Signed-off-by: Richard Henderson <richard.hender...@linaro.org> --- target/arm/tcg/helper-sve.h | 3 +++ target/arm/tcg/sve_helper.c | 49 ++++++++++++++++++++++++++++++++++ target/arm/tcg/translate-sve.c | 22 +++++++++++---- target/arm/tcg/sve.decode | 11 ++++++++ 4 files changed, 80 insertions(+), 5 deletions(-)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index eac23e75b9..74029c641b 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -944,6 +944,9 @@ DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32) DEF_HELPER_FLAGS_3(sve_while2l, TCG_CALL_NO_RWG, i32, ptr, i32, i32) DEF_HELPER_FLAGS_3(sve_while2g, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_whilecl, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_whilecg, TCG_CALL_NO_RWG, i32, ptr, i32, i32) + DEF_HELPER_FLAGS_4(sve_subri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_subri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_subri_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c index 2beb012292..dfc3e5cabe 100644 --- a/target/arm/tcg/sve_helper.c +++ b/target/arm/tcg/sve_helper.c @@ -4096,6 +4096,29 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) return sum; } +/* C.f. Arm pseudocode EncodePredCount */ +static uint64_t encode_pred_count(uint32_t elements, uint32_t count, + uint32_t esz, bool invert) +{ + uint32_t pred; + + if (count == 0) { + return 0; + } + if (invert) { + count = elements - count; + } else if (count == elements) { + count = 0; + invert = true; + } + + pred = (count << 1) | 1; + pred <<= esz; + pred |= invert << 15; + + return pred; +} + /* C.f. Arm pseudocode PredCountTest */ static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert) { @@ -4179,6 +4202,19 @@ uint32_t HELPER(sve_while2l)(void *vd, uint32_t count, uint32_t pred_desc) return pred_count_test(2 * oprbits, count, false); } +uint32_t HELPER(sve_whilecl)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t scale = FIELD_EX32(pred_desc, PREDDESC, DATA); + uint32_t elements = (oprsz >> esz) << scale; + ARMPredicateReg *d = vd; + + do_zero(d, oprsz); + d->p[0] = encode_pred_count(elements, count, esz, false); + return pred_count_test(elements, count, false); +} + static void do_whileg(uint64_t *d, uint64_t esz_mask, uint32_t count, uint32_t oprbits) { @@ -4234,6 +4270,19 @@ uint32_t HELPER(sve_while2g)(void *vd, uint32_t count, uint32_t pred_desc) return pred_count_test(2 * oprbits, count, true); } +uint32_t HELPER(sve_whilecg)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t scale = FIELD_EX32(pred_desc, PREDDESC, DATA); + uint32_t elements = (oprsz >> esz) << scale; + ARMPredicateReg *d = vd; + + do_zero(d, oprsz); + d->p[0] = encode_pred_count(elements, count, esz, true); + return pred_count_test(elements, count, true); +} + /* Recursive reduction on a function; * C.f. the ARM ARM function ReducePredicated. * diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index c2a5b2f76f..3e82c1ed49 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -3093,7 +3093,7 @@ static bool trans_CTERM(DisasContext *s, arg_CTERM *a) typedef void gen_while_fn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); static bool do_WHILE(DisasContext *s, arg_while *a, - bool lt, int scale, gen_while_fn *fn) + bool lt, int scale, int data, gen_while_fn *fn) { TCGv_i64 op0, op1, t0, t1, tmax; TCGv_i32 t2; @@ -3179,6 +3179,7 @@ static bool do_WHILE(DisasContext *s, arg_while *a, desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8); desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz); + desc = FIELD_DP32(desc, PREDDESC, DATA, data); ptr = tcg_temp_new_ptr(); tcg_gen_addi_ptr(ptr, tcg_env, pred_full_reg_offset(s, a->rd)); @@ -3189,13 +3190,24 @@ static bool do_WHILE(DisasContext *s, arg_while *a, return true; } -TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, 0, gen_helper_sve_whilel) -TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, 0, gen_helper_sve_whileg) +TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, + a, true, 0, 0, gen_helper_sve_whilel) +TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, + a, false, 0, 0, gen_helper_sve_whileg) TRANS_FEAT(WHILE_lt_pair, aa64_sme2_or_sve2p1, do_WHILE, - a, true, 1, gen_helper_sve_while2l) + a, true, 1, 0, gen_helper_sve_while2l) TRANS_FEAT(WHILE_gt_pair, aa64_sme2_or_sve2p1, do_WHILE, - a, false, 1, gen_helper_sve_while2g) + a, false, 1, 0, gen_helper_sve_while2g) + +TRANS_FEAT(WHILE_lt_cnt2, aa64_sme2_or_sve2p1, do_WHILE, + a, true, 1, 1, gen_helper_sve_whilecl) +TRANS_FEAT(WHILE_lt_cnt4, aa64_sme2_or_sve2p1, do_WHILE, + a, true, 2, 2, gen_helper_sve_whilecl) +TRANS_FEAT(WHILE_gt_cnt2, aa64_sme2_or_sve2p1, do_WHILE, + a, false, 1, 1, gen_helper_sve_whilecg) +TRANS_FEAT(WHILE_gt_cnt4, aa64_sme2_or_sve2p1, do_WHILE, + a, false, 2, 2, gen_helper_sve_whilecg) static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) { diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index a919fe117b..fbc4487b06 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -59,6 +59,8 @@ %rn_ax2 6:4 !function=times_2 +%pnd 0:3 !function=plus_8 + ########################################################################### # Named attribute sets. These are used to make nice(er) names # when creating helpers common to those for the individual @@ -804,6 +806,15 @@ WHILE_ptr 00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4 WHILE_lt_pair 00100101 .. 1 ..... 0101 . 1 ..... 1 ... . @while_pair WHILE_gt_pair 00100101 .. 1 ..... 0101 . 0 ..... 1 ... . @while_pair +# SVE2.1 predicate as count +@while_cnt ........ esz:2 . rm:5 .... u:1 . rn:5 . eq:1 ... \ + &while rd=%pnd sf=1 + +WHILE_lt_cnt2 00100101 .. 1 ..... 0100 . 1 ..... 1 . ... @while_cnt +WHILE_lt_cnt4 00100101 .. 1 ..... 0110 . 1 ..... 1 . ... @while_cnt +WHILE_gt_cnt2 00100101 .. 1 ..... 0100 . 0 ..... 1 . ... @while_cnt +WHILE_gt_cnt4 00100101 .. 1 ..... 0110 . 0 ..... 1 . ... @while_cnt + ### SVE Integer Wide Immediate - Unpredicated Group # SVE broadcast floating-point immediate (unpredicated) -- 2.43.0