diff options
| author | Richard Henderson <richard.henderson@linaro.org> | 2022-05-27 11:18:10 -0700 |
|---|---|---|
| committer | Peter Maydell <peter.maydell@linaro.org> | 2022-05-30 17:05:08 +0100 |
| commit | 09eb6d7025d14bc01293a1bd6ecfcde985dec4d9 (patch) | |
| tree | 4903c2442594371d0e8a53e70ddc9b1056c667b3 /target | |
| parent | 1d0fce4bd0c6ceff32f14f8bab118351c4366a6c (diff) | |
target/arm: Move sve zip high_ofs into simd_data
This is in line with how we treat uzp, and will
eliminate the special case code during translation.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20220527181907.189259-58-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Diffstat (limited to 'target')
| -rw-r--r-- | target/arm/sve_helper.c | 6 | ||||
| -rw-r--r-- | target/arm/translate-sve.c | 12 |
2 files changed, 10 insertions, 8 deletions
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index e0f9aa9983..3bdcd4ce9d 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -3382,6 +3382,7 @@ void HELPER(sve_punpk_p)(void *vd, void *vn, uint32_t pred_desc) void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ intptr_t oprsz = simd_oprsz(desc); \ + intptr_t odd_ofs = simd_data(desc); \ intptr_t i, oprsz_2 = oprsz / 2; \ ARMVectorReg tmp_n, tmp_m; \ /* We produce output faster than we consume input. \ @@ -3393,8 +3394,9 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ vm = memcpy(&tmp_m, vm, oprsz_2); \ } \ for (i = 0; i < oprsz_2; i += sizeof(TYPE)) { \ - *(TYPE *)(vd + H(2 * i + 0)) = *(TYPE *)(vn + H(i)); \ - *(TYPE *)(vd + H(2 * i + sizeof(TYPE))) = *(TYPE *)(vm + H(i)); \ + *(TYPE *)(vd + H(2 * i + 0)) = *(TYPE *)(vn + odd_ofs + H(i)); \ + *(TYPE *)(vd + H(2 * i + sizeof(TYPE))) = \ + *(TYPE *)(vm + odd_ofs + H(i)); \ } \ if (sizeof(TYPE) == 16 && unlikely(oprsz & 16)) { \ memset(vd + oprsz - 16, 0, 16); \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index 1e6bcedb9d..c2ced3e2bb 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -2298,9 +2298,9 @@ static bool do_zip(DisasContext *s, arg_rrr_esz *a, bool high) unsigned vsz = vec_full_reg_size(s); unsigned high_ofs = high ? vsz / 2 : 0; tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn) + high_ofs, - vec_full_reg_offset(s, a->rm) + high_ofs, - vsz, vsz, 0, fns[a->esz]); + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vsz, vsz, high_ofs, fns[a->esz]); } return true; } @@ -2324,9 +2324,9 @@ static bool do_zip_q(DisasContext *s, arg_rrr_esz *a, bool high) unsigned vsz = vec_full_reg_size(s); unsigned high_ofs = high ? QEMU_ALIGN_DOWN(vsz, 32) / 2 : 0; tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), - vec_full_reg_offset(s, a->rn) + high_ofs, - vec_full_reg_offset(s, a->rm) + high_ofs, - vsz, vsz, 0, gen_helper_sve2_zip_q); + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vsz, vsz, high_ofs, gen_helper_sve2_zip_q); } return true; } |