[PATCH v6 3/8] target/riscv: zfh: half-precision convert and move

From: Kito Cheng Signed-off-by: Kito Cheng Signed-off-by: Chih-Min Chao Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Acked-by: Alistair Francis --- target/riscv/fpu_helper.c | 67 + target/riscv/helper.h | 12 + target/riscv/insn32

[PATCH v6 0/8] target/riscv: support Zfh, Zfhmin extension v0.1

From: Frank Chang Zfh - Half width floating point Zfhmin - Subset of half width floating point Zfh, Zfhmin v0.1 is now in public review period and is required by RVV extension: https://groups.google.com/a/groups.riscv.org/g/isa-dev/c/63gDCinXTwE/m/871Wm9XIBQAJ Zfh, Zfhmin can be enabled

Re: [PATCH v10 00/77] support vector extension v1.0

On Wed, Dec 8, 2021 at 2:40 PM Alistair Francis wrote: > On Mon, Nov 29, 2021 at 1:04 PM wrote: > > > > From: Frank Chang > > > > This patchset implements the vector extension v1.0 for RISC-V on QEMU. > > > > RVV v1.0 spec is now fronzen for public revie

[PATCH v10 46/77] target/riscv: rvv-1.0: single-width saturating add and subtract instructions

From: Frank Chang Sign-extend vsaddu.vi immediate value. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/insn_trans/trans_rvv.c.inc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv

[PATCH v10 34/77] target/riscv: rvv-1.0: allow load element with sign-extended

From: Frank Chang For some vector instructions (e.g. vmv.s.x), the element is loaded with sign-extended. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/insn_trans/trans_rvv.c.inc | 32 + 1 file changed, 22

[PATCH v10 76/77] target/riscv: rvv-1.0: update opivv_vadc_check() comment

From: Frank Chang Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions is moved to Section 11.4 in RVV v1.0 spec. Update the comment, no functional changes. Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/insn_trans/trans_rvv.c.inc | 2 +- 1 file

[PATCH v10 74/77] target/riscv: rvv-1.0: add vector unit-stride mask load/store insns

From: Frank Chang Signed-off-by: Frank Chang Acked-by: Alistair Francis --- target/riscv/helper.h | 2 ++ target/riscv/insn32.decode | 4 +++ target/riscv/insn_trans/trans_rvv.c.inc | 40 + target/riscv/vector_helper.c| 21

[PATCH v10 13/77] target/riscv: rvv-1.0: add fractional LMUL

From: Frank Chang Introduce the concepts of fractional LMUL for RVV 1.0. In RVV 1.0, LMUL bits are contiguous in vtype register. Also rearrange rvv bits in TB_FLAGS to skip MSTATUS_VS (0x600) and MSTATUS_FS (0x6000) bits. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed

[PATCH v10 70/77] target/riscv: rvv-1.0: floating-point reciprocal estimate instruction

From: Frank Chang Implement the floating-point reciprocal estimate to 7 bits instruction. Signed-off-by: Frank Chang --- target/riscv/helper.h | 4 + target/riscv/insn32.decode | 1 + target/riscv/insn_trans/trans_rvv.c.inc | 1 + target/riscv

[PATCH v10 69/77] target/riscv: rvv-1.0: floating-point reciprocal square-root estimate instruction

From: Frank Chang Implement the floating-point reciprocal square-root estimate to 7 bits instruction. Signed-off-by: Frank Chang --- target/riscv/helper.h | 4 + target/riscv/insn32.decode | 1 + target/riscv/insn_trans/trans_rvv.c.inc | 1 + target/riscv

[PATCH v10 68/77] target/riscv: gdb: support vector registers for rv64 & rv32

From: Hsiangkai Wang Signed-off-by: Hsiangkai Wang Signed-off-by: Greentime Hu Signed-off-by: Frank Chang Acked-by: Alistair Francis --- target/riscv/cpu.c | 2 + target/riscv/cpu.h | 1 + target/riscv/gdbstub.c | 184 + 3 files changed

[PATCH v10 77/77] target/riscv: rvv-1.0: Add ELEN checks for widening and narrowing instructions

From: Frank Chang SEW has the limitation which cannot exceed ELEN. Widening instructions have a destination group with EEW = 2*SEW and narrowing instructions have a source operand with EEW = 2*SEW. Both of the instructions have the limitation of: 2*SEW <= ELEN. Signed-off-by: Frank Ch

[PATCH v10 67/77] target/riscv: rvv-1.0: trigger illegal instruction exception if frm is not valid

From: Frank Chang If the frm field contains an invalid rounding mode (101-111), attempting to execute any vector floating-point instruction, even those that do not depend on the rounding mode, will raise an illegal instruction exception. Call gen_set_rm() with DYN rounding mode to check

[PATCH v10 73/77] target/riscv: rvv-1.0: add evl parameter to vext_ldst_us()

From: Frank Chang Add supports of Vector unit-stride mask load/store instructions (vlm.v, vsm.v), which has: evl (effective vector length) = ceil(env->vl / 8). The new instructions operate the same as unmasked byte loads and stores. Add evl parameter to reuse vext_ldst_us(). Signed-

[PATCH v10 66/77] target/riscv: rvv-1.0: implement vstart CSR

From: Frank Chang * Update and check vstart value for vector instructions. * Add whole register move instruction helper functions as we have to call helper function for case where vstart is not zero. * Remove probe_pages() calls in vector load/store instructions (except fault-only-first

[PATCH v10 72/77] target/riscv: rvv-1.0: add vsetivli instruction

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/insn32.decode | 2 ++ target/riscv/insn_trans/trans_rvv.c.inc | 27 + 2 files changed, 29 insertions(+) diff --git a/target/riscv/insn32.decode b/target/riscv

[PATCH v10 44/77] target/riscv: rvv-1.0: narrowing integer right shift instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/helper.h | 24 +++--- target/riscv/insn32.decode | 12 +++ target/riscv/insn_trans/trans_rvv.c.inc | 42 - target/riscv

[PATCH v10 02/77] target/riscv: Use FIELD_EX32() to extract wd field

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/vector_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 12c31aa4b4d

[PATCH v10 63/77] target/riscv: add "set round to odd" rounding mode helper function

From: Frank Chang helper_set_rounding_mode() is responsible for SIGILL, and "round to odd" should be an interface private to translation, so add a new independent helper_set_rod_rounding_mode(). Signed-off-by: Frank Chang Acked-by: Alistair Francis --- target/riscv/fpu_he

[PATCH v10 64/77] target/riscv: rvv-1.0: narrowing floating-point/integer type-convert

From: Frank Chang Signed-off-by: Frank Chang Acked-by: Alistair Francis --- target/riscv/helper.h | 22 - target/riscv/insn32.decode | 15 --- target/riscv/insn_trans/trans_rvv.c.inc | 59 + target/riscv/vector_helper.c

[PATCH v10 60/77] target/riscv: introduce floating-point rounding mode enum

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/fpu_helper.c | 12 ++-- target/riscv/insn_trans/trans_rvv.c.inc | 18 +- target/riscv/internals.h| 9 + 3 files changed, 24 insertions

[PATCH v10 12/77] target/riscv: rvv-1.0: remove MLEN calculations

From: Frank Chang As in RVV 1.0 design, MLEN is hardcoded with value 1 (Section 4.5). Thus, remove all MLEN related calculations. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/insn_trans/trans_rvv.c.inc | 35 +--- target/riscv

[PATCH v10 01/77] target/riscv: drop vector 0.7.1 and add 1.0 support

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis Reviewed-by: Bin Meng --- target/riscv/cpu.c | 16 target/riscv/cpu.h | 2 +- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/target/riscv/cpu.c b

[PATCH v10 59/77] target/riscv: rvv-1.0: floating-point min/max instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/vector_helper.c | 24 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index aed230e1ad8

[PATCH v10 15/77] target/riscv: rvv-1.0: update check functions

From: Frank Chang Update check functions with RVV 1.0 rules. Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/insn_trans/trans_rvv.c.inc | 715 +--- 1 file changed, 507 insertions(+), 208 deletions(-) diff --git a/target/riscv/insn_trans

[PATCH v10 75/77] target/riscv: rvv-1.0: rename vmandnot.mm and vmornot.mm to vmandn.mm and vmorn.mm

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/helper.h | 4 ++-- target/riscv/insn32.decode | 4 ++-- target/riscv/insn_trans/trans_rvv.c.inc | 4 ++-- target/riscv/vector_helper.c| 4 ++-- 4 files

[PATCH v10 52/77] target/riscv: rvv-1.0: narrowing fixed-point clip instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/helper.h | 24 ++-- target/riscv/insn32.decode | 12 +++--- target/riscv/insn_trans/trans_rvv.c.inc | 12 +++--- target/riscv/vector_helper.c| 52

[PATCH v10 71/77] target/riscv: rvv-1.0: rename r2_zimm to r2_zimm11

From: Frank Chang Rename r2_zimm to r2_zimm11 for the upcoming vsetivli instruction. vsetivli has 10-bits of zimm but vsetvli has 11-bits of zimm. Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/insn32.decode | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions

[PATCH v10 53/77] target/riscv: rvv-1.0: single-width floating-point reduction

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/insn_trans/trans_rvv.c.inc | 12 +--- target/riscv/vector_helper.c| 12 ++-- 2 files changed, 15 insertions(+), 9 deletions(-) diff --git a/target/riscv/insn_trans

[PATCH v10 51/77] target/riscv: rvv-1.0: floating-point slide instructions

From: Frank Chang Add the following instructions: * vfslide1up.vf * vfslide1down.vf Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/helper.h | 7 ++ target/riscv/insn32.decode | 2 + target/riscv/insn_trans/trans_rvv.c.inc | 16

[PATCH v10 65/77] target/riscv: rvv-1.0: relax RV_VLEN_MAX to 1024-bits

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/cpu.h | 2 +- target/riscv/insn_trans/trans_rvv.c.inc | 4 ++-- target/riscv/vector_helper.c| 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git

[PATCH v10 50/77] target/riscv: rvv-1.0: slide instructions

From: Frank Chang * Remove clear function from helper functions as the tail elements are unchanged in RVV 1.0. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/vector_helper.c | 19 --- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git

[PATCH v10 48/77] target/riscv: rvv-1.0: floating-point compare instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/vector_helper.c | 9 - 1 file changed, 9 deletions(-) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 277a5e4120a..71d7b1e8796 100644 --- a/target/riscv

[PATCH v10 58/77] target/riscv: rvv-1.0: remove integer extract instruction

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/insn32.decode | 1 - target/riscv/insn_trans/trans_rvv.c.inc | 23 --- 2 files changed, 24 deletions(-) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32

[PATCH v10 62/77] target/riscv: rvv-1.0: widening floating-point/integer type-convert

From: Frank Chang Add the following instructions: * vfwcvt.rtz.xu.f.v * vfwcvt.rtz.x.f.v Also adjust GEN_OPFV_WIDEN_TRANS() to accept multiple floating-point rounding modes. Signed-off-by: Frank Chang Acked-by: Alistair Francis --- target/riscv/helper.h | 2 + target

[PATCH v10 45/77] target/riscv: rvv-1.0: widening integer multiply-add instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/insn32.decode | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index a3f1101cd63..7548b71efdb 100644 --- a/target/riscv

[PATCH v10 47/77] target/riscv: rvv-1.0: integer comparison instructions

From: Frank Chang * Sign-extend vmselu.vi and vmsgtu.vi immediate values. * Remove "set tail elements to zeros" as tail elements can be unchanged for either VTA to have undisturbed or agnostic setting. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/

[PATCH v10 57/77] target/riscv: rvv-1.0: remove vmford.vv and vmford.vf

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/helper.h | 6 -- target/riscv/insn32.decode | 2 -- target/riscv/insn_trans/trans_rvv.c.inc | 2 -- target/riscv/vector_helper.c| 7 --- 4 files

[PATCH v10 61/77] target/riscv: rvv-1.0: floating-point/integer type-convert instructions

From: Frank Chang Add the following instructions: * vfcvt.rtz.xu.f.v * vfcvt.rtz.x.f.v Also adjust GEN_OPFV_TRANS() to accept multiple floating-point rounding modes. Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/insn32.decode | 11 ++-- target/riscv

[PATCH v10 41/77] target/riscv: rvv-1.0: single-width averaging add and subtract instructions

From: Frank Chang Add the following instructions: * vaaddu.vv * vaaddu.vx * vasubu.vv * vasubu.vx Remove the following instructions: * vadd.vi Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/helper.h | 16 ++ target/riscv/insn32.decode

[PATCH v10 43/77] target/riscv: rvv-1.0: integer add-with-carry/subtract-with-borrow

From: Frank Chang * Only do carry-in or borrow-in if is masked (vm=0). * Remove clear function from helper functions as the tail elements are unchanged in RVV 1.0. Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/insn32.decode | 20

[PATCH v10 55/77] target/riscv: rvv-1.0: single-width scaling shift instructions

From: Frank Chang log(SEW) truncate vssra.vi immediate value. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/insn_trans/trans_rvv.c.inc | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv

[PATCH v10 56/77] target/riscv: rvv-1.0: remove widening saturating scaled multiply-add

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/helper.h | 22 --- target/riscv/insn32.decode | 7 - target/riscv/insn_trans/trans_rvv.c.inc | 9 -- target/riscv/vector_helper.c| 205

[PATCH v10 39/77] target/riscv: rvv-1.0: whole register move instructions

From: Frank Chang Add the following instructions: * vmv1r.v * vmv2r.v * vmv4r.v * vmv8r.v Signed-off-by: Frank Chang Acked-by: Alistair Francis --- target/riscv/insn32.decode | 4 target/riscv/insn_trans/trans_rvv.c.inc | 25 + 2 files changed, 29

[PATCH v10 38/77] target/riscv: rvv-1.0: floating-point scalar move instructions

From: Frank Chang NaN-boxed the scalar floating-point register based on RVV 1.0's rules. Signed-off-by: Frank Chang Acked-by: Alistair Francis --- target/riscv/insn32.decode | 4 +-- target/riscv/insn_trans/trans_rvv.c.inc | 38 - target/riscv

[PATCH v10 40/77] target/riscv: rvv-1.0: integer extension instructions

From: Frank Chang Add the following instructions: * vzext.vf2 * vzext.vf4 * vzext.vf8 * vsext.vf2 * vsext.vf4 * vsext.vf8 Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/helper.h | 14 + target/riscv/insn32.decode | 8

[PATCH v10 54/77] target/riscv: rvv-1.0: widening floating-point reduction instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/insn_trans/trans_rvv.c.inc | 9 - 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc index

[PATCH v10 36/77] target/riscv: rvv-1.0: integer scalar move instructions

From: Frank Chang * Remove "vmv.s.x: dothing if rs1 == 0" constraint. * Add vmv.x.s instruction. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Acked-by: Alistair Francis --- target/riscv/insn32.decode | 3 +- target/riscv/insn_trans/trans_rvv.

[PATCH v10 37/77] target/riscv: rvv-1.0: floating-point move instruction

From: Frank Chang NaN-boxed the scalar floating-point register based on RVV 1.0's rules. Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/insn_trans/trans_rvv.c.inc | 16 ++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/target/riscv

[PATCH v10 31/77] target/riscv: rvv-1.0: set-X-first mask bit instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/insn32.decode | 6 +++--- target/riscv/insn_trans/trans_rvv.c.inc | 5 - target/riscv/vector_helper.c| 4 3 files changed, 7 insertions

[PATCH v10 49/77] target/riscv: rvv-1.0: mask-register logical instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/insn_trans/trans_rvv.c.inc | 3 ++- target/riscv/vector_helper.c| 4 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target

[PATCH v10 33/77] target/riscv: rvv-1.0: element index instruction

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/insn32.decode | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 3ac5162aeb7..ab274dcde12

[PATCH v10 30/77] target/riscv: rvv-1.0: find-first-set mask bit instruction

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 2 +- target/riscv/insn32.decode | 2 +- target/riscv/insn_trans/trans_rvv.c.inc | 4 ++-- target/riscv/vector_helper.c

[PATCH v10 32/77] target/riscv: rvv-1.0: iota instruction

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/insn32.decode | 2 +- target/riscv/insn_trans/trans_rvv.c.inc | 10 -- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/target/riscv

[PATCH v10 42/77] target/riscv: rvv-1.0: single-width bit shift instructions

From: Frank Chang Truncate vsll.vi, vsrl.vi, vsra.vi's immediate values to lg2(SEW) bits. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/insn_trans/trans_rvv.c.inc | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/riscv/insn_trans

[PATCH v10 29/77] target/riscv: rvv-1.0: count population in mask instruction

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 2 +- target/riscv/insn32.decode | 2 +- target/riscv/insn_trans/trans_rvv.c.inc | 7 --- target/riscv/vector_helper.c

[PATCH v10 25/77] target/riscv: rvv-1.0: update vext_max_elems() for load/store insns

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/insn_trans/trans_rvv.c.inc | 32 ++-- target/riscv/vector_helper.c| 99 ++--- 2 files changed, 80 insertions(+), 51 deletions(-) diff --git a/target/riscv

[PATCH v10 26/77] target/riscv: rvv-1.0: take fractional LMUL into vector max elements calculation

From: Frank Chang Update vext_get_vlmax() and MAXSZ() to take fractional LMUL into calculation for RVV 1.0. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/cpu.h | 27 - target/riscv

[PATCH v10 35/77] target/riscv: rvv-1.0: register gather instructions

From: Frank Chang * Add vrgatherei16.vv instruction. Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/helper.h | 4 target/riscv/insn32.decode | 1 + target/riscv/insn_trans/trans_rvv.c.inc | 27 ++--- target

[PATCH v10 21/77] target/riscv: rvv-1.0: index load and store instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/helper.h | 67 +++ target/riscv/insn32.decode | 21 +++-- target/riscv/insn_trans/trans_rvv.c.inc | 110 +--- target/riscv

[PATCH v10 24/77] target/riscv: rvv-1.0: load/store whole register instructions

From: Frank Chang Add the following instructions: * vlre.v * vsr.v Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/helper.h | 21 target/riscv/insn32.decode | 22 target/riscv/insn_trans/trans_rvv.c.inc | 68

[PATCH v10 28/77] target/riscv: rvv-1.0: floating-point classify instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/insn32.decode | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 92a0e6fe51e..f61eaf7c6ba

[PATCH v10 27/77] target/riscv: rvv-1.0: floating-point square-root instruction

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/insn32.decode | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 7d8441d1f21..92a0e6fe51e

[PATCH v10 18/77] target/riscv: rvv-1.0: remove amo operations instructions

From: Frank Chang Vector AMOs are removed from standard vector extensions. Will be added later as separate Zvamo extension, but will need a different encoding from earlier proposal. Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/helper.h | 27

[PATCH v10 23/77] target/riscv: rvv-1.0: fault-only-first unit stride load

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 26 ++--- target/riscv/insn32.decode | 14 ++--- target/riscv/insn_trans/trans_rvv.c.inc | 33 +++ target/riscv

[PATCH v10 08/77] target/riscv: rvv-1.0: remove rvv related codes from fcsr registers

From: Frank Chang * Remove VXRM and VXSAT fields from FCSR register as they are only presented in VCSR register. * Remove RVV loose check in fs() predicate function. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/csr.c | 13

[PATCH v10 20/77] target/riscv: rvv-1.0: stride load and store instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/helper.h | 129 ++-- target/riscv/insn32.decode | 43 ++- target/riscv/insn_trans/trans_rvv.c.inc | 376 target/riscv/vector_helper.c

[PATCH v10 22/77] target/riscv: rvv-1.0: fix address index overflow bug of indexed load/store insns

From: Frank Chang Replace ETYPE from signed int to unsigned int to prevent index overflow issue, which would lead to wrong index address. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/vector_helper.c | 8 1 file changed, 4

[PATCH v10 17/77] target/riscv: rvv:1.0: add translation-time nan-box helper function

From: Frank Chang * Add fp16 nan-box check generator function, if a 16-bit input is not properly nanboxed, then the input is replaced with the default qnan. * Add do_nanbox() helper function to utilize gen_check_nanbox_X() to generate the NaN-boxed floating-point values based on SEW setting

[PATCH v10 09/77] target/riscv: rvv-1.0: add vcsr register

From: LIU Zhiwei Signed-off-by: LIU Zhiwei Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/cpu_bits.h | 7 +++ target/riscv/csr.c | 17 + 2 files changed, 24 insertions(+) diff --git a/target/riscv

[PATCH v10 19/77] target/riscv: rvv-1.0: configure instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/insn_trans/trans_rvv.c.inc | 62 +++-- target/riscv/vector_helper.c| 14 +- 2 files changed, 40 insertions(+), 36 deletions(-) diff

[PATCH v10 11/77] target/riscv: rvv-1.0: check MSTATUS_VS when accessing vector csr registers

From: Frank Chang If VS field is off, accessing vector csr registers should raise an illegal-instruction exception. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/csr.c | 5 + 1 file changed, 5 insertions(+) diff --git a/target

[PATCH v10 16/77] target/riscv: introduce more imm value modes in translator functions

From: Frank Chang Immediate value in translator function is extended not only zero-extended and sign-extended but with more modes to be applicable with multiple formats of vector instructions. * IMM_ZX: Zero-extended * IMM_SX: Sign-extended * IMM_TRUNC_SEW: Truncate to log(SEW

[PATCH v10 06/77] target/riscv: rvv-1.0: introduce writable misa.v field

From: Frank Chang Implementations may have a writable misa.v field. Analogous to the way in which the floating-point unit is handled, the mstatus.vs field may exist even if misa.v is clear. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target

[PATCH v10 10/77] target/riscv: rvv-1.0: add vlenb register

From: Greentime Hu Signed-off-by: Greentime Hu Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/cpu_bits.h | 1 + target/riscv/csr.c | 7 +++ 2 files changed, 8 insertions(+) diff --git a/target/riscv/cpu_bits.h b/target

[PATCH v10 05/77] target/riscv: rvv-1.0: add sstatus VS field

From: LIU Zhiwei Signed-off-by: LIU Zhiwei Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/cpu_bits.h | 1 + target/riscv/csr.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/target/riscv/cpu_bits.h b

[PATCH v10 04/77] target/riscv: rvv-1.0: set mstatus.SD bit if mstatus.VS is dirty

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/csr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/target/riscv/csr.c b/target/riscv/csr.c index 9b5bd5d7b49..bb500afdeb5 100644 --- a/target/riscv/csr.c +++ b/target/riscv/csr.c @@ -502,6

[PATCH v10 07/77] target/riscv: rvv-1.0: add translation-time vector context status

From: Frank Chang Signed-off-by: LIU Zhiwei Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/cpu.h | 5 +- target/riscv/cpu_helper.c | 3 + target/riscv/insn_trans/trans_rvv.c.inc | 75

[PATCH v10 03/77] target/riscv: rvv-1.0: add mstatus VS field

From: LIU Zhiwei Signed-off-by: LIU Zhiwei Signed-off-by: Frank Chang Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/cpu.h| 2 ++ target/riscv/cpu_bits.h | 1 + target/riscv/cpu_helper.c | 20 +++- target/riscv/csr.c| 12

[PATCH v10 00/77] support vector extension v1.0

From: Frank Chang This patchset implements the vector extension v1.0 for RISC-V on QEMU. RVV v1.0 spec is now fronzen for public review: https://github.com/riscv/riscv-v-spec/releases/tag/v1.0 The port is available here: https://github.com/sifive/qemu/tree/rvv-1.0-upstream-v10 RVV v1.0 can

Re: [PATCH v5 0/8] target/riscv: support Zfh, Zfhmin extension v0.1

On Fri, Oct 22, 2021 at 12:30 AM wrote: > From: Frank Chang > > Zfh - Half width floating point > Zfhmin - Subset of half width floating point > > Zfh, Zfhmin v0.1 is now in public review period and is required by > RVV extension: > > https://groups.google.com/a/g

[PATCH v9 76/76] target/riscv: rvv-1.0: update opivv_vadc_check() comment

From: Frank Chang Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions is moved to Section 11.4 in RVV v1.0 spec. Update the comment, no functional changes. Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/insn_trans/trans_rvv.c.inc | 2 +- 1 file

[PATCH v9 74/76] target/riscv: rvv-1.0: add vector unit-stride mask load/store insns

From: Frank Chang Signed-off-by: Frank Chang --- target/riscv/helper.h | 2 ++ target/riscv/insn32.decode | 4 +++ target/riscv/insn_trans/trans_rvv.c.inc | 40 + target/riscv/vector_helper.c| 21 + 4 files

[PATCH v9 72/76] target/riscv: rvv-1.0: add vsetivli instruction

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/insn32.decode | 2 ++ target/riscv/insn_trans/trans_rvv.c.inc | 27 + 2 files changed, 29 insertions(+) diff --git a/target/riscv/insn32.decode b/target/riscv

[PATCH v9 75/76] target/riscv: rvv-1.0: rename vmandnot.mm and vmornot.mm to vmandn.mm and vmorn.mm

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/helper.h | 4 ++-- target/riscv/insn32.decode | 4 ++-- target/riscv/insn_trans/trans_rvv.c.inc | 4 ++-- target/riscv/vector_helper.c| 4 ++-- 4 files

[PATCH v9 71/76] target/riscv: rvv-1.0: rename r2_zimm to r2_zimm11

From: Frank Chang Rename r2_zimm to r2_zimm11 for the upcoming vsetivli instruction. vsetivli has 10-bits of zimm but vsetvli has 11-bits of zimm. Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/insn32.decode | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions

[PATCH v9 62/76] target/riscv: rvv-1.0: widening floating-point/integer type-convert

From: Frank Chang Add the following instructions: * vfwcvt.rtz.xu.f.v * vfwcvt.rtz.x.f.v Also adjust GEN_OPFV_WIDEN_TRANS() to accept multiple floating-point rounding modes. Signed-off-by: Frank Chang Acked-by: Alistair Francis --- target/riscv/helper.h | 2 + target

[PATCH v9 68/76] target/riscv: gdb: support vector registers for rv64 & rv32

From: Hsiangkai Wang Signed-off-by: Hsiangkai Wang Signed-off-by: Greentime Hu Signed-off-by: Frank Chang --- target/riscv/cpu.c | 2 + target/riscv/cpu.h | 1 + target/riscv/gdbstub.c | 184 + 3 files changed, 187 insertions(+) diff --git

[PATCH v9 65/76] target/riscv: rvv-1.0: relax RV_VLEN_MAX to 1024-bits

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/cpu.h | 2 +- target/riscv/insn_trans/trans_rvv.c.inc | 4 ++-- target/riscv/vector_helper.c| 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git

[PATCH v9 61/76] target/riscv: rvv-1.0: floating-point/integer type-convert instructions

From: Frank Chang Add the following instructions: * vfcvt.rtz.xu.f.v * vfcvt.rtz.x.f.v Also adjust GEN_OPFV_TRANS() to accept multiple floating-point rounding modes. Signed-off-by: Frank Chang Reviewed-by: Alistair Francis --- target/riscv/insn32.decode | 11 ++-- target/riscv

[PATCH v9 60/76] target/riscv: introduce floating-point rounding mode enum

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/fpu_helper.c | 12 ++-- target/riscv/insn_trans/trans_rvv.c.inc | 18 +- target/riscv/internals.h| 9 + 3 files changed, 24 insertions

[PATCH v9 59/76] target/riscv: rvv-1.0: floating-point min/max instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/vector_helper.c | 24 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index aed230e1ad8

[PATCH v9 55/76] target/riscv: rvv-1.0: single-width scaling shift instructions

From: Frank Chang log(SEW) truncate vssra.vi immediate value. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/insn_trans/trans_rvv.c.inc | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv

[PATCH v9 67/76] target/riscv: rvv-1.0: trigger illegal instruction exception if frm is not valid

From: Frank Chang If the frm field contains an invalid rounding mode (101-111), attempting to execute any vector floating-point instruction, even those that do not depend on the rounding mode, will raise an illegal instruction exception. Call gen_set_rm() with DYN rounding mode to check

[PATCH v9 57/76] target/riscv: rvv-1.0: remove vmford.vv and vmford.vf

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/helper.h | 6 -- target/riscv/insn32.decode | 2 -- target/riscv/insn_trans/trans_rvv.c.inc | 2 -- target/riscv/vector_helper.c| 7 --- 4 files

[PATCH v9 54/76] target/riscv: rvv-1.0: widening floating-point reduction instructions

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/insn_trans/trans_rvv.c.inc | 9 - 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc index

[PATCH v9 73/76] target/riscv: rvv-1.0: add evl parameter to vext_ldst_us()

From: Frank Chang Add supports of Vector unit-stride mask load/store instructions (vlm.v, vsm.v), which has: evl (effective vector length) = ceil(env->vl / 8). The new instructions operate the same as unmasked byte loads and stores. Add evl parameter to reuse vext_ldst_us(). Signed-

[PATCH v9 64/76] target/riscv: rvv-1.0: narrowing floating-point/integer type-convert

From: Frank Chang Signed-off-by: Frank Chang Acked-by: Alistair Francis --- target/riscv/helper.h | 22 - target/riscv/insn32.decode | 15 --- target/riscv/insn_trans/trans_rvv.c.inc | 59 + target/riscv/vector_helper.c

[PATCH v9 56/76] target/riscv: rvv-1.0: remove widening saturating scaled multiply-add

From: Frank Chang Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/helper.h | 22 --- target/riscv/insn32.decode | 7 - target/riscv/insn_trans/trans_rvv.c.inc | 9 -- target/riscv/vector_helper.c| 205

[PATCH v9 50/76] target/riscv: rvv-1.0: slide instructions

From: Frank Chang * Remove clear function from helper functions as the tail elements are unchanged in RVV 1.0. Signed-off-by: Frank Chang Reviewed-by: Richard Henderson --- target/riscv/vector_helper.c | 19 --- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git

<    1   2   3   4   5   6   7   8   9   10   >