[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH 10/17] target/arm: Introduce gen_gvec_sshr, gen_gvec_ushr
From: |
Richard Henderson |
Subject: |
[PATCH 10/17] target/arm: Introduce gen_gvec_sshr, gen_gvec_ushr |
Date: |
Wed, 17 Jul 2024 16:08:56 +1000 |
Handle the two special cases within these new
functions instead of higher in the call stack.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate.h | 5 +++++
target/arm/tcg/gengvec.c | 19 +++++++++++++++++++
target/arm/tcg/translate-a64.c | 16 +---------------
target/arm/tcg/translate-neon.c | 25 ++-----------------------
4 files changed, 27 insertions(+), 38 deletions(-)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index a8672c857c..d1a836ca6f 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -514,6 +514,11 @@ void gen_sqsub_d(TCGv_i64 d, TCGv_i64 q, TCGv_i64 a,
TCGv_i64 b);
void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_sshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+ int64_t shift, uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_ushr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+ int64_t shift, uint32_t opr_sz, uint32_t max_sz);
+
void gen_gvec_ssra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
int64_t shift, uint32_t opr_sz, uint32_t max_sz);
void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index 56a1dc1f75..47ac2634ce 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -88,6 +88,25 @@ GEN_CMP0(gen_gvec_cgt0, TCG_COND_GT)
#undef GEN_CMP0
+void gen_gvec_sshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+ int64_t shift, uint32_t opr_sz, uint32_t max_sz)
+{
+ /* Signed shift out of range results in all-sign-bits */
+ shift = MIN(shift, (8 << vece) - 1);
+ tcg_gen_gvec_sari(vece, rd_ofs, rm_ofs, shift, opr_sz, max_sz);
+}
+
+void gen_gvec_ushr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+ int64_t shift, uint32_t opr_sz, uint32_t max_sz)
+{
+ /* Unsigned shift out of range results in all-zero-bits */
+ if (shift >= (8 << vece)) {
+ tcg_gen_gvec_dup_imm(vece, rd_ofs, opr_sz, max_sz, 0);
+ } else {
+ tcg_gen_gvec_shri(vece, rd_ofs, rm_ofs, shift, opr_sz, max_sz);
+ }
+}
+
static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
{
tcg_gen_vec_sar8i_i64(a, a, shift);
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 1fa9dc3172..d0a3450d75 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -10411,21 +10411,7 @@ static void handle_vec_simd_shri(DisasContext *s, bool
is_q, bool is_u,
break;
case 0x00: /* SSHR / USHR */
- if (is_u) {
- if (shift == 8 << size) {
- /* Shift count the same size as element size produces zero. */
- tcg_gen_gvec_dup_imm(size, vec_full_reg_offset(s, rd),
- is_q ? 16 : 8, vec_full_reg_size(s), 0);
- return;
- }
- gvec_fn = tcg_gen_gvec_shri;
- } else {
- /* Shift count the same size as element size produces all sign. */
- if (shift == 8 << size) {
- shift -= 1;
- }
- gvec_fn = tcg_gen_gvec_sari;
- }
+ gvec_fn = is_u ? gen_gvec_ushr : gen_gvec_sshr;
break;
case 0x04: /* SRSHR / URSHR (rounding) */
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index 915c9e56db..05d4016633 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -1068,29 +1068,8 @@ DO_2SH(VRSHR_S, gen_gvec_srshr)
DO_2SH(VRSHR_U, gen_gvec_urshr)
DO_2SH(VRSRA_S, gen_gvec_srsra)
DO_2SH(VRSRA_U, gen_gvec_ursra)
-
-static bool trans_VSHR_S_2sh(DisasContext *s, arg_2reg_shift *a)
-{
- /* Signed shift out of range results in all-sign-bits */
- a->shift = MIN(a->shift, (8 << a->size) - 1);
- return do_vector_2sh(s, a, tcg_gen_gvec_sari);
-}
-
-static void gen_zero_rd_2sh(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
- int64_t shift, uint32_t oprsz, uint32_t maxsz)
-{
- tcg_gen_gvec_dup_imm(vece, rd_ofs, oprsz, maxsz, 0);
-}
-
-static bool trans_VSHR_U_2sh(DisasContext *s, arg_2reg_shift *a)
-{
- /* Shift out of range is architecturally valid and results in zero. */
- if (a->shift >= (8 << a->size)) {
- return do_vector_2sh(s, a, gen_zero_rd_2sh);
- } else {
- return do_vector_2sh(s, a, tcg_gen_gvec_shri);
- }
-}
+DO_2SH(VSHR_S, gen_gvec_sshr)
+DO_2SH(VSHR_U, gen_gvec_ushr)
static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a,
NeonGenTwo64OpEnvFn *fn)
--
2.43.0
- Re: [PATCH 02/17] target/arm: Convert EXT to decodetree, (continued)
- [PATCH 03/17] target/arm: Convert TBL, TBX to decodetree, Richard Henderson, 2024/07/17
- [PATCH 04/17] target/arm: Convert UZP, TRN, ZIP to decodetree, Richard Henderson, 2024/07/17
- [PATCH 05/17] target/arm: Simplify do_reduction_op, Richard Henderson, 2024/07/17
- [PATCH 07/17] target/arm: Convert FMAXNMV, FMINNMV, FMAXV, FMINV to decodetree, Richard Henderson, 2024/07/17
- [PATCH 09/17] target/arm: Convert MOVI, FMOV, ORR, BIC (vector immediate) to decodetree, Richard Henderson, 2024/07/17
- [PATCH 06/17] target/arm: Convert ADDV, *ADDLV, *MAXV, *MINV to decodetree, Richard Henderson, 2024/07/17
- [PATCH 08/17] target/arm: Convert FMOVI (scalar, immediate) to decodetree, Richard Henderson, 2024/07/17
- [PATCH 10/17] target/arm: Introduce gen_gvec_sshr, gen_gvec_ushr,
Richard Henderson <=
- [PATCH 12/17] target/arm: Convert handle_vec_simd_shri to decodetree, Richard Henderson, 2024/07/17
- [PATCH 13/17] target/arm: Convet handle_vec_simd_shli to decodetree, Richard Henderson, 2024/07/17
- [PATCH 11/17] target/arm: Fix whitespace near gen_srshr64_i64, Richard Henderson, 2024/07/17
- [PATCH 14/17] target/arm: Clear high SVE elements in handle_vec_simd_wshli, Richard Henderson, 2024/07/17
- [PATCH 15/17] target/arm: Use {,s}extract in handle_vec_simd_wshli, Richard Henderson, 2024/07/17
- [PATCH 16/17] target/arm: Convert SSHLL, USHLL to decodetree, Richard Henderson, 2024/07/17
- [PATCH 17/17] target/arm: Push tcg_rnd into handle_shri_with_rndacc, Richard Henderson, 2024/07/17