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

re PR tree-optimization/91201 (SIMD not generated for horizontal sum of bytes in array)

Browse source 
PR tree-optimization/91201
	* config/i386/i386-expand.c (ix86_expand_vector_extract): For elt == 0
	V16QImode extraction without sse4.1 try to use V4SImode lowpart
	extraction.

	* gcc.target/i386/sse2-pr91201-3.c: New test.
	* gcc.target/i386/sse2-pr91201-4.c: New test.
	* gcc.target/i386/sse2-pr91201-5.c: New test.
	* gcc.target/i386/sse2-pr91201-6.c: New test.

From-SVN: r273998
This commit is contained in:
Jakub Jelinek 2019-08-02 10:28:31 +02:00 • committed by Jakub Jelinek
parent 3bad953b2b
commit f66e6e2bea
7 changed files with 78 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
gcc/ChangeLog
View file

@ -1,3 +1,10 @@
2019-08-02 Jakub Jelinek <jakub@redhat.com>
PR tree-optimization/91201
* config/i386/i386-expand.c (ix86_expand_vector_extract): For elt == 0
V16QImode extraction without sse4.1 try to use V4SImode lowpart
extraction.
2019-08-01 Martin Sebor <msebor@redhat.com>
PR c++/90947

11
gcc/config/i386/i386-expand.c
View file

@ -14706,6 +14706,17 @@ ix86_expand_vector_extract (bool mmx_ok, rtx target, rtx vec, int elt)
case E_V16QImode:
use_vec_extr = TARGET_SSE4_1;
if (!use_vec_extr
&& TARGET_SSE2
&& elt == 0
&& (optimize_insn_for_size_p () || TARGET_INTER_UNIT_MOVES_FROM_VEC))
{
tmp = gen_reg_rtx (SImode);
ix86_expand_vector_extract (false, tmp, gen_lowpart (V4SImode, vec),
0);
emit_insn (gen_rtx_SET (target, gen_lowpart (QImode, tmp)));
return;
}
break;
case E_V8SFmode:

8
gcc/testsuite/ChangeLog
View file

@ -1,3 +1,11 @@
2019-08-02 Jakub Jelinek <jakub@redhat.com>
PR tree-optimization/91201
* gcc.target/i386/sse2-pr91201-3.c: New test.
* gcc.target/i386/sse2-pr91201-4.c: New test.
* gcc.target/i386/sse2-pr91201-5.c: New test.
* gcc.target/i386/sse2-pr91201-6.c: New test.
2019-08-02 Martin Liska <mliska@suse.cz>
* g++.dg/cpp1y/new2.C: New test.

13
gcc/testsuite/gcc.target/i386/sse2-pr91201-3.c Normal file
View file

@ -0,0 +1,13 @@
/* PR tree-optimization/91201 */
/* { dg-do compile } */
/* { dg-options "-O2 -msse2 -mno-sse3 -mtune=generic -masm=att" } */
/* { dg-final { scan-assembler "\tmovd\t%xmm0, %eax" } } */
/* { dg-final { scan-assembler-not "\\(%" } } */
typedef unsigned char V __attribute__((vector_size (16)));
unsigned char
foo (V x)
{
return x[0];
}

13
gcc/testsuite/gcc.target/i386/sse2-pr91201-4.c Normal file
View file

@ -0,0 +1,13 @@
/* PR tree-optimization/91201 */
/* { dg-do compile } */
/* { dg-options "-Os -msse2 -mno-sse3 -mtune=generic -masm=att" } */
/* { dg-final { scan-assembler "\tmovd\t%xmm0, %eax" } } */
/* { dg-final { scan-assembler-not "\\(%" } } */
typedef unsigned char V __attribute__((vector_size (16)));
unsigned char
foo (V x)
{
return x[0];
}

13
gcc/testsuite/gcc.target/i386/sse2-pr91201-5.c Normal file
View file

@ -0,0 +1,13 @@
/* PR tree-optimization/91201 */
/* { dg-do compile } */
/* { dg-options "-O2 -msse2 -mno-sse3 -mtune=k8 -masm=att" } */
/* { dg-final { scan-assembler-not "\tmovd\t%xmm0, %eax" } } */
/* { dg-final { scan-assembler "\tmov(zbl|b)\t\[^\n\r]*\\(%" } } */
typedef unsigned char V __attribute__((vector_size (16)));
unsigned char
foo (V x)
{
return x[0];
}

13
gcc/testsuite/gcc.target/i386/sse2-pr91201-6.c Normal file
View file

@ -0,0 +1,13 @@
/* PR tree-optimization/91201 */
/* { dg-do compile } */
/* { dg-options "-Os -msse2 -mno-sse3 -mtune=k8 -masm=att" } */
/* { dg-final { scan-assembler "\tmovd\t%xmm0, %eax" } } */
/* { dg-final { scan-assembler-not "\\(%" } } */
typedef unsigned char V __attribute__((vector_size (16)));
unsigned char
foo (V x)
{
return x[0];
}