https://gcc.gnu.org/g:0e05b793fba2a9bea9f0fbb1f068679f5dadf514
commit r15-6844-g0e05b793fba2a9bea9f0fbb1f068679f5dadf514
Author: liuhongt <hongtao....@intel.com>
Date: Wed Jan 8 23:11:17 2025 -0800
Refactor ix86_expand_vecop_qihi2.
Since there's regression to use vpermq, and it's manually disabled by
!TARGET_AVX512BW. I remove the codes related to vpermq and make
ix86_expand_vecop_qihi2 only handle vpmovbw + op + vpmovwb case.
gcc/ChangeLog:
* config/i386/i386-expand.cc (ix86_expand_vecop_qihi2):
Refactor to avoid redundant TARGET_AVX512BW in many places.
Diff:
---
gcc/config/i386/i386-expand.cc | 39 +++++----------------------------------
1 file changed, 5 insertions(+), 34 deletions(-)
diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
index 2ab57874234b..da030832bba7 100644
--- a/gcc/config/i386/i386-expand.cc
+++ b/gcc/config/i386/i386-expand.cc
@@ -24864,11 +24864,9 @@ ix86_expand_vecop_qihi2 (enum rtx_code code, rtx dest,
rtx op1, rtx op2)
generic permutation to merge the data back into the right place. This
permutation results in VPERMQ, which is slow, so better fall back to
ix86_expand_vecop_qihi. */
- if (!TARGET_AVX512BW)
- return false;
-
- if ((qimode == V16QImode && !TARGET_AVX2)
- || (qimode == V32QImode && (!TARGET_AVX512BW || !TARGET_EVEX512))
+ if (!TARGET_AVX512BW
+ || (qimode == V16QImode && !TARGET_AVX512VL)
+ || (qimode == V32QImode && !TARGET_EVEX512)
/* There are no V64HImode instructions. */
|| qimode == V64QImode)
return false;
@@ -24883,8 +24881,7 @@ ix86_expand_vecop_qihi2 (enum rtx_code code, rtx dest,
rtx op1, rtx op2)
{
case E_V16QImode:
himode = V16HImode;
- if (TARGET_AVX512VL && TARGET_AVX512BW)
- gen_truncate = gen_truncv16hiv16qi2;
+ gen_truncate = gen_truncv16hiv16qi2;
break;
case E_V32QImode:
himode = V32HImode;
@@ -24926,33 +24923,7 @@ ix86_expand_vecop_qihi2 (enum rtx_code code, rtx dest,
rtx op1, rtx op2)
hdest = expand_simple_binop (himode, code, hop1, hop2,
NULL_RTX, 1, OPTAB_DIRECT);
- if (gen_truncate)
- emit_insn (gen_truncate (dest, hdest));
- else
- {
- struct expand_vec_perm_d d;
- rtx wqdest = gen_reg_rtx (wqimode);
- rtx wqres = gen_lowpart (wqimode, hdest);
- bool ok;
- int i;
-
- /* Merge the data back into the right place. */
- d.target = wqdest;
- d.op0 = d.op1 = wqres;
- d.vmode = wqimode;
- d.nelt = GET_MODE_NUNITS (wqimode);
- d.one_operand_p = false;
- d.testing_p = false;
-
- for (i = 0; i < d.nelt; ++i)
- d.perm[i] = i * 2;
-
- ok = ix86_expand_vec_perm_const_1 (&d);
- gcc_assert (ok);
-
- emit_move_insn (dest, gen_lowpart (qimode, wqdest));
- }
-
+ emit_insn (gen_truncate (dest, hdest));
return true;
}
