_VF(vfmul_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmul_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmul_vf_d, 8, 8, clearq) + +RVVCALL(OPFVV2, vfdiv_vv_h, OP_UUU_H, H2, H2, H2, float16_div) +RVVCALL(OPFVV2, vfdiv_vv_w, OP_UUU_W, H4, H4, H4, float32_div) +RVVCALL(OPFVV2, vfdiv_vv_d, OP_UUU_D, H8, H8, H8, float64_div) +GEN_VEXT_VV_ENV(vfdiv_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfdiv_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfdiv_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfdiv_vf_h, OP_UUU_H, H2, H2, float16_div) +RVVCALL(OPFVF2, vfdiv_vf_w, OP_UUU_W, H4, H4, float32_div) +RVVCALL(OPFVF2, vfdiv_vf_d, OP_UUU_D, H8, H8, float64_div) +GEN_VEXT_VF(vfdiv_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfdiv_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfdiv_vf_d, 8, 8, clearq) + +static uint16_t
[PATCH v10 31/61] target/riscv: vector widening floating-point add/subtract instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 17 +++
target/riscv/insn32.decode | 8 ++
target/riscv/insn_trans/trans_rvv.inc.c | 149
target/riscv/vector_helper.c| 83 +
4 files changed, 257 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index ba8a3710e1..828b145150 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -819,3 +819,20 @@ DEF_HELPER_6(vfsub_vf_d, void, ptr, ptr, i64, ptr, env,
i32)
DEF_HELPER_6(vfrsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfrsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfrsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(vfwadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwadd_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wf_w, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 9e26ed36e7..42d8a967d0 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -450,6 +450,14 @@ vfadd_vf00 . . . 101 . 1010111
@r_vm
vfsub_vv10 . . . 001 . 1010111 @r_vm
vfsub_vf10 . . . 101 . 1010111 @r_vm
vfrsub_vf 100111 . . . 101 . 1010111 @r_vm
+vfwadd_vv 11 . . . 001 . 1010111 @r_vm
+vfwadd_vf 11 . . . 101 . 1010111 @r_vm
+vfwadd_wv 110100 . . . 001 . 1010111 @r_vm
+vfwadd_wf 110100 . . . 101 . 1010111 @r_vm
+vfwsub_vv 110010 . . . 001 . 1010111 @r_vm
+vfwsub_vf 110010 . . . 101 . 1010111 @r_vm
+vfwsub_wv 110110 . . . 001 . 1010111 @r_vm
+vfwsub_wf 110110 . . . 101 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 7461e86de8..bee4d4cb76 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1901,3 +1901,152 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)
\
GEN_OPFVF_TRANS(vfadd_vf, opfvf_check)
GEN_OPFVF_TRANS(vfsub_vf, opfvf_check)
GEN_OPFVF_TRANS(vfrsub_vf, opfvf_check)
+
+/* Vector Widening Floating-Point Add/Subtract Instructions */
+static bool opfvv_widen_check(DisasContext *s, arg_rmrr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+vext_check_reg(s, a->rd, true) &&
+vext_check_reg(s, a->rs2, false) &&
+vext_check_reg(s, a->rs1, false) &&
+vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs2,
+ 1 << s->lmul) &&
+vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs1,
+ 1 << s->lmul) &&
+(s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0));
+}
+
+/* OPFVV with WIDEN */
+#define GEN_OPFVV_WIDEN_TRANS(NAME, CHECK) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{\
+if (CHECK(s, a)) { \
+uint32_t data = 0; \
+static gen_helper_gvec_4_ptr * const fns[2] = { \
+gen_helper_##NAME##_h, gen_helper_##NAME##_w,\
+}; \
+TCGLabel *over = gen_new_label();\
+gen_set_rm(s, 7);\
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);\
+ \
+dat
[PATCH v10 30/61] target/riscv: vector single-width floating-point add/subtract instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 16
target/riscv/insn32.decode | 5 +
target/riscv/insn_trans/trans_rvv.inc.c | 118
target/riscv/vector_helper.c| 111 ++
4 files changed, 250 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 5fa4330200..ba8a3710e1 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -803,3 +803,19 @@ DEF_HELPER_6(vnclipu_vx_w, void, ptr, ptr, tl, ptr, env,
i32)
DEF_HELPER_6(vnclip_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vnclip_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vnclip_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vfadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfadd_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfadd_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfadd_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfrsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfrsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfrsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 78e6da6205..9e26ed36e7 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -445,6 +445,11 @@ vnclipu_vi 101110 . . . 011 . 1010111
@r_vm
vnclip_vv 10 . . . 000 . 1010111 @r_vm
vnclip_vx 10 . . . 100 . 1010111 @r_vm
vnclip_vi 10 . . . 011 . 1010111 @r_vm
+vfadd_vv00 . . . 001 . 1010111 @r_vm
+vfadd_vf00 . . . 101 . 1010111 @r_vm
+vfsub_vv10 . . . 001 . 1010111 @r_vm
+vfsub_vf10 . . . 101 . 1010111 @r_vm
+vfrsub_vf 100111 . . . 101 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 96fcf02a8c..7461e86de8 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1783,3 +1783,121 @@ GEN_OPIVX_NARROW_TRANS(vnclipu_vx)
GEN_OPIVX_NARROW_TRANS(vnclip_vx)
GEN_OPIVI_NARROW_TRANS(vnclipu_vi, 1, vnclipu_vx)
GEN_OPIVI_NARROW_TRANS(vnclip_vi, 1, vnclip_vx)
+
+/*
+ *** Vector Float Point Arithmetic Instructions
+ */
+/* Vector Single-Width Floating-Point Add/Subtract Instructions */
+
+/*
+ * If the current SEW does not correspond to a supported IEEE floating-point
+ * type, an illegal instruction exception is raised.
+ */
+static bool opfvv_check(DisasContext *s, arg_rmrr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, false) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs2, false) &&
+vext_check_reg(s, a->rs1, false) &&
+(s->sew != 0));
+}
+
+/* OPFVV without GVEC IR */
+#define GEN_OPFVV_TRANS(NAME, CHECK) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+if (CHECK(s, a)) { \
+uint32_t data = 0; \
+static gen_helper_gvec_4_ptr * const fns[3] = {\
+gen_helper_##NAME##_h, \
+gen_helper_##NAME##_w, \
+gen_helper_##NAME##_d, \
+}; \
+TCGLabel *over = gen_new_label(); \
+gen_set_rm(s, 7); \
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ \
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \
+data = FIELD_DP32(data, VDATA, VM, a->vm); \
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd)
[PATCH v10 29/61] target/riscv: vector narrowing fixed-point clip instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 13 +++
target/riscv/insn32.decode | 6 +
target/riscv/insn_trans/trans_rvv.inc.c | 8 ++
target/riscv/vector_helper.c| 141
4 files changed, 168 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 78438f1ad6..5fa4330200 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -790,3 +790,16 @@ DEF_HELPER_6(vssra_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssra_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vnclip_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclip_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclip_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_vx_w, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 7d5dfeb5c7..78e6da6205 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -439,6 +439,12 @@ vssrl_vi101010 . . . 011 . 1010111
@r_vm
vssra_vv101011 . . . 000 . 1010111 @r_vm
vssra_vx101011 . . . 100 . 1010111 @r_vm
vssra_vi101011 . . . 011 . 1010111 @r_vm
+vnclipu_vv 101110 . . . 000 . 1010111 @r_vm
+vnclipu_vx 101110 . . . 100 . 1010111 @r_vm
+vnclipu_vi 101110 . . . 011 . 1010111 @r_vm
+vnclip_vv 10 . . . 000 . 1010111 @r_vm
+vnclip_vx 10 . . . 100 . 1010111 @r_vm
+vnclip_vi 10 . . . 011 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 0d9e65a194..96fcf02a8c 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1775,3 +1775,11 @@ GEN_OPIVX_TRANS(vssrl_vx, opivx_check)
GEN_OPIVX_TRANS(vssra_vx, opivx_check)
GEN_OPIVI_TRANS(vssrl_vi, 1, vssrl_vx, opivx_check)
GEN_OPIVI_TRANS(vssra_vi, 0, vssra_vx, opivx_check)
+
+/* Vector Narrowing Fixed-Point Clip Instructions */
+GEN_OPIVV_NARROW_TRANS(vnclipu_vv)
+GEN_OPIVV_NARROW_TRANS(vnclip_vv)
+GEN_OPIVX_NARROW_TRANS(vnclipu_vx)
+GEN_OPIVX_NARROW_TRANS(vnclip_vx)
+GEN_OPIVI_NARROW_TRANS(vnclipu_vi, 1, vnclipu_vx)
+GEN_OPIVI_NARROW_TRANS(vnclip_vi, 1, vnclip_vx)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index c33e845a90..1c375f437a 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -875,6 +875,12 @@ GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w,
clearl)
#define WOP_SSU_B int16_t, int8_t, uint8_t, int16_t, uint16_t
#define WOP_SSU_H int32_t, int16_t, uint16_t, int32_t, uint32_t
#define WOP_SSU_W int64_t, int32_t, uint32_t, int64_t, uint64_t
+#define NOP_SSS_B int8_t, int8_t, int16_t, int8_t, int16_t
+#define NOP_SSS_H int16_t, int16_t, int32_t, int16_t, int32_t
+#define NOP_SSS_W int32_t, int32_t, int64_t, int32_t, int64_t
+#define NOP_UUU_B uint8_t, uint8_t, uint16_t, uint8_t, uint16_t
+#define NOP_UUU_H uint16_t, uint16_t, uint32_t, uint16_t, uint32_t
+#define NOP_UUU_W uint32_t, uint32_t, uint64_t, uint32_t, uint64_t
/* operation of two vector elements */
typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
@@ -3009,6 +3015,7 @@ vssra64(CPURISCVState *env, int vxrm, int64_t a, int64_t
b)
res = (a >> shift) + round;
return res;
}
+
RVVCALL(OPIVV2_RM, vssra_vv_b, OP_SSS_B, H1, H1, H1, vssra8)
RVVCALL(OPIVV2_RM, vssra_vv_h, OP_SSS_H, H2, H2, H2, vssra16)
RVVCALL(OPIVV2_RM, vssra_vv_w, OP_SSS_W, H4, H4, H4, vssra32)
@@ -3026,3 +3033,137 @@ GEN_VEXT_VX_RM(vssra_vx_b, 1, 1, clearb)
GEN_VEXT_VX_RM(vssra_vx_h, 2, 2, clearh)
GEN_VEXT_VX_RM(vssra_vx_w, 4, 4, clearl)
GEN_VEXT_VX_RM(vssra_vx_d, 8, 8, clearq)
+
+/* Vector Narrowing Fixed-Point Clip Instructions */
+static inline int8_t
+vnclip8(CPURISCVState *env, int vxrm, int16_t a, int8_t b)
+{
+uint8_t round, shift = b & 0xf;
+int16_t res;
+
+round = get_round(vxrm, a, shift);
+res = (a >> shift) + round;
+if (res > INT8_MAX) {
+
[PATCH v10 28/61] target/riscv: vector single-width scaling shift instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 17
target/riscv/insn32.decode | 6 ++
target/riscv/insn_trans/trans_rvv.inc.c | 8 ++
target/riscv/vector_helper.c| 117
4 files changed, 148 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index f123302b82..78438f1ad6 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -773,3 +773,20 @@ DEF_HELPER_6(vwsmaccsu_vx_w, void, ptr, ptr, tl, ptr, env,
i32)
DEF_HELPER_6(vwsmaccus_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vwsmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vwsmaccus_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vssrl_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssrl_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssrl_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssrl_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssra_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssra_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssra_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssra_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssrl_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssrl_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssrl_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssrl_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssra_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssra_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 8cc2bf4864..7d5dfeb5c7 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -433,6 +433,12 @@ vwsmacc_vx 01 . . . 100 . 1010111
@r_vm
vwsmaccsu_vv10 . . . 000 . 1010111 @r_vm
vwsmaccsu_vx10 . . . 100 . 1010111 @r_vm
vwsmaccus_vx11 . . . 100 . 1010111 @r_vm
+vssrl_vv101010 . . . 000 . 1010111 @r_vm
+vssrl_vx101010 . . . 100 . 1010111 @r_vm
+vssrl_vi101010 . . . 011 . 1010111 @r_vm
+vssra_vv101011 . . . 000 . 1010111 @r_vm
+vssra_vx101011 . . . 100 . 1010111 @r_vm
+vssra_vi101011 . . . 011 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 3886b2f45a..0d9e65a194 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1767,3 +1767,11 @@ GEN_OPIVX_WIDEN_TRANS(vwsmaccu_vx)
GEN_OPIVX_WIDEN_TRANS(vwsmacc_vx)
GEN_OPIVX_WIDEN_TRANS(vwsmaccsu_vx)
GEN_OPIVX_WIDEN_TRANS(vwsmaccus_vx)
+
+/* Vector Single-Width Scaling Shift Instructions */
+GEN_OPIVV_TRANS(vssrl_vv, opivv_check)
+GEN_OPIVV_TRANS(vssra_vv, opivv_check)
+GEN_OPIVX_TRANS(vssrl_vx, opivx_check)
+GEN_OPIVX_TRANS(vssra_vx, opivx_check)
+GEN_OPIVI_TRANS(vssrl_vi, 1, vssrl_vx, opivx_check)
+GEN_OPIVI_TRANS(vssra_vi, 0, vssra_vx, opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d653ec5e2b..c33e845a90 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2909,3 +2909,120 @@ RVVCALL(OPIVX3_RM, vwsmaccus_vx_w, WOP_SUS_W, H8, H4,
vwsmaccus32)
GEN_VEXT_VX_RM(vwsmaccus_vx_b, 1, 2, clearh)
GEN_VEXT_VX_RM(vwsmaccus_vx_h, 2, 4, clearl)
GEN_VEXT_VX_RM(vwsmaccus_vx_w, 4, 8, clearq)
+
+/* Vector Single-Width Scaling Shift Instructions */
+static inline uint8_t
+vssrl8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
+{
+uint8_t round, shift = b & 0x7;
+uint8_t res;
+
+round = get_round(vxrm, a, shift);
+res = (a >> shift) + round;
+return res;
+}
+static inline uint16_t
+vssrl16(CPURISCVState *env, int vxrm, uint16_t a, uint16_t b)
+{
+uint8_t round, shift = b & 0xf;
+uint16_t res;
+
+round = get_round(vxrm, a, shift);
+res = (a >> shift) + round;
+return res;
+}
+static inline uint32_t
+vssrl32(CPURISCVState *env, int vxrm, uint32_t a, uint32_t b)
+{
+uint8_t round, shift = b & 0x1f;
+uint32_t res;
+
+round = get_round(vxrm, a, shift);
+res = (a >> shift) + round;
+return res;
+}
+static inline uint64_t
+vssrl64(CPURISCVState *env, int vxrm, uint64_t a, uint64_t b)
+{
+uint8_t round, shift = b & 0x3f;
+uint64_t res;
+
+round = get_round(vxrm, a, shift);
+res = (a >> shift) + round;
+return res;
+}
+RVVCALL(OPIVV2_RM, vssrl_vv_b, OP_UUU_B, H1, H1, H1, vssrl8)
+RVVCALL(OPIVV2_RM, vssrl_vv_h,
[PATCH v10 27/61] target/riscv: vector widening saturating scaled multiply-add
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 22 +++
target/riscv/insn32.decode | 7 +
target/riscv/insn_trans/trans_rvv.inc.c | 9 ++
target/riscv/vector_helper.c| 205
4 files changed, 243 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index b2fc71c2ea..f123302b82 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -751,3 +751,25 @@ DEF_HELPER_6(vsmul_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsmul_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsmul_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsmul_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vwsmaccu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmaccu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmaccu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmacc_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmaccsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmaccsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmaccsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmaccu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmacc_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmacc_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmacc_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccsu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccsu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccsu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccus_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccus_vx_w, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 1dfc5f7ca0..8cc2bf4864 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -426,6 +426,13 @@ vasub_vv100110 . . . 000 . 1010111
@r_vm
vasub_vx100110 . . . 100 . 1010111 @r_vm
vsmul_vv100111 . . . 000 . 1010111 @r_vm
vsmul_vx100111 . . . 100 . 1010111 @r_vm
+vwsmaccu_vv 00 . . . 000 . 1010111 @r_vm
+vwsmaccu_vx 00 . . . 100 . 1010111 @r_vm
+vwsmacc_vv 01 . . . 000 . 1010111 @r_vm
+vwsmacc_vx 01 . . . 100 . 1010111 @r_vm
+vwsmaccsu_vv10 . . . 000 . 1010111 @r_vm
+vwsmaccsu_vx10 . . . 100 . 1010111 @r_vm
+vwsmaccus_vx11 . . . 100 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 23714793df..3886b2f45a 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1758,3 +1758,12 @@ GEN_OPIVI_TRANS(vaadd_vi, 0, vaadd_vx, opivx_check)
/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
GEN_OPIVV_TRANS(vsmul_vv, opivv_check)
GEN_OPIVX_TRANS(vsmul_vx, opivx_check)
+
+/* Vector Widening Saturating Scaled Multiply-Add */
+GEN_OPIVV_WIDEN_TRANS(vwsmaccu_vv, opivv_widen_check)
+GEN_OPIVV_WIDEN_TRANS(vwsmacc_vv, opivv_widen_check)
+GEN_OPIVV_WIDEN_TRANS(vwsmaccsu_vv, opivv_widen_check)
+GEN_OPIVX_WIDEN_TRANS(vwsmaccu_vx)
+GEN_OPIVX_WIDEN_TRANS(vwsmacc_vx)
+GEN_OPIVX_WIDEN_TRANS(vwsmaccsu_vx)
+GEN_OPIVX_WIDEN_TRANS(vwsmaccus_vx)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index dd3fc39016..d653ec5e2b 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2704,3 +2704,208 @@ GEN_VEXT_VX_RM(vsmul_vx_b, 1, 1, clearb)
GEN_VEXT_VX_RM(vsmul_vx_h, 2, 2, clearh)
GEN_VEXT_VX_RM(vsmul_vx_w, 4, 4, clearl)
GEN_VEXT_VX_RM(vsmul_vx_d, 8, 8, clearq)
+
+/* Vector Widening Saturating Scaled Multiply-Add */
+static inline uint16_t
+vwsmaccu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b,
+ uint16_t c)
+{
+uint8_t round;
+uint16_t res = (uint16_t)a * b;
+
+round = get_round(vxrm, res, 4);
+res = (res >> 4) + round;
+return saddu16(env, vxrm, c, res);
+}
+
+static inline uint32_t
+vwsmaccu16(CPURISCVState *env, int vxrm, uint16_t a, uint16_t b,
+ uint32_t c)
+{
+uint8_t round;
+uint32_t res = (uint32_t)a * b;
+
+round = get_round(vxrm, res, 8);
+res = (res >> 8) + round;
+return saddu32(env, vxrm, c, res);
+}
+
+static inline uint64_t
[PATCH v10 26/61] target/riscv: vector single-width fractional multiply with rounding and saturation
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 9 ++
target/riscv/insn32.decode | 2 +
target/riscv/insn_trans/trans_rvv.inc.c | 4 +
target/riscv/vector_helper.c| 107
4 files changed, 122 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index db9e2024ae..b2fc71c2ea 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -742,3 +742,12 @@ DEF_HELPER_6(vasub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vasub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vasub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vasub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vsmul_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 57228242aa..1dfc5f7ca0 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -424,6 +424,8 @@ vaadd_vx100100 . . . 100 . 1010111 @r_vm
vaadd_vi100100 . . . 011 . 1010111 @r_vm
vasub_vv100110 . . . 000 . 1010111 @r_vm
vasub_vx100110 . . . 100 . 1010111 @r_vm
+vsmul_vv100111 . . . 000 . 1010111 @r_vm
+vsmul_vx100111 . . . 100 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index ed1ee0f1b5..23714793df 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1754,3 +1754,7 @@ GEN_OPIVV_TRANS(vasub_vv, opivv_check)
GEN_OPIVX_TRANS(vaadd_vx, opivx_check)
GEN_OPIVX_TRANS(vasub_vx, opivx_check)
GEN_OPIVI_TRANS(vaadd_vi, 0, vaadd_vx, opivx_check)
+
+/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
+GEN_OPIVV_TRANS(vsmul_vv, opivv_check)
+GEN_OPIVX_TRANS(vsmul_vx, opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index ada95ab1e7..dd3fc39016 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2597,3 +2597,110 @@ GEN_VEXT_VX_RM(vasub_vx_b, 1, 1, clearb)
GEN_VEXT_VX_RM(vasub_vx_h, 2, 2, clearh)
GEN_VEXT_VX_RM(vasub_vx_w, 4, 4, clearl)
GEN_VEXT_VX_RM(vasub_vx_d, 8, 8, clearq)
+
+/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
+static inline int8_t vsmul8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
+{
+uint8_t round;
+int16_t res;
+
+res = (int16_t)a * (int16_t)b;
+round = get_round(vxrm, res, 7);
+res = (res >> 7) + round;
+
+if (res > INT8_MAX) {
+env->vxsat = 0x1;
+return INT8_MAX;
+} else if (res < INT8_MIN) {
+env->vxsat = 0x1;
+return INT8_MIN;
+} else {
+return res;
+}
+}
+
+static int16_t vsmul16(CPURISCVState *env, int vxrm, int16_t a, int16_t b)
+{
+uint8_t round;
+int32_t res;
+
+res = (int32_t)a * (int32_t)b;
+round = get_round(vxrm, res, 15);
+res = (res >> 15) + round;
+
+if (res > INT16_MAX) {
+env->vxsat = 0x1;
+return INT16_MAX;
+} else if (res < INT16_MIN) {
+env->vxsat = 0x1;
+return INT16_MIN;
+} else {
+return res;
+}
+}
+
+static int32_t vsmul32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
+{
+uint8_t round;
+int64_t res;
+
+res = (int64_t)a * (int64_t)b;
+round = get_round(vxrm, res, 31);
+res = (res >> 31) + round;
+
+if (res > INT32_MAX) {
+env->vxsat = 0x1;
+return INT32_MAX;
+} else if (res < INT32_MIN) {
+env->vxsat = 0x1;
+return INT32_MIN;
+} else {
+return res;
+}
+}
+
+static int64_t vsmul64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
+{
+uint8_t round;
+uint64_t hi_64, lo_64;
+int64_t res;
+
+if (a == INT64_MIN && b == INT64_MIN) {
+env->vxsat = 1;
+return INT64_MAX;
+}
+
+muls64(_64, _64, a, b);
+round = get_round(vxrm, lo_64, 63);
+/*
+ * Cannot overflow, as there are always
+ * 2 sign bits after multiply.
+ */
+res = (hi_64 << 1) | (lo_64 >> 63);
+if (round) {
+if (res == INT64_MAX) {
+env->vxsat = 1;
+} else {
+res += 1;
+}
+
[PATCH v10 25/61] target/riscv: vector single-width averaging add and subtract
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 17
target/riscv/insn32.decode | 5 ++
target/riscv/insn_trans/trans_rvv.inc.c | 7 ++
target/riscv/vector_helper.c| 100
4 files changed, 129 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 85bd4b91bc..db9e2024ae 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -725,3 +725,20 @@ DEF_HELPER_6(vssub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vaadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 70df42de9a..57228242aa 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -419,6 +419,11 @@ vssubu_vv 100010 . . . 000 . 1010111
@r_vm
vssubu_vx 100010 . . . 100 . 1010111 @r_vm
vssub_vv100011 . . . 000 . 1010111 @r_vm
vssub_vx100011 . . . 100 . 1010111 @r_vm
+vaadd_vv100100 . . . 000 . 1010111 @r_vm
+vaadd_vx100100 . . . 100 . 1010111 @r_vm
+vaadd_vi100100 . . . 011 . 1010111 @r_vm
+vasub_vv100110 . . . 000 . 1010111 @r_vm
+vasub_vx100110 . . . 100 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 4d5eae8dde..ed1ee0f1b5 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1747,3 +1747,10 @@ GEN_OPIVX_TRANS(vssubu_vx, opivx_check)
GEN_OPIVX_TRANS(vssub_vx, opivx_check)
GEN_OPIVI_TRANS(vsaddu_vi, 1, vsaddu_vx, opivx_check)
GEN_OPIVI_TRANS(vsadd_vi, 0, vsadd_vx, opivx_check)
+
+/* Vector Single-Width Averaging Add and Subtract */
+GEN_OPIVV_TRANS(vaadd_vv, opivv_check)
+GEN_OPIVV_TRANS(vasub_vv, opivv_check)
+GEN_OPIVX_TRANS(vaadd_vx, opivx_check)
+GEN_OPIVX_TRANS(vasub_vx, opivx_check)
+GEN_OPIVI_TRANS(vaadd_vi, 0, vaadd_vx, opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 3d4212ea4a..ada95ab1e7 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2497,3 +2497,103 @@ GEN_VEXT_VX_RM(vssub_vx_b, 1, 1, clearb)
GEN_VEXT_VX_RM(vssub_vx_h, 2, 2, clearh)
GEN_VEXT_VX_RM(vssub_vx_w, 4, 4, clearl)
GEN_VEXT_VX_RM(vssub_vx_d, 8, 8, clearq)
+
+/* Vector Single-Width Averaging Add and Subtract */
+static inline uint8_t get_round(int vxrm, uint64_t v, uint8_t shift)
+{
+uint8_t d = extract64(v, shift, 1);
+uint8_t d1;
+uint64_t D1, D2;
+
+if (shift == 0 || shift > 64) {
+return 0;
+}
+
+d1 = extract64(v, shift - 1, 1);
+D1 = extract64(v, 0, shift);
+if (vxrm == 0) { /* round-to-nearest-up (add +0.5 LSB) */
+return d1;
+} else if (vxrm == 1) { /* round-to-nearest-even */
+if (shift > 1) {
+D2 = extract64(v, 0, shift - 1);
+return d1 & ((D2 != 0) | d);
+} else {
+return d1 & d;
+}
+} else if (vxrm == 3) { /* round-to-odd (OR bits into LSB, aka "jam") */
+return !d & (D1 != 0);
+}
+return 0; /* round-down (truncate) */
+}
+
+static inline int32_t aadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t
b)
+{
+int64_t res = (int64_t)a + b;
+uint8_t round = get_round(vxrm, res, 1);
+
+return (res >> 1) + round;
+}
+
+static inline int64_t aadd64(CPURISCVState *env, int vxrm, int64_t a, int64_t
b)
+{
+int64_t res = a + b;
+uint8_t round = get_round(vxrm, res, 1);
+int64_t over = (res ^ a) & (res ^ b) & INT64_M
[PATCH v10 24/61] target/riscv: vector single-width saturating add and subtract
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 33 ++ target/riscv/insn32.decode | 10 + target/riscv/insn_trans/trans_rvv.inc.c | 16 + target/riscv/vector_helper.c| 385 4 files changed, 444 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 9851086730..85bd4b91bc 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -692,3 +692,36 @@ DEF_HELPER_4(vmv_v_x_b, void, ptr, i64, env, i32) DEF_HELPER_4(vmv_v_x_h, void, ptr, i64, env, i32) DEF_HELPER_4(vmv_v_x_w, void, ptr, i64, env, i32) DEF_HELPER_4(vmv_v_x_d, void, ptr, i64, env, i32) + +DEF_HELPER_6(vsaddu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsaddu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsaddu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsaddu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssubu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssubu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssubu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssubu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssub_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsaddu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsaddu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsaddu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsaddu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsadd_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsadd_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsadd_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsadd_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssubu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssubu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssubu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssubu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssub_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssub_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssub_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssub_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 238aa014d1..70df42de9a 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -409,6 +409,16 @@ vmv_v_i 010111 1 0 . 011 . 1010111 @r2 vmerge_vvm 010111 0 . . 000 . 1010111 @r_vm_0 vmerge_vxm 010111 0 . . 100 . 1010111 @r_vm_0 vmerge_vim 010111 0 . . 011 . 1010111 @r_vm_0 +vsaddu_vv 10 . . . 000 . 1010111 @r_vm +vsaddu_vx 10 . . . 100 . 1010111 @r_vm +vsaddu_vi 10 . . . 011 . 1010111 @r_vm +vsadd_vv11 . . . 000 . 1010111 @r_vm +vsadd_vx11 . . . 100 . 1010111 @r_vm +vsadd_vi11 . . . 011 . 1010111 @r_vm +vssubu_vv 100010 . . . 000 . 1010111 @r_vm +vssubu_vx 100010 . . . 100 . 1010111 @r_vm +vssub_vv100011 . . . 000 . 1010111 @r_vm +vssub_vx100011 . . . 100 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index d726995f84..4d5eae8dde 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1731,3 +1731,19 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a) GEN_OPIVV_TRANS(vmerge_vvm, opivv_vadc_check) GEN_OPIVX_TRANS(vmerge_vxm, opivx_vadc_check) GEN_OPIVI_TRANS(vmerge_vim, 0, vmerge_vxm, opivx_vadc_check) + +/* + *** Vector Fixed-Point Arithmetic Instructions + */ + +/* Vector Single-Width Saturating Add and Subtract */ +GEN_OPIVV_TRANS(vsaddu_vv, opivv_check) +GEN_OPIVV_TRANS(vsadd_vv, opivv_check) +GEN_OPIVV_TRANS(vssubu_vv, opivv_check) +GEN_OPIVV_TRANS(vssub_vv, opivv_check) +GEN_OPIVX_TRANS(vsaddu_vx, opivx_check) +GEN_OPIVX_TRANS(vsadd_vx, opivx_check) +GEN_OPIVX_TRANS(vssubu_vx, opivx_check) +GEN_OPIVX_TRANS(vssub_vx, opivx_check) +GEN_OPIVI_TRANS(vsaddu_vi, 1, vsaddu_vx, opivx_check) +GEN_OPIVI_TRANS(vsadd_vi, 0, vsadd_vx, opivx_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index
[PATCH v10 23/61] target/riscv: vector integer merge and move instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 17
target/riscv/insn32.decode | 7 ++
target/riscv/insn_trans/trans_rvv.inc.c | 113
target/riscv/vector_helper.c| 88 ++
4 files changed, 225 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 1249ee274d..9851086730 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -675,3 +675,20 @@ DEF_HELPER_6(vwmaccsu_vx_w, void, ptr, ptr, tl, ptr, env,
i32)
DEF_HELPER_6(vwmaccus_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vwmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vwmaccus_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vmerge_vvm_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmerge_vvm_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmerge_vvm_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmerge_vvm_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmerge_vxm_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmerge_vxm_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmerge_vxm_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmerge_vxm_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_4(vmv_v_v_b, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vmv_v_v_h, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vmv_v_v_w, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vmv_v_v_d, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vmv_v_x_b, void, ptr, i64, env, i32)
+DEF_HELPER_4(vmv_v_x_h, void, ptr, i64, env, i32)
+DEF_HELPER_4(vmv_v_x_w, void, ptr, i64, env, i32)
+DEF_HELPER_4(vmv_v_x_d, void, ptr, i64, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 843c15f8fa..238aa014d1 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -71,6 +71,7 @@
@r_nfvm ... ... vm:1 . . ... . ... %nf %rs2 %rs1 %rd
@r_vm.. vm:1 . . ... . ... %rs2 %rs1 %rd
@r_vm_1 .. . . . ... . ... vm=1 %rs2 %rs1 %rd
+@r_vm_0 .. . . . ... . ... vm=0 %rs2 %rs1 %rd
@r_wdvm . wd:1 vm:1 . . ... . ... %rs2 %rs1 %rd
@r2_zimm . zimm:11 . ... . ... %rs1 %rd
@@ -402,6 +403,12 @@ vwmacc_vx 01 . . . 110 . 1010111
@r_vm
vwmaccsu_vv 10 . . . 010 . 1010111 @r_vm
vwmaccsu_vx 10 . . . 110 . 1010111 @r_vm
vwmaccus_vx 11 . . . 110 . 1010111 @r_vm
+vmv_v_v 010111 1 0 . 000 . 1010111 @r2
+vmv_v_x 010111 1 0 . 100 . 1010111 @r2
+vmv_v_i 010111 1 0 . 011 . 1010111 @r2
+vmerge_vvm 010111 0 . . 000 . 1010111 @r_vm_0
+vmerge_vxm 010111 0 . . 100 . 1010111 @r_vm_0
+vmerge_vim 010111 0 . . 011 . 1010111 @r_vm_0
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 3093191edc..d726995f84 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1618,3 +1618,116 @@ GEN_OPIVX_WIDEN_TRANS(vwmaccu_vx)
GEN_OPIVX_WIDEN_TRANS(vwmacc_vx)
GEN_OPIVX_WIDEN_TRANS(vwmaccsu_vx)
GEN_OPIVX_WIDEN_TRANS(vwmaccus_vx)
+
+/* Vector Integer Merge and Move Instructions */
+static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
+{
+if (vext_check_isa_ill(s) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs1, false)) {
+
+if (s->vl_eq_vlmax) {
+tcg_gen_gvec_mov(s->sew, vreg_ofs(s, a->rd),
+ vreg_ofs(s, a->rs1),
+ MAXSZ(s), MAXSZ(s));
+} else {
+uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+static gen_helper_gvec_2_ptr * const fns[4] = {
+gen_helper_vmv_v_v_b, gen_helper_vmv_v_v_h,
+gen_helper_vmv_v_v_w, gen_helper_vmv_v_v_d,
+};
+TCGLabel *over = gen_new_label();
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),
+ cpu_env, 0, s->vlen / 8, data, fns[s->sew]);
+gen_set_label(over);
+}
+return true;
+}
+return false;
+}
+
+typedef void gen_helper_vmv_vx(TCGv_ptr, TCGv_i64, TCGv_env, TCGv_i32);
+static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
+{
+if (vext_check_isa_ill(s) &&
+vext_check_reg(s, a->rd, false)) {
+
+TCGv s1;
+TCGLabel *over = gen_new_label();
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+s1 = tcg_temp_new();
+
[PATCH v10 22/61] target/riscv: vector widening integer multiply-add instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 22 target/riscv/insn32.decode | 7 target/riscv/insn_trans/trans_rvv.inc.c | 9 + target/riscv/vector_helper.c| 45 + 4 files changed, 83 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index a65a38596b..1249ee274d 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -653,3 +653,25 @@ DEF_HELPER_6(vnmsub_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnmsub_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnmsub_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnmsub_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vwmaccu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmacc_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmacc_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmacc_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmacc_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccus_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccus_vx_w, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index f01cf14777..843c15f8fa 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -395,6 +395,13 @@ vmadd_vv101001 . . . 010 . 1010111 @r_vm vmadd_vx101001 . . . 110 . 1010111 @r_vm vnmsub_vv 101011 . . . 010 . 1010111 @r_vm vnmsub_vx 101011 . . . 110 . 1010111 @r_vm +vwmaccu_vv 00 . . . 010 . 1010111 @r_vm +vwmaccu_vx 00 . . . 110 . 1010111 @r_vm +vwmacc_vv 01 . . . 010 . 1010111 @r_vm +vwmacc_vx 01 . . . 110 . 1010111 @r_vm +vwmaccsu_vv 10 . . . 010 . 1010111 @r_vm +vwmaccsu_vx 10 . . . 110 . 1010111 @r_vm +vwmaccus_vx 11 . . . 110 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index dc122eb2e5..3093191edc 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1609,3 +1609,12 @@ GEN_OPIVX_TRANS(vmacc_vx, opivx_check) GEN_OPIVX_TRANS(vnmsac_vx, opivx_check) GEN_OPIVX_TRANS(vmadd_vx, opivx_check) GEN_OPIVX_TRANS(vnmsub_vx, opivx_check) + +/* Vector Widening Integer Multiply-Add Instructions */ +GEN_OPIVV_WIDEN_TRANS(vwmaccu_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwmacc_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwmaccsu_vv, opivv_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwmaccu_vx) +GEN_OPIVX_WIDEN_TRANS(vwmacc_vx) +GEN_OPIVX_WIDEN_TRANS(vwmaccsu_vx) +GEN_OPIVX_WIDEN_TRANS(vwmaccus_vx) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index e787e00b01..c966ad8470 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -1979,3 +1979,48 @@ GEN_VEXT_VX(vnmsub_vx_b, 1, 1, clearb) GEN_VEXT_VX(vnmsub_vx_h, 2, 2, clearh) GEN_VEXT_VX(vnmsub_vx_w, 4, 4, clearl) GEN_VEXT_VX(vnmsub_vx_d, 8, 8, clearq) + +/* Vector Widening Integer Multiply-Add Instructions */ +RVVCALL(OPIVV3, vwmaccu_vv_b, WOP_UUU_B, H2, H1, H1, DO_MACC) +RVVCALL(OPIVV3, vwmaccu_vv_h, WOP_UUU_H, H4, H2, H2, DO_MACC) +RVVCALL(OPIVV3, vwmaccu_vv_w, WOP_UUU_W, H8, H4, H4, DO_MACC) +RVVCALL(OPIVV3, vwmacc_vv_b, WOP_SSS_B, H2, H1, H1, DO_MACC) +RVVCALL(OPIVV3, vwmacc_vv_h, WOP_SSS_H, H4, H2, H2, DO_MACC) +RVVCALL(OPIVV3, vwmacc_vv_w, WOP_SSS_W, H8, H4, H4, DO_MACC) +RVVCALL(OPIVV3, vwmaccsu_vv_b, WOP_SSU_B, H2, H1, H1, DO_MACC) +RVVCALL(OPIVV3, vwmaccsu_vv_h, WOP_SSU_H, H4, H2, H2, DO_MACC) +RVVCALL(OPIVV3, vwmaccsu_vv_w, WOP_SSU_W, H8, H4, H4, DO_MACC) +GEN_VEXT_VV(vwmaccu_vv_b, 1, 2, clearh) +GEN_VEXT_VV(vwmaccu_vv_h, 2, 4, clearl) +GEN_VEXT_VV(vwmaccu_vv_w, 4, 8
[PATCH v10 21/61] target/riscv: vector single-width integer multiply-add instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 33 ++ target/riscv/insn32.decode | 8 +++ target/riscv/insn_trans/trans_rvv.inc.c | 10 +++ target/riscv/vector_helper.c| 88 + 4 files changed, 139 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 60c436616a..a65a38596b 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -620,3 +620,36 @@ DEF_HELPER_6(vwmulu_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vwmulsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vwmulsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vwmulsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vmacc_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmacc_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsac_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsac_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsub_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnmsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmacc_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmacc_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmacc_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmacc_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsac_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsac_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsac_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsac_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadd_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadd_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadd_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadd_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsub_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsub_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsub_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnmsub_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 877d999129..f01cf14777 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -387,6 +387,14 @@ vwmulsu_vv 111010 . . . 010 . 1010111 @r_vm vwmulsu_vx 111010 . . . 110 . 1010111 @r_vm vwmul_vv111011 . . . 010 . 1010111 @r_vm vwmul_vx111011 . . . 110 . 1010111 @r_vm +vmacc_vv101101 . . . 010 . 1010111 @r_vm +vmacc_vx101101 . . . 110 . 1010111 @r_vm +vnmsac_vv 10 . . . 010 . 1010111 @r_vm +vnmsac_vx 10 . . . 110 . 1010111 @r_vm +vmadd_vv101001 . . . 010 . 1010111 @r_vm +vmadd_vx101001 . . . 110 . 1010111 @r_vm +vnmsub_vv 101011 . . . 010 . 1010111 @r_vm +vnmsub_vx 101011 . . . 110 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index fbdd1b43d6..dc122eb2e5 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1599,3 +1599,13 @@ GEN_OPIVV_WIDEN_TRANS(vwmulsu_vv, opivv_widen_check) GEN_OPIVX_WIDEN_TRANS(vwmul_vx) GEN_OPIVX_WIDEN_TRANS(vwmulu_vx) GEN_OPIVX_WIDEN_TRANS(vwmulsu_vx) + +/* Vector Single-Width Integer Multiply-Add Instructions */ +GEN_OPIVV_TRANS(vmacc_vv, opivv_check) +GEN_OPIVV_TRANS(vnmsac_vv, opivv_check) +GEN_OPIVV_TRANS(vmadd_vv, opivv_check) +GEN_OPIVV_TRANS(vnmsub_vv, opivv_check) +GEN_OPIVX_TRANS(vmacc_vx, opivx_check) +GEN_OPIVX_TRANS(vnmsac_vx, opivx_check) +GEN_OPIVX_TRANS(vmadd_vx, opivx_check) +GEN_OPIVX_TRANS(vnmsub_vx, opivx_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 116cc9f092..e787e00b01 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -1891,3 +1891,91 @@ GEN_VEXT_VX(vwmulu_vx_w, 4, 8, clearq) GEN_VEXT_VX(vwmulsu_vx_b, 1, 2, clearh) GEN_VEXT_VX(vwmulsu_vx_h, 2, 4, clearl) GEN_VEXT_VX(vwmulsu_vx_w, 4, 8, clearq) + +/* Vector
[PATCH v10 20/61] target/riscv: vector widening integer multiply instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 19 + target/riscv/insn32.decode | 6 +++ target/riscv/insn_trans/trans_rvv.inc.c | 8 target/riscv/vector_helper.c| 51 + 4 files changed, 84 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index e14979e452..60c436616a 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -601,3 +601,22 @@ DEF_HELPER_6(vrem_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vrem_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vrem_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vrem_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vwmul_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmulu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmulu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmulu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmulsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmulsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmulsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmul_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmul_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmul_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmulu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmulu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmulu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmulsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmulsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmulsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index cf58764308..877d999129 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -381,6 +381,12 @@ vremu_vv100010 . . . 010 . 1010111 @r_vm vremu_vx100010 . . . 110 . 1010111 @r_vm vrem_vv 100011 . . . 010 . 1010111 @r_vm vrem_vx 100011 . . . 110 . 1010111 @r_vm +vwmulu_vv 111000 . . . 010 . 1010111 @r_vm +vwmulu_vx 111000 . . . 110 . 1010111 @r_vm +vwmulsu_vv 111010 . . . 010 . 1010111 @r_vm +vwmulsu_vx 111010 . . . 110 . 1010111 @r_vm +vwmul_vv111011 . . . 010 . 1010111 @r_vm +vwmul_vx111011 . . . 110 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index 4b4312fa99..fbdd1b43d6 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1591,3 +1591,11 @@ GEN_OPIVX_TRANS(vdivu_vx, opivx_check) GEN_OPIVX_TRANS(vdiv_vx, opivx_check) GEN_OPIVX_TRANS(vremu_vx, opivx_check) GEN_OPIVX_TRANS(vrem_vx, opivx_check) + +/* Vector Widening Integer Multiply Instructions */ +GEN_OPIVV_WIDEN_TRANS(vwmul_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwmulu_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwmulsu_vv, opivv_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwmul_vx) +GEN_OPIVX_WIDEN_TRANS(vwmulu_vx) +GEN_OPIVX_WIDEN_TRANS(vwmulsu_vx) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index aee107a82e..116cc9f092 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -863,6 +863,18 @@ GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w, clearl) #define OP_SUS_H int16_t, uint16_t, int16_t, uint16_t, int16_t #define OP_SUS_W int32_t, uint32_t, int32_t, uint32_t, int32_t #define OP_SUS_D int64_t, uint64_t, int64_t, uint64_t, int64_t +#define WOP_UUU_B uint16_t, uint8_t, uint8_t, uint16_t, uint16_t +#define WOP_UUU_H uint32_t, uint16_t, uint16_t, uint32_t, uint32_t +#define WOP_UUU_W uint64_t, uint32_t, uint32_t, uint64_t, uint64_t +#define WOP_SSS_B int16_t, int8_t, int8_t, int16_t, int16_t +#define WOP_SSS_H int32_t, int16_t, int16_t, int32_t, int32_t +#define WOP_SSS_W int64_t, int32_t, int32_t, int64_t, int64_t +#define WOP_SUS_B int16_t, uint8_t, int8_t, uint16_t, int16_t +#define WOP_SUS_H int32_t, uint16_t, int16_t, uint32_t, int32_t +#define WOP_SUS_W int64_t, uint32_t, int32_t, uint64_t, int64_t +#define WOP_SSU_B int16_t, int8_t, uint8_t, int16_t, uint16_t +#define WOP_SSU_H int32_t, int16_t, uint16_t, int32_t, uint32_t +#define WOP_SSU_W int64_t, int32_t, uint32_t, int64_t, uint64_t /* operation of two vector elements */ typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i); @@ -1840,3 +1852,42 @@ GEN_VEXT_VX(vrem_vx_b, 1, 1, clearb) GEN_VEXT_VX(vrem_vx_h, 2, 2, clearh
[PATCH v10 19/61] target/riscv: vector integer divide instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 33 +++ target/riscv/insn32.decode | 8 +++ target/riscv/insn_trans/trans_rvv.inc.c | 10 target/riscv/vector_helper.c| 74 + 4 files changed, 125 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index c2de0d29ba..e14979e452 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -568,3 +568,36 @@ DEF_HELPER_6(vmulhsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmulhsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmulhsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmulhsu_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vdivu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdivu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdivu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdivu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdiv_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdiv_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdiv_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdiv_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vremu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vremu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vremu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vremu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrem_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrem_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrem_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vrem_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vdivu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdivu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdivu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdivu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdiv_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdiv_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdiv_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vdiv_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vremu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vremu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vremu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vremu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrem_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrem_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrem_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vrem_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 6b29aad4d2..cf58764308 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -373,6 +373,14 @@ vmulhu_vv 100100 . . . 010 . 1010111 @r_vm vmulhu_vx 100100 . . . 110 . 1010111 @r_vm vmulhsu_vv 100110 . . . 010 . 1010111 @r_vm vmulhsu_vx 100110 . . . 110 . 1010111 @r_vm +vdivu_vv10 . . . 010 . 1010111 @r_vm +vdivu_vx10 . . . 110 . 1010111 @r_vm +vdiv_vv 11 . . . 010 . 1010111 @r_vm +vdiv_vx 11 . . . 110 . 1010111 @r_vm +vremu_vv100010 . . . 010 . 1010111 @r_vm +vremu_vx100010 . . . 110 . 1010111 @r_vm +vrem_vv 100011 . . . 010 . 1010111 @r_vm +vrem_vx 100011 . . . 110 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index de5b8b7df6..4b4312fa99 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1581,3 +1581,13 @@ GEN_OPIVX_GVEC_TRANS(vmul_vx, muls) GEN_OPIVX_TRANS(vmulh_vx, opivx_check) GEN_OPIVX_TRANS(vmulhu_vx, opivx_check) GEN_OPIVX_TRANS(vmulhsu_vx, opivx_check) + +/* Vector Integer Divide Instructions */ +GEN_OPIVV_TRANS(vdivu_vv, opivv_check) +GEN_OPIVV_TRANS(vdiv_vv, opivv_check) +GEN_OPIVV_TRANS(vremu_vv, opivv_check) +GEN_OPIVV_TRANS(vrem_vv, opivv_check) +GEN_OPIVX_TRANS(vdivu_vx, opivx_check) +GEN_OPIVX_TRANS(vdiv_vx, opivx_check) +GEN_OPIVX_TRANS(vremu_vx, opivx_check) +GEN_OPIVX_TRANS(vrem_vx, opivx_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 3319370ae2..aee107a82e 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -1766,3 +1766,77 @@ GEN_VEXT_VX(vmulhsu_vx_b, 1, 1, clearb) GEN_VEXT_VX(vmulhsu_vx_h, 2, 2, clearh) GEN_VEXT_VX(vmulhsu_vx_w, 4, 4, clearl) GEN_VEXT_VX(vmulhsu_vx_d, 8, 8, clearq) + +/* Vector Integer Divide Instructions */ +#define DO_DIVU(N
[PATCH v10 18/61] target/riscv: vector single-width integer multiply instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Alistair Francis Reviewed-by: Richard Henderson --- target/riscv/helper.h | 33 + target/riscv/insn32.decode | 8 ++ target/riscv/insn_trans/trans_rvv.inc.c | 10 ++ target/riscv/vector_helper.c| 163 4 files changed, 214 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 9c576e1220..c2de0d29ba 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -535,3 +535,36 @@ DEF_HELPER_6(vmax_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmax_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmax_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmax_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vmul_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmul_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulh_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulh_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulh_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulh_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmul_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmul_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmul_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmul_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulh_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulh_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulh_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulh_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmulhsu_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 3d8986c74d..6b29aad4d2 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -365,6 +365,14 @@ vmaxu_vv000110 . . . 000 . 1010111 @r_vm vmaxu_vx000110 . . . 100 . 1010111 @r_vm vmax_vv 000111 . . . 000 . 1010111 @r_vm vmax_vx 000111 . . . 100 . 1010111 @r_vm +vmul_vv 100101 . . . 010 . 1010111 @r_vm +vmul_vx 100101 . . . 110 . 1010111 @r_vm +vmulh_vv100111 . . . 010 . 1010111 @r_vm +vmulh_vx100111 . . . 110 . 1010111 @r_vm +vmulhu_vv 100100 . . . 010 . 1010111 @r_vm +vmulhu_vx 100100 . . . 110 . 1010111 @r_vm +vmulhsu_vv 100110 . . . 010 . 1010111 @r_vm +vmulhsu_vx 100110 . . . 110 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index cbcb40e682..de5b8b7df6 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1571,3 +1571,13 @@ GEN_OPIVX_TRANS(vminu_vx, opivx_check) GEN_OPIVX_TRANS(vmin_vx, opivx_check) GEN_OPIVX_TRANS(vmaxu_vx, opivx_check) GEN_OPIVX_TRANS(vmax_vx, opivx_check) + +/* Vector Single-Width Integer Multiply Instructions */ +GEN_OPIVV_GVEC_TRANS(vmul_vv, mul) +GEN_OPIVV_TRANS(vmulh_vv, opivv_check) +GEN_OPIVV_TRANS(vmulhu_vv, opivv_check) +GEN_OPIVV_TRANS(vmulhsu_vv, opivv_check) +GEN_OPIVX_GVEC_TRANS(vmul_vx, muls) +GEN_OPIVX_TRANS(vmulh_vx, opivx_check) +GEN_OPIVX_TRANS(vmulhu_vx, opivx_check) +GEN_OPIVX_TRANS(vmulhsu_vx, opivx_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index cb41daa3ac..3319370ae2 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -859,6 +859,10 @@ GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w, clearl) #define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t #define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
[PATCH v10 17/61] target/riscv: vector integer min/max instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 33 target/riscv/insn32.decode | 8 +++ target/riscv/insn_trans/trans_rvv.inc.c | 10 target/riscv/vector_helper.c| 71 + 4 files changed, 122 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 2bcb6c7889..9c576e1220 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -502,3 +502,36 @@ DEF_HELPER_6(vmsgt_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmsgt_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmsgt_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmsgt_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vminu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vminu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vminu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vminu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmin_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmin_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmin_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmin_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmaxu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmaxu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmaxu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmaxu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmax_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmax_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmax_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmax_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vminu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vminu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vminu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vminu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmin_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmin_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmin_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmin_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmaxu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmaxu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmaxu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmaxu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmax_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmax_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmax_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmax_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 5d022ff414..3d8986c74d 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -357,6 +357,14 @@ vmsgtu_vx 00 . . . 100 . 1010111 @r_vm vmsgtu_vi 00 . . . 011 . 1010111 @r_vm vmsgt_vx01 . . . 100 . 1010111 @r_vm vmsgt_vi01 . . . 011 . 1010111 @r_vm +vminu_vv000100 . . . 000 . 1010111 @r_vm +vminu_vx000100 . . . 100 . 1010111 @r_vm +vmin_vv 000101 . . . 000 . 1010111 @r_vm +vmin_vx 000101 . . . 100 . 1010111 @r_vm +vmaxu_vv000110 . . . 000 . 1010111 @r_vm +vmaxu_vx000110 . . . 100 . 1010111 @r_vm +vmax_vv 000111 . . . 000 . 1010111 @r_vm +vmax_vx 000111 . . . 100 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index 8fa3d5ecb0..cbcb40e682 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1561,3 +1561,13 @@ GEN_OPIVI_TRANS(vmsleu_vi, 1, vmsleu_vx, opivx_cmp_check) GEN_OPIVI_TRANS(vmsle_vi, 0, vmsle_vx, opivx_cmp_check) GEN_OPIVI_TRANS(vmsgtu_vi, 1, vmsgtu_vx, opivx_cmp_check) GEN_OPIVI_TRANS(vmsgt_vi, 0, vmsgt_vx, opivx_cmp_check) + +/* Vector Integer Min/Max Instructions */ +GEN_OPIVV_GVEC_TRANS(vminu_vv, umin) +GEN_OPIVV_GVEC_TRANS(vmin_vv, smin) +GEN_OPIVV_GVEC_TRANS(vmaxu_vv, umax) +GEN_OPIVV_GVEC_TRANS(vmax_vv, smax) +GEN_OPIVX_TRANS(vminu_vx, opivx_check) +GEN_OPIVX_TRANS(vmin_vx, opivx_check) +GEN_OPIVX_TRANS(vmaxu_vx, opivx_check) +GEN_OPIVX_TRANS(vmax_vx, opivx_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 07e474781c..cb41daa3ac 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -855,6 +855,10 @@ GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w, clearl) #define OP_SSS_H int16_t, int16_t, int16_t, int16_t, int16_t #define OP_SSS_W int32_t, int32_t, int32_t
[PATCH v10 16/61] target/riscv: vector integer comparison instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 57 +++ target/riscv/insn32.decode | 20 target/riscv/insn_trans/trans_rvv.inc.c | 46 + target/riscv/vector_helper.c| 123 4 files changed, 246 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 1ec2202814..2bcb6c7889 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -445,3 +445,60 @@ DEF_HELPER_6(vnsrl_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnsra_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnsra_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnsra_vx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vmseq_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmseq_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmseq_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmseq_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsne_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsne_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsne_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsne_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsltu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsltu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsltu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsltu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmslt_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmslt_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmslt_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmslt_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsleu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsleu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsleu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsleu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsle_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsle_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsle_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsle_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmseq_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmseq_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmseq_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmseq_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsne_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsne_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsne_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsne_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsltu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsltu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsltu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsltu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmslt_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmslt_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmslt_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmslt_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsleu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsleu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsleu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsleu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsle_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsle_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsle_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsle_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgtu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgtu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgtu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgtu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgt_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgt_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgt_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsgt_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 435415f9f9..5d022ff414 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -337,6 +337,26 @@ vnsrl_vi101100 . . . 011 . 1010111 @r_vm vnsra_vv101101 . . . 000 . 1010111 @r_vm vnsra_vx101101 . . . 100 . 1010111 @r_vm vnsra_vi101101 . . . 011 . 1010111 @r_vm +vmseq_vv011000 . . . 000 . 1010111 @r_vm +vmseq_vx011000 . . . 100 . 1010111 @r_vm +vmseq_vi011000 . . . 011 . 1010111 @r_vm +vmsne_vv011001 . . . 000 . 1010111 @r_vm +vmsne_vx011001 . . . 100 . 1010111 @r_vm
[PATCH v10 15/61] target/riscv: vector narrowing integer right shift instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 13
target/riscv/insn32.decode | 6 ++
target/riscv/insn_trans/trans_rvv.inc.c | 90 +
target/riscv/vector_helper.c| 14
4 files changed, 123 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 6805bf7dbd..1ec2202814 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -432,3 +432,16 @@ DEF_HELPER_6(vsra_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsra_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vnsrl_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnsrl_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnsrl_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnsra_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnsra_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnsra_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnsrl_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnsrl_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnsrl_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnsra_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnsra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnsra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index e5334230df..435415f9f9 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -331,6 +331,12 @@ vsrl_vi 101000 . . . 011 . 1010111
@r_vm
vsra_vv 101001 . . . 000 . 1010111 @r_vm
vsra_vx 101001 . . . 100 . 1010111 @r_vm
vsra_vi 101001 . . . 011 . 1010111 @r_vm
+vnsrl_vv101100 . . . 000 . 1010111 @r_vm
+vnsrl_vx101100 . . . 100 . 1010111 @r_vm
+vnsrl_vi101100 . . . 011 . 1010111 @r_vm
+vnsra_vv101101 . . . 000 . 1010111 @r_vm
+vnsra_vx101101 . . . 100 . 1010111 @r_vm
+vnsra_vi101101 . . . 011 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 8ea7c437ee..87f9ee7f6c 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1425,3 +1425,93 @@ GEN_OPIVX_GVEC_SHIFT_TRANS(vsra_vx, sars)
GEN_OPIVI_GVEC_TRANS(vsll_vi, 1, vsll_vx, shli)
GEN_OPIVI_GVEC_TRANS(vsrl_vi, 1, vsrl_vx, shri)
GEN_OPIVI_GVEC_TRANS(vsra_vi, 1, vsra_vx, sari)
+
+/* Vector Narrowing Integer Right Shift Instructions */
+static bool opivv_narrow_check(DisasContext *s, arg_rmrr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, false) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs2, true) &&
+vext_check_reg(s, a->rs1, false) &&
+vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs2,
+2 << s->lmul) &&
+(s->lmul < 0x3) && (s->sew < 0x3));
+}
+
+/* OPIVV with NARROW */
+#define GEN_OPIVV_NARROW_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+if (opivv_narrow_check(s, a)) {\
+uint32_t data = 0; \
+static gen_helper_gvec_4_ptr * const fns[3] = {\
+gen_helper_##NAME##_b, \
+gen_helper_##NAME##_h, \
+gen_helper_##NAME##_w, \
+}; \
+TCGLabel *over = gen_new_label(); \
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ \
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \
+data = FIELD_DP32(data, VDATA, VM, a->vm); \
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
+ vreg_ofs(s, a->rs1),\
+ vreg_ofs(s, a->rs2), cpu_env, 0,\
+ s->v
[PATCH v10 14/61] target/riscv: vector single-width bit shift instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 25
target/riscv/insn32.decode | 9 +++
target/riscv/insn_trans/trans_rvv.inc.c | 52
target/riscv/vector_helper.c| 79 +
4 files changed, 165 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index f8b1c8a800..6805bf7dbd 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -407,3 +407,28 @@ DEF_HELPER_6(vxor_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vxor_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vxor_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vxor_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vsll_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsll_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsll_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsll_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsrl_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsrl_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsrl_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsrl_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsra_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsra_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsra_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsra_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsll_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsll_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsll_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsll_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsrl_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsrl_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsrl_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsrl_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsra_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsra_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 34d05a5917..e5334230df 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -322,6 +322,15 @@ vor_vi 001010 . . . 011 . 1010111
@r_vm
vxor_vv 001011 . . . 000 . 1010111 @r_vm
vxor_vx 001011 . . . 100 . 1010111 @r_vm
vxor_vi 001011 . . . 011 . 1010111 @r_vm
+vsll_vv 100101 . . . 000 . 1010111 @r_vm
+vsll_vx 100101 . . . 100 . 1010111 @r_vm
+vsll_vi 100101 . . . 011 . 1010111 @r_vm
+vsrl_vv 101000 . . . 000 . 1010111 @r_vm
+vsrl_vx 101000 . . . 100 . 1010111 @r_vm
+vsrl_vi 101000 . . . 011 . 1010111 @r_vm
+vsra_vv 101001 . . . 000 . 1010111 @r_vm
+vsra_vx 101001 . . . 100 . 1010111 @r_vm
+vsra_vi 101001 . . . 011 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 35c92986a6..8ea7c437ee 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1373,3 +1373,55 @@ GEN_OPIVX_GVEC_TRANS(vxor_vx, xors)
GEN_OPIVI_GVEC_TRANS(vand_vi, 0, vand_vx, andi)
GEN_OPIVI_GVEC_TRANS(vor_vi, 0, vor_vx, ori)
GEN_OPIVI_GVEC_TRANS(vxor_vi, 0, vxor_vx, xori)
+
+/* Vector Single-Width Bit Shift Instructions */
+GEN_OPIVV_GVEC_TRANS(vsll_vv, shlv)
+GEN_OPIVV_GVEC_TRANS(vsrl_vv, shrv)
+GEN_OPIVV_GVEC_TRANS(vsra_vv, sarv)
+
+typedef void GVecGen2sFn32(unsigned, uint32_t, uint32_t, TCGv_i32,
+ uint32_t, uint32_t);
+
+static inline bool
+do_opivx_gvec_shift(DisasContext *s, arg_rmrr *a, GVecGen2sFn32 *gvec_fn,
+gen_helper_opivx *fn)
+{
+if (!opivx_check(s, a)) {
+return false;
+}
+
+if (a->vm && s->vl_eq_vlmax) {
+TCGv_i32 src1 = tcg_temp_new_i32();
+TCGv tmp = tcg_temp_new();
+
+gen_get_gpr(tmp, a->rs1);
+tcg_gen_trunc_tl_i32(src1, tmp);
+tcg_gen_extract_i32(src1, src1, 0, s->sew + 3);
+gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
+src1, MAXSZ(s), MAXSZ(s));
+
+tcg_temp_free_i32(src1);
+tcg_temp_free(tmp);
+return true;
+}
+return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s);
+}
+
+#define GEN_OPIVX_GVEC_SHIFT_TRANS(NAME, SUF) \
+static bo
[PATCH v10 13/61] target/riscv: vector bitwise logical instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 25 target/riscv/insn32.decode | 9 + target/riscv/insn_trans/trans_rvv.inc.c | 11 ++ target/riscv/vector_helper.c| 51 + 4 files changed, 96 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 67a2e64c4a..f8b1c8a800 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -382,3 +382,28 @@ DEF_HELPER_6(vmsbc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmsbc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmsbc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vmsbc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vand_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vand_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vand_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vand_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vor_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vor_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vor_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vor_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vxor_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vxor_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vxor_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vxor_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vand_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vand_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vand_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vand_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vor_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vor_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vor_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vor_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vxor_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vxor_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vxor_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vxor_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index be63e900c6..34d05a5917 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -313,6 +313,15 @@ vsbc_vvm010010 1 . . 000 . 1010111 @r_vm_1 vsbc_vxm010010 1 . . 100 . 1010111 @r_vm_1 vmsbc_vvm 010011 1 . . 000 . 1010111 @r_vm_1 vmsbc_vxm 010011 1 . . 100 . 1010111 @r_vm_1 +vand_vv 001001 . . . 000 . 1010111 @r_vm +vand_vx 001001 . . . 100 . 1010111 @r_vm +vand_vi 001001 . . . 011 . 1010111 @r_vm +vor_vv 001010 . . . 000 . 1010111 @r_vm +vor_vx 001010 . . . 100 . 1010111 @r_vm +vor_vi 001010 . . . 011 . 1010111 @r_vm +vxor_vv 001011 . . . 000 . 1010111 @r_vm +vxor_vx 001011 . . . 100 . 1010111 @r_vm +vxor_vi 001011 . . . 011 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index 6fe2f071e6..35c92986a6 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1362,3 +1362,14 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ GEN_OPIVI_TRANS(vadc_vim, 0, vadc_vxm, opivx_vadc_check) GEN_OPIVI_TRANS(vmadc_vim, 0, vmadc_vxm, opivx_vmadc_check) + +/* Vector Bitwise Logical Instructions */ +GEN_OPIVV_GVEC_TRANS(vand_vv, and) +GEN_OPIVV_GVEC_TRANS(vor_vv, or) +GEN_OPIVV_GVEC_TRANS(vxor_vv, xor) +GEN_OPIVX_GVEC_TRANS(vand_vx, ands) +GEN_OPIVX_GVEC_TRANS(vor_vx, ors) +GEN_OPIVX_GVEC_TRANS(vxor_vx, xors) +GEN_OPIVI_GVEC_TRANS(vand_vi, 0, vand_vx, andi) +GEN_OPIVI_GVEC_TRANS(vor_vi, 0, vor_vx, ori) +GEN_OPIVI_GVEC_TRANS(vxor_vi, 0, vxor_vx, xori) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index ad746175bd..6c53dc5796 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -1265,3 +1265,54 @@ GEN_VEXT_VMADC_VXM(vmsbc_vxm_b, uint8_t, H1, DO_MSBC) GEN_VEXT_VMADC_VXM(vmsbc_vxm_h, uint16_t, H2, DO_MSBC) GEN_VEXT_VMADC_VXM(vmsbc_vxm_w, uint32_t, H4, DO_MSBC) GEN_VEXT_VMADC_VXM(vmsbc_vxm_d, uint64_t, H8, DO_MSBC) + +/* Vector Bitwise Logical Instructions */ +RVVCALL(OPIVV2, vand_vv_b, OP_SSS_B, H1, H1, H1, DO_AND) +RVVCALL(OPIVV2, vand_vv_h, OP_SSS_H, H2, H2, H2, DO_AND) +RVVCALL(OPIVV2, vand_vv_w, OP_SSS_W, H4, H4, H4, DO_AND) +RVVCALL(OPIVV2, vand_vv_d, OP_SSS_D, H8, H8, H8, DO_AND) +RVVCALL(OPIVV2, vor_vv_b, OP_SSS_B, H1, H1, H1, DO_OR) +RVVCALL(OPIVV2, vor_vv_h
[PATCH v10 12/61] target/riscv: vector integer add-with-carry / subtract-with-borrow instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Alistair Francis Reviewed-by: Richard Henderson --- target/riscv/helper.h | 33 ++ target/riscv/insn32.decode | 11 ++ target/riscv/insn_trans/trans_rvv.inc.c | 113 +++ target/riscv/vector_helper.c| 137 4 files changed, 294 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index da6acc067b..67a2e64c4a 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -349,3 +349,36 @@ DEF_HELPER_6(vwadd_wx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vwsub_wx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vwsub_wx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vwsub_wx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vadc_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadc_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadc_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadc_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsbc_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsbc_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsbc_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsbc_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadc_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadc_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadc_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmadc_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsbc_vvm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsbc_vvm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsbc_vvm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vmsbc_vvm_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vadc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vadc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vadc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vadc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsbc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsbc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsbc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsbc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmadc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsbc_vxm_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsbc_vxm_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsbc_vxm_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vmsbc_vxm_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 6ec166d0ed..be63e900c6 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -70,6 +70,7 @@ @r2_nfvm ... ... vm:1 . . ... . ... %nf %rs1 %rd @r_nfvm ... ... vm:1 . . ... . ... %nf %rs2 %rs1 %rd @r_vm.. vm:1 . . ... . ... %rs2 %rs1 %rd +@r_vm_1 .. . . . ... . ... vm=1 %rs2 %rs1 %rd @r_wdvm . wd:1 vm:1 . . ... . ... %rs2 %rs1 %rd @r2_zimm . zimm:11 . ... . ... %rs1 %rd @@ -302,6 +303,16 @@ vwsubu_wv 110110 . . . 010 . 1010111 @r_vm vwsubu_wx 110110 . . . 110 . 1010111 @r_vm vwsub_wv110111 . . . 010 . 1010111 @r_vm vwsub_wx110111 . . . 110 . 1010111 @r_vm +vadc_vvm01 1 . . 000 . 1010111 @r_vm_1 +vadc_vxm01 1 . . 100 . 1010111 @r_vm_1 +vadc_vim01 1 . . 011 . 1010111 @r_vm_1 +vmadc_vvm 010001 1 . . 000 . 1010111 @r_vm_1 +vmadc_vxm 010001 1 . . 100 . 1010111 @r_vm_1 +vmadc_vim 010001 1 . . 011 . 1010111 @r_vm_1 +vsbc_vvm010010 1 . . 000 . 1010111 @r_vm_1 +vsbc_vxm010010 1 . . 100 . 1010111 @r_vm_1 +vmsbc_vvm 010011 1 . . 000 . 1010111 @r_vm_1 +vmsbc_vxm 010011 1 . . 100 . 1010111 @r_vm_1 vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index 7a14b64c3d..6fe2f071e6 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1249,3 +1249,116 @@ GEN_OPIWX_WIDEN_TRANS(vwaddu_wx) GEN_OPIWX_WIDEN_TRANS(vwadd_wx) GEN_OPIWX_WIDEN_TRANS(vwsubu_wx) GEN_OPIWX_WIDEN_TRANS(vwsub_wx) + +/* Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions */ +/* OPIVV without GVEC IR */ +#define GEN_OPIVV_TRANS(NAME, CHECK) \ +static bool trans_##NAME(DisasContext
[PATCH v10 11/61] target/riscv: vector widening integer add and subtract
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 49 +++ target/riscv/insn32.decode | 16 ++ target/riscv/insn_trans/trans_rvv.inc.c | 186 target/riscv/vector_helper.c| 111 ++ 4 files changed, 362 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 7660bec01f..da6acc067b 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -300,3 +300,52 @@ DEF_HELPER_FLAGS_4(vec_rsubs8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(vec_rsubs16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(vec_rsubs32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(vec_rsubs64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) + +DEF_HELPER_6(vwaddu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_wv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_wv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsubu_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_wv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwadd_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_wv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_wv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsub_wv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwaddu_wx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_wx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwaddu_wx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_wx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_wx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsubu_wx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_wx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_wx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwadd_wx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_wx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_wx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsub_wx_w, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index bb1e47a2be..6ec166d0ed 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -286,6 +286,22 @@ vsub_vv 10 . . . 000 . 1010111 @r_vm vsub_vx 10 . . . 100 . 1010111 @r_vm vrsub_vx11 . . . 100 . 1010111 @r_vm vrsub_vi11 . . . 011 . 1010111 @r_vm +vwaddu_vv 11 . . . 010 . 1010111 @r_vm +vwaddu_vx 11 . . . 110 . 1010111 @r_vm +vwadd_vv110001 . . . 010 . 1010111 @r_vm +vwadd_vx110001 . . . 110 . 1010111 @r_vm +vwsubu_vv 110010 . . . 010 . 1010111 @r_vm +vwsubu_vx 110010 . . . 110 . 1010111 @r_vm +vwsub_vv110011 . . . 010 . 1010111 @r_vm +vwsub_vx110011 . . . 110 . 1010111 @r_vm +vwaddu_wv 110100 . . . 010 . 1010111 @r_vm +vwaddu_wx 110100 . . . 110 . 1010111 @r_vm +vwadd_wv110101 . . . 010 . 1010111 @r_vm +vwadd_wx110101 . . . 110
[PATCH v10 10/61] target/riscv: vector single-width integer add and subtract
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 25 ++
target/riscv/insn32.decode | 10 +
target/riscv/insn_trans/trans_rvv.inc.c | 291
target/riscv/vector_helper.c| 183 +++
4 files changed, 509 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index c5f43b5b64..7660bec01f 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -275,3 +275,28 @@ DEF_HELPER_6(vamominw_v_w, void, ptr, ptr, tl, ptr, env,
i32)
DEF_HELPER_6(vamomaxw_v_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vamominuw_v_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vamomaxuw_v_w, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsub_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vadd_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vadd_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vadd_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vadd_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrsub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrsub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrsub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrsub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_FLAGS_4(vec_rsubs8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vec_rsubs16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vec_rsubs32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vec_rsubs64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 625914c85f..bb1e47a2be 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -44,6 +44,7 @@
imm rd
shamt rs1 rd
aq rl rs2 rs1 rd
+ vm rd rs1 rs2
vm wd rd rs1 rs2
vm rd rs1 nf
vm rd rs1 rs2 nf
@@ -68,6 +69,7 @@
@r2 ... . . ... . ... %rs1 %rd
@r2_nfvm ... ... vm:1 . . ... . ... %nf %rs1 %rd
@r_nfvm ... ... vm:1 . . ... . ... %nf %rs2 %rs1 %rd
+@r_vm.. vm:1 . . ... . ... %rs2 %rs1 %rd
@r_wdvm . wd:1 vm:1 . . ... . ... %rs2 %rs1 %rd
@r2_zimm . zimm:11 . ... . ... %rs1 %rd
@@ -277,5 +279,13 @@ vamominuw_v 11000 . . . . 110 . 010
@r_wdvm
vamomaxuw_v 11100 . . . . 110 . 010 @r_wdvm
# *** new major opcode OP-V ***
+vadd_vv 00 . . . 000 . 1010111 @r_vm
+vadd_vx 00 . . . 100 . 1010111 @r_vm
+vadd_vi 00 . . . 011 . 1010111 @r_vm
+vsub_vv 10 . . . 000 . 1010111 @r_vm
+vsub_vx 10 . . . 100 . 1010111 @r_vm
+vrsub_vx11 . . . 100 . 1010111 @r_vm
+vrsub_vi11 . . . 011 . 1010111 @r_vm
+
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index a551139207..79b6cd9b4a 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -772,3 +772,294 @@ GEN_VEXT_TRANS(vamomaxd_v, 15, rwdvm, amo_op, amo_check)
GEN_VEXT_TRANS(vamominud_v, 16, rwdvm, amo_op, amo_check)
GEN_VEXT_TRANS(vamomaxud_v, 17, rwdvm, amo_op, amo_check)
#endif
+
+/*
+ *** Vector Integer Arithmetic Instructions
+ */
+#define MAXSZ(s) (s->vlen >> (3 - s->lmul))
+
+static bool opivv_check(DisasContext *s, arg_rmrr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, false) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs2, false) &&
+vext_check_reg(s, a->rs1, false));
+}
+
+typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t,
+uint32_t, uint32_t, uint32_t);
+
+static inline bool
+do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
+ gen_helper_gvec_4_ptr *fn)
+{
+TCGLabel *over = gen_new_la
[PATCH v10 09/61] target/riscv: add vector amo operations
Vector AMOs operate as if aq and rl bits were zero on each element with regard to ordering relative to other instructions in the same hart. Vector AMOs provide no ordering guarantee between element operations in the same vector AMO instruction Signed-off-by: LIU Zhiwei Reviewed-by: Alistair Francis Reviewed-by: Richard Henderson --- target/riscv/helper.h | 29 + target/riscv/insn32-64.decode | 11 ++ target/riscv/insn32.decode | 13 +++ target/riscv/insn_trans/trans_rvv.inc.c | 138 ++ target/riscv/internals.h| 1 + target/riscv/vector_helper.c| 147 6 files changed, 339 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 5c97bc446e..c5f43b5b64 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -246,3 +246,32 @@ DEF_HELPER_5(vlhuff_v_w, void, ptr, ptr, tl, env, i32) DEF_HELPER_5(vlhuff_v_d, void, ptr, ptr, tl, env, i32) DEF_HELPER_5(vlwuff_v_w, void, ptr, ptr, tl, env, i32) DEF_HELPER_5(vlwuff_v_d, void, ptr, ptr, tl, env, i32) +#ifdef TARGET_RISCV64 +DEF_HELPER_6(vamoswapw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoswapd_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoaddw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoaddd_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoxorw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoxord_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoandw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoandd_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoorw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoord_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomind_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxd_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominuw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominud_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxuw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxud_v_d, void, ptr, ptr, tl, ptr, env, i32) +#endif +DEF_HELPER_6(vamoswapw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoaddw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoxorw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoandw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamoorw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamominuw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vamomaxuw_v_w, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32-64.decode b/target/riscv/insn32-64.decode index 380bf791bc..86153d93fa 100644 --- a/target/riscv/insn32-64.decode +++ b/target/riscv/insn32-64.decode @@ -57,6 +57,17 @@ amomax_d 10100 . . . . 011 . 010 @atom_st amominu_d 11000 . . . . 011 . 010 @atom_st amomaxu_d 11100 . . . . 011 . 010 @atom_st +#*** Vector AMO operations (in addition to Zvamo) *** +vamoswapd_v 1 . . . . 111 . 010 @r_wdvm +vamoaddd_v 0 . . . . 111 . 010 @r_wdvm +vamoxord_v 00100 . . . . 111 . 010 @r_wdvm +vamoandd_v 01100 . . . . 111 . 010 @r_wdvm +vamoord_v 01000 . . . . 111 . 010 @r_wdvm +vamomind_v 1 . . . . 111 . 010 @r_wdvm +vamomaxd_v 10100 . . . . 111 . 010 @r_wdvm +vamominud_v 11000 . . . . 111 . 010 @r_wdvm +vamomaxud_v 11100 . . . . 111 . 010 @r_wdvm + # *** RV64F Standard Extension (in addition to RV32F) *** fcvt_l_s 110 00010 . ... . 1010011 @r2_rm fcvt_lu_s 110 00011 . ... . 1010011 @r2_rm diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 7146aec22a..625914c85f 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -44,6 +44,7 @@ imm rd shamt rs1 rd aq rl rs2 rs1 rd + vm wd rd rs1 rs2 vm rd rs1 nf vm rd rs1 rs2 nf @@ -67,6 +68,7 @@ @r2 ... . . ... . ... %rs1 %rd @r2_nfvm ... ... vm:1 . . ... . ... %nf %rs1 %rd @r_nfvm ... ... vm:1 . . ... . ... %nf %rs2 %rs1 %rd +@r_wdvm . wd:1 vm:1 . . ... . ... %rs2 %rs1 %rd @r2_zimm . zimm:11 . ... . ... %rs1 %rd @hfence_gvma ... . . ... . ... %rs2 %rs1 @@ -263,6 +265,17 @@ vsxh_v ... -11 . . . 101 . 0100111 @r_nfvm vsxw_v ... -11 . . . 110 . 0100111 @r_nfvm vsxe_v ... -11 . . . 111 . 0100111 @r_nfvm
[PATCH v10 08/61] target/riscv: add fault-only-first unit stride load
The unit-stride fault-only-fault load instructions are used to
vectorize loops with data-dependent exit conditions(while loops).
These instructions execute as a regular load except that they
will only take a trap on element 0.
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 22 +
target/riscv/insn32.decode | 7 ++
target/riscv/insn_trans/trans_rvv.inc.c | 73
target/riscv/vector_helper.c| 110
4 files changed, 212 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index f3650f736e..5c97bc446e 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -224,3 +224,25 @@ DEF_HELPER_6(vsxe_v_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsxe_v_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsxe_v_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsxe_v_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_5(vlbff_v_b, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbff_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbff_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlhff_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlhff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlhff_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlwff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlwff_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vleff_v_b, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vleff_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vleff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vleff_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbuff_v_b, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbuff_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbuff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlbuff_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlhuff_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlhuff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlhuff_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlwuff_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(vlwuff_v_d, void, ptr, ptr, tl, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 287d52bcc9..7146aec22a 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -226,6 +226,13 @@ vle_v ... 000 . 0 . 111 . 111 @r2_nfvm
vlbu_v ... 000 . 0 . 000 . 111 @r2_nfvm
vlhu_v ... 000 . 0 . 101 . 111 @r2_nfvm
vlwu_v ... 000 . 0 . 110 . 111 @r2_nfvm
+vlbff_v... 100 . 1 . 000 . 111 @r2_nfvm
+vlhff_v... 100 . 1 . 101 . 111 @r2_nfvm
+vlwff_v... 100 . 1 . 110 . 111 @r2_nfvm
+vleff_v... 000 . 1 . 111 . 111 @r2_nfvm
+vlbuff_v ... 000 . 1 . 000 . 111 @r2_nfvm
+vlhuff_v ... 000 . 1 . 101 . 111 @r2_nfvm
+vlwuff_v ... 000 . 1 . 110 . 111 @r2_nfvm
vsb_v ... 000 . 0 . 000 . 0100111 @r2_nfvm
vsh_v ... 000 . 0 . 101 . 0100111 @r2_nfvm
vsw_v ... 000 . 0 . 110 . 0100111 @r2_nfvm
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index c3a79c5232..299b479ec1 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -561,3 +561,76 @@ GEN_VEXT_TRANS(vsxb_v, 0, rnfvm, st_index_op,
st_index_check)
GEN_VEXT_TRANS(vsxh_v, 1, rnfvm, st_index_op, st_index_check)
GEN_VEXT_TRANS(vsxw_v, 2, rnfvm, st_index_op, st_index_check)
GEN_VEXT_TRANS(vsxe_v, 3, rnfvm, st_index_op, st_index_check)
+
+/*
+ *** unit stride fault-only-first load
+ */
+static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data,
+ gen_helper_ldst_us *fn, DisasContext *s)
+{
+TCGv_ptr dest, mask;
+TCGv base;
+TCGv_i32 desc;
+
+TCGLabel *over = gen_new_label();
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+dest = tcg_temp_new_ptr();
+mask = tcg_temp_new_ptr();
+base = tcg_temp_new();
+desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
+
+gen_get_gpr(base, rs1);
+tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd));
+tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0));
+
+fn(dest, mask, base, cpu_env, desc);
+
+tcg_temp_free_ptr(dest);
+tcg_temp_free_ptr(mask);
+tcg_temp_free(base);
+tcg_temp_free_i32(desc);
+gen_set_label(over);
+return true;
+}
+
+static bool ldff_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq)
+{
+uint32_t data = 0;
+gen_helper_ldst_us *fn;
+static gen_helper_ldst_us * const fns[7][4] = {
+{ gen_helper_vlbff_v_b, gen_helper_vlbff_v_h,
+ gen_helper_vlbff_v_w, gen_helper_vlbff_v_d },
+{ NULL, gen_helper_vlhff_v_h,
+ gen_helper_vlhff_
[PATCH v10 07/61] target/riscv: add vector index load and store instructions
Vector indexed operations add the contents of each element of the vector offset operand specified by vs2 to the base effective address to give the effective address of each element. Signed-off-by: LIU Zhiwei Reviewed-by: Alistair Francis Reviewed-by: Richard Henderson --- target/riscv/helper.h | 35 +++ target/riscv/insn32.decode | 13 +++ target/riscv/insn_trans/trans_rvv.inc.c | 129 target/riscv/vector_helper.c| 116 + 4 files changed, 293 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index f03b3d52f5..f3650f736e 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -189,3 +189,38 @@ DEF_HELPER_6(vsse_v_b, void, ptr, ptr, tl, tl, env, i32) DEF_HELPER_6(vsse_v_h, void, ptr, ptr, tl, tl, env, i32) DEF_HELPER_6(vsse_v_w, void, ptr, ptr, tl, tl, env, i32) DEF_HELPER_6(vsse_v_d, void, ptr, ptr, tl, tl, env, i32) +DEF_HELPER_6(vlxb_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxb_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxb_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxb_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxh_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxh_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxh_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxe_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxe_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxe_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxe_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxbu_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxbu_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxbu_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxbu_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxhu_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxhu_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxhu_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxwu_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vlxwu_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxb_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxb_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxb_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxb_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxh_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxh_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxh_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxw_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxw_v_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxe_v_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxe_v_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxe_v_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsxe_v_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 58b95792e6..287d52bcc9 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -243,6 +243,19 @@ vssh_v ... 010 . . . 101 . 0100111 @r_nfvm vssw_v ... 010 . . . 110 . 0100111 @r_nfvm vsse_v ... 010 . . . 111 . 0100111 @r_nfvm +vlxb_v ... 111 . . . 000 . 111 @r_nfvm +vlxh_v ... 111 . . . 101 . 111 @r_nfvm +vlxw_v ... 111 . . . 110 . 111 @r_nfvm +vlxe_v ... 011 . . . 111 . 111 @r_nfvm +vlxbu_v... 011 . . . 000 . 111 @r_nfvm +vlxhu_v... 011 . . . 101 . 111 @r_nfvm +vlxwu_v... 011 . . . 110 . 111 @r_nfvm +# Vector ordered-indexed and unordered-indexed store insns. +vsxb_v ... -11 . . . 000 . 0100111 @r_nfvm +vsxh_v ... -11 . . . 101 . 0100111 @r_nfvm +vsxw_v ... -11 . . . 110 . 0100111 @r_nfvm +vsxe_v ... -11 . . . 111 . 0100111 @r_nfvm + # *** new major opcode OP-V *** vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index f9950ad5a0..c3a79c5232 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -432,3 +432,132 @@ GEN_VEXT_TRANS(vssb_v, 0, rnfvm, st_stride_op, st_stride_check) GEN_VEXT_TRANS(vssh_v, 1, rnfvm, st_stride_op, st_stride_check) GEN_VEXT_TRANS(vssw_v, 2, rnfvm, st_stride_op, st_stride_check) GEN_VEXT_TRANS(vsse_v, 3, rnfvm, st_stride_op, st_stride_check) + +/* + *** index load and store + */ +typedef void gen_helper_ldst_index(TCGv_ptr, TCGv_ptr, TCGv, + TCGv_ptr, TCGv_env, TCGv_i32); + +static bool ldst_index_trans
[PATCH v10 06/61] target/riscv: add vector stride load and store instructions
Vector strided operations access the first memory element at the base address, and then access subsequent elements at address increments given by the byte offset contained in the x register specified by rs2. Vector unit-stride operations access elements stored contiguously in memory starting from the base effective address. It can been seen as a special case of strided operations. Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 105 ++ target/riscv/insn32.decode | 32 ++ target/riscv/insn_trans/trans_rvv.inc.c | 355 target/riscv/internals.h| 5 + target/riscv/translate.c| 7 + target/riscv/vector_helper.c| 410 6 files changed, 914 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 8e81ff440b..f03b3d52f5 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -84,3 +84,108 @@ DEF_HELPER_1(hyp_tlb_flush, void, env) /* Vector functions */ DEF_HELPER_3(vsetvl, tl, env, tl, tl) +DEF_HELPER_5(vlb_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlb_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlh_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlw_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlw_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlw_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlw_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vle_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlbu_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlhu_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwu_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwu_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwu_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vlwu_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsb_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsh_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsw_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsw_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsw_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vsw_v_d_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_b, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_b_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_h, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_h_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_w, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_w_mask, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5(vse_v_d, void, ptr, ptr, tl, env, i32) +DEF_HELPER_5
[PATCH v10 05/61] target/riscv: add an internals.h header
The internals.h keeps things that are not relevant to the actual architecture, only to the implementation, separate. Signed-off-by: LIU Zhiwei Reviewed-by: Alistair Francis Reviewed-by: Richard Henderson --- target/riscv/internals.h | 24 1 file changed, 24 insertions(+) create mode 100644 target/riscv/internals.h diff --git a/target/riscv/internals.h b/target/riscv/internals.h new file mode 100644 index 00..22a49af413 --- /dev/null +++ b/target/riscv/internals.h @@ -0,0 +1,24 @@ +/* + * QEMU RISC-V CPU -- internal functions and types + * + * Copyright (c) 2020 T-Head Semiconductor Co., Ltd. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef RISCV_CPU_INTERNALS_H +#define RISCV_CPU_INTERNALS_H + +#include "hw/registerfields.h" + +#endif -- 2.23.0
[PATCH v10 04/61] target/riscv: add vector configure instruction
vsetvl and vsetvli are two configure instructions for vl, vtype. TB flags
should update after configure instructions. The (ill, lmul, sew ) of vtype
and the bit of (VSTART == 0 && VL == VLMAX) will be placed within tb_flags.
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/Makefile.objs | 2 +-
target/riscv/cpu.h | 63 +---
target/riscv/helper.h | 3 +
target/riscv/insn32.decode | 5 ++
target/riscv/insn_trans/trans_rvv.inc.c | 79 +
target/riscv/translate.c| 17 +-
target/riscv/vector_helper.c| 53 +
7 files changed, 210 insertions(+), 12 deletions(-)
create mode 100644 target/riscv/insn_trans/trans_rvv.inc.c
create mode 100644 target/riscv/vector_helper.c
diff --git a/target/riscv/Makefile.objs b/target/riscv/Makefile.objs
index ff651f69f6..ff38df6219 100644
--- a/target/riscv/Makefile.objs
+++ b/target/riscv/Makefile.objs
@@ -1,4 +1,4 @@
-obj-y += translate.o op_helper.o cpu_helper.o cpu.o csr.o fpu_helper.o
gdbstub.o
+obj-y += translate.o op_helper.o cpu_helper.o cpu.o csr.o fpu_helper.o
vector_helper.o gdbstub.o
obj-$(CONFIG_SOFTMMU) += pmp.o
ifeq ($(CONFIG_SOFTMMU),y)
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index 302e0859a0..0ad51c6580 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -21,6 +21,7 @@
#define RISCV_CPU_H
#include "hw/core/cpu.h"
+#include "hw/registerfields.h"
#include "exec/cpu-defs.h"
#include "fpu/softfloat-types.h"
@@ -93,6 +94,12 @@ typedef struct CPURISCVState CPURISCVState;
#define RV_VLEN_MAX 512
+FIELD(VTYPE, VLMUL, 0, 2)
+FIELD(VTYPE, VSEW, 2, 3)
+FIELD(VTYPE, VEDIV, 5, 2)
+FIELD(VTYPE, RESERVED, 7, sizeof(target_ulong) * 8 - 9)
+FIELD(VTYPE, VILL, sizeof(target_ulong) * 8 - 2, 1)
+
struct CPURISCVState {
target_ulong gpr[32];
uint64_t fpr[32]; /* assume both F and D extensions */
@@ -352,19 +359,62 @@ void riscv_cpu_set_fflags(CPURISCVState *env,
target_ulong);
#define TB_FLAGS_MMU_MASK 3
#define TB_FLAGS_MSTATUS_FS MSTATUS_FS
+typedef CPURISCVState CPUArchState;
+typedef RISCVCPU ArchCPU;
+#include "exec/cpu-all.h"
+
+FIELD(TB_FLAGS, VL_EQ_VLMAX, 2, 1)
+FIELD(TB_FLAGS, LMUL, 3, 2)
+FIELD(TB_FLAGS, SEW, 5, 3)
+FIELD(TB_FLAGS, VILL, 8, 1)
+
+/*
+ * A simplification for VLMAX
+ * = (1 << LMUL) * VLEN / (8 * (1 << SEW))
+ * = (VLEN << LMUL) / (8 << SEW)
+ * = (VLEN << LMUL) >> (SEW + 3)
+ * = VLEN >> (SEW + 3 - LMUL)
+ */
+static inline uint32_t vext_get_vlmax(RISCVCPU *cpu, target_ulong vtype)
+{
+uint8_t sew, lmul;
+
+sew = FIELD_EX64(vtype, VTYPE, VSEW);
+lmul = FIELD_EX64(vtype, VTYPE, VLMUL);
+return cpu->cfg.vlen >> (sew + 3 - lmul);
+}
+
static inline void cpu_get_tb_cpu_state(CPURISCVState *env, target_ulong *pc,
-target_ulong *cs_base, uint32_t *flags)
+target_ulong *cs_base, uint32_t
*pflags)
{
+uint32_t flags = 0;
+
*pc = env->pc;
*cs_base = 0;
+
+if (riscv_has_ext(env, RVV)) {
+uint32_t vlmax = vext_get_vlmax(env_archcpu(env), env->vtype);
+bool vl_eq_vlmax = (env->vstart == 0) && (vlmax == env->vl);
+flags = FIELD_DP32(flags, TB_FLAGS, VILL,
+FIELD_EX64(env->vtype, VTYPE, VILL));
+flags = FIELD_DP32(flags, TB_FLAGS, SEW,
+FIELD_EX64(env->vtype, VTYPE, VSEW));
+flags = FIELD_DP32(flags, TB_FLAGS, LMUL,
+FIELD_EX64(env->vtype, VTYPE, VLMUL));
+flags = FIELD_DP32(flags, TB_FLAGS, VL_EQ_VLMAX, vl_eq_vlmax);
+} else {
+flags = FIELD_DP32(flags, TB_FLAGS, VILL, 1);
+}
+
#ifdef CONFIG_USER_ONLY
-*flags = TB_FLAGS_MSTATUS_FS;
+flags |= TB_FLAGS_MSTATUS_FS;
#else
-*flags = cpu_mmu_index(env, 0);
+flags |= cpu_mmu_index(env, 0);
if (riscv_cpu_fp_enabled(env)) {
-*flags |= env->mstatus & MSTATUS_FS;
+flags |= env->mstatus & MSTATUS_FS;
}
#endif
+*pflags = flags;
}
int riscv_csrrw(CPURISCVState *env, int csrno, target_ulong *ret_value,
@@ -405,9 +455,4 @@ void riscv_set_csr_ops(int csrno, riscv_csr_operations
*ops);
void riscv_cpu_register_gdb_regs_for_features(CPUState *cs);
-typedef CPURISCVState CPUArchState;
-typedef RISCVCPU ArchCPU;
-
-#include "exec/cpu-all.h"
-
#endif /* RISCV_CPU_H */
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index b36be978d5..8e81ff440b 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -81,3 +81,6 @@ DEF_HELPER_1(tlb_flush, void, env)
#ifndef CONFIG_USER_ONLY
DEF_HELPER_1(hyp_tlb_flush, void, env)
#endif
+
+/* Vector functions */
+DEF_HELPER_3(vsetvl, tl, env, tl, tl)
diff --git a/targ
[PATCH v10 03/61] target/riscv: support vector extension csr
The v0.7.1 specification does not define vector status within mstatus.
A future revision will define the privileged portion of the vector status.
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/cpu_bits.h | 15 +
target/riscv/csr.c | 75 -
2 files changed, 89 insertions(+), 1 deletion(-)
diff --git a/target/riscv/cpu_bits.h b/target/riscv/cpu_bits.h
index 7f64ee1174..8117e8b5a7 100644
--- a/target/riscv/cpu_bits.h
+++ b/target/riscv/cpu_bits.h
@@ -29,6 +29,14 @@
#define FSR_NXA (FPEXC_NX << FSR_AEXC_SHIFT)
#define FSR_AEXC(FSR_NVA | FSR_OFA | FSR_UFA | FSR_DZA | FSR_NXA)
+/* Vector Fixed-Point round model */
+#define FSR_VXRM_SHIFT 9
+#define FSR_VXRM(0x3 << FSR_VXRM_SHIFT)
+
+/* Vector Fixed-Point saturation flag */
+#define FSR_VXSAT_SHIFT 8
+#define FSR_VXSAT (0x1 << FSR_VXSAT_SHIFT)
+
/* Control and Status Registers */
/* User Trap Setup */
@@ -48,6 +56,13 @@
#define CSR_FRM 0x002
#define CSR_FCSR0x003
+/* User Vector CSRs */
+#define CSR_VSTART 0x008
+#define CSR_VXSAT 0x009
+#define CSR_VXRM0x00a
+#define CSR_VL 0xc20
+#define CSR_VTYPE 0xc21
+
/* User Timers and Counters */
#define CSR_CYCLE 0xc00
#define CSR_TIME0xc01
diff --git a/target/riscv/csr.c b/target/riscv/csr.c
index 383be0a955..ac01c835e1 100644
--- a/target/riscv/csr.c
+++ b/target/riscv/csr.c
@@ -46,6 +46,10 @@ void riscv_set_csr_ops(int csrno, riscv_csr_operations *ops)
static int fs(CPURISCVState *env, int csrno)
{
#if !defined(CONFIG_USER_ONLY)
+/* loose check condition for fcsr in vector extension */
+if ((csrno == CSR_FCSR) && (env->misa & RVV)) {
+return 0;
+}
if (!env->debugger && !riscv_cpu_fp_enabled(env)) {
return -1;
}
@@ -53,6 +57,14 @@ static int fs(CPURISCVState *env, int csrno)
return 0;
}
+static int vs(CPURISCVState *env, int csrno)
+{
+if (env->misa & RVV) {
+return 0;
+}
+return -1;
+}
+
static int ctr(CPURISCVState *env, int csrno)
{
#if !defined(CONFIG_USER_ONLY)
@@ -154,6 +166,10 @@ static int read_fcsr(CPURISCVState *env, int csrno,
target_ulong *val)
#endif
*val = (riscv_cpu_get_fflags(env) << FSR_AEXC_SHIFT)
| (env->frm << FSR_RD_SHIFT);
+if (vs(env, csrno) >= 0) {
+*val |= (env->vxrm << FSR_VXRM_SHIFT)
+| (env->vxsat << FSR_VXSAT_SHIFT);
+}
return 0;
}
@@ -166,10 +182,62 @@ static int write_fcsr(CPURISCVState *env, int csrno,
target_ulong val)
env->mstatus |= MSTATUS_FS;
#endif
env->frm = (val & FSR_RD) >> FSR_RD_SHIFT;
+if (vs(env, csrno) >= 0) {
+env->vxrm = (val & FSR_VXRM) >> FSR_VXRM_SHIFT;
+env->vxsat = (val & FSR_VXSAT) >> FSR_VXSAT_SHIFT;
+}
riscv_cpu_set_fflags(env, (val & FSR_AEXC) >> FSR_AEXC_SHIFT);
return 0;
}
+static int read_vtype(CPURISCVState *env, int csrno, target_ulong *val)
+{
+*val = env->vtype;
+return 0;
+}
+
+static int read_vl(CPURISCVState *env, int csrno, target_ulong *val)
+{
+*val = env->vl;
+return 0;
+}
+
+static int read_vxrm(CPURISCVState *env, int csrno, target_ulong *val)
+{
+*val = env->vxrm;
+return 0;
+}
+
+static int write_vxrm(CPURISCVState *env, int csrno, target_ulong val)
+{
+env->vxrm = val;
+return 0;
+}
+
+static int read_vxsat(CPURISCVState *env, int csrno, target_ulong *val)
+{
+*val = env->vxsat;
+return 0;
+}
+
+static int write_vxsat(CPURISCVState *env, int csrno, target_ulong val)
+{
+env->vxsat = val;
+return 0;
+}
+
+static int read_vstart(CPURISCVState *env, int csrno, target_ulong *val)
+{
+*val = env->vstart;
+return 0;
+}
+
+static int write_vstart(CPURISCVState *env, int csrno, target_ulong val)
+{
+env->vstart = val;
+return 0;
+}
+
/* User Timers and Counters */
static int read_instret(CPURISCVState *env, int csrno, target_ulong *val)
{
@@ -1183,7 +1251,12 @@ static riscv_csr_operations csr_ops[CSR_TABLE_SIZE] = {
[CSR_FFLAGS] = { fs, read_fflags, write_fflags },
[CSR_FRM] = { fs, read_frm, write_frm },
[CSR_FCSR] ={ fs, read_fcsr,write_fcsr},
-
+/* Vector CSRs */
+[CSR_VSTART] = { vs, read_vstart, write_vstart },
+[CSR_VXSAT] = { vs, read_vxsat, write_vxsat },
+[CSR_VXRM] ={ vs, read_vxrm,write_vxrm},
+[CSR_VL] = { vs, read_vl },
+[CSR_VTYPE] = { vs, read_vtype
[PATCH v10 02/61] target/riscv: implementation-defined constant parameters
vlen is the vector register length in bits.
elen is the max element size in bits.
vext_spec is the vector specification version, default value is v0.7.1.
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/cpu.c | 7 +++
target/riscv/cpu.h | 5 +
2 files changed, 12 insertions(+)
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index 391a0b9eec..d525cfb687 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -106,6 +106,11 @@ static void set_priv_version(CPURISCVState *env, int
priv_ver)
env->priv_ver = priv_ver;
}
+static void set_vext_version(CPURISCVState *env, int vext_ver)
+{
+env->vext_ver = vext_ver;
+}
+
static void set_feature(CPURISCVState *env, int feature)
{
env->features |= (1ULL << feature);
@@ -334,6 +339,7 @@ static void riscv_cpu_realize(DeviceState *dev, Error
**errp)
CPURISCVState *env = >env;
RISCVCPUClass *mcc = RISCV_CPU_GET_CLASS(dev);
int priv_version = PRIV_VERSION_1_11_0;
+int vext_version = VEXT_VERSION_0_07_1;
target_ulong target_misa = 0;
Error *local_err = NULL;
@@ -357,6 +363,7 @@ static void riscv_cpu_realize(DeviceState *dev, Error
**errp)
}
set_priv_version(env, priv_version);
+set_vext_version(env, vext_version);
if (cpu->cfg.mmu) {
set_feature(env, RISCV_FEATURE_MMU);
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index 0018a79fa3..302e0859a0 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -78,6 +78,8 @@ enum {
#define PRIV_VERSION_1_10_0 0x00011000
#define PRIV_VERSION_1_11_0 0x00011100
+#define VEXT_VERSION_0_07_1 0x0701
+
#define TRANSLATE_PMP_FAIL 2
#define TRANSLATE_FAIL 1
#define TRANSLATE_SUCCESS 0
@@ -113,6 +115,7 @@ struct CPURISCVState {
target_ulong guest_phys_fault_addr;
target_ulong priv_ver;
+target_ulong vext_ver;
target_ulong misa;
target_ulong misa_mask;
@@ -275,6 +278,8 @@ typedef struct RISCVCPU {
char *priv_spec;
char *user_spec;
+uint16_t vlen;
+uint16_t elen;
bool mmu;
bool pmp;
} cfg;
--
2.23.0
[PATCH v10 01/61] target/riscv: add vector extension field in CPURISCVState
The 32 vector registers will be viewed as a continuous memory block.
It avoids the convension between element index and (regno, offset).
Thus elements can be directly accessed by offset from the first vector
base address.
Signed-off-by: LIU Zhiwei
Acked-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/cpu.h | 12
target/riscv/translate.c | 3 ++-
2 files changed, 14 insertions(+), 1 deletion(-)
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index 80569f0d44..0018a79fa3 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -59,6 +59,7 @@
#define RVA RV('A')
#define RVF RV('F')
#define RVD RV('D')
+#define RVV RV('V')
#define RVC RV('C')
#define RVS RV('S')
#define RVU RV('U')
@@ -88,9 +89,20 @@ typedef struct CPURISCVState CPURISCVState;
#include "pmp.h"
+#define RV_VLEN_MAX 512
+
struct CPURISCVState {
target_ulong gpr[32];
uint64_t fpr[32]; /* assume both F and D extensions */
+
+/* vector coprocessor state. */
+uint64_t vreg[32 * RV_VLEN_MAX / 64] QEMU_ALIGNED(16);
+target_ulong vxrm;
+target_ulong vxsat;
+target_ulong vl;
+target_ulong vstart;
+target_ulong vtype;
+
target_ulong pc;
target_ulong load_res;
target_ulong load_val;
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index ce71ca7a92..b269f15920 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -32,7 +32,7 @@
#include "instmap.h"
/* global register indices */
-static TCGv cpu_gpr[32], cpu_pc;
+static TCGv cpu_gpr[32], cpu_pc, cpu_vl;
static TCGv_i64 cpu_fpr[32]; /* assume F and D extensions */
static TCGv load_res;
static TCGv load_val;
@@ -887,6 +887,7 @@ void riscv_translate_init(void)
}
cpu_pc = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, pc), "pc");
+cpu_vl = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, vl), "vl");
load_res = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, load_res),
"load_res");
load_val = tcg_global_mem_new(cpu_env, offsetof(CPURISCVState, load_val),
--
2.23.0
[PATCH v10 00/61] target/riscv: support vector extension v0.7.1
This patchset implements the vector extension for RISC-V on QEMU.
You can also find the patchset and all *test cases* in
my repo(https://github.com/romanheros/qemu.git branch:vector-upstream-v10).
All the test cases are in the directory qemu/tests/riscv/vector/. They are
riscv64 linux user mode programs.
You can test the patchset by the script qemu/tests/riscv/vector/runcase.sh.
Features:
* support specification
riscv-v-spec-0.7.1.(https://github.com/riscv/riscv-v-spec/releases/tag/0.7.1/)
* support basic vector extension.
* support Zvlsseg.
* support Zvamo.
* not support Zvediv as it is changing.
* SLEN always equals VLEN.
* element width support 8bit, 16bit, 32bit, 64bit.
Changelog:
v10
* rebase to https://github.com/alistair23/qemu/tree/riscv-to-apply.next.
* fix compile error in patch 57/61.
* fix review tag typo.
v9
* always set dynamic rounding mode for vector float insns.
* bug fix atomic implementation.
* bug fix first-only-fault.
* some small tidy up.
v8
* support different float rounding modes for vector instructions.
* use lastest released TCG GVEC DUP IR.
* set RV_VLEN_MAX to 256 bits, as GVEC IR uses simd_desc.
v7
* move vl == 0 check to translation time by add a global cpu_vl.
* implement vector element inline load and store function by TCG IR.
* based on vec_element_load(store), implement some permutation instructions.
* implement rsubs GVEC IR.
* fixup vsmul, vmfne, vfmerge, vslidedown.
* some other small bugs and indentation errors.
v6
* use gvec_dup Gvec IR to accellerate move and merge.
* a better way to implement fixed point instructions.
* a global check when vl == 0.
* limit some macros to only one inline function call.
* fixup sew error when use Gvec IR.
* fixup bugs for corner cases.
v5
* fixup a bug in tb flags.
v4
* no change
v3
* move check code from execution-time to translation-time
* use a continous memory block for vector register description.
* vector registers as direct fields in RISCVCPUState.
* support VLEN configure from qemu command line.
* support ELEN configure from qemu command line.
* support vector specification version configure from qemu command line.
* probe pages before real load or store access.
* use probe_page_check for no-fault operations in linux user mode.
* generation atomic exit exception when in parallel environment.
* fixup a lot of concrete bugs.
V2
* use float16_compare{_quiet}
* only use GETPC() in outer most helper
* add ctx.ext_v Property
LIU Zhiwei (61):
target/riscv: add vector extension field in CPURISCVState
target/riscv: implementation-defined constant parameters
target/riscv: support vector extension csr
target/riscv: add vector configure instruction
target/riscv: add an internals.h header
target/riscv: add vector stride load and store instructions
target/riscv: add vector index load and store instructions
target/riscv: add fault-only-first unit stride load
target/riscv: add vector amo operations
target/riscv: vector single-width integer add and subtract
target/riscv: vector widening integer add and subtract
target/riscv: vector integer add-with-carry / subtract-with-borrow
instructions
target/riscv: vector bitwise logical instructions
target/riscv: vector single-width bit shift instructions
target/riscv: vector narrowing integer right shift instructions
target/riscv: vector integer comparison instructions
target/riscv: vector integer min/max instructions
target/riscv: vector single-width integer multiply instructions
target/riscv: vector integer divide instructions
target/riscv: vector widening integer multiply instructions
target/riscv: vector single-width integer multiply-add instructions
target/riscv: vector widening integer multiply-add instructions
target/riscv: vector integer merge and move instructions
target/riscv: vector single-width saturating add and subtract
target/riscv: vector single-width averaging add and subtract
target/riscv: vector single-width fractional multiply with rounding
and saturation
target/riscv: vector widening saturating scaled multiply-add
target/riscv: vector single-width scaling shift instructions
target/riscv: vector narrowing fixed-point clip instructions
target/riscv: vector single-width floating-point add/subtract
instructions
target/riscv: vector widening floating-point add/subtract instructions
target/riscv: vector single-width floating-point multiply/divide
instructions
target/riscv: vector widening floating-point multiply
target/riscv: vector single-width floating-point fused multiply-add
instructions
target/riscv: vector widening floating-point fused multiply-add
instructions
target/riscv: vector floating-point square-root instruction
target/riscv: vector floating-point min/max instructions
target/riscv: vector floating-point sign-injection instructions
target/riscv: vector floating-point
Re: [PATCH v9 57/61] target/riscv: floating-point scalar move instructions
On 2020/6/20 9:06, Alistair Francis wrote:
On Fri, Jun 19, 2020 at 6:09 PM LIU Zhiwei wrote:
On 2020/6/20 8:44, Alistair Francis wrote:
On Wed, Jun 10, 2020 at 6:44 AM LIU Zhiwei wrote:
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Hello,
This patch fails to compile with this error:
target/riscv/insn32.decode:566: error: undefined format @r2rd
Do you mind looking into why this test fails?
Sorry, it's a mistake.
the @r2rd is defined in the next patch "[PATCH v9 58/61] target/riscv:
vector slide instructions", where doesn't need the definition at all.
When I split patch set, I must make a mistake here. After that I only
build and tested the whole patch set.
Thanks for pointing it.
No worries.
Do you mind fixing that problem and also rebasing the series on this
branch (it should be in master in a few days):
https://github.com/alistair23/qemu/tree/riscv-to-apply.next
Then send a new patch series.
Of course not.
I will rebase and send it later.
Zhiwei
Alistair
Zhiwei
Alistair
---
target/riscv/insn32.decode | 2 +
target/riscv/insn_trans/trans_rvv.inc.c | 49 +
2 files changed, 51 insertions(+)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 0741a25540..79f9b37b29 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -563,6 +563,8 @@ viota_m 010110 . . 1 010 . 1010111
@r2_vm
vid_v 010110 . 0 10001 010 . 1010111 @r1_vm
vext_x_v001100 1 . . 010 . 1010111 @r
vmv_s_x 001101 1 0 . 110 . 1010111 @r2
+vfmv_f_s001100 1 . 0 001 . 1010111 @r2rd
+vfmv_s_f001101 1 0 . 101 . 1010111 @r2
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index e67eff0a7f..884ad910b1 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2709,3 +2709,52 @@ static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_x
*a)
}
return false;
}
+
+/* Floating-Point Scalar Move Instructions */
+static bool trans_vfmv_f_s(DisasContext *s, arg_vfmv_f_s *a)
+{
+if (!s->vill && has_ext(s, RVF) &&
+(s->mstatus_fs != 0) && (s->sew != 0)) {
+unsigned int len = 8 << s->sew;
+
+vec_element_loadi(s, cpu_fpr[a->rd], a->rs2, 0);
+if (len < 64) {
+tcg_gen_ori_i64(cpu_fpr[a->rd], cpu_fpr[a->rd],
+MAKE_64BIT_MASK(len, 64 - len));
+}
+
+mark_fs_dirty(s);
+return true;
+}
+return false;
+}
+
+/* vfmv.s.f vd, rs1 # vd[0] = rs1 (vs2=0) */
+static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv_s_f *a)
+{
+if (!s->vill && has_ext(s, RVF) && (s->sew != 0)) {
+TCGv_i64 t1;
+/* The instructions ignore LMUL and vector register group. */
+uint32_t vlmax = s->vlen >> 3;
+
+/* if vl == 0, skip vector register write back */
+TCGLabel *over = gen_new_label();
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+/* zeroed all elements */
+tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd), vlmax, vlmax, 0);
+
+/* NaN-box f[rs1] as necessary for SEW */
+t1 = tcg_temp_new_i64();
+if (s->sew == MO_64 && !has_ext(s, RVD)) {
+tcg_gen_ori_i64(t1, cpu_fpr[a->rs1], MAKE_64BIT_MASK(32, 32));
+} else {
+tcg_gen_mov_i64(t1, cpu_fpr[a->rs1]);
+}
+vec_element_storei(s, a->rd, 0, t1);
+tcg_temp_free_i64(t1);
+gen_set_label(over);
+return true;
+}
+return false;
+}
--
2.23.0
Re: [PATCH v9 57/61] target/riscv: floating-point scalar move instructions
On 2020/6/20 8:44, Alistair Francis wrote:
On Wed, Jun 10, 2020 at 6:44 AM LIU Zhiwei wrote:
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Hello,
This patch fails to compile with this error:
target/riscv/insn32.decode:566: error: undefined format @r2rd
Do you mind looking into why this test fails?
Sorry, it's a mistake.
the @r2rd is defined in the next patch "[PATCH v9 58/61] target/riscv:
vector slide instructions", where doesn't need the definition at all.
When I split patch set, I must make a mistake here. After that I only
build and tested the whole patch set.
Thanks for pointing it.
Zhiwei
Alistair
---
target/riscv/insn32.decode | 2 +
target/riscv/insn_trans/trans_rvv.inc.c | 49 +
2 files changed, 51 insertions(+)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 0741a25540..79f9b37b29 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -563,6 +563,8 @@ viota_m 010110 . . 1 010 . 1010111
@r2_vm
vid_v 010110 . 0 10001 010 . 1010111 @r1_vm
vext_x_v001100 1 . . 010 . 1010111 @r
vmv_s_x 001101 1 0 . 110 . 1010111 @r2
+vfmv_f_s001100 1 . 0 001 . 1010111 @r2rd
+vfmv_s_f001101 1 0 . 101 . 1010111 @r2
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index e67eff0a7f..884ad910b1 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2709,3 +2709,52 @@ static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_x
*a)
}
return false;
}
+
+/* Floating-Point Scalar Move Instructions */
+static bool trans_vfmv_f_s(DisasContext *s, arg_vfmv_f_s *a)
+{
+if (!s->vill && has_ext(s, RVF) &&
+(s->mstatus_fs != 0) && (s->sew != 0)) {
+unsigned int len = 8 << s->sew;
+
+vec_element_loadi(s, cpu_fpr[a->rd], a->rs2, 0);
+if (len < 64) {
+tcg_gen_ori_i64(cpu_fpr[a->rd], cpu_fpr[a->rd],
+MAKE_64BIT_MASK(len, 64 - len));
+}
+
+mark_fs_dirty(s);
+return true;
+}
+return false;
+}
+
+/* vfmv.s.f vd, rs1 # vd[0] = rs1 (vs2=0) */
+static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv_s_f *a)
+{
+if (!s->vill && has_ext(s, RVF) && (s->sew != 0)) {
+TCGv_i64 t1;
+/* The instructions ignore LMUL and vector register group. */
+uint32_t vlmax = s->vlen >> 3;
+
+/* if vl == 0, skip vector register write back */
+TCGLabel *over = gen_new_label();
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+/* zeroed all elements */
+tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd), vlmax, vlmax, 0);
+
+/* NaN-box f[rs1] as necessary for SEW */
+t1 = tcg_temp_new_i64();
+if (s->sew == MO_64 && !has_ext(s, RVD)) {
+tcg_gen_ori_i64(t1, cpu_fpr[a->rs1], MAKE_64BIT_MASK(32, 32));
+} else {
+tcg_gen_mov_i64(t1, cpu_fpr[a->rs1]);
+}
+vec_element_storei(s, a->rd, 0, t1);
+tcg_temp_free_i64(t1);
+gen_set_label(over);
+return true;
+}
+return false;
+}
--
2.23.0
Re: fpu/softfloat: a question on BFloat 16 support on QEMU
On 2020/6/8 23:50, Alex Bennée wrote: LIU Zhiwei writes: Hi Richard, I am doing bfloat16 support on QEMU. Once I tried to reuse float32 interface, but I couldn't properly process rounding in some insns like fadd. What do you mean by re-use the float32 interface? Isn't bfloat16 going to be pretty much the same as float16 but with some slightly different float parameters for the different encoding? Like the float16 code it won't have to deal with any of the hardfloat wrappers so it should look pretty similar. What's your opinion about it? Should I expand the fpu/softfloat? bfloat16 is certainly going to become more common that we should have common softfloat code to handle it. It would be nice is TestFloat could exercise it as well. Hi Alex, I have add the bfloat16 interfaces in QEMU softfloat. Now I moved forward to test the bfloat16 interfaces. When I looked into the fp-test.c and the berkeley-testfloat-3, I found it's some difficult to add bfloat16 interfaces test cases. There are no corresponding bfloat16 slow_X interlaces in slowfloat.c. Nor there is bfloat16 test_X interfaces in berkeley-testfloat-3. case F16_MULADD:  test_abcz_f16(slow_f16_mulAdd, qemu_f16_mulAdd);  break; If I want to test bfloat16 interfaces, could you give some advice? Should I need to modify berkeley-testfloat-3 to support the bfloat16 test. Best Regards, Zhiwei Best Regards, Zhiwei
Re: [PATCH v9 39/61] target/riscv: vector floating-point compare instructions
On 2020/6/11 1:33, Richard Henderson wrote: On 6/10/20 4:37 AM, LIU Zhiwei wrote: Signed-off-by: LIU Zhiwei Reviewed-by: Alistair Francis Richard Henderson --- Missed the actual "Reviewed-by:" :-) I tried to make a reasonable explanation, but failed:-). "Reviewed-by: " is really what I mean here. Zhiwei r~
[PATCH v9 61/61] target/riscv: configure and turn on vector extension from command line
Vector extension is default off. The only way to use vector extension is
1. use cpu rv32 or rv64
2. turn on it by command line
"-cpu rv64,x-v=true,vlen=128,elen=64,vext_spec=v0.7.1".
vlen is the vector register length, default value is 128 bit.
elen is the max operator size in bits, default value is 64 bit.
vext_spec is the vector specification version, default value is v0.7.1.
These properties can be specified with other values.
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/cpu.c | 43 +++
target/riscv/cpu.h | 4 +++-
2 files changed, 46 insertions(+), 1 deletion(-)
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index 1af79404fa..33483acd25 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -457,6 +457,45 @@ static void riscv_cpu_realize(DeviceState *dev, Error
**errp)
if (cpu->cfg.ext_h) {
target_misa |= RVH;
}
+if (cpu->cfg.ext_v) {
+target_misa |= RVV;
+if (!is_power_of_2(cpu->cfg.vlen)) {
+error_setg(errp,
+"Vector extension VLEN must be power of 2");
+return;
+}
+if (cpu->cfg.vlen > RV_VLEN_MAX || cpu->cfg.vlen < 128) {
+error_setg(errp,
+"Vector extension implementation only supports VLEN "
+"in the range [128, %d]", RV_VLEN_MAX);
+return;
+}
+if (!is_power_of_2(cpu->cfg.elen)) {
+error_setg(errp,
+"Vector extension ELEN must be power of 2");
+return;
+}
+if (cpu->cfg.elen > 64 || cpu->cfg.vlen < 8) {
+error_setg(errp,
+"Vector extension implementation only supports ELEN "
+"in the range [8, 64]");
+return;
+}
+if (cpu->cfg.vext_spec) {
+if (!g_strcmp0(cpu->cfg.vext_spec, "v0.7.1")) {
+vext_version = VEXT_VERSION_0_07_1;
+} else {
+error_setg(errp,
+ "Unsupported vector spec version '%s'",
+ cpu->cfg.vext_spec);
+return;
+}
+} else {
+qemu_log("vector verison is not specified, "
+"use the default value v0.7.1\n");
+}
+set_vext_version(env, vext_version);
+}
set_misa(env, RVXLEN | target_misa);
}
@@ -496,10 +535,14 @@ static Property riscv_cpu_properties[] = {
DEFINE_PROP_BOOL("u", RISCVCPU, cfg.ext_u, true),
/* This is experimental so mark with 'x-' */
DEFINE_PROP_BOOL("x-h", RISCVCPU, cfg.ext_h, false),
+DEFINE_PROP_BOOL("x-v", RISCVCPU, cfg.ext_v, false),
DEFINE_PROP_BOOL("Counters", RISCVCPU, cfg.ext_counters, true),
DEFINE_PROP_BOOL("Zifencei", RISCVCPU, cfg.ext_ifencei, true),
DEFINE_PROP_BOOL("Zicsr", RISCVCPU, cfg.ext_icsr, true),
DEFINE_PROP_STRING("priv_spec", RISCVCPU, cfg.priv_spec),
+DEFINE_PROP_STRING("vext_spec", RISCVCPU, cfg.vext_spec),
+DEFINE_PROP_UINT16("vlen", RISCVCPU, cfg.vlen, 128),
+DEFINE_PROP_UINT16("elen", RISCVCPU, cfg.elen, 64),
DEFINE_PROP_BOOL("mmu", RISCVCPU, cfg.mmu, true),
DEFINE_PROP_BOOL("pmp", RISCVCPU, cfg.pmp, true),
DEFINE_PROP_END_OF_LIST(),
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index 0ad51c6580..eef20ca6e5 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -92,7 +92,7 @@ typedef struct CPURISCVState CPURISCVState;
#include "pmp.h"
-#define RV_VLEN_MAX 512
+#define RV_VLEN_MAX 256
FIELD(VTYPE, VLMUL, 0, 2)
FIELD(VTYPE, VSEW, 2, 3)
@@ -279,12 +279,14 @@ typedef struct RISCVCPU {
bool ext_s;
bool ext_u;
bool ext_h;
+bool ext_v;
bool ext_counters;
bool ext_ifencei;
bool ext_icsr;
char *priv_spec;
char *user_spec;
+char *vext_spec;
uint16_t vlen;
uint16_t elen;
bool mmu;
--
2.23.0
[PATCH v9 60/61] target/riscv: vector compress instruction
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 5
target/riscv/insn32.decode | 1 +
target/riscv/insn_trans/trans_rvv.inc.c | 32 +
target/riscv/vector_helper.c| 26
4 files changed, 64 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 3da863ac13..8d97114d81 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1139,3 +1139,8 @@ DEF_HELPER_6(vrgather_vx_b, void, ptr, ptr, tl, ptr, env,
i32)
DEF_HELPER_6(vrgather_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vrgather_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vrgather_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vcompress_vm_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vcompress_vm_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vcompress_vm_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vcompress_vm_d, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index e07ff7eff6..a37e205eb7 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -575,6 +575,7 @@ vslide1down_vx 00 . . . 110 . 1010111 @r_vm
vrgather_vv 001100 . . . 000 . 1010111 @r_vm
vrgather_vx 001100 . . . 100 . 1010111 @r_vm
vrgather_vi 001100 . . . 011 . 1010111 @r_vm
+vcompress_vm010111 - . . 010 . 1010111 @r
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index f6547f7e6d..ebc4e8174f 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2854,3 +2854,35 @@ static bool trans_vrgather_vi(DisasContext *s, arg_rmrr
*a)
}
return true;
}
+
+/* Vector Compress Instruction */
+static bool vcompress_vm_check(DisasContext *s, arg_r *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs2, false) &&
+vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs1, 1) &&
+(a->rd != a->rs2));
+}
+
+static bool trans_vcompress_vm(DisasContext *s, arg_r *a)
+{
+if (vcompress_vm_check(s, a)) {
+uint32_t data = 0;
+static gen_helper_gvec_4_ptr * const fns[4] = {
+gen_helper_vcompress_vm_b, gen_helper_vcompress_vm_h,
+gen_helper_vcompress_vm_w, gen_helper_vcompress_vm_d,
+};
+TCGLabel *over = gen_new_label();
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
+ vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),
+ cpu_env, 0, s->vlen / 8, data, fns[s->sew]);
+gen_set_label(over);
+return true;
+}
+return false;
+}
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 220fa76d54..e9e0b1e7a8 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4871,3 +4871,29 @@ GEN_VEXT_VRGATHER_VX(vrgather_vx_b, uint8_t, H1, clearb)
GEN_VEXT_VRGATHER_VX(vrgather_vx_h, uint16_t, H2, clearh)
GEN_VEXT_VRGATHER_VX(vrgather_vx_w, uint32_t, H4, clearl)
GEN_VEXT_VRGATHER_VX(vrgather_vx_d, uint64_t, H8, clearq)
+
+/* Vector Compress Instruction */
+#define GEN_VEXT_VCOMPRESS_VM(NAME, ETYPE, H, CLEAR_FN) \
+void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
+ CPURISCVState *env, uint32_t desc) \
+{ \
+uint32_t mlen = vext_mlen(desc); \
+uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \
+uint32_t vl = env->vl;\
+uint32_t num = 0, i; \
+ \
+for (i = 0; i < vl; i++) {\
+if (!vext_elem_mask(vs1, mlen, i)) { \
+continue; \
+} \
+*((ETYPE *)vd + H(num)) = *((ETYPE *)vs2 + H(i)); \
+num++;\
+} \
+CLEAR_FN(vd, num, num *
[PATCH v9 55/61] target/riscv: integer extract instruction
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
---
target/riscv/insn32.decode | 1 +
target/riscv/insn_trans/trans_rvv.inc.c | 116
2 files changed, 117 insertions(+)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 1231628cb2..26dd0f1b1b 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -561,6 +561,7 @@ vmsif_m 010110 . . 00011 010 . 1010111
@r2_vm
vmsof_m 010110 . . 00010 010 . 1010111 @r2_vm
viota_m 010110 . . 1 010 . 1010111 @r2_vm
vid_v 010110 . 0 10001 010 . 1010111 @r1_vm
+vext_x_v001100 1 . . 010 . 1010111 @r
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index e73e9dac33..0dedf4983d 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2533,3 +2533,119 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a)
}
return false;
}
+
+/*
+ *** Vector Permutation Instructions
+ */
+
+/* Integer Extract Instruction */
+
+static void load_element(TCGv_i64 dest, TCGv_ptr base,
+ int ofs, int sew)
+{
+switch (sew) {
+case MO_8:
+tcg_gen_ld8u_i64(dest, base, ofs);
+break;
+case MO_16:
+tcg_gen_ld16u_i64(dest, base, ofs);
+break;
+case MO_32:
+tcg_gen_ld32u_i64(dest, base, ofs);
+break;
+case MO_64:
+tcg_gen_ld_i64(dest, base, ofs);
+break;
+default:
+g_assert_not_reached();
+break;
+}
+}
+
+/* offset of the idx element with base regsiter r */
+static uint32_t endian_ofs(DisasContext *s, int r, int idx)
+{
+#ifdef HOST_WORDS_BIGENDIAN
+return vreg_ofs(s, r) + ((idx ^ (7 >> s->sew)) << s->sew);
+#else
+return vreg_ofs(s, r) + (idx << s->sew);
+#endif
+}
+
+/* adjust the index according to the endian */
+static void endian_adjust(TCGv_i32 ofs, int sew)
+{
+#ifdef HOST_WORDS_BIGENDIAN
+tcg_gen_xori_i32(ofs, ofs, 7 >> sew);
+#endif
+}
+
+/* Load idx >= VLMAX ? 0 : vreg[idx] */
+static void vec_element_loadx(DisasContext *s, TCGv_i64 dest,
+ int vreg, TCGv idx, int vlmax)
+{
+TCGv_i32 ofs = tcg_temp_new_i32();
+TCGv_ptr base = tcg_temp_new_ptr();
+TCGv_i64 t_idx = tcg_temp_new_i64();
+TCGv_i64 t_vlmax, t_zero;
+
+/*
+ * Mask the index to the length so that we do
+ * not produce an out-of-range load.
+ */
+tcg_gen_trunc_tl_i32(ofs, idx);
+tcg_gen_andi_i32(ofs, ofs, vlmax - 1);
+
+/* Convert the index to an offset. */
+endian_adjust(ofs, s->sew);
+tcg_gen_shli_i32(ofs, ofs, s->sew);
+
+/* Convert the index to a pointer. */
+tcg_gen_ext_i32_ptr(base, ofs);
+tcg_gen_add_ptr(base, base, cpu_env);
+
+/* Perform the load. */
+load_element(dest, base,
+ vreg_ofs(s, vreg), s->sew);
+tcg_temp_free_ptr(base);
+tcg_temp_free_i32(ofs);
+
+/* Flush out-of-range indexing to zero. */
+t_vlmax = tcg_const_i64(vlmax);
+t_zero = tcg_const_i64(0);
+tcg_gen_extu_tl_i64(t_idx, idx);
+
+tcg_gen_movcond_i64(TCG_COND_LTU, dest, t_idx,
+t_vlmax, dest, t_zero);
+
+tcg_temp_free_i64(t_vlmax);
+tcg_temp_free_i64(t_zero);
+tcg_temp_free_i64(t_idx);
+}
+
+static void vec_element_loadi(DisasContext *s, TCGv_i64 dest,
+ int vreg, int idx)
+{
+load_element(dest, cpu_env, endian_ofs(s, vreg, idx), s->sew);
+}
+
+static bool trans_vext_x_v(DisasContext *s, arg_r *a)
+{
+TCGv_i64 tmp = tcg_temp_new_i64();
+TCGv dest = tcg_temp_new();
+
+if (a->rs1 == 0) {
+/* Special case vmv.x.s rd, vs2. */
+vec_element_loadi(s, tmp, a->rs2, 0);
+} else {
+/* This instruction ignores LMUL and vector register groups */
+int vlmax = s->vlen >> (3 + s->sew);
+vec_element_loadx(s, tmp, a->rs2, cpu_gpr[a->rs1], vlmax);
+}
+tcg_gen_trunc_i64_tl(dest, tmp);
+gen_set_gpr(a->rd, dest);
+
+tcg_temp_free(dest);
+tcg_temp_free_i64(tmp);
+return true;
+}
--
2.23.0
[PATCH v9 57/61] target/riscv: floating-point scalar move instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
---
target/riscv/insn32.decode | 2 +
target/riscv/insn_trans/trans_rvv.inc.c | 49 +
2 files changed, 51 insertions(+)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 0741a25540..79f9b37b29 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -563,6 +563,8 @@ viota_m 010110 . . 1 010 . 1010111
@r2_vm
vid_v 010110 . 0 10001 010 . 1010111 @r1_vm
vext_x_v001100 1 . . 010 . 1010111 @r
vmv_s_x 001101 1 0 . 110 . 1010111 @r2
+vfmv_f_s001100 1 . 0 001 . 1010111 @r2rd
+vfmv_s_f001101 1 0 . 101 . 1010111 @r2
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index e67eff0a7f..884ad910b1 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2709,3 +2709,52 @@ static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_x
*a)
}
return false;
}
+
+/* Floating-Point Scalar Move Instructions */
+static bool trans_vfmv_f_s(DisasContext *s, arg_vfmv_f_s *a)
+{
+if (!s->vill && has_ext(s, RVF) &&
+(s->mstatus_fs != 0) && (s->sew != 0)) {
+unsigned int len = 8 << s->sew;
+
+vec_element_loadi(s, cpu_fpr[a->rd], a->rs2, 0);
+if (len < 64) {
+tcg_gen_ori_i64(cpu_fpr[a->rd], cpu_fpr[a->rd],
+MAKE_64BIT_MASK(len, 64 - len));
+}
+
+mark_fs_dirty(s);
+return true;
+}
+return false;
+}
+
+/* vfmv.s.f vd, rs1 # vd[0] = rs1 (vs2=0) */
+static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv_s_f *a)
+{
+if (!s->vill && has_ext(s, RVF) && (s->sew != 0)) {
+TCGv_i64 t1;
+/* The instructions ignore LMUL and vector register group. */
+uint32_t vlmax = s->vlen >> 3;
+
+/* if vl == 0, skip vector register write back */
+TCGLabel *over = gen_new_label();
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+/* zeroed all elements */
+tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd), vlmax, vlmax, 0);
+
+/* NaN-box f[rs1] as necessary for SEW */
+t1 = tcg_temp_new_i64();
+if (s->sew == MO_64 && !has_ext(s, RVD)) {
+tcg_gen_ori_i64(t1, cpu_fpr[a->rs1], MAKE_64BIT_MASK(32, 32));
+} else {
+tcg_gen_mov_i64(t1, cpu_fpr[a->rs1]);
+}
+vec_element_storei(s, a->rd, 0, t1);
+tcg_temp_free_i64(t1);
+gen_set_label(over);
+return true;
+}
+return false;
+}
--
2.23.0
[PATCH v9 54/61] target/riscv: vector element index instruction
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 5 +
target/riscv/insn32.decode | 2 ++
target/riscv/insn_trans/trans_rvv.inc.c | 25 +
target/riscv/vector_helper.c| 24
4 files changed, 56 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 90e6d31d78..9e80e4ca23 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1108,3 +1108,8 @@ DEF_HELPER_5(viota_m_b, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(viota_m_h, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(viota_m_w, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(viota_m_d, void, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_4(vid_v_b, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vid_v_h, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vid_v_w, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vid_v_d, void, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 37756fa76d..1231628cb2 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -70,6 +70,7 @@
@r2 ... . . ... . ... %rs1 %rd
@r2_nfvm ... ... vm:1 . . ... . ... %nf %rs1 %rd
@r2_vm .. vm:1 . . ... . ... %rs2 %rd
+@r1_vm .. vm:1 . . ... . ... %rd
@r_nfvm ... ... vm:1 . . ... . ... %nf %rs2 %rs1 %rd
@r_vm.. vm:1 . . ... . ... %rs2 %rs1 %rd
@r_vm_1 .. . . . ... . ... vm=1 %rs2 %rs1 %rd
@@ -559,6 +560,7 @@ vmsbf_m 010110 . . 1 010 . 1010111
@r2_vm
vmsif_m 010110 . . 00011 010 . 1010111 @r2_vm
vmsof_m 010110 . . 00010 010 . 1010111 @r2_vm
viota_m 010110 . . 1 010 . 1010111 @r2_vm
+vid_v 010110 . 0 10001 010 . 1010111 @r1_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index b109732d11..e73e9dac33 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2508,3 +2508,28 @@ static bool trans_viota_m(DisasContext *s, arg_viota_m
*a)
}
return false;
}
+
+/* Vector Element Index Instruction */
+static bool trans_vid_v(DisasContext *s, arg_vid_v *a)
+{
+if (vext_check_isa_ill(s) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_overlap_mask(s, a->rd, a->vm, false)) {
+uint32_t data = 0;
+TCGLabel *over = gen_new_label();
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
+data = FIELD_DP32(data, VDATA, VM, a->vm);
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+static gen_helper_gvec_2_ptr * const fns[4] = {
+gen_helper_vid_v_b, gen_helper_vid_v_h,
+gen_helper_vid_v_w, gen_helper_vid_v_d,
+};
+tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
+ cpu_env, 0, s->vlen / 8, data, fns[s->sew]);
+gen_set_label(over);
+return true;
+}
+return false;
+}
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d6283053f1..1dc2a1ccb1 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4673,3 +4673,27 @@ GEN_VEXT_VIOTA_M(viota_m_b, uint8_t, H1, clearb)
GEN_VEXT_VIOTA_M(viota_m_h, uint16_t, H2, clearh)
GEN_VEXT_VIOTA_M(viota_m_w, uint32_t, H4, clearl)
GEN_VEXT_VIOTA_M(viota_m_d, uint64_t, H8, clearq)
+
+/* Vector Element Index Instruction */
+#define GEN_VEXT_VID_V(NAME, ETYPE, H, CLEAR_FN) \
+void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc) \
+{ \
+uint32_t mlen = vext_mlen(desc); \
+uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \
+uint32_t vm = vext_vm(desc); \
+uint32_t vl = env->vl;\
+int i;\
+ \
+for (i = 0; i < vl; i++) {\
+if (!vm && !vext_elem_mask(v0, mlen, i)) {\
+continue; \
+} \
+*((ETYPE *)vd + H(i)) = i;\
+} \
+
[PATCH v9 53/61] target/riscv: vector iota instruction
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 5 +
target/riscv/insn32.decode | 1 +
target/riscv/insn_trans/trans_rvv.inc.c | 27 +++
target/riscv/vector_helper.c| 29 +
4 files changed, 62 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index ae93b6018d..90e6d31d78 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1103,3 +1103,8 @@ DEF_HELPER_4(vmfirst_m, tl, ptr, ptr, env, i32)
DEF_HELPER_5(vmsbf_m, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vmsif_m, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vmsof_m, void, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_5(viota_m_b, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(viota_m_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(viota_m_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(viota_m_d, void, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index b2bc6ab3dd..37756fa76d 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -558,6 +558,7 @@ vmfirst_m 010101 . . - 010 . 1010111
@r2_vm
vmsbf_m 010110 . . 1 010 . 1010111 @r2_vm
vmsif_m 010110 . . 00011 010 . 1010111 @r2_vm
vmsof_m 010110 . . 00010 010 . 1010111 @r2_vm
+viota_m 010110 . . 1 010 . 1010111 @r2_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 3b59170bed..b109732d11 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2481,3 +2481,30 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)
\
GEN_M_TRANS(vmsbf_m)
GEN_M_TRANS(vmsif_m)
GEN_M_TRANS(vmsof_m)
+
+/* Vector Iota Instruction */
+static bool trans_viota_m(DisasContext *s, arg_viota_m *a)
+{
+if (vext_check_isa_ill(s) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs2, 1) &&
+(a->vm != 0 || a->rd != 0)) {
+uint32_t data = 0;
+TCGLabel *over = gen_new_label();
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
+data = FIELD_DP32(data, VDATA, VM, a->vm);
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+static gen_helper_gvec_3_ptr * const fns[4] = {
+gen_helper_viota_m_b, gen_helper_viota_m_h,
+gen_helper_viota_m_w, gen_helper_viota_m_d,
+};
+tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
+ vreg_ofs(s, a->rs2), cpu_env, 0,
+ s->vlen / 8, data, fns[s->sew]);
+gen_set_label(over);
+return true;
+}
+return false;
+}
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 6a579a6300..d6283053f1 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4644,3 +4644,32 @@ void HELPER(vmsof_m)(void *vd, void *v0, void *vs2,
CPURISCVState *env,
{
vmsetm(vd, v0, vs2, env, desc, ONLY_FIRST);
}
+
+/* Vector Iota Instruction */
+#define GEN_VEXT_VIOTA_M(NAME, ETYPE, H, CLEAR_FN)\
+void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \
+ uint32_t desc) \
+{ \
+uint32_t mlen = vext_mlen(desc); \
+uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \
+uint32_t vm = vext_vm(desc); \
+uint32_t vl = env->vl;\
+uint32_t sum = 0; \
+int i;\
+ \
+for (i = 0; i < vl; i++) {\
+if (!vm && !vext_elem_mask(v0, mlen, i)) {\
+continue; \
+} \
+*((ETYPE *)vd + H(i)) = sum; \
+if (vext_elem_mask(vs2, mlen, i)) { \
+sum++;\
+} \
+} \
+CLEAR_FN
[PATCH v9 59/61] target/riscv: vector register gather instruction
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 9 +++
target/riscv/insn32.decode | 3 +
target/riscv/insn_trans/trans_rvv.inc.c | 78 +
target/riscv/vector_helper.c| 60 +++
4 files changed, 150 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 6a5e32d1e4..3da863ac13 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1130,3 +1130,12 @@ DEF_HELPER_6(vslide1down_vx_b, void, ptr, ptr, tl, ptr,
env, i32)
DEF_HELPER_6(vslide1down_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vslide1down_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vslide1down_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vrgather_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgather_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgather_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgather_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgather_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrgather_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrgather_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrgather_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 34ccad53a9..e07ff7eff6 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -572,6 +572,9 @@ vslide1up_vx001110 . . . 110 . 1010111 @r_vm
vslidedown_vx 00 . . . 100 . 1010111 @r_vm
vslidedown_vi 00 . . . 011 . 1010111 @r_vm
vslide1down_vx 00 . . . 110 . 1010111 @r_vm
+vrgather_vv 001100 . . . 000 . 1010111 @r_vm
+vrgather_vx 001100 . . . 100 . 1010111 @r_vm
+vrgather_vi 001100 . . . 011 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index ffb9835d07..f6547f7e6d 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2776,3 +2776,81 @@ GEN_OPIVI_TRANS(vslideup_vi, 1, vslideup_vx,
slideup_check)
GEN_OPIVX_TRANS(vslidedown_vx, opivx_check)
GEN_OPIVX_TRANS(vslide1down_vx, opivx_check)
GEN_OPIVI_TRANS(vslidedown_vi, 1, vslidedown_vx, opivx_check)
+
+/* Vector Register Gather Instruction */
+static bool vrgather_vv_check(DisasContext *s, arg_rmrr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs1, false) &&
+vext_check_reg(s, a->rs2, false) &&
+(a->rd != a->rs2) && (a->rd != a->rs1));
+}
+
+GEN_OPIVV_TRANS(vrgather_vv, vrgather_vv_check)
+
+static bool vrgather_vx_check(DisasContext *s, arg_rmrr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs2, false) &&
+(a->rd != a->rs2));
+}
+
+/* vrgather.vx vd, vs2, rs1, vm # vd[i] = (x[rs1] >= VLMAX) ? 0 : vs2[rs1] */
+static bool trans_vrgather_vx(DisasContext *s, arg_rmrr *a)
+{
+if (!vrgather_vx_check(s, a)) {
+return false;
+}
+
+if (a->vm && s->vl_eq_vlmax) {
+int vlmax = s->vlen / s->mlen;
+TCGv_i64 dest = tcg_temp_new_i64();
+
+if (a->rs1 == 0) {
+vec_element_loadi(s, dest, a->rs2, 0);
+} else {
+vec_element_loadx(s, dest, a->rs2, cpu_gpr[a->rs1], vlmax);
+}
+
+tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd),
+ MAXSZ(s), MAXSZ(s), dest);
+tcg_temp_free_i64(dest);
+} else {
+static gen_helper_opivx * const fns[4] = {
+gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h,
+gen_helper_vrgather_vx_w, gen_helper_vrgather_vx_d
+};
+return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s);
+}
+return true;
+}
+
+/* vrgather.vi vd, vs2, imm, vm # vd[i] = (imm >= VLMAX) ? 0 : vs2[imm] */
+static bool trans_vrgather_vi(DisasContext *s, arg_rmrr *a)
+{
+if (!vrgather_vx_check(s, a)) {
+return false;
+}
+
+if (a->vm && s->vl_eq_vlmax) {
+if (a->rs1 >= s->vlen / s->mlen) {
+tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd),
+ MAXSZ(s), MAXSZ(s), 0);
+} else {
+tcg_gen_gvec_dup_mem(s->sew, vreg_ofs(s, a->rd),
+
[PATCH v9 52/61] target/riscv: set-X-first mask bit
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 4 ++
target/riscv/insn32.decode | 3 ++
target/riscv/insn_trans/trans_rvv.inc.c | 28 +++
target/riscv/vector_helper.c| 63 +
4 files changed, 98 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index e78298e479..ae93b6018d 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1099,3 +1099,7 @@ DEF_HELPER_6(vmxnor_mm, void, ptr, ptr, ptr, ptr, env,
i32)
DEF_HELPER_4(vmpopc_m, tl, ptr, ptr, env, i32)
DEF_HELPER_4(vmfirst_m, tl, ptr, ptr, env, i32)
+
+DEF_HELPER_5(vmsbf_m, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vmsif_m, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vmsof_m, void, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 4c7706561a..b2bc6ab3dd 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -555,6 +555,9 @@ vmornot_mm 011100 - . . 010 . 1010111 @r
vmxnor_mm 01 - . . 010 . 1010111 @r
vmpopc_m010100 . . - 010 . 1010111 @r2_vm
vmfirst_m 010101 . . - 010 . 1010111 @r2_vm
+vmsbf_m 010110 . . 1 010 . 1010111 @r2_vm
+vmsif_m 010110 . . 00011 010 . 1010111 @r2_vm
+vmsof_m 010110 . . 00010 010 . 1010111 @r2_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 735ae8377e..3b59170bed 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2453,3 +2453,31 @@ static bool trans_vmfirst_m(DisasContext *s, arg_rmr *a)
}
return false;
}
+
+/* vmsbf.m set-before-first mask bit */
+/* vmsif.m set-includ-first mask bit */
+/* vmsof.m set-only-first mask bit */
+#define GEN_M_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
+{ \
+if (vext_check_isa_ill(s)) { \
+uint32_t data = 0; \
+gen_helper_gvec_3_ptr *fn = gen_helper_##NAME; \
+TCGLabel *over = gen_new_label(); \
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ \
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \
+data = FIELD_DP32(data, VDATA, VM, a->vm); \
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), \
+ vreg_ofs(s, 0), vreg_ofs(s, a->rs2),\
+ cpu_env, 0, s->vlen / 8, data, fn); \
+gen_set_label(over); \
+return true; \
+} \
+return false; \
+}
+
+GEN_M_TRANS(vmsbf_m)
+GEN_M_TRANS(vmsif_m)
+GEN_M_TRANS(vmsof_m)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d178ed4c0b..6a579a6300 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4581,3 +4581,66 @@ target_ulong HELPER(vmfirst_m)(void *v0, void *vs2,
CPURISCVState *env,
}
return -1LL;
}
+
+enum set_mask_type {
+ONLY_FIRST = 1,
+INCLUDE_FIRST,
+BEFORE_FIRST,
+};
+
+static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env,
+ uint32_t desc, enum set_mask_type type)
+{
+uint32_t mlen = vext_mlen(desc);
+uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen;
+uint32_t vm = vext_vm(desc);
+uint32_t vl = env->vl;
+int i;
+bool first_mask_bit = false;
+
+for (i = 0; i < vl; i++) {
+if (!vm && !vext_elem_mask(v0, mlen, i)) {
+continue;
+}
+/* write a zero to all following active elements */
+if (first_mask_bit) {
+vext_set_elem_mask(vd, mlen, i, 0);
+continue;
+}
+if (vext_elem_mask(vs2, mlen, i)) {
+first_mask_bit = true;
+if (type == BEFORE_FIRST) {
+vext_set_elem_mask(vd, mlen, i, 0);
+} else {
+vext_set_elem_mask(vd, mlen, i, 1);
+}
+} else {
+if (type == ONLY_FIRST) {
+vext_set_elem_mask(vd, mlen, i, 0);
+} else {
+vext_set_elem_mask(vd, mlen, i, 1);
+}
+}
+}
+for (; i < vlmax;
[PATCH v9 58/61] target/riscv: vector slide instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 17
target/riscv/insn32.decode | 7 ++
target/riscv/insn_trans/trans_rvv.inc.c | 18
target/riscv/vector_helper.c| 114
4 files changed, 156 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 9e80e4ca23..6a5e32d1e4 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1113,3 +1113,20 @@ DEF_HELPER_4(vid_v_b, void, ptr, ptr, env, i32)
DEF_HELPER_4(vid_v_h, void, ptr, ptr, env, i32)
DEF_HELPER_4(vid_v_w, void, ptr, ptr, env, i32)
DEF_HELPER_4(vid_v_d, void, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vslideup_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslideup_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslideup_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslideup_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslidedown_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslidedown_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslidedown_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslidedown_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslide1up_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslide1up_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslide1up_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslide1up_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslide1down_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslide1down_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslide1down_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslide1down_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 79f9b37b29..34ccad53a9 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -72,6 +72,7 @@
@r2_vm .. vm:1 . . ... . ... %rs2 %rd
@r1_vm .. vm:1 . . ... . ... %rd
@r_nfvm ... ... vm:1 . . ... . ... %nf %rs2 %rs1 %rd
+@r2rd... . . ... . ... %rs2 %rd
@r_vm.. vm:1 . . ... . ... %rs2 %rs1 %rd
@r_vm_1 .. . . . ... . ... vm=1 %rs2 %rs1 %rd
@r_vm_0 .. . . . ... . ... vm=0 %rs2 %rs1 %rd
@@ -565,6 +566,12 @@ vext_x_v001100 1 . . 010 . 1010111 @r
vmv_s_x 001101 1 0 . 110 . 1010111 @r2
vfmv_f_s001100 1 . 0 001 . 1010111 @r2rd
vfmv_s_f001101 1 0 . 101 . 1010111 @r2
+vslideup_vx 001110 . . . 100 . 1010111 @r_vm
+vslideup_vi 001110 . . . 011 . 1010111 @r_vm
+vslide1up_vx001110 . . . 110 . 1010111 @r_vm
+vslidedown_vx 00 . . . 100 . 1010111 @r_vm
+vslidedown_vi 00 . . . 011 . 1010111 @r_vm
+vslide1down_vx 00 . . . 110 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 884ad910b1..ffb9835d07 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2758,3 +2758,21 @@ static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv_s_f
*a)
}
return false;
}
+
+/* Vector Slide Instructions */
+static bool slideup_check(DisasContext *s, arg_rmrr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs2, false) &&
+(a->rd != a->rs2));
+}
+
+GEN_OPIVX_TRANS(vslideup_vx, slideup_check)
+GEN_OPIVX_TRANS(vslide1up_vx, slideup_check)
+GEN_OPIVI_TRANS(vslideup_vi, 1, vslideup_vx, slideup_check)
+
+GEN_OPIVX_TRANS(vslidedown_vx, opivx_check)
+GEN_OPIVX_TRANS(vslide1down_vx, opivx_check)
+GEN_OPIVI_TRANS(vslidedown_vi, 1, vslidedown_vx, opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 1dc2a1ccb1..28b54d2589 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4697,3 +4697,117 @@ GEN_VEXT_VID_V(vid_v_b, uint8_t, H1, clearb)
GEN_VEXT_VID_V(vid_v_h, uint16_t, H2, clearh)
GEN_VEXT_VID_V(vid_v_w, uint32_t, H4, clearl)
GEN_VEXT_VID_V(vid_v_d, uint64_t, H8, clearq)
+
+/*
+ *** Vector Permutation Instructions
+ */
+
+/* Vector Slide Instructions */
+#define GEN_VEXT_VSLIDEUP_VX(NAME, ETYPE, H, CLEAR_FN)\
+void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
+ CPURISCVState *env, uint32_t desc) \
+{
[PATCH v9 50/61] target/riscv: vector mask population count vmpopc
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 2 ++
target/riscv/insn32.decode | 1 +
target/riscv/insn_trans/trans_rvv.inc.c | 32 +
target/riscv/vector_helper.c| 20
4 files changed, 55 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 9bb4d8efd5..7ae41ebc2c 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1095,3 +1095,5 @@ DEF_HELPER_6(vmor_mm, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vmnor_mm, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vmornot_mm, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vmxnor_mm, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_4(vmpopc_m, tl, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index a4128c26a0..decb7f773f 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -553,6 +553,7 @@ vmor_mm 011010 - . . 010 . 1010111 @r
vmnor_mm00 - . . 010 . 1010111 @r
vmornot_mm 011100 - . . 010 . 1010111 @r
vmxnor_mm 01 - . . 010 . 1010111 @r
+vmpopc_m010100 . . - 010 . 1010111 @r2_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 13e2c31421..d1c8c6a11f 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2389,3 +2389,35 @@ GEN_MM_TRANS(vmor_mm)
GEN_MM_TRANS(vmnor_mm)
GEN_MM_TRANS(vmornot_mm)
GEN_MM_TRANS(vmxnor_mm)
+
+/* Vector mask population count vmpopc */
+static bool trans_vmpopc_m(DisasContext *s, arg_rmr *a)
+{
+if (vext_check_isa_ill(s)) {
+TCGv_ptr src2, mask;
+TCGv dst;
+TCGv_i32 desc;
+uint32_t data = 0;
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
+data = FIELD_DP32(data, VDATA, VM, a->vm);
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+
+mask = tcg_temp_new_ptr();
+src2 = tcg_temp_new_ptr();
+dst = tcg_temp_new();
+desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
+
+tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, a->rs2));
+tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0));
+
+gen_helper_vmpopc_m(dst, mask, src2, cpu_env, desc);
+gen_set_gpr(a->rd, dst);
+
+tcg_temp_free_ptr(mask);
+tcg_temp_free_ptr(src2);
+tcg_temp_free(dst);
+tcg_temp_free_i32(desc);
+return true;
+}
+return false;
+}
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 54c1b2e739..f572388981 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4542,3 +4542,23 @@ GEN_VEXT_MASK_VV(vmor_mm, DO_OR)
GEN_VEXT_MASK_VV(vmnor_mm, DO_NOR)
GEN_VEXT_MASK_VV(vmornot_mm, DO_ORNOT)
GEN_VEXT_MASK_VV(vmxnor_mm, DO_XNOR)
+
+/* Vector mask population count vmpopc */
+target_ulong HELPER(vmpopc_m)(void *v0, void *vs2, CPURISCVState *env,
+ uint32_t desc)
+{
+target_ulong cnt = 0;
+uint32_t mlen = vext_mlen(desc);
+uint32_t vm = vext_vm(desc);
+uint32_t vl = env->vl;
+int i;
+
+for (i = 0; i < vl; i++) {
+if (vm || vext_elem_mask(v0, mlen, i)) {
+if (vext_elem_mask(vs2, mlen, i)) {
+cnt++;
+}
+}
+}
+return cnt;
+}
--
2.23.0
[PATCH v9 51/61] target/riscv: vmfirst find-first-set mask bit
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 2 ++
target/riscv/insn32.decode | 1 +
target/riscv/insn_trans/trans_rvv.inc.c | 32 +
target/riscv/vector_helper.c| 19 +++
4 files changed, 54 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 7ae41ebc2c..e78298e479 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1097,3 +1097,5 @@ DEF_HELPER_6(vmornot_mm, void, ptr, ptr, ptr, ptr, env,
i32)
DEF_HELPER_6(vmxnor_mm, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_4(vmpopc_m, tl, ptr, ptr, env, i32)
+
+DEF_HELPER_4(vmfirst_m, tl, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index decb7f773f..4c7706561a 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -554,6 +554,7 @@ vmnor_mm00 - . . 010 . 1010111 @r
vmornot_mm 011100 - . . 010 . 1010111 @r
vmxnor_mm 01 - . . 010 . 1010111 @r
vmpopc_m010100 . . - 010 . 1010111 @r2_vm
+vmfirst_m 010101 . . - 010 . 1010111 @r2_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index d1c8c6a11f..735ae8377e 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2421,3 +2421,35 @@ static bool trans_vmpopc_m(DisasContext *s, arg_rmr *a)
}
return false;
}
+
+/* vmfirst find-first-set mask bit */
+static bool trans_vmfirst_m(DisasContext *s, arg_rmr *a)
+{
+if (vext_check_isa_ill(s)) {
+TCGv_ptr src2, mask;
+TCGv dst;
+TCGv_i32 desc;
+uint32_t data = 0;
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
+data = FIELD_DP32(data, VDATA, VM, a->vm);
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+
+mask = tcg_temp_new_ptr();
+src2 = tcg_temp_new_ptr();
+dst = tcg_temp_new();
+desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
+
+tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, a->rs2));
+tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0));
+
+gen_helper_vmfirst_m(dst, mask, src2, cpu_env, desc);
+gen_set_gpr(a->rd, dst);
+
+tcg_temp_free_ptr(mask);
+tcg_temp_free_ptr(src2);
+tcg_temp_free(dst);
+tcg_temp_free_i32(desc);
+return true;
+}
+return false;
+}
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index f572388981..d178ed4c0b 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4562,3 +4562,22 @@ target_ulong HELPER(vmpopc_m)(void *v0, void *vs2,
CPURISCVState *env,
}
return cnt;
}
+
+/* vmfirst find-first-set mask bit*/
+target_ulong HELPER(vmfirst_m)(void *v0, void *vs2, CPURISCVState *env,
+ uint32_t desc)
+{
+uint32_t mlen = vext_mlen(desc);
+uint32_t vm = vext_vm(desc);
+uint32_t vl = env->vl;
+int i;
+
+for (i = 0; i < vl; i++) {
+if (vm || vext_elem_mask(v0, mlen, i)) {
+if (vext_elem_mask(vs2, mlen, i)) {
+return i;
+}
+}
+}
+return -1LL;
+}
--
2.23.0
[PATCH v9 56/61] target/riscv: integer scalar move instruction
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
---
target/riscv/insn32.decode | 1 +
target/riscv/insn_trans/trans_rvv.inc.c | 60 +
target/riscv/internals.h| 6 +++
3 files changed, 67 insertions(+)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 26dd0f1b1b..0741a25540 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -562,6 +562,7 @@ vmsof_m 010110 . . 00010 010 . 1010111
@r2_vm
viota_m 010110 . . 1 010 . 1010111 @r2_vm
vid_v 010110 . 0 10001 010 . 1010111 @r1_vm
vext_x_v001100 1 . . 010 . 1010111 @r
+vmv_s_x 001101 1 0 . 110 . 1010111 @r2
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 0dedf4983d..e67eff0a7f 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2649,3 +2649,63 @@ static bool trans_vext_x_v(DisasContext *s, arg_r *a)
tcg_temp_free_i64(tmp);
return true;
}
+
+/* Integer Scalar Move Instruction */
+
+static void store_element(TCGv_i64 val, TCGv_ptr base,
+ int ofs, int sew)
+{
+switch (sew) {
+case MO_8:
+tcg_gen_st8_i64(val, base, ofs);
+break;
+case MO_16:
+tcg_gen_st16_i64(val, base, ofs);
+break;
+case MO_32:
+tcg_gen_st32_i64(val, base, ofs);
+break;
+case MO_64:
+tcg_gen_st_i64(val, base, ofs);
+break;
+default:
+g_assert_not_reached();
+break;
+}
+}
+
+/*
+ * Store vreg[idx] = val.
+ * The index must be in range of VLMAX.
+ */
+static void vec_element_storei(DisasContext *s, int vreg,
+ int idx, TCGv_i64 val)
+{
+store_element(val, cpu_env, endian_ofs(s, vreg, idx), s->sew);
+}
+
+/* vmv.s.x vd, rs1 # vd[0] = rs1 */
+static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_x *a)
+{
+if (vext_check_isa_ill(s)) {
+/* This instruction ignores LMUL and vector register groups */
+int maxsz = s->vlen >> 3;
+TCGv_i64 t1;
+TCGLabel *over = gen_new_label();
+
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd), maxsz, maxsz, 0);
+if (a->rs1 == 0) {
+goto done;
+}
+
+t1 = tcg_temp_new_i64();
+tcg_gen_extu_tl_i64(t1, cpu_gpr[a->rs1]);
+vec_element_storei(s, a->rd, 0, t1);
+tcg_temp_free_i64(t1);
+done:
+gen_set_label(over);
+return true;
+}
+return false;
+}
diff --git a/target/riscv/internals.h b/target/riscv/internals.h
index f3cea478f7..37d33820ad 100644
--- a/target/riscv/internals.h
+++ b/target/riscv/internals.h
@@ -32,4 +32,10 @@ FIELD(VDATA, WD, 11, 1)
target_ulong fclass_h(uint64_t frs1);
target_ulong fclass_s(uint64_t frs1);
target_ulong fclass_d(uint64_t frs1);
+
+#define SEW8 0
+#define SEW16 1
+#define SEW32 2
+#define SEW64 3
+
#endif
--
2.23.0
[PATCH v9 49/61] target/riscv: vector mask-register logical instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 9 ++
target/riscv/insn32.decode | 8 +
target/riscv/insn_trans/trans_rvv.inc.c | 35 ++
target/riscv/vector_helper.c| 40 +
4 files changed, 92 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 6b932b444d..9bb4d8efd5 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1086,3 +1086,12 @@ DEF_HELPER_6(vfredmin_vs_d, void, ptr, ptr, ptr, ptr,
env, i32)
DEF_HELPER_6(vfwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vfwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vmand_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmnand_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmandnot_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmxor_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmor_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmnor_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmornot_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmxnor_mm, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 526a964d28..a4128c26a0 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -545,6 +545,14 @@ vfredmin_vs 000101 . . . 001 . 1010111
@r_vm
vfredmax_vs 000111 . . . 001 . 1010111 @r_vm
# Vector widening ordered and unordered float reduction sum
vfwredsum_vs1100-1 . . . 001 . 1010111 @r_vm
+vmand_mm011001 - . . 010 . 1010111 @r
+vmnand_mm 011101 - . . 010 . 1010111 @r
+vmandnot_mm 011000 - . . 010 . 1010111 @r
+vmxor_mm011011 - . . 010 . 1010111 @r
+vmor_mm 011010 - . . 010 . 1010111 @r
+vmnor_mm00 - . . 010 . 1010111 @r
+vmornot_mm 011100 - . . 010 . 1010111 @r
+vmxnor_mm 01 - . . 010 . 1010111 @r
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 1f1559b0bd..13e2c31421 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2354,3 +2354,38 @@ GEN_OPFVV_TRANS(vfredmin_vs, reduction_check)
/* Vector Widening Floating-Point Reduction Instructions */
GEN_OPFVV_WIDEN_TRANS(vfwredsum_vs, reduction_check)
+
+/*
+ *** Vector Mask Operations
+ */
+
+/* Vector Mask-Register Logical Instructions */
+#define GEN_MM_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_r *a)\
+{ \
+if (vext_check_isa_ill(s)) { \
+uint32_t data = 0; \
+gen_helper_gvec_4_ptr *fn = gen_helper_##NAME; \
+TCGLabel *over = gen_new_label(); \
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ \
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
+ vreg_ofs(s, a->rs1),\
+ vreg_ofs(s, a->rs2), cpu_env, 0,\
+ s->vlen / 8, data, fn); \
+gen_set_label(over); \
+return true; \
+} \
+return false; \
+}
+
+GEN_MM_TRANS(vmand_mm)
+GEN_MM_TRANS(vmnand_mm)
+GEN_MM_TRANS(vmandnot_mm)
+GEN_MM_TRANS(vmxor_mm)
+GEN_MM_TRANS(vmor_mm)
+GEN_MM_TRANS(vmnor_mm)
+GEN_MM_TRANS(vmornot_mm)
+GEN_MM_TRANS(vmxnor_mm)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index e30f8f83d3..54c1b2e739 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4502,3 +4502,43 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void
*vs1,
*((uint64_t *)vd) = s1;
clearq(vd, 1, sizeof(uint64_t), tot);
}
+
+/*
+ *** Vector Mask Operations
+ */
+/* Vector Mask-Register Logical Instructions */
+#define GEN_VEXT_MASK_VV(NAME, OP)\
+void HELPER(NAME)(void *vd, void *v0, void *vs1, \
+ void *vs2, CPURISCVState *env, \
+
[PATCH v9 48/61] target/riscv: vector widening floating-point reduction instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 3 ++
target/riscv/insn32.decode | 2 ++
target/riscv/insn_trans/trans_rvv.inc.c | 3 ++
target/riscv/vector_helper.c| 46 +
4 files changed, 54 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 17fd02c323..6b932b444d 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1083,3 +1083,6 @@ DEF_HELPER_6(vfredmax_vs_d, void, ptr, ptr, ptr, ptr,
env, i32)
DEF_HELPER_6(vfredmin_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vfredmin_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vfredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vfwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 0592075167..526a964d28 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -543,6 +543,8 @@ vwredsum_vs 110001 . . . 000 . 1010111 @r_vm
vfredsum_vs -1 . . . 001 . 1010111 @r_vm
vfredmin_vs 000101 . . . 001 . 1010111 @r_vm
vfredmax_vs 000111 . . . 001 . 1010111 @r_vm
+# Vector widening ordered and unordered float reduction sum
+vfwredsum_vs1100-1 . . . 001 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 7e9d0ded37..1f1559b0bd 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2351,3 +2351,6 @@ GEN_OPIVV_WIDEN_TRANS(vwredsumu_vs, reduction_check)
GEN_OPFVV_TRANS(vfredsum_vs, reduction_check)
GEN_OPFVV_TRANS(vfredmax_vs, reduction_check)
GEN_OPFVV_TRANS(vfredmin_vs, reduction_check)
+
+/* Vector Widening Floating-Point Reduction Instructions */
+GEN_OPFVV_WIDEN_TRANS(vfwredsum_vs, reduction_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index ba961230f6..e30f8f83d3 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4456,3 +4456,49 @@ GEN_VEXT_FRED(vfredmax_vs_d, uint64_t, uint64_t, H8, H8,
float64_maxnum, clearq)
GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2, float16_minnum,
clearh)
GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4, float32_minnum,
clearl)
GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minnum,
clearq)
+
+/* Vector Widening Floating-Point Reduction Instructions */
+/* Unordered reduce 2*SEW = 2*SEW + sum(promote(SEW)) */
+void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1,
+void *vs2, CPURISCVState *env, uint32_t desc)
+{
+uint32_t mlen = vext_mlen(desc);
+uint32_t vm = vext_vm(desc);
+uint32_t vl = env->vl;
+uint32_t i;
+uint32_t tot = env_archcpu(env)->cfg.vlen / 8;
+uint32_t s1 = *((uint32_t *)vs1 + H4(0));
+
+for (i = 0; i < vl; i++) {
+uint16_t s2 = *((uint16_t *)vs2 + H2(i));
+if (!vm && !vext_elem_mask(v0, mlen, i)) {
+continue;
+}
+s1 = float32_add(s1, float16_to_float32(s2, true, >fp_status),
+ >fp_status);
+}
+*((uint32_t *)vd + H4(0)) = s1;
+clearl(vd, 1, sizeof(uint32_t), tot);
+}
+
+void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
+void *vs2, CPURISCVState *env, uint32_t desc)
+{
+uint32_t mlen = vext_mlen(desc);
+uint32_t vm = vext_vm(desc);
+uint32_t vl = env->vl;
+uint32_t i;
+uint32_t tot = env_archcpu(env)->cfg.vlen / 8;
+uint64_t s1 = *((uint64_t *)vs1);
+
+for (i = 0; i < vl; i++) {
+uint32_t s2 = *((uint32_t *)vs2 + H4(i));
+if (!vm && !vext_elem_mask(v0, mlen, i)) {
+continue;
+}
+s1 = float64_add(s1, float32_to_float64(s2, >fp_status),
+ >fp_status);
+}
+*((uint64_t *)vd) = s1;
+clearq(vd, 1, sizeof(uint64_t), tot);
+}
--
2.23.0
[PATCH v9 46/61] target/riscv: vector wideing integer reduction instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 7 +++ target/riscv/insn32.decode | 2 ++ target/riscv/insn_trans/trans_rvv.inc.c | 4 target/riscv/vector_helper.c| 11 +++ 4 files changed, 24 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 93a7a303ee..ce31577ea9 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -1066,3 +1066,10 @@ DEF_HELPER_6(vredxor_vs_b, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vredxor_vs_h, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vredxor_vs_w, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vredxor_vs_d, void, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vwredsumu_vs_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwredsumu_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwredsumu_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwredsum_vs_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 773b32f0b4..b69d804fda 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -537,6 +537,8 @@ vredminu_vs 000100 . . . 010 . 1010111 @r_vm vredmin_vs 000101 . . . 010 . 1010111 @r_vm vredmaxu_vs 000110 . . . 010 . 1010111 @r_vm vredmax_vs 000111 . . . 010 . 1010111 @r_vm +vwredsumu_vs11 . . . 000 . 1010111 @r_vm +vwredsum_vs 110001 . . . 000 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index b3920eed23..06842c424e 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -2342,3 +2342,7 @@ GEN_OPIVV_TRANS(vredmin_vs, reduction_check) GEN_OPIVV_TRANS(vredand_vs, reduction_check) GEN_OPIVV_TRANS(vredor_vs, reduction_check) GEN_OPIVV_TRANS(vredxor_vs, reduction_check) + +/* Vector Widening Integer Reduction Instructions */ +GEN_OPIVV_WIDEN_TRANS(vwredsum_vs, reduction_check) +GEN_OPIVV_WIDEN_TRANS(vwredsumu_vs, reduction_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 5c357b688f..fdeedad64f 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -4406,3 +4406,14 @@ GEN_VEXT_RED(vredxor_vs_b, int8_t, int8_t, H1, H1, DO_XOR, clearb) GEN_VEXT_RED(vredxor_vs_h, int16_t, int16_t, H2, H2, DO_XOR, clearh) GEN_VEXT_RED(vredxor_vs_w, int32_t, int32_t, H4, H4, DO_XOR, clearl) GEN_VEXT_RED(vredxor_vs_d, int64_t, int64_t, H8, H8, DO_XOR, clearq) + +/* Vector Widening Integer Reduction Instructions */ +/* signed sum reduction into double-width accumulator */ +GEN_VEXT_RED(vwredsum_vs_b, int16_t, int8_t, H2, H1, DO_ADD, clearh) +GEN_VEXT_RED(vwredsum_vs_h, int32_t, int16_t, H4, H2, DO_ADD, clearl) +GEN_VEXT_RED(vwredsum_vs_w, int64_t, int32_t, H8, H4, DO_ADD, clearq) + +/* Unsigned sum reduction into double-width accumulator */ +GEN_VEXT_RED(vwredsumu_vs_b, uint16_t, uint8_t, H2, H1, DO_ADD, clearh) +GEN_VEXT_RED(vwredsumu_vs_h, uint32_t, uint16_t, H4, H2, DO_ADD, clearl) +GEN_VEXT_RED(vwredsumu_vs_w, uint64_t, uint32_t, H8, H4, DO_ADD, clearq) -- 2.23.0
[PATCH v9 47/61] target/riscv: vector single-width floating-point reduction instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 10 +++
target/riscv/insn32.decode | 4 +++
target/riscv/insn_trans/trans_rvv.inc.c | 5
target/riscv/vector_helper.c| 39 +
4 files changed, 58 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index ce31577ea9..17fd02c323 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1073,3 +1073,13 @@ DEF_HELPER_6(vwredsumu_vs_w, void, ptr, ptr, ptr, ptr,
env, i32)
DEF_HELPER_6(vwredsum_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vfredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredsum_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredmax_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredmax_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredmax_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredmin_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredmin_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index b69d804fda..0592075167 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -539,6 +539,10 @@ vredmaxu_vs 000110 . . . 010 . 1010111
@r_vm
vredmax_vs 000111 . . . 010 . 1010111 @r_vm
vwredsumu_vs11 . . . 000 . 1010111 @r_vm
vwredsum_vs 110001 . . . 000 . 1010111 @r_vm
+# Vector ordered and unordered reduction sum
+vfredsum_vs -1 . . . 001 . 1010111 @r_vm
+vfredmin_vs 000101 . . . 001 . 1010111 @r_vm
+vfredmax_vs 000111 . . . 001 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 06842c424e..7e9d0ded37 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2346,3 +2346,8 @@ GEN_OPIVV_TRANS(vredxor_vs, reduction_check)
/* Vector Widening Integer Reduction Instructions */
GEN_OPIVV_WIDEN_TRANS(vwredsum_vs, reduction_check)
GEN_OPIVV_WIDEN_TRANS(vwredsumu_vs, reduction_check)
+
+/* Vector Single-Width Floating-Point Reduction Instructions */
+GEN_OPFVV_TRANS(vfredsum_vs, reduction_check)
+GEN_OPFVV_TRANS(vfredmax_vs, reduction_check)
+GEN_OPFVV_TRANS(vfredmin_vs, reduction_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index fdeedad64f..ba961230f6 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4417,3 +4417,42 @@ GEN_VEXT_RED(vwredsum_vs_w, int64_t, int32_t, H8, H4,
DO_ADD, clearq)
GEN_VEXT_RED(vwredsumu_vs_b, uint16_t, uint8_t, H2, H1, DO_ADD, clearh)
GEN_VEXT_RED(vwredsumu_vs_h, uint32_t, uint16_t, H4, H2, DO_ADD, clearl)
GEN_VEXT_RED(vwredsumu_vs_w, uint64_t, uint32_t, H8, H4, DO_ADD, clearq)
+
+/* Vector Single-Width Floating-Point Reduction Instructions */
+#define GEN_VEXT_FRED(NAME, TD, TS2, HD, HS2, OP, CLEAR_FN)\
+void HELPER(NAME)(void *vd, void *v0, void *vs1, \
+ void *vs2, CPURISCVState *env, \
+ uint32_t desc) \
+{ \
+uint32_t mlen = vext_mlen(desc); \
+uint32_t vm = vext_vm(desc); \
+uint32_t vl = env->vl; \
+uint32_t i;\
+uint32_t tot = env_archcpu(env)->cfg.vlen / 8; \
+TD s1 = *((TD *)vs1 + HD(0)); \
+ \
+for (i = 0; i < vl; i++) { \
+TS2 s2 = *((TS2 *)vs2 + HS2(i)); \
+if (!vm && !vext_elem_mask(v0, mlen, i)) { \
+continue; \
+} \
+s1 = OP(s1, (TD)s2, >fp_status); \
+} \
+*((TD *)vd + HD(0)) = s1; \
+CLEAR_FN(vd, 1, sizeof(TD), tot); \
+}
+
+/* Unordered sum */
+GEN_VEXT_FRED(vfredsum_vs_h, uint16_t, uint16_t, H2, H2, float16_add, clearh)
+GEN_VEXT_FRED(vfredsum_vs_w, uint32_t, uint32_t, H4, H4, float32_add, clearl)
+GEN_VEXT_FRED(vfredsum_vs_d, uint64_t, uint64_t, H8, H8, float64_add, clearq)
+
+/* Maximum val
[PATCH v9 45/61] target/riscv: vector single-width integer reduction instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 33 +++
target/riscv/insn32.decode | 8 +++
target/riscv/insn_trans/trans_rvv.inc.c | 18 ++
target/riscv/vector_helper.c| 74 +
4 files changed, 133 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 82c5d1129e..93a7a303ee 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1033,3 +1033,36 @@ DEF_HELPER_5(vfncvt_f_x_v_h, void, ptr, ptr, ptr, env,
i32)
DEF_HELPER_5(vfncvt_f_x_v_w, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfncvt_f_f_v_h, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfncvt_f_f_v_w, void, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vredsum_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredsum_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmaxu_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmaxu_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmaxu_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmaxu_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmax_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmax_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmax_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmax_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredminu_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredminu_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredminu_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredminu_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmin_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmin_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmin_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredand_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredand_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredand_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredand_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredor_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredor_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredor_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredor_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredxor_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredxor_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredxor_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredxor_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 57ac4de1c2..773b32f0b4 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -529,6 +529,14 @@ vfncvt_x_f_v100010 . . 10001 001 . 1010111
@r2_vm
vfncvt_f_xu_v 100010 . . 10010 001 . 1010111 @r2_vm
vfncvt_f_x_v100010 . . 10011 001 . 1010111 @r2_vm
vfncvt_f_f_v100010 . . 10100 001 . 1010111 @r2_vm
+vredsum_vs 00 . . . 010 . 1010111 @r_vm
+vredand_vs 01 . . . 010 . 1010111 @r_vm
+vredor_vs 10 . . . 010 . 1010111 @r_vm
+vredxor_vs 11 . . . 010 . 1010111 @r_vm
+vredminu_vs 000100 . . . 010 . 1010111 @r_vm
+vredmin_vs 000101 . . . 010 . 1010111 @r_vm
+vredmaxu_vs 000110 . . . 010 . 1010111 @r_vm
+vredmax_vs 000111 . . . 010 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 4e4631ac6a..b3920eed23 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2324,3 +2324,21 @@ GEN_OPFV_NARROW_TRANS(vfncvt_x_f_v)
GEN_OPFV_NARROW_TRANS(vfncvt_f_xu_v)
GEN_OPFV_NARROW_TRANS(vfncvt_f_x_v)
GEN_OPFV_NARROW_TRANS(vfncvt_f_f_v)
+
+/*
+ *** Vector Reduction Operations
+ */
+/* Vector Single-Width Integer Reduction Instructions */
+static bool reduction_check(DisasContext *s, arg_rmrr *a)
+{
+return vext_check_isa_ill(s) && vext_check_reg(s, a->rs2, false);
+}
+
+GEN_OPIVV_TRANS(vredsum_vs, reduction_check)
+GEN_OPIVV_TRANS(vredmaxu_vs, reduction_check)
+GEN_OPIVV_TRANS(vredmax_vs, reduction_check)
+GEN_OPIVV_TRANS(vredminu_vs, reduction_check)
+GEN_OPIVV_TRANS(vredmin_vs, reduction_check)
+GEN_OPIVV_TRANS(vredand_vs, reduction_check)
+GEN_OPIVV_TRANS(vredor_vs, reduction_check)
+GEN_OPIVV_TRANS(vredxor_vs, reduction_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index
[PATCH v9 44/61] target/riscv: narrowing floating-point/integer type-convert instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 11 ++
target/riscv/insn32.decode | 5 +++
target/riscv/insn_trans/trans_rvv.inc.c | 48 +
target/riscv/vector_helper.c| 39
4 files changed, 103 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index e59dcc5a7c..82c5d1129e 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1022,3 +1022,14 @@ DEF_HELPER_5(vfwcvt_f_x_v_h, void, ptr, ptr, ptr, env,
i32)
DEF_HELPER_5(vfwcvt_f_x_v_w, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfwcvt_f_f_v_h, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfwcvt_f_f_v_w, void, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_5(vfncvt_xu_f_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfncvt_xu_f_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfncvt_x_f_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfncvt_x_f_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfncvt_f_xu_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfncvt_f_xu_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfncvt_f_x_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfncvt_f_x_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfncvt_f_f_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfncvt_f_f_v_w, void, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index e0efc63ec2..57ac4de1c2 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -524,6 +524,11 @@ vfwcvt_x_f_v100010 . . 01001 001 . 1010111
@r2_vm
vfwcvt_f_xu_v 100010 . . 01010 001 . 1010111 @r2_vm
vfwcvt_f_x_v100010 . . 01011 001 . 1010111 @r2_vm
vfwcvt_f_f_v100010 . . 01100 001 . 1010111 @r2_vm
+vfncvt_xu_f_v 100010 . . 1 001 . 1010111 @r2_vm
+vfncvt_x_f_v100010 . . 10001 001 . 1010111 @r2_vm
+vfncvt_f_xu_v 100010 . . 10010 001 . 1010111 @r2_vm
+vfncvt_f_x_v100010 . . 10011 001 . 1010111 @r2_vm
+vfncvt_f_f_v100010 . . 10100 001 . 1010111 @r2_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index dd4182c327..4e4631ac6a 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2276,3 +2276,51 @@ GEN_OPFV_WIDEN_TRANS(vfwcvt_x_f_v)
GEN_OPFV_WIDEN_TRANS(vfwcvt_f_xu_v)
GEN_OPFV_WIDEN_TRANS(vfwcvt_f_x_v)
GEN_OPFV_WIDEN_TRANS(vfwcvt_f_f_v)
+
+/* Narrowing Floating-Point/Integer Type-Convert Instructions */
+
+/*
+ * If the current SEW does not correspond to a supported IEEE floating-point
+ * type, an illegal instruction exception is raised
+ */
+static bool opfv_narrow_check(DisasContext *s, arg_rmr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, false) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs2, true) &&
+vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs2,
+ 2 << s->lmul) &&
+(s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0));
+}
+
+#define GEN_OPFV_NARROW_TRANS(NAME)\
+static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
+{ \
+if (opfv_narrow_check(s, a)) { \
+uint32_t data = 0; \
+static gen_helper_gvec_3_ptr * const fns[2] = {\
+gen_helper_##NAME##_h, \
+gen_helper_##NAME##_w, \
+}; \
+TCGLabel *over = gen_new_label(); \
+gen_set_rm(s, 7); \
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ \
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \
+data = FIELD_DP32(data, VDATA, VM, a->vm); \
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
+ vreg_ofs(s, a->rs2), cpu_env, 0,\
+ s->vlen / 8, data, fns[s->sew - 1]);\
+gen_set_label(over); \
+return true; \
+}
[PATCH v9 43/61] target/riscv: widening floating-point/integer type-convert instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 11 ++
target/riscv/insn32.decode | 5 +++
target/riscv/insn_trans/trans_rvv.inc.c | 48 +
target/riscv/vector_helper.c| 42 ++
4 files changed, 106 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 05f8fb5ffc..e59dcc5a7c 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1011,3 +1011,14 @@ DEF_HELPER_5(vfcvt_f_xu_v_d, void, ptr, ptr, ptr, env,
i32)
DEF_HELPER_5(vfcvt_f_x_v_h, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfcvt_f_x_v_w, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfcvt_f_x_v_d, void, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_5(vfwcvt_xu_f_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_xu_f_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_x_f_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_x_f_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_f_xu_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_f_xu_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_f_x_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_f_x_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_f_f_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_f_f_v_w, void, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 53562c6663..e0efc63ec2 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -519,6 +519,11 @@ vfcvt_xu_f_v100010 . . 0 001 . 1010111
@r2_vm
vfcvt_x_f_v 100010 . . 1 001 . 1010111 @r2_vm
vfcvt_f_xu_v100010 . . 00010 001 . 1010111 @r2_vm
vfcvt_f_x_v 100010 . . 00011 001 . 1010111 @r2_vm
+vfwcvt_xu_f_v 100010 . . 01000 001 . 1010111 @r2_vm
+vfwcvt_x_f_v100010 . . 01001 001 . 1010111 @r2_vm
+vfwcvt_f_xu_v 100010 . . 01010 001 . 1010111 @r2_vm
+vfwcvt_f_x_v100010 . . 01011 001 . 1010111 @r2_vm
+vfwcvt_f_f_v100010 . . 01100 001 . 1010111 @r2_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index a2a851de87..dd4182c327 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2228,3 +2228,51 @@ GEN_OPFV_TRANS(vfcvt_xu_f_v, opfv_check)
GEN_OPFV_TRANS(vfcvt_x_f_v, opfv_check)
GEN_OPFV_TRANS(vfcvt_f_xu_v, opfv_check)
GEN_OPFV_TRANS(vfcvt_f_x_v, opfv_check)
+
+/* Widening Floating-Point/Integer Type-Convert Instructions */
+
+/*
+ * If the current SEW does not correspond to a supported IEEE floating-point
+ * type, an illegal instruction exception is raised
+ */
+static bool opfv_widen_check(DisasContext *s, arg_rmr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+vext_check_reg(s, a->rd, true) &&
+vext_check_reg(s, a->rs2, false) &&
+vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs2,
+ 1 << s->lmul) &&
+(s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0));
+}
+
+#define GEN_OPFV_WIDEN_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
+{ \
+if (opfv_widen_check(s, a)) { \
+uint32_t data = 0; \
+static gen_helper_gvec_3_ptr * const fns[2] = {\
+gen_helper_##NAME##_h, \
+gen_helper_##NAME##_w, \
+}; \
+TCGLabel *over = gen_new_label(); \
+gen_set_rm(s, 7); \
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ \
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \
+data = FIELD_DP32(data, VDATA, VM, a->vm); \
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
+ vreg_ofs(s, a->rs2), cpu_env, 0,\
+ s->vlen / 8, data, fns[s->sew - 1]);\
+gen_set_label(over); \
+return true;
[PATCH v9 42/61] target/riscv: vector floating-point/integer type-convert instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 13 ++ target/riscv/insn32.decode | 4 +++ target/riscv/insn_trans/trans_rvv.inc.c | 6 + target/riscv/vector_helper.c| 33 + 4 files changed, 56 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 21054cc957..05f8fb5ffc 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -998,3 +998,16 @@ DEF_HELPER_5(vfclass_v_d, void, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfmerge_vfm_h, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfmerge_vfm_w, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfmerge_vfm_d, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_5(vfcvt_xu_f_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_xu_f_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_xu_f_v_d, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_x_f_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_x_f_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_x_f_v_d, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_f_xu_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_f_xu_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_f_xu_v_d, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_f_x_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_f_x_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfcvt_f_x_v_d, void, ptr, ptr, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 14cb4e2e66..53562c6663 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -515,6 +515,10 @@ vmford_vf 011010 . . . 101 . 1010111 @r_vm vfclass_v 100011 . . 1 001 . 1010111 @r2_vm vfmerge_vfm 010111 0 . . 101 . 1010111 @r_vm_0 vfmv_v_f010111 1 0 . 101 . 1010111 @r2 +vfcvt_xu_f_v100010 . . 0 001 . 1010111 @r2_vm +vfcvt_x_f_v 100010 . . 1 001 . 1010111 @r2_vm +vfcvt_f_xu_v100010 . . 00010 001 . 1010111 @r2_vm +vfcvt_f_x_v 100010 . . 00011 001 . 1010111 @r2_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index 51ee83255e..a2a851de87 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -,3 +,9 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a) } return false; } + +/* Single-Width Floating-Point/Integer Type-Convert Instructions */ +GEN_OPFV_TRANS(vfcvt_xu_f_v, opfv_check) +GEN_OPFV_TRANS(vfcvt_x_f_v, opfv_check) +GEN_OPFV_TRANS(vfcvt_f_xu_v, opfv_check) +GEN_OPFV_TRANS(vfcvt_f_x_v, opfv_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 5a0dd9304d..354d69b800 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -4218,3 +4218,36 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ GEN_VFMERGE_VF(vfmerge_vfm_h, int16_t, H2, clearh) GEN_VFMERGE_VF(vfmerge_vfm_w, int32_t, H4, clearl) GEN_VFMERGE_VF(vfmerge_vfm_d, int64_t, H8, clearq) + +/* Single-Width Floating-Point/Integer Type-Convert Instructions */ +/* vfcvt.xu.f.v vd, vs2, vm # Convert float to unsigned integer. */ +RVVCALL(OPFVV1, vfcvt_xu_f_v_h, OP_UU_H, H2, H2, float16_to_uint16) +RVVCALL(OPFVV1, vfcvt_xu_f_v_w, OP_UU_W, H4, H4, float32_to_uint32) +RVVCALL(OPFVV1, vfcvt_xu_f_v_d, OP_UU_D, H8, H8, float64_to_uint64) +GEN_VEXT_V_ENV(vfcvt_xu_f_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfcvt_xu_f_v_w, 4, 4, clearl) +GEN_VEXT_V_ENV(vfcvt_xu_f_v_d, 8, 8, clearq) + +/* vfcvt.x.f.v vd, vs2, vm # Convert float to signed integer. */ +RVVCALL(OPFVV1, vfcvt_x_f_v_h, OP_UU_H, H2, H2, float16_to_int16) +RVVCALL(OPFVV1, vfcvt_x_f_v_w, OP_UU_W, H4, H4, float32_to_int32) +RVVCALL(OPFVV1, vfcvt_x_f_v_d, OP_UU_D, H8, H8, float64_to_int64) +GEN_VEXT_V_ENV(vfcvt_x_f_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfcvt_x_f_v_w, 4, 4, clearl) +GEN_VEXT_V_ENV(vfcvt_x_f_v_d, 8, 8, clearq) + +/* vfcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to float. */ +RVVCALL(OPFVV1, vfcvt_f_xu_v_h, OP_UU_H, H2, H2, uint16_to_float16) +RVVCALL(OPFVV1, vfcvt_f_xu_v_w, OP_UU_W, H4, H4, uint32_to_float32) +RVVCALL(OPFVV1, vfcvt_f_xu_v_d, OP_UU_D, H8, H8, uint64_to_float64) +GEN_VEXT_V_ENV(vfcvt_f_xu_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfcvt_f_xu_v_w, 4, 4, clearl) +GEN_VEXT_V_ENV(vfcvt_f_xu_v_d, 8, 8, clearq) + +/* vfcvt.f.x.v vd, vs2, vm # Convert integer to float. */ +RVVCALL(OPFVV1, vfcvt_f_x_v_h, OP_UU_H, H2, H2, int16_to_float16) +RVVCALL(OPFVV1, vfcvt_f_x_v_w, OP_UU_W, H4, H4, int32_to_float32) +RVVCALL(OPFVV1, vfcvt_f_x_v_d, OP_UU_D, H8, H8, int64_to_float64) +GEN_VEXT_V_ENV(vfcvt_f_x_v_h, 2, 2, clearh) +GEN_VEXT_V_ENV(vfcvt_f_x_v_w, 4, 4, clearl
[PATCH v9 41/61] target/riscv: vector floating-point merge instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 4 +++
target/riscv/insn32.decode | 2 ++
target/riscv/insn_trans/trans_rvv.inc.c | 38 +
target/riscv/vector_helper.c| 24
4 files changed, 68 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 23b268df90..21054cc957 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -994,3 +994,7 @@ DEF_HELPER_6(vmford_vf_d, void, ptr, ptr, i64, ptr, env,
i32)
DEF_HELPER_5(vfclass_v_h, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfclass_v_w, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfclass_v_d, void, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vfmerge_vfm_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfmerge_vfm_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfmerge_vfm_d, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 23e80fe954..14cb4e2e66 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -513,6 +513,8 @@ vmfge_vf01 . . . 101 . 1010111 @r_vm
vmford_vv 011010 . . . 001 . 1010111 @r_vm
vmford_vf 011010 . . . 101 . 1010111 @r_vm
vfclass_v 100011 . . 1 001 . 1010111 @r2_vm
+vfmerge_vfm 010111 0 . . 101 . 1010111 @r_vm_0
+vfmv_v_f010111 1 0 . 101 . 1010111 @r2
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 80058669f0..51ee83255e 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2184,3 +2184,41 @@ GEN_OPFVF_TRANS(vmford_vf, opfvf_cmp_check)
/* Vector Floating-Point Classify Instruction */
GEN_OPFV_TRANS(vfclass_v, opfv_check)
+
+/* Vector Floating-Point Merge Instruction */
+GEN_OPFVF_TRANS(vfmerge_vfm, opfvf_check)
+
+static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
+{
+if (vext_check_isa_ill(s) &&
+vext_check_reg(s, a->rd, false) &&
+(s->sew != 0)) {
+
+if (s->vl_eq_vlmax) {
+tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd),
+ MAXSZ(s), MAXSZ(s), cpu_fpr[a->rs1]);
+} else {
+TCGv_ptr dest;
+TCGv_i32 desc;
+uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+static gen_helper_vmv_vx * const fns[3] = {
+gen_helper_vmv_v_x_h,
+gen_helper_vmv_v_x_w,
+gen_helper_vmv_v_x_d,
+};
+TCGLabel *over = gen_new_label();
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+dest = tcg_temp_new_ptr();
+desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
+tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, a->rd));
+fns[s->sew - 1](dest, cpu_fpr[a->rs1], cpu_env, desc);
+
+tcg_temp_free_ptr(dest);
+tcg_temp_free_i32(desc);
+gen_set_label(over);
+}
+return true;
+}
+return false;
+}
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index b0ccb32de0..5a0dd9304d 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4194,3 +4194,27 @@ RVVCALL(OPIVV1, vfclass_v_d, OP_UU_D, H8, H8, fclass_d)
GEN_VEXT_V(vfclass_v_h, 2, 2, clearh)
GEN_VEXT_V(vfclass_v_w, 4, 4, clearl)
GEN_VEXT_V(vfclass_v_d, 8, 8, clearq)
+
+/* Vector Floating-Point Merge Instruction */
+#define GEN_VFMERGE_VF(NAME, ETYPE, H, CLEAR_FN) \
+void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
+ CPURISCVState *env, uint32_t desc) \
+{ \
+uint32_t mlen = vext_mlen(desc); \
+uint32_t vm = vext_vm(desc); \
+uint32_t vl = env->vl;\
+uint32_t esz = sizeof(ETYPE); \
+uint32_t vlmax = vext_maxsz(desc) / esz; \
+uint32_t i; \
+ \
+for (i = 0; i < vl; i++) {\
+ETYPE s2 = *((ETYPE *)vs2 + H(i));\
+*((ETYPE *)vd + H(i)) \
+ = (!vm && !vext_elem_mask(v0, mlen, i) ? s2 : s1); \
+} \
+CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \
+}
+
+GEN_VFMERGE_VF(vfmerge_vfm_h, int16_t, H2, clearh)
+GEN_VFMERGE_VF(vf
[PATCH v9 40/61] target/riscv: vector floating-point classify instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/fpu_helper.c | 33 +
target/riscv/helper.h | 4 ++
target/riscv/insn32.decode | 1 +
target/riscv/insn_trans/trans_rvv.inc.c | 3 +
target/riscv/internals.h| 5 ++
target/riscv/vector_helper.c| 91 +
6 files changed, 107 insertions(+), 30 deletions(-)
diff --git a/target/riscv/fpu_helper.c b/target/riscv/fpu_helper.c
index 0b79562a69..4379756dc4 100644
--- a/target/riscv/fpu_helper.c
+++ b/target/riscv/fpu_helper.c
@@ -22,6 +22,7 @@
#include "exec/exec-all.h"
#include "exec/helper-proto.h"
#include "fpu/softfloat.h"
+#include "internals.h"
target_ulong riscv_cpu_get_fflags(CPURISCVState *env)
{
@@ -230,21 +231,7 @@ uint64_t helper_fcvt_s_lu(CPURISCVState *env, uint64_t rs1)
target_ulong helper_fclass_s(uint64_t frs1)
{
-float32 f = frs1;
-bool sign = float32_is_neg(f);
-
-if (float32_is_infinity(f)) {
-return sign ? 1 << 0 : 1 << 7;
-} else if (float32_is_zero(f)) {
-return sign ? 1 << 3 : 1 << 4;
-} else if (float32_is_zero_or_denormal(f)) {
-return sign ? 1 << 2 : 1 << 5;
-} else if (float32_is_any_nan(f)) {
-float_status s = { }; /* for snan_bit_is_one */
-return float32_is_quiet_nan(f, ) ? 1 << 9 : 1 << 8;
-} else {
-return sign ? 1 << 1 : 1 << 6;
-}
+return fclass_s(frs1);
}
uint64_t helper_fadd_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2)
@@ -353,19 +340,5 @@ uint64_t helper_fcvt_d_lu(CPURISCVState *env, uint64_t rs1)
target_ulong helper_fclass_d(uint64_t frs1)
{
-float64 f = frs1;
-bool sign = float64_is_neg(f);
-
-if (float64_is_infinity(f)) {
-return sign ? 1 << 0 : 1 << 7;
-} else if (float64_is_zero(f)) {
-return sign ? 1 << 3 : 1 << 4;
-} else if (float64_is_zero_or_denormal(f)) {
-return sign ? 1 << 2 : 1 << 5;
-} else if (float64_is_any_nan(f)) {
-float_status s = { }; /* for snan_bit_is_one */
-return float64_is_quiet_nan(f, ) ? 1 << 9 : 1 << 8;
-} else {
-return sign ? 1 << 1 : 1 << 6;
-}
+return fclass_d(frs1);
}
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index bedd4d0114..23b268df90 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -990,3 +990,7 @@ DEF_HELPER_6(vmford_vv_d, void, ptr, ptr, ptr, ptr, env,
i32)
DEF_HELPER_6(vmford_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vmford_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vmford_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_5(vfclass_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfclass_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfclass_v_d, void, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index b0f1c54d53..23e80fe954 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -512,6 +512,7 @@ vmfgt_vf011101 . . . 101 . 1010111 @r_vm
vmfge_vf01 . . . 101 . 1010111 @r_vm
vmford_vv 011010 . . . 001 . 1010111 @r_vm
vmford_vf 011010 . . . 101 . 1010111 @r_vm
+vfclass_v 100011 . . 1 001 . 1010111 @r2_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 11473b8f72..80058669f0 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2181,3 +2181,6 @@ GEN_OPFVF_TRANS(vmfle_vf, opfvf_cmp_check)
GEN_OPFVF_TRANS(vmfgt_vf, opfvf_cmp_check)
GEN_OPFVF_TRANS(vmfge_vf, opfvf_cmp_check)
GEN_OPFVF_TRANS(vmford_vf, opfvf_cmp_check)
+
+/* Vector Floating-Point Classify Instruction */
+GEN_OPFV_TRANS(vfclass_v, opfv_check)
diff --git a/target/riscv/internals.h b/target/riscv/internals.h
index e59e8b30ad..f3cea478f7 100644
--- a/target/riscv/internals.h
+++ b/target/riscv/internals.h
@@ -27,4 +27,9 @@ FIELD(VDATA, VM, 8, 1)
FIELD(VDATA, LMUL, 9, 2)
FIELD(VDATA, NF, 11, 4)
FIELD(VDATA, WD, 11, 1)
+
+/* float point classify helpers */
+target_ulong fclass_h(uint64_t frs1);
+target_ulong fclass_s(uint64_t frs1);
+target_ulong fclass_d(uint64_t frs1);
#endif
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index f4264c51b5..b0ccb32de0 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4103,3 +4103,94 @@ GEN_VEXT_CMP_VV_ENV(vmford_vv_d, uint64_t, H8,
!float64_unordered_quiet)
GEN_VEXT_CMP_VF(vmford_vf_h, uint16_t, H2, !float16_unordered_quiet)
GEN_VEXT_CMP_VF(vmford_vf_w
[PATCH v9 39/61] target/riscv: vector floating-point compare instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Richard Henderson
---
target/riscv/helper.h | 37 +
target/riscv/insn32.decode | 12 ++
target/riscv/insn_trans/trans_rvv.inc.c | 35 +
target/riscv/vector_helper.c| 174
4 files changed, 258 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index d6e7ce57be..bedd4d0114 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -953,3 +953,40 @@ DEF_HELPER_6(vfsgnjn_vf_d, void, ptr, ptr, i64, ptr, env,
i32)
DEF_HELPER_6(vfsgnjx_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfsgnjx_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfsgnjx_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(vmfeq_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmfeq_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmfeq_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmfne_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmfne_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmfne_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmflt_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmflt_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmflt_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmfle_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmfle_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmfle_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmfeq_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfeq_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfeq_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfne_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfne_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfne_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmflt_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmflt_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmflt_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfle_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfle_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfle_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfgt_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfgt_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfgt_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfge_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfge_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmfge_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmford_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmford_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmford_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmford_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmford_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vmford_vf_d, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index ce2f497ed2..b0f1c54d53 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -500,6 +500,18 @@ vfsgnjn_vv 001001 . . . 001 . 1010111
@r_vm
vfsgnjn_vf 001001 . . . 101 . 1010111 @r_vm
vfsgnjx_vv 001010 . . . 001 . 1010111 @r_vm
vfsgnjx_vf 001010 . . . 101 . 1010111 @r_vm
+vmfeq_vv011000 . . . 001 . 1010111 @r_vm
+vmfeq_vf011000 . . . 101 . 1010111 @r_vm
+vmfne_vv011100 . . . 001 . 1010111 @r_vm
+vmfne_vf011100 . . . 101 . 1010111 @r_vm
+vmflt_vv011011 . . . 001 . 1010111 @r_vm
+vmflt_vf011011 . . . 101 . 1010111 @r_vm
+vmfle_vv011001 . . . 001 . 1010111 @r_vm
+vmfle_vf011001 . . . 101 . 1010111 @r_vm
+vmfgt_vf011101 . . . 101 . 1010111 @r_vm
+vmfge_vf01 . . . 101 . 1010111 @r_vm
+vmford_vv 011010 . . . 001 . 1010111 @r_vm
+vmford_vf 011010 . . . 101 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 6170fce05d..11473b8f72 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2146,3 +2146,38 @@ GEN_OPFVV_TRANS(vfsgnjx_vv, opfvv_check)
GEN_OPFVF_TRANS(vfsgnj_vf, opfvf_check)
GEN_OPFVF_TRANS(vfsgnjn_vf, opfvf_check)
GEN_OPFVF_TRANS(vfsgnjx_vf, opfvf_check)
+
+/* Vector Floating-Point Compare Instructions */
+static bool opfvv_cmp_check(DisasContext *s, arg_rmrr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_reg(s, a->rs2, false) &&
+vext_check_r
[PATCH v9 38/61] target/riscv: vector floating-point sign-injection instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 19 ++
target/riscv/insn32.decode | 6 ++
target/riscv/insn_trans/trans_rvv.inc.c | 8 +++
target/riscv/vector_helper.c| 85 +
4 files changed, 118 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 12d959ba0d..d6e7ce57be 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -934,3 +934,22 @@ DEF_HELPER_6(vfmin_vf_d, void, ptr, ptr, i64, ptr, env,
i32)
DEF_HELPER_6(vfmax_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfmax_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfmax_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(vfsgnj_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsgnj_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsgnj_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsgnjn_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsgnjn_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsgnjn_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsgnjx_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsgnjx_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsgnjx_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsgnj_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsgnj_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsgnj_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsgnjn_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsgnjn_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsgnjn_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsgnjx_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsgnjx_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsgnjx_vf_d, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 5ec5595e2c..ce2f497ed2 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -494,6 +494,12 @@ vfmin_vv000100 . . . 001 . 1010111
@r_vm
vfmin_vf000100 . . . 101 . 1010111 @r_vm
vfmax_vv000110 . . . 001 . 1010111 @r_vm
vfmax_vf000110 . . . 101 . 1010111 @r_vm
+vfsgnj_vv 001000 . . . 001 . 1010111 @r_vm
+vfsgnj_vf 001000 . . . 101 . 1010111 @r_vm
+vfsgnjn_vv 001001 . . . 001 . 1010111 @r_vm
+vfsgnjn_vf 001001 . . . 101 . 1010111 @r_vm
+vfsgnjx_vv 001010 . . . 001 . 1010111 @r_vm
+vfsgnjx_vf 001010 . . . 101 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 0c1e45123d..6170fce05d 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2138,3 +2138,11 @@ GEN_OPFVV_TRANS(vfmin_vv, opfvv_check)
GEN_OPFVV_TRANS(vfmax_vv, opfvv_check)
GEN_OPFVF_TRANS(vfmin_vf, opfvf_check)
GEN_OPFVF_TRANS(vfmax_vf, opfvf_check)
+
+/* Vector Floating-Point Sign-Injection Instructions */
+GEN_OPFVV_TRANS(vfsgnj_vv, opfvv_check)
+GEN_OPFVV_TRANS(vfsgnjn_vv, opfvv_check)
+GEN_OPFVV_TRANS(vfsgnjx_vv, opfvv_check)
+GEN_OPFVF_TRANS(vfsgnj_vf, opfvf_check)
+GEN_OPFVF_TRANS(vfsgnjn_vf, opfvf_check)
+GEN_OPFVF_TRANS(vfsgnjx_vf, opfvf_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 82e570da4e..7a1c5311bb 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3844,3 +3844,88 @@ RVVCALL(OPFVF2, vfmax_vf_d, OP_UUU_D, H8, H8,
float64_maxnum)
GEN_VEXT_VF(vfmax_vf_h, 2, 2, clearh)
GEN_VEXT_VF(vfmax_vf_w, 4, 4, clearl)
GEN_VEXT_VF(vfmax_vf_d, 8, 8, clearq)
+
+/* Vector Floating-Point Sign-Injection Instructions */
+static uint16_t fsgnj16(uint16_t a, uint16_t b, float_status *s)
+{
+return deposit64(b, 0, 15, a);
+}
+
+static uint32_t fsgnj32(uint32_t a, uint32_t b, float_status *s)
+{
+return deposit64(b, 0, 31, a);
+}
+
+static uint64_t fsgnj64(uint64_t a, uint64_t b, float_status *s)
+{
+return deposit64(b, 0, 63, a);
+}
+
+RVVCALL(OPFVV2, vfsgnj_vv_h, OP_UUU_H, H2, H2, H2, fsgnj16)
+RVVCALL(OPFVV2, vfsgnj_vv_w, OP_UUU_W, H4, H4, H4, fsgnj32)
+RVVCALL(OPFVV2, vfsgnj_vv_d, OP_UUU_D, H8, H8, H8, fsgnj64)
+GEN_VEXT_VV_ENV(vfsgnj_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_ENV(vfsgnj_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_ENV(vfsgnj_vv_d, 8, 8, clearq)
+RVVCALL(OPFVF2, vfsgnj_vf_h, OP_UUU_H, H2, H2, fsgnj16)
+RVVCALL(OPFVF2, vfsgnj_vf_w, OP_UUU_W, H4, H4, fsgnj32)
+RVVCALL(OPFVF2, vfsgnj_vf_d, OP_UUU_D, H8, H8, fsgnj64)
+GEN_VEXT_VF(vfsgnj_vf_h, 2, 2, clearh)
+GEN_VEXT_VF(vfsgnj_vf_w, 4, 4, clearl)
+GEN_VEXT_VF(vfsgnj_vf_d, 8, 8, clearq)
+
+static uint16_t fsgnjn16(uint16_t
[PATCH v9 37/61] target/riscv: vector floating-point min/max instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 13 target/riscv/insn32.decode | 4 target/riscv/insn_trans/trans_rvv.inc.c | 6 ++ target/riscv/vector_helper.c| 27 + 4 files changed, 50 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index db4de7135b..12d959ba0d 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -921,3 +921,16 @@ DEF_HELPER_6(vfwnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_5(vfsqrt_v_h, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfsqrt_v_w, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfsqrt_v_d, void, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vfmin_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmin_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmin_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmax_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmax_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmax_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmin_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmin_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmin_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmax_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmax_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmax_vf_d, void, ptr, ptr, i64, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 4ea71eaf39..5ec5595e2c 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -490,6 +490,10 @@ vfwmsac_vf 10 . . . 101 . 1010111 @r_vm vfwnmsac_vv 11 . . . 001 . 1010111 @r_vm vfwnmsac_vf 11 . . . 101 . 1010111 @r_vm vfsqrt_v100011 . . 0 001 . 1010111 @r2_vm +vfmin_vv000100 . . . 001 . 1010111 @r_vm +vfmin_vf000100 . . . 101 . 1010111 @r_vm +vfmax_vv000110 . . . 001 . 1010111 @r_vm +vfmax_vf000110 . . . 101 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index 35db704bbc..0c1e45123d 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -2132,3 +2132,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ } GEN_OPFV_TRANS(vfsqrt_v, opfv_check) + +/* Vector Floating-Point MIN/MAX Instructions */ +GEN_OPFVV_TRANS(vfmin_vv, opfvv_check) +GEN_OPFVV_TRANS(vfmax_vv, opfvv_check) +GEN_OPFVF_TRANS(vfmin_vf, opfvf_check) +GEN_OPFVF_TRANS(vfmax_vf, opfvf_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 7f527c95e0..82e570da4e 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -3817,3 +3817,30 @@ RVVCALL(OPFVV1, vfsqrt_v_d, OP_UU_D, H8, H8, float64_sqrt) GEN_VEXT_V_ENV(vfsqrt_v_h, 2, 2, clearh) GEN_VEXT_V_ENV(vfsqrt_v_w, 4, 4, clearl) GEN_VEXT_V_ENV(vfsqrt_v_d, 8, 8, clearq) + +/* Vector Floating-Point MIN/MAX Instructions */ +RVVCALL(OPFVV2, vfmin_vv_h, OP_UUU_H, H2, H2, H2, float16_minnum) +RVVCALL(OPFVV2, vfmin_vv_w, OP_UUU_W, H4, H4, H4, float32_minnum) +RVVCALL(OPFVV2, vfmin_vv_d, OP_UUU_D, H8, H8, H8, float64_minnum) +GEN_VEXT_VV_ENV(vfmin_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmin_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmin_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfmin_vf_h, OP_UUU_H, H2, H2, float16_minnum) +RVVCALL(OPFVF2, vfmin_vf_w, OP_UUU_W, H4, H4, float32_minnum) +RVVCALL(OPFVF2, vfmin_vf_d, OP_UUU_D, H8, H8, float64_minnum) +GEN_VEXT_VF(vfmin_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmin_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmin_vf_d, 8, 8, clearq) + +RVVCALL(OPFVV2, vfmax_vv_h, OP_UUU_H, H2, H2, H2, float16_maxnum) +RVVCALL(OPFVV2, vfmax_vv_w, OP_UUU_W, H4, H4, H4, float32_maxnum) +RVVCALL(OPFVV2, vfmax_vv_d, OP_UUU_D, H8, H8, H8, float64_maxnum) +GEN_VEXT_VV_ENV(vfmax_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmax_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmax_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfmax_vf_h, OP_UUU_H, H2, H2, float16_maxnum) +RVVCALL(OPFVF2, vfmax_vf_w, OP_UUU_W, H4, H4, float32_maxnum) +RVVCALL(OPFVF2, vfmax_vf_d, OP_UUU_D, H8, H8, float64_maxnum) +GEN_VEXT_VF(vfmax_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmax_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmax_vf_d, 8, 8, clearq) -- 2.23.0
[PATCH v9 36/61] target/riscv: vector floating-point square-root instruction
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 4 +++
target/riscv/insn32.decode | 3 ++
target/riscv/insn_trans/trans_rvv.inc.c | 43 +
target/riscv/vector_helper.c| 43 +
4 files changed, 93 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index edf963e787..db4de7135b 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -917,3 +917,7 @@ DEF_HELPER_6(vfwmsac_vf_h, void, ptr, ptr, i64, ptr, env,
i32)
DEF_HELPER_6(vfwmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfwnmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfwnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_5(vfsqrt_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfsqrt_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfsqrt_v_d, void, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 56bfd4a919..4ea71eaf39 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -45,6 +45,7 @@
shamt rs1 rd
aq rl rs2 rs1 rd
vm rd rs1 rs2
+ vm rd rs2
vm wd rd rs1 rs2
vm rd rs1 nf
vm rd rs1 rs2 nf
@@ -68,6 +69,7 @@
@r2_rm ... . . ... . ... %rs1 %rm %rd
@r2 ... . . ... . ... %rs1 %rd
@r2_nfvm ... ... vm:1 . . ... . ... %nf %rs1 %rd
+@r2_vm .. vm:1 . . ... . ... %rs2 %rd
@r_nfvm ... ... vm:1 . . ... . ... %nf %rs2 %rs1 %rd
@r_vm.. vm:1 . . ... . ... %rs2 %rs1 %rd
@r_vm_1 .. . . . ... . ... vm=1 %rs2 %rs1 %rd
@@ -487,6 +489,7 @@ vfwmsac_vv 10 . . . 001 . 1010111 @r_vm
vfwmsac_vf 10 . . . 101 . 1010111 @r_vm
vfwnmsac_vv 11 . . . 001 . 1010111 @r_vm
vfwnmsac_vf 11 . . . 101 . 1010111 @r_vm
+vfsqrt_v100011 . . 0 001 . 1010111 @r2_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 945c9424ba..35db704bbc 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2089,3 +2089,46 @@ GEN_OPFVF_WIDEN_TRANS(vfwmacc_vf)
GEN_OPFVF_WIDEN_TRANS(vfwnmacc_vf)
GEN_OPFVF_WIDEN_TRANS(vfwmsac_vf)
GEN_OPFVF_WIDEN_TRANS(vfwnmsac_vf)
+
+/* Vector Floating-Point Square-Root Instruction */
+
+/*
+ * If the current SEW does not correspond to a supported IEEE floating-point
+ * type, an illegal instruction exception is raised
+ */
+static bool opfv_check(DisasContext *s, arg_rmr *a)
+{
+ return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, false) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs2, false) &&
+(s->sew != 0));
+}
+
+#define GEN_OPFV_TRANS(NAME, CHECK)\
+static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
+{ \
+if (CHECK(s, a)) { \
+uint32_t data = 0; \
+static gen_helper_gvec_3_ptr * const fns[3] = {\
+gen_helper_##NAME##_h, \
+gen_helper_##NAME##_w, \
+gen_helper_##NAME##_d, \
+}; \
+TCGLabel *over = gen_new_label(); \
+gen_set_rm(s, 7); \
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ \
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \
+data = FIELD_DP32(data, VDATA, VM, a->vm); \
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
+ vreg_ofs(s, a->rs2), cpu_env, 0,\
+ s->vlen / 8, data, fns[s->sew - 1]);\
+gen_set_label(over); \
+return true; \
+} \
+return false; \
+}
+
+GEN_OPFV_TRANS(vfsqrt_v, opfv_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 7abdc2b7d
[PATCH v9 34/61] target/riscv: vector single-width floating-point fused multiply-add instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 49 + target/riscv/insn32.decode | 16 ++ target/riscv/insn_trans/trans_rvv.inc.c | 18 ++ target/riscv/vector_helper.c| 251 4 files changed, 334 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 5b3340a4af..5cd1694412 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -851,3 +851,52 @@ DEF_HELPER_6(vfwmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfwmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfwmul_vf_h, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfwmul_vf_w, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_6(vfmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmacc_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsac_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmacc_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsac_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmadd_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmadd_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmadd_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 1d963f0b8a..c42bcd141c 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -463,6 +463,22 @@ vfdiv_vf10 . . . 101 . 1010111 @r_vm vfrdiv_vf 11 . . . 101 . 1010111 @r_vm vfwmul_vv 111000 . . . 001 . 1010111 @r_vm vfwmul_vf 111000 . . . 101 . 1010111 @r_vm +vfmacc_vv 101100 . . . 001 . 1010111 @r_vm +vfnmacc_vv 101101 . . . 001 . 1010111 @r_vm +vfnmacc_vf 101101 . . . 101 . 1010111 @r_vm +vfmacc_vf 101100 . . . 101 . 1010111 @r_vm +vfmsac_vv 101110 . . . 001 . 1010111 @r_vm +vfmsac_vf 101110 . . . 101 . 1010111 @r_vm +vfnmsac_vv 10 . . . 001 . 1010111 @r_vm +vfnmsac_vf 10 . . . 101 . 1010111 @r_vm +vfmadd_vv 101000 . . . 001 . 1010111 @r_vm +vfmadd_vf 101000 . . . 101 . 1010111 @r_vm +vfnmadd_vv 101001 . . . 001 . 1010111 @r_vm +vfnmadd_vf 101001 . . . 101
[PATCH v9 31/61] target/riscv: vector widening floating-point add/subtract instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 17 +++
target/riscv/insn32.decode | 8 ++
target/riscv/insn_trans/trans_rvv.inc.c | 149
target/riscv/vector_helper.c| 83 +
4 files changed, 257 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 3031a941c2..73fc7a5a00 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -813,3 +813,20 @@ DEF_HELPER_6(vfsub_vf_d, void, ptr, ptr, i64, ptr, env,
i32)
DEF_HELPER_6(vfrsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfrsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfrsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(vfwadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwadd_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wf_w, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index c8e3f10162..68e9448842 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -448,6 +448,14 @@ vfadd_vf00 . . . 101 . 1010111
@r_vm
vfsub_vv10 . . . 001 . 1010111 @r_vm
vfsub_vf10 . . . 101 . 1010111 @r_vm
vfrsub_vf 100111 . . . 101 . 1010111 @r_vm
+vfwadd_vv 11 . . . 001 . 1010111 @r_vm
+vfwadd_vf 11 . . . 101 . 1010111 @r_vm
+vfwadd_wv 110100 . . . 001 . 1010111 @r_vm
+vfwadd_wf 110100 . . . 101 . 1010111 @r_vm
+vfwsub_vv 110010 . . . 001 . 1010111 @r_vm
+vfwsub_vf 110010 . . . 101 . 1010111 @r_vm
+vfwsub_wv 110110 . . . 001 . 1010111 @r_vm
+vfwsub_wf 110110 . . . 101 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 7461e86de8..bee4d4cb76 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1901,3 +1901,152 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)
\
GEN_OPFVF_TRANS(vfadd_vf, opfvf_check)
GEN_OPFVF_TRANS(vfsub_vf, opfvf_check)
GEN_OPFVF_TRANS(vfrsub_vf, opfvf_check)
+
+/* Vector Widening Floating-Point Add/Subtract Instructions */
+static bool opfvv_widen_check(DisasContext *s, arg_rmrr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+vext_check_reg(s, a->rd, true) &&
+vext_check_reg(s, a->rs2, false) &&
+vext_check_reg(s, a->rs1, false) &&
+vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs2,
+ 1 << s->lmul) &&
+vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs1,
+ 1 << s->lmul) &&
+(s->lmul < 0x3) && (s->sew < 0x3) && (s->sew != 0));
+}
+
+/* OPFVV with WIDEN */
+#define GEN_OPFVV_WIDEN_TRANS(NAME, CHECK) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{\
+if (CHECK(s, a)) { \
+uint32_t data = 0; \
+static gen_helper_gvec_4_ptr * const fns[2] = { \
+gen_helper_##NAME##_h, gen_helper_##NAME##_w,\
+}; \
+TCGLabel *over = gen_new_label();\
+gen_set_rm(s, 7);\
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);\
+ \
+dat
[PATCH v9 35/61] target/riscv: vector widening floating-point fused multiply-add instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 17 +
target/riscv/insn32.decode | 8 +++
target/riscv/insn_trans/trans_rvv.inc.c | 10 +++
target/riscv/vector_helper.c| 91 +
4 files changed, 126 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 5cd1694412..edf963e787 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -900,3 +900,20 @@ DEF_HELPER_6(vfmsub_vf_d, void, ptr, ptr, i64, ptr, env,
i32)
DEF_HELPER_6(vfnmsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfnmsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfnmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(vfwmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index c42bcd141c..56bfd4a919 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -479,6 +479,14 @@ vfmsub_vv 101010 . . . 001 . 1010111
@r_vm
vfmsub_vf 101010 . . . 101 . 1010111 @r_vm
vfnmsub_vv 101011 . . . 001 . 1010111 @r_vm
vfnmsub_vf 101011 . . . 101 . 1010111 @r_vm
+vfwmacc_vv 00 . . . 001 . 1010111 @r_vm
+vfwmacc_vf 00 . . . 101 . 1010111 @r_vm
+vfwnmacc_vv 01 . . . 001 . 1010111 @r_vm
+vfwnmacc_vf 01 . . . 101 . 1010111 @r_vm
+vfwmsac_vv 10 . . . 001 . 1010111 @r_vm
+vfwmsac_vf 10 . . . 101 . 1010111 @r_vm
+vfwnmsac_vv 11 . . . 001 . 1010111 @r_vm
+vfwnmsac_vf 11 . . . 101 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 439bfc0469..945c9424ba 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2079,3 +2079,13 @@ GEN_OPFVF_TRANS(vfmadd_vf, opfvf_check)
GEN_OPFVF_TRANS(vfnmadd_vf, opfvf_check)
GEN_OPFVF_TRANS(vfmsub_vf, opfvf_check)
GEN_OPFVF_TRANS(vfnmsub_vf, opfvf_check)
+
+/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
+GEN_OPFVV_WIDEN_TRANS(vfwmacc_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwnmacc_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwmsac_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwnmsac_vv, opfvv_widen_check)
+GEN_OPFVF_WIDEN_TRANS(vfwmacc_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwnmacc_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwmsac_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwnmsac_vf)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d3ad4aa8f1..7abdc2b7d8 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3683,3 +3683,94 @@ RVVCALL(OPFVF3, vfnmsub_vf_d, OP_UUU_D, H8, H8, fnmsub64)
GEN_VEXT_VF(vfnmsub_vf_h, 2, 2, clearh)
GEN_VEXT_VF(vfnmsub_vf_w, 4, 4, clearl)
GEN_VEXT_VF(vfnmsub_vf_d, 8, 8, clearq)
+
+/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
+static uint32_t fwmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
+{
+return float32_muladd(float16_to_float32(a, true, s),
+float16_to_float32(b, true, s), d, 0, s);
+}
+
+static uint64_t fwmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
+{
+return float64_muladd(float32_to_float64(a, s),
+float32_to_float64(b, s), d, 0, s);
+}
+
+RVVCALL(OPFVV3, vfwmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwmacc16)
+RVVCALL(OPFVV3, vfwmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwmacc32)
+GEN_VEXT_VV_ENV(vfwmacc_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwmacc_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF3, vfwmacc_vf_h, WOP_UUU_H, H4, H2, fwmacc16)
+RVVCALL(OPFVF3, vfwmacc_vf_w, WOP_UUU_W, H8, H4, fwmacc32)
+GEN_VEXT_VF(vfwmacc_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwmacc_vf_w, 4
[PATCH v9 33/61] target/riscv: vector widening floating-point multiply
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 5 +
target/riscv/insn32.decode | 2 ++
target/riscv/insn_trans/trans_rvv.inc.c | 4
target/riscv/vector_helper.c| 22 ++
4 files changed, 33 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index fa1558179a..5b3340a4af 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -846,3 +846,8 @@ DEF_HELPER_6(vfdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfrdiv_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfrdiv_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfrdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(vfwmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmul_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmul_vf_w, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 16fd938261..1d963f0b8a 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -461,6 +461,8 @@ vfmul_vf100100 . . . 101 . 1010111 @r_vm
vfdiv_vv10 . . . 001 . 1010111 @r_vm
vfdiv_vf10 . . . 101 . 1010111 @r_vm
vfrdiv_vf 11 . . . 101 . 1010111 @r_vm
+vfwmul_vv 111000 . . . 001 . 1010111 @r_vm
+vfwmul_vf 111000 . . . 101 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index be60115801..7ff3af0c61 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2057,3 +2057,7 @@ GEN_OPFVV_TRANS(vfdiv_vv, opfvv_check)
GEN_OPFVF_TRANS(vfmul_vf, opfvf_check)
GEN_OPFVF_TRANS(vfdiv_vf, opfvf_check)
GEN_OPFVF_TRANS(vfrdiv_vf, opfvf_check)
+
+/* Vector Widening Floating-Point Multiply */
+GEN_OPFVV_WIDEN_TRANS(vfwmul_vv, opfvv_widen_check)
+GEN_OPFVF_WIDEN_TRANS(vfwmul_vf)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index ea807ef731..0dd94348e8 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3410,3 +3410,25 @@ RVVCALL(OPFVF2, vfrdiv_vf_d, OP_UUU_D, H8, H8,
float64_rdiv)
GEN_VEXT_VF(vfrdiv_vf_h, 2, 2, clearh)
GEN_VEXT_VF(vfrdiv_vf_w, 4, 4, clearl)
GEN_VEXT_VF(vfrdiv_vf_d, 8, 8, clearq)
+
+/* Vector Widening Floating-Point Multiply */
+static uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s)
+{
+return float32_mul(float16_to_float32(a, true, s),
+float16_to_float32(b, true, s), s);
+}
+
+static uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s)
+{
+return float64_mul(float32_to_float64(a, s),
+float32_to_float64(b, s), s);
+
+}
+RVVCALL(OPFVV2, vfwmul_vv_h, WOP_UUU_H, H4, H2, H2, vfwmul16)
+RVVCALL(OPFVV2, vfwmul_vv_w, WOP_UUU_W, H8, H4, H4, vfwmul32)
+GEN_VEXT_VV_ENV(vfwmul_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwmul_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF2, vfwmul_vf_h, WOP_UUU_H, H4, H2, vfwmul16)
+RVVCALL(OPFVF2, vfwmul_vf_w, WOP_UUU_W, H8, H4, vfwmul32)
+GEN_VEXT_VF(vfwmul_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwmul_vf_w, 4, 8, clearq)
--
2.23.0
[PATCH v9 29/61] target/riscv: vector narrowing fixed-point clip instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 13 +++
target/riscv/insn32.decode | 6 +
target/riscv/insn_trans/trans_rvv.inc.c | 8 ++
target/riscv/vector_helper.c| 141
4 files changed, 168 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index f36f840714..7f7fdcb451 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -784,3 +784,16 @@ DEF_HELPER_6(vssra_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssra_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vnclip_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclip_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclip_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_vx_w, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 2ecac3d96d..8b898f9bad 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -437,6 +437,12 @@ vssrl_vi101010 . . . 011 . 1010111
@r_vm
vssra_vv101011 . . . 000 . 1010111 @r_vm
vssra_vx101011 . . . 100 . 1010111 @r_vm
vssra_vi101011 . . . 011 . 1010111 @r_vm
+vnclipu_vv 101110 . . . 000 . 1010111 @r_vm
+vnclipu_vx 101110 . . . 100 . 1010111 @r_vm
+vnclipu_vi 101110 . . . 011 . 1010111 @r_vm
+vnclip_vv 10 . . . 000 . 1010111 @r_vm
+vnclip_vx 10 . . . 100 . 1010111 @r_vm
+vnclip_vi 10 . . . 011 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 0d9e65a194..96fcf02a8c 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1775,3 +1775,11 @@ GEN_OPIVX_TRANS(vssrl_vx, opivx_check)
GEN_OPIVX_TRANS(vssra_vx, opivx_check)
GEN_OPIVI_TRANS(vssrl_vi, 1, vssrl_vx, opivx_check)
GEN_OPIVI_TRANS(vssra_vi, 0, vssra_vx, opivx_check)
+
+/* Vector Narrowing Fixed-Point Clip Instructions */
+GEN_OPIVV_NARROW_TRANS(vnclipu_vv)
+GEN_OPIVV_NARROW_TRANS(vnclip_vv)
+GEN_OPIVX_NARROW_TRANS(vnclipu_vx)
+GEN_OPIVX_NARROW_TRANS(vnclip_vx)
+GEN_OPIVI_NARROW_TRANS(vnclipu_vi, 1, vnclipu_vx)
+GEN_OPIVI_NARROW_TRANS(vnclip_vi, 1, vnclip_vx)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index c33e845a90..1c375f437a 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -875,6 +875,12 @@ GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w,
clearl)
#define WOP_SSU_B int16_t, int8_t, uint8_t, int16_t, uint16_t
#define WOP_SSU_H int32_t, int16_t, uint16_t, int32_t, uint32_t
#define WOP_SSU_W int64_t, int32_t, uint32_t, int64_t, uint64_t
+#define NOP_SSS_B int8_t, int8_t, int16_t, int8_t, int16_t
+#define NOP_SSS_H int16_t, int16_t, int32_t, int16_t, int32_t
+#define NOP_SSS_W int32_t, int32_t, int64_t, int32_t, int64_t
+#define NOP_UUU_B uint8_t, uint8_t, uint16_t, uint8_t, uint16_t
+#define NOP_UUU_H uint16_t, uint16_t, uint32_t, uint16_t, uint32_t
+#define NOP_UUU_W uint32_t, uint32_t, uint64_t, uint32_t, uint64_t
/* operation of two vector elements */
typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
@@ -3009,6 +3015,7 @@ vssra64(CPURISCVState *env, int vxrm, int64_t a, int64_t
b)
res = (a >> shift) + round;
return res;
}
+
RVVCALL(OPIVV2_RM, vssra_vv_b, OP_SSS_B, H1, H1, H1, vssra8)
RVVCALL(OPIVV2_RM, vssra_vv_h, OP_SSS_H, H2, H2, H2, vssra16)
RVVCALL(OPIVV2_RM, vssra_vv_w, OP_SSS_W, H4, H4, H4, vssra32)
@@ -3026,3 +3033,137 @@ GEN_VEXT_VX_RM(vssra_vx_b, 1, 1, clearb)
GEN_VEXT_VX_RM(vssra_vx_h, 2, 2, clearh)
GEN_VEXT_VX_RM(vssra_vx_w, 4, 4, clearl)
GEN_VEXT_VX_RM(vssra_vx_d, 8, 8, clearq)
+
+/* Vector Narrowing Fixed-Point Clip Instructions */
+static inline int8_t
+vnclip8(CPURISCVState *env, int vxrm, int16_t a, int8_t b)
+{
+uint8_t round, shift = b & 0xf;
+int16_t res;
+
+round = get_round(vxrm, a, shift);
+res = (a >> shift) + round;
+if (res > INT8_MAX) {
+
[PATCH v9 26/61] target/riscv: vector single-width fractional multiply with rounding and saturation
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 9 ++
target/riscv/insn32.decode | 2 +
target/riscv/insn_trans/trans_rvv.inc.c | 4 +
target/riscv/vector_helper.c| 107
4 files changed, 122 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 32d549ce36..e6cae1b59c 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -736,3 +736,12 @@ DEF_HELPER_6(vasub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vasub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vasub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vasub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vsmul_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index e617d7bd60..633f782fbf 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -422,6 +422,8 @@ vaadd_vx100100 . . . 100 . 1010111 @r_vm
vaadd_vi100100 . . . 011 . 1010111 @r_vm
vasub_vv100110 . . . 000 . 1010111 @r_vm
vasub_vx100110 . . . 100 . 1010111 @r_vm
+vsmul_vv100111 . . . 000 . 1010111 @r_vm
+vsmul_vx100111 . . . 100 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index ed1ee0f1b5..23714793df 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1754,3 +1754,7 @@ GEN_OPIVV_TRANS(vasub_vv, opivv_check)
GEN_OPIVX_TRANS(vaadd_vx, opivx_check)
GEN_OPIVX_TRANS(vasub_vx, opivx_check)
GEN_OPIVI_TRANS(vaadd_vi, 0, vaadd_vx, opivx_check)
+
+/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
+GEN_OPIVV_TRANS(vsmul_vv, opivv_check)
+GEN_OPIVX_TRANS(vsmul_vx, opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index ada95ab1e7..dd3fc39016 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2597,3 +2597,110 @@ GEN_VEXT_VX_RM(vasub_vx_b, 1, 1, clearb)
GEN_VEXT_VX_RM(vasub_vx_h, 2, 2, clearh)
GEN_VEXT_VX_RM(vasub_vx_w, 4, 4, clearl)
GEN_VEXT_VX_RM(vasub_vx_d, 8, 8, clearq)
+
+/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
+static inline int8_t vsmul8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
+{
+uint8_t round;
+int16_t res;
+
+res = (int16_t)a * (int16_t)b;
+round = get_round(vxrm, res, 7);
+res = (res >> 7) + round;
+
+if (res > INT8_MAX) {
+env->vxsat = 0x1;
+return INT8_MAX;
+} else if (res < INT8_MIN) {
+env->vxsat = 0x1;
+return INT8_MIN;
+} else {
+return res;
+}
+}
+
+static int16_t vsmul16(CPURISCVState *env, int vxrm, int16_t a, int16_t b)
+{
+uint8_t round;
+int32_t res;
+
+res = (int32_t)a * (int32_t)b;
+round = get_round(vxrm, res, 15);
+res = (res >> 15) + round;
+
+if (res > INT16_MAX) {
+env->vxsat = 0x1;
+return INT16_MAX;
+} else if (res < INT16_MIN) {
+env->vxsat = 0x1;
+return INT16_MIN;
+} else {
+return res;
+}
+}
+
+static int32_t vsmul32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
+{
+uint8_t round;
+int64_t res;
+
+res = (int64_t)a * (int64_t)b;
+round = get_round(vxrm, res, 31);
+res = (res >> 31) + round;
+
+if (res > INT32_MAX) {
+env->vxsat = 0x1;
+return INT32_MAX;
+} else if (res < INT32_MIN) {
+env->vxsat = 0x1;
+return INT32_MIN;
+} else {
+return res;
+}
+}
+
+static int64_t vsmul64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
+{
+uint8_t round;
+uint64_t hi_64, lo_64;
+int64_t res;
+
+if (a == INT64_MIN && b == INT64_MIN) {
+env->vxsat = 1;
+return INT64_MAX;
+}
+
+muls64(_64, _64, a, b);
+round = get_round(vxrm, lo_64, 63);
+/*
+ * Cannot overflow, as there are always
+ * 2 sign bits after multiply.
+ */
+res = (hi_64 << 1) | (lo_64 >> 63);
+if (round) {
+if (res == INT64_MAX) {
+env->vxsat = 1;
+} else {
+res += 1;
+}
+
[PATCH v9 32/61] target/riscv: vector single-width floating-point multiply/divide instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 16 target/riscv/insn32.decode | 5 +++ target/riscv/insn_trans/trans_rvv.inc.c | 7 target/riscv/vector_helper.c| 49 + 4 files changed, 77 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 73fc7a5a00..fa1558179a 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -830,3 +830,19 @@ DEF_HELPER_6(vfwadd_wf_h, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfwadd_wf_w, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfwsub_wf_h, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfwsub_wf_w, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_6(vfmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmul_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfdiv_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfdiv_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfdiv_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmul_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmul_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmul_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfdiv_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfdiv_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrdiv_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrdiv_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 68e9448842..16fd938261 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -456,6 +456,11 @@ vfwsub_vv 110010 . . . 001 . 1010111 @r_vm vfwsub_vf 110010 . . . 101 . 1010111 @r_vm vfwsub_wv 110110 . . . 001 . 1010111 @r_vm vfwsub_wf 110110 . . . 101 . 1010111 @r_vm +vfmul_vv100100 . . . 001 . 1010111 @r_vm +vfmul_vf100100 . . . 101 . 1010111 @r_vm +vfdiv_vv10 . . . 001 . 1010111 @r_vm +vfdiv_vf10 . . . 101 . 1010111 @r_vm +vfrdiv_vf 11 . . . 101 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index bee4d4cb76..be60115801 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -2050,3 +2050,10 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ GEN_OPFWF_WIDEN_TRANS(vfwadd_wf) GEN_OPFWF_WIDEN_TRANS(vfwsub_wf) + +/* Vector Single-Width Floating-Point Multiply/Divide Instructions */ +GEN_OPFVV_TRANS(vfmul_vv, opfvv_check) +GEN_OPFVV_TRANS(vfdiv_vv, opfvv_check) +GEN_OPFVF_TRANS(vfmul_vf, opfvf_check) +GEN_OPFVF_TRANS(vfdiv_vf, opfvf_check) +GEN_OPFVF_TRANS(vfrdiv_vf, opfvf_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index b65ef51116..ea807ef731 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -3361,3 +3361,52 @@ RVVCALL(OPFVF2, vfwsub_wf_h, WOP_WUUU_H, H4, H2, vfwsubw16) RVVCALL(OPFVF2, vfwsub_wf_w, WOP_WUUU_W, H8, H4, vfwsubw32) GEN_VEXT_VF(vfwsub_wf_h, 2, 4, clearl) GEN_VEXT_VF(vfwsub_wf_w, 4, 8, clearq) + +/* Vector Single-Width Floating-Point Multiply/Divide Instructions */ +RVVCALL(OPFVV2, vfmul_vv_h, OP_UUU_H, H2, H2, H2, float16_mul) +RVVCALL(OPFVV2, vfmul_vv_w, OP_UUU_W, H4, H4, H4, float32_mul) +RVVCALL(OPFVV2, vfmul_vv_d, OP_UUU_D, H8, H8, H8, float64_mul) +GEN_VEXT_VV_ENV(vfmul_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmul_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmul_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfmul_vf_h, OP_UUU_H, H2, H2, float16_mul) +RVVCALL(OPFVF2, vfmul_vf_w, OP_UUU_W, H4, H4, float32_mul) +RVVCALL(OPFVF2, vfmul_vf_d, OP_UUU_D, H8, H8, float64_mul) +GEN_VEXT_VF(vfmul_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmul_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmul_vf_d, 8, 8, clearq) + +RVVCALL(OPFVV2, vfdiv_vv_h, OP_UUU_H, H2, H2, H2, float16_div) +RVVCALL(OPFVV2, vfdiv_vv_w, OP_UUU_W, H4, H4, H4, float32_div) +RVVCALL(OPFVV2, vfdiv_vv_d, OP_UUU_D, H8, H8, H8, float64_div) +GEN_VEXT_VV_ENV(vfdiv_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfdiv_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfdiv_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfdiv_vf_h, OP_UUU_H, H2, H2, float16_div) +RVVCALL(OPFVF2, vfdiv_vf_w, OP_UUU_W, H4, H4, float32_div) +RVVCALL(OPFVF2, vfdiv_vf_d, OP_UUU_D, H8, H8, float64_div) +GEN_VEXT_VF(vfdiv_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfdiv_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfdiv_vf_d, 8, 8, clearq) + +static uint16_t
[PATCH v9 25/61] target/riscv: vector single-width averaging add and subtract
Signed-off-by: LIU Zhiwei
Reviewed-by: Alistair Francis
Reviewed-by: Richard Henderson
---
target/riscv/helper.h | 17
target/riscv/insn32.decode | 5 ++
target/riscv/insn_trans/trans_rvv.inc.c | 7 ++
target/riscv/vector_helper.c| 100
4 files changed, 129 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 9416ebb090..32d549ce36 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -719,3 +719,20 @@ DEF_HELPER_6(vssub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vaadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index c9a4050adc..e617d7bd60 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -417,6 +417,11 @@ vssubu_vv 100010 . . . 000 . 1010111
@r_vm
vssubu_vx 100010 . . . 100 . 1010111 @r_vm
vssub_vv100011 . . . 000 . 1010111 @r_vm
vssub_vx100011 . . . 100 . 1010111 @r_vm
+vaadd_vv100100 . . . 000 . 1010111 @r_vm
+vaadd_vx100100 . . . 100 . 1010111 @r_vm
+vaadd_vi100100 . . . 011 . 1010111 @r_vm
+vasub_vv100110 . . . 000 . 1010111 @r_vm
+vasub_vx100110 . . . 100 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 4d5eae8dde..ed1ee0f1b5 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1747,3 +1747,10 @@ GEN_OPIVX_TRANS(vssubu_vx, opivx_check)
GEN_OPIVX_TRANS(vssub_vx, opivx_check)
GEN_OPIVI_TRANS(vsaddu_vi, 1, vsaddu_vx, opivx_check)
GEN_OPIVI_TRANS(vsadd_vi, 0, vsadd_vx, opivx_check)
+
+/* Vector Single-Width Averaging Add and Subtract */
+GEN_OPIVV_TRANS(vaadd_vv, opivv_check)
+GEN_OPIVV_TRANS(vasub_vv, opivv_check)
+GEN_OPIVX_TRANS(vaadd_vx, opivx_check)
+GEN_OPIVX_TRANS(vasub_vx, opivx_check)
+GEN_OPIVI_TRANS(vaadd_vi, 0, vaadd_vx, opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 3d4212ea4a..ada95ab1e7 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2497,3 +2497,103 @@ GEN_VEXT_VX_RM(vssub_vx_b, 1, 1, clearb)
GEN_VEXT_VX_RM(vssub_vx_h, 2, 2, clearh)
GEN_VEXT_VX_RM(vssub_vx_w, 4, 4, clearl)
GEN_VEXT_VX_RM(vssub_vx_d, 8, 8, clearq)
+
+/* Vector Single-Width Averaging Add and Subtract */
+static inline uint8_t get_round(int vxrm, uint64_t v, uint8_t shift)
+{
+uint8_t d = extract64(v, shift, 1);
+uint8_t d1;
+uint64_t D1, D2;
+
+if (shift == 0 || shift > 64) {
+return 0;
+}
+
+d1 = extract64(v, shift - 1, 1);
+D1 = extract64(v, 0, shift);
+if (vxrm == 0) { /* round-to-nearest-up (add +0.5 LSB) */
+return d1;
+} else if (vxrm == 1) { /* round-to-nearest-even */
+if (shift > 1) {
+D2 = extract64(v, 0, shift - 1);
+return d1 & ((D2 != 0) | d);
+} else {
+return d1 & d;
+}
+} else if (vxrm == 3) { /* round-to-odd (OR bits into LSB, aka "jam") */
+return !d & (D1 != 0);
+}
+return 0; /* round-down (truncate) */
+}
+
+static inline int32_t aadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t
b)
+{
+int64_t res = (int64_t)a + b;
+uint8_t round = get_round(vxrm, res, 1);
+
+return (res >> 1) + round;
+}
+
+static inline int64_t aadd64(CPURISCVState *env, int vxrm, int64_t a, int64_t
b)
+{
+int64_t res = a + b;
+uint8_t round = get_round(vxrm, res, 1);
+int64_t over = (res ^ a) & (res ^ b) & INT64_M
[PATCH v9 22/61] target/riscv: vector widening integer multiply-add instructions
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 22 target/riscv/insn32.decode | 7 target/riscv/insn_trans/trans_rvv.inc.c | 9 + target/riscv/vector_helper.c| 45 + 4 files changed, 83 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 08c2544b20..1a9495ceac 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -647,3 +647,25 @@ DEF_HELPER_6(vnmsub_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnmsub_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnmsub_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnmsub_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vwmaccu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmacc_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmacc_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmacc_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmacc_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccus_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwmaccus_vx_w, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index b49b60aea1..9735ac3565 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -393,6 +393,13 @@ vmadd_vv101001 . . . 010 . 1010111 @r_vm vmadd_vx101001 . . . 110 . 1010111 @r_vm vnmsub_vv 101011 . . . 010 . 1010111 @r_vm vnmsub_vx 101011 . . . 110 . 1010111 @r_vm +vwmaccu_vv 00 . . . 010 . 1010111 @r_vm +vwmaccu_vx 00 . . . 110 . 1010111 @r_vm +vwmacc_vv 01 . . . 010 . 1010111 @r_vm +vwmacc_vx 01 . . . 110 . 1010111 @r_vm +vwmaccsu_vv 10 . . . 010 . 1010111 @r_vm +vwmaccsu_vx 10 . . . 110 . 1010111 @r_vm +vwmaccus_vx 11 . . . 110 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index dc122eb2e5..3093191edc 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1609,3 +1609,12 @@ GEN_OPIVX_TRANS(vmacc_vx, opivx_check) GEN_OPIVX_TRANS(vnmsac_vx, opivx_check) GEN_OPIVX_TRANS(vmadd_vx, opivx_check) GEN_OPIVX_TRANS(vnmsub_vx, opivx_check) + +/* Vector Widening Integer Multiply-Add Instructions */ +GEN_OPIVV_WIDEN_TRANS(vwmaccu_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwmacc_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwmaccsu_vv, opivv_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwmaccu_vx) +GEN_OPIVX_WIDEN_TRANS(vwmacc_vx) +GEN_OPIVX_WIDEN_TRANS(vwmaccsu_vx) +GEN_OPIVX_WIDEN_TRANS(vwmaccus_vx) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index e787e00b01..c966ad8470 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -1979,3 +1979,48 @@ GEN_VEXT_VX(vnmsub_vx_b, 1, 1, clearb) GEN_VEXT_VX(vnmsub_vx_h, 2, 2, clearh) GEN_VEXT_VX(vnmsub_vx_w, 4, 4, clearl) GEN_VEXT_VX(vnmsub_vx_d, 8, 8, clearq) + +/* Vector Widening Integer Multiply-Add Instructions */ +RVVCALL(OPIVV3, vwmaccu_vv_b, WOP_UUU_B, H2, H1, H1, DO_MACC) +RVVCALL(OPIVV3, vwmaccu_vv_h, WOP_UUU_H, H4, H2, H2, DO_MACC) +RVVCALL(OPIVV3, vwmaccu_vv_w, WOP_UUU_W, H8, H4, H4, DO_MACC) +RVVCALL(OPIVV3, vwmacc_vv_b, WOP_SSS_B, H2, H1, H1, DO_MACC) +RVVCALL(OPIVV3, vwmacc_vv_h, WOP_SSS_H, H4, H2, H2, DO_MACC) +RVVCALL(OPIVV3, vwmacc_vv_w, WOP_SSS_W, H8, H4, H4, DO_MACC) +RVVCALL(OPIVV3, vwmaccsu_vv_b, WOP_SSU_B, H2, H1, H1, DO_MACC) +RVVCALL(OPIVV3, vwmaccsu_vv_h, WOP_SSU_H, H4, H2, H2, DO_MACC) +RVVCALL(OPIVV3, vwmaccsu_vv_w, WOP_SSU_W, H8, H4, H4, DO_MACC) +GEN_VEXT_VV(vwmaccu_vv_b, 1, 2, clearh) +GEN_VEXT_VV(vwmaccu_vv_h, 2, 4, clearl) +GEN_VEXT_VV(vwmaccu_vv_w, 4, 8
[PATCH v9 27/61] target/riscv: vector widening saturating scaled multiply-add
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 22 +++
target/riscv/insn32.decode | 7 +
target/riscv/insn_trans/trans_rvv.inc.c | 9 ++
target/riscv/vector_helper.c| 205
4 files changed, 243 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index e6cae1b59c..eb383787a2 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -745,3 +745,25 @@ DEF_HELPER_6(vsmul_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsmul_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsmul_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vsmul_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vwsmaccu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmaccu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmaccu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmacc_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmaccsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmaccsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmaccsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsmaccu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmacc_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmacc_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmacc_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccsu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccsu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccsu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccus_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsmaccus_vx_w, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 633f782fbf..2e0e66bdfa 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -424,6 +424,13 @@ vasub_vv100110 . . . 000 . 1010111
@r_vm
vasub_vx100110 . . . 100 . 1010111 @r_vm
vsmul_vv100111 . . . 000 . 1010111 @r_vm
vsmul_vx100111 . . . 100 . 1010111 @r_vm
+vwsmaccu_vv 00 . . . 000 . 1010111 @r_vm
+vwsmaccu_vx 00 . . . 100 . 1010111 @r_vm
+vwsmacc_vv 01 . . . 000 . 1010111 @r_vm
+vwsmacc_vx 01 . . . 100 . 1010111 @r_vm
+vwsmaccsu_vv10 . . . 000 . 1010111 @r_vm
+vwsmaccsu_vx10 . . . 100 . 1010111 @r_vm
+vwsmaccus_vx11 . . . 100 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 23714793df..3886b2f45a 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1758,3 +1758,12 @@ GEN_OPIVI_TRANS(vaadd_vi, 0, vaadd_vx, opivx_check)
/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
GEN_OPIVV_TRANS(vsmul_vv, opivv_check)
GEN_OPIVX_TRANS(vsmul_vx, opivx_check)
+
+/* Vector Widening Saturating Scaled Multiply-Add */
+GEN_OPIVV_WIDEN_TRANS(vwsmaccu_vv, opivv_widen_check)
+GEN_OPIVV_WIDEN_TRANS(vwsmacc_vv, opivv_widen_check)
+GEN_OPIVV_WIDEN_TRANS(vwsmaccsu_vv, opivv_widen_check)
+GEN_OPIVX_WIDEN_TRANS(vwsmaccu_vx)
+GEN_OPIVX_WIDEN_TRANS(vwsmacc_vx)
+GEN_OPIVX_WIDEN_TRANS(vwsmaccsu_vx)
+GEN_OPIVX_WIDEN_TRANS(vwsmaccus_vx)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index dd3fc39016..d653ec5e2b 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2704,3 +2704,208 @@ GEN_VEXT_VX_RM(vsmul_vx_b, 1, 1, clearb)
GEN_VEXT_VX_RM(vsmul_vx_h, 2, 2, clearh)
GEN_VEXT_VX_RM(vsmul_vx_w, 4, 4, clearl)
GEN_VEXT_VX_RM(vsmul_vx_d, 8, 8, clearq)
+
+/* Vector Widening Saturating Scaled Multiply-Add */
+static inline uint16_t
+vwsmaccu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b,
+ uint16_t c)
+{
+uint8_t round;
+uint16_t res = (uint16_t)a * b;
+
+round = get_round(vxrm, res, 4);
+res = (res >> 4) + round;
+return saddu16(env, vxrm, c, res);
+}
+
+static inline uint32_t
+vwsmaccu16(CPURISCVState *env, int vxrm, uint16_t a, uint16_t b,
+ uint32_t c)
+{
+uint8_t round;
+uint32_t res = (uint32_t)a * b;
+
+round = get_round(vxrm, res, 8);
+res = (res >> 8) + round;
+return saddu32(env, vxrm, c, res);
+}
+
+static inline uint64_t
[PATCH v9 24/61] target/riscv: vector single-width saturating add and subtract
Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 33 ++ target/riscv/insn32.decode | 10 + target/riscv/insn_trans/trans_rvv.inc.c | 16 + target/riscv/vector_helper.c| 385 4 files changed, 444 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 279b2e049f..9416ebb090 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -686,3 +686,36 @@ DEF_HELPER_4(vmv_v_x_b, void, ptr, i64, env, i32) DEF_HELPER_4(vmv_v_x_h, void, ptr, i64, env, i32) DEF_HELPER_4(vmv_v_x_w, void, ptr, i64, env, i32) DEF_HELPER_4(vmv_v_x_d, void, ptr, i64, env, i32) + +DEF_HELPER_6(vsaddu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsaddu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsaddu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsaddu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssubu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssubu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssubu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssubu_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssub_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vssub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vsaddu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsaddu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsaddu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsaddu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsadd_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsadd_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsadd_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vsadd_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssubu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssubu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssubu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssubu_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssub_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssub_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssub_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vssub_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index adb76956c9..c9a4050adc 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -407,6 +407,16 @@ vmv_v_i 010111 1 0 . 011 . 1010111 @r2 vmerge_vvm 010111 0 . . 000 . 1010111 @r_vm_0 vmerge_vxm 010111 0 . . 100 . 1010111 @r_vm_0 vmerge_vim 010111 0 . . 011 . 1010111 @r_vm_0 +vsaddu_vv 10 . . . 000 . 1010111 @r_vm +vsaddu_vx 10 . . . 100 . 1010111 @r_vm +vsaddu_vi 10 . . . 011 . 1010111 @r_vm +vsadd_vv11 . . . 000 . 1010111 @r_vm +vsadd_vx11 . . . 100 . 1010111 @r_vm +vsadd_vi11 . . . 011 . 1010111 @r_vm +vssubu_vv 100010 . . . 000 . 1010111 @r_vm +vssubu_vx 100010 . . . 100 . 1010111 @r_vm +vssub_vv100011 . . . 000 . 1010111 @r_vm +vssub_vx100011 . . . 100 . 1010111 @r_vm vsetvli 0 ... . 111 . 1010111 @r2_zimm vsetvl 100 . . 111 . 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c index d726995f84..4d5eae8dde 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1731,3 +1731,19 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a) GEN_OPIVV_TRANS(vmerge_vvm, opivv_vadc_check) GEN_OPIVX_TRANS(vmerge_vxm, opivx_vadc_check) GEN_OPIVI_TRANS(vmerge_vim, 0, vmerge_vxm, opivx_vadc_check) + +/* + *** Vector Fixed-Point Arithmetic Instructions + */ + +/* Vector Single-Width Saturating Add and Subtract */ +GEN_OPIVV_TRANS(vsaddu_vv, opivv_check) +GEN_OPIVV_TRANS(vsadd_vv, opivv_check) +GEN_OPIVV_TRANS(vssubu_vv, opivv_check) +GEN_OPIVV_TRANS(vssub_vv, opivv_check) +GEN_OPIVX_TRANS(vsaddu_vx, opivx_check) +GEN_OPIVX_TRANS(vsadd_vx, opivx_check) +GEN_OPIVX_TRANS(vssubu_vx, opivx_check) +GEN_OPIVX_TRANS(vssub_vx, opivx_check) +GEN_OPIVI_TRANS(vsaddu_vi, 1, vsaddu_vx, opivx_check) +GEN_OPIVI_TRANS(vsadd_vi, 0, vsadd_vx, opivx_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index
[PATCH v9 30/61] target/riscv: vector single-width floating-point add/subtract instructions
Signed-off-by: LIU Zhiwei
Reviewed-by: Richard Henderson
Reviewed-by: Alistair Francis
---
target/riscv/helper.h | 16
target/riscv/insn32.decode | 5 +
target/riscv/insn_trans/trans_rvv.inc.c | 118
target/riscv/vector_helper.c| 111 ++
4 files changed, 250 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 7f7fdcb451..3031a941c2 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -797,3 +797,19 @@ DEF_HELPER_6(vnclipu_vx_w, void, ptr, ptr, tl, ptr, env,
i32)
DEF_HELPER_6(vnclip_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vnclip_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vnclip_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vfadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfadd_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfadd_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfadd_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfrsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfrsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfrsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 8b898f9bad..c8e3f10162 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -443,6 +443,11 @@ vnclipu_vi 101110 . . . 011 . 1010111
@r_vm
vnclip_vv 10 . . . 000 . 1010111 @r_vm
vnclip_vx 10 . . . 100 . 1010111 @r_vm
vnclip_vi 10 . . . 011 . 1010111 @r_vm
+vfadd_vv00 . . . 001 . 1010111 @r_vm
+vfadd_vf00 . . . 101 . 1010111 @r_vm
+vfsub_vv10 . . . 001 . 1010111 @r_vm
+vfsub_vf10 . . . 101 . 1010111 @r_vm
+vfrsub_vf 100111 . . . 101 . 1010111 @r_vm
vsetvli 0 ... . 111 . 1010111 @r2_zimm
vsetvl 100 . . 111 . 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 96fcf02a8c..7461e86de8 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1783,3 +1783,121 @@ GEN_OPIVX_NARROW_TRANS(vnclipu_vx)
GEN_OPIVX_NARROW_TRANS(vnclip_vx)
GEN_OPIVI_NARROW_TRANS(vnclipu_vi, 1, vnclipu_vx)
GEN_OPIVI_NARROW_TRANS(vnclip_vi, 1, vnclip_vx)
+
+/*
+ *** Vector Float Point Arithmetic Instructions
+ */
+/* Vector Single-Width Floating-Point Add/Subtract Instructions */
+
+/*
+ * If the current SEW does not correspond to a supported IEEE floating-point
+ * type, an illegal instruction exception is raised.
+ */
+static bool opfvv_check(DisasContext *s, arg_rmrr *a)
+{
+return (vext_check_isa_ill(s) &&
+vext_check_overlap_mask(s, a->rd, a->vm, false) &&
+vext_check_reg(s, a->rd, false) &&
+vext_check_reg(s, a->rs2, false) &&
+vext_check_reg(s, a->rs1, false) &&
+(s->sew != 0));
+}
+
+/* OPFVV without GVEC IR */
+#define GEN_OPFVV_TRANS(NAME, CHECK) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+if (CHECK(s, a)) { \
+uint32_t data = 0; \
+static gen_helper_gvec_4_ptr * const fns[3] = {\
+gen_helper_##NAME##_h, \
+gen_helper_##NAME##_w, \
+gen_helper_##NAME##_d, \
+}; \
+TCGLabel *over = gen_new_label(); \
+gen_set_rm(s, 7); \
+tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ \
+data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \
+data = FIELD_DP32(data, VDATA, VM, a->vm); \
+data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd)
