procyberian/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Revert "Optimize v4sf reduction.".

Browse source 
This reverts commit 8f323c712e.

     PR target/102473
     PR target/101059
This commit is contained in:
liuhongt 2021-09-27 14:57:02 +08:00
parent 1932e1169a
commit e7b8d70200
3 changed files with 11 additions and 73 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

39
gcc/config/i386/sse.md
View file

@ -3156,36 +3156,19 @@
(set_attr "prefix_rep" "1,*")
(set_attr "mode" "V4SF")])
(define_expand "reduc_plus_scal_v4sf"
[(plus:V4SF
(match_operand:SF 0 "register_operand")
(match_operand:V4SF 1 "register_operand"))]
"TARGET_SSE"
{
rtx vtmp = gen_reg_rtx (V4SFmode);
rtx stmp = gen_reg_rtx (SFmode);
if (TARGET_SSE3)
emit_insn (gen_sse3_movshdup (vtmp, operands[1]));
else
emit_insn (gen_sse_shufps (vtmp, operands[1], operands[1], GEN_INT(177)));
(define_mode_iterator REDUC_SSE_PLUS_MODE
[(V2DF "TARGET_SSE") (V4SF "TARGET_SSE")])
emit_insn (gen_addv4sf3 (operands[1], operands[1], vtmp));
emit_insn (gen_sse_movhlps (vtmp, vtmp, operands[1]));
emit_insn (gen_vec_extractv4sfsf (stmp, vtmp, const0_rtx));
emit_insn (gen_vec_extractv4sfsf (operands[0], operands[1], const0_rtx));
emit_insn (gen_addsf3 (operands[0], operands[0], stmp));
DONE;
})
(define_expand "reduc_plus_scal_v2df"
[(plus:V2DF
(match_operand:DF 0 "register_operand")
(match_operand:V2DF 1 "register_operand"))]
"TARGET_SSE"
(define_expand "reduc_plus_scal_<mode>"
[(plus:REDUC_SSE_PLUS_MODE
(match_operand:<ssescalarmode> 0 "register_operand")
(match_operand:REDUC_SSE_PLUS_MODE 1 "register_operand"))]
""
{
rtx tmp = gen_reg_rtx (V2DFmode);
ix86_expand_reduc (gen_addv2df3, tmp, operands[1]);
emit_insn (gen_vec_extractv2dfdf (operands[0], tmp, const0_rtx));
rtx tmp = gen_reg_rtx (<MODE>mode);
ix86_expand_reduc (gen_add<mode>3, tmp, operands[1]);
emit_insn (gen_vec_extract<mode><ssescalarmodelower> (operands[0], tmp,
const0_rtx));
DONE;
})

32
gcc/testsuite/gcc.target/i386/sse2-pr101059.c
View file

@ -1,32 +0,0 @@
/* { dg-do run } */
/* { dg-options "-O2 -ffast-math -msse2" } */
/* { dg-require-effective-target sse2 } */
#ifndef CHECK_H
#define CHECK_H "sse2-check.h"
#endif
#ifndef TEST
#define TEST sse2_test
#endif
#include CHECK_H
float
__attribute__((noipa, optimize("tree-vectorize")))
foo (float* p)
{
float sum = 0.f;
for (int i = 0; i != 4; i++)
sum += p[i];
return sum;
}
static void
TEST (void)
{
float p[4] = {1.0f, 2.0f, 3.0f, 4.0f};
float res = foo (p);
if (res != 10.0f)
abort();
}

13
gcc/testsuite/gcc.target/i386/sse3-pr101059.c
View file

@ -1,13 +0,0 @@
/* { dg-do run } */
/* { dg-options "-O2 -ffast-math -msse3" } */
/* { dg-require-effective-target sse3 } */
#ifndef CHECK_H
#define CHECK_H "sse3-check.h"
#endif
#ifndef TEST
#define TEST sse3_test
#endif
#include "sse2-pr101059.c"