x86: Use XMM31 for scratch SSE register

In 64-bit mode, use XMM31 for scratch SSE register to avoid vzeroupper
if possible.

gcc/

	* config/i386/i386.c (ix86_gen_scratch_sse_rtx): In 64-bit mode,
	try XMM31 to avoid vzeroupper.

gcc/testsuite/

	* gcc.target/i386/avx-vzeroupper-14.c: Pass -mno-avx512f to
	disable XMM31.
	* gcc.target/i386/avx-vzeroupper-15.c: Likewise.
	* gcc.target/i386/pr82941-1.c: Updated.  Check for vzeroupper.
	* gcc.target/i386/pr82942-1.c: Likewise.
	* gcc.target/i386/pr82990-1.c: Likewise.
	* gcc.target/i386/pr82990-3.c: Likewise.
	* gcc.target/i386/pr82990-5.c: Likewise.
	* gcc.target/i386/pr100865-4b.c: Likewise.
	* gcc.target/i386/pr100865-6b.c: Likewise.
	* gcc.target/i386/pr100865-7b.c: Likewise.
	* gcc.target/i386/pr100865-10b.c: Likewise.
	* gcc.target/i386/pr100865-8b.c: Updated.
	* gcc.target/i386/pr100865-9b.c: Likewise.
	* gcc.target/i386/pr100865-11b.c: Likewise.
	* gcc.target/i386/pr100865-12b.c: Likewise.
This commit is contained in:
H.J. Lu 2021-07-16 10:29:46 -07:00
parent a1a2654cdc
commit 98d7f305d5
16 changed files with 42 additions and 16 deletions

View file

@ -23335,9 +23335,21 @@ rtx
ix86_gen_scratch_sse_rtx (machine_mode mode)
{
if (TARGET_SSE && !lra_in_progress)
return gen_rtx_REG (mode, (TARGET_64BIT
? LAST_REX_SSE_REG
: LAST_SSE_REG));
{
unsigned int regno;
if (TARGET_64BIT)
{
/* In 64-bit mode, use XMM31 to avoid vzeroupper and always
use XMM31 for CSE. */
if (ix86_hard_regno_mode_ok (LAST_EXT_REX_SSE_REG, mode))
regno = LAST_EXT_REX_SSE_REG;
else
regno = LAST_REX_SSE_REG;
}
else
regno = LAST_SSE_REG;
return gen_rtx_REG (mode, regno);
}
else
return gen_reg_rtx (mode);
}

View file

@ -1,5 +1,5 @@
/* { dg-do compile } */
/* { dg-options "-O2 -mavx -mtune=generic -dp" } */
/* { dg-options "-O2 -mavx -mno-avx512f -mtune=generic -dp" } */
#include <immintrin.h>

View file

@ -1,5 +1,5 @@
/* { dg-do compile } */
/* { dg-options "-O2 -mavx -mtune=generic -dp" } */
/* { dg-options "-O2 -mavx -mno-avx512f -mtune=generic -dp" } */
#include <immintrin.h>

View file

@ -5,3 +5,4 @@
/* { dg-final { scan-assembler-times "vpbroadcastb\[\\t \]+%(?:r|e)\[^\n\]*, %ymm\[0-9\]+" 1 } } */
/* { dg-final { scan-assembler-times "vmovdqu8\[\\t \]%ymm\[0-9\]+, " 8 } } */
/* { dg-final { scan-assembler-not "vzeroupper" } } */

View file

@ -5,4 +5,4 @@
/* { dg-final { scan-assembler-times "movabsq" 1 } } */
/* { dg-final { scan-assembler-times "vpbroadcastq\[\\t \]+%(?:r|e)\[^\n\]*, %xmm\[0-9\]+" 1 } } */
/* { dg-final { scan-assembler-times "vmovdqa\[\\t \]%xmm\[0-9\]+, " 16 } } */
/* { dg-final { scan-assembler-times "vmovdqa64\[\\t \]%xmm\[0-9\]+, " 16 } } */

View file

@ -5,4 +5,4 @@
/* { dg-final { scan-assembler-times "movabsq" 1 } } */
/* { dg-final { scan-assembler-times "vpbroadcastq\[\\t \]+%(?:r|e)\[^\n\]*, %xmm\[0-9\]+" 1 } } */
/* { dg-final { scan-assembler-times "vmovdqa\[\\t \]%xmm\[0-9\]+, " 16 } } */
/* { dg-final { scan-assembler-times "vmovdqa64\[\\t \]%xmm\[0-9\]+, " 16 } } */

View file

@ -5,5 +5,7 @@
/* { dg-final { scan-assembler-times "vpbroadcastb\[\\t \]+%(?:r|e)\[^\n\]*, %ymm\[0-9\]+" 1 } } */
/* { dg-final { scan-assembler-times "vmovdqu8\[\\t \]%ymm\[0-9\]+, " 2 } } */
/* { dg-final { scan-assembler-times "vzeroupper" 1 { target ia32 } } } */
/* { dg-final { scan-assembler-not "vzeroupper" { target { ! ia32 } } } } */
/* { dg-final { scan-assembler-not "vpbroadcastb\[\\t \]+%xmm\[0-9\]+, %ymm\[0-9\]+" } } */
/* { dg-final { scan-assembler-not "vmovdqa" } } */

View file

@ -4,6 +4,9 @@
#include "pr100865-6a.c"
/* { dg-final { scan-assembler-times "vpbroadcastd\[\\t \]+%(?:r|e)\[^\n\]*, %ymm\[0-9\]+" 1 } } */
/* { dg-final { scan-assembler-times "vmovdqu\[\\t \]%ymm\[0-9\]+, " 8 } } */
/* { dg-final { scan-assembler-times "vmovdqu\[\\t \]%ymm\[0-9\]+, " 8 { target ia32 } } } */
/* { dg-final { scan-assembler-times "vmovdqu32\[\\t \]%ymm\[0-9\]+, " 8 { target { ! ia32 } } } } */
/* { dg-final { scan-assembler-times "vzeroupper" 1 { target ia32 } } } */
/* { dg-final { scan-assembler-not "vzeroupper" { target { ! ia32 } } } } */
/* { dg-final { scan-assembler-not "vpbroadcastd\[\\t \]+%xmm\[0-9\]+, %ymm\[0-9\]+" } } */
/* { dg-final { scan-assembler-not "vmovdqa" } } */

View file

@ -5,5 +5,8 @@
/* { dg-final { scan-assembler-times "vpbroadcastq\[\\t \]+%r\[^\n\]*, %ymm\[0-9\]+" 1 { target { ! ia32 } } } } */
/* { dg-final { scan-assembler-times "vpbroadcastq\[\\t \]+\[^\n\]*, %ymm\[0-9\]+" 1 { target ia32 } } } */
/* { dg-final { scan-assembler-times "vmovdqu\[\\t \]%ymm\[0-9\]+, " 16 } } */
/* { dg-final { scan-assembler-times "vmovdqu\[\\t \]%ymm\[0-9\]+, " 16 { target ia32 } } } */
/* { dg-final { scan-assembler-times "vmovdqu64\[\\t \]%ymm\[0-9\]+, " 16 { target { ! ia32 } } } } */
/* { dg-final { scan-assembler-times "vzeroupper" 1 { target ia32 } } } */
/* { dg-final { scan-assembler-not "vzeroupper" { target { ! ia32 } } } } */
/* { dg-final { scan-assembler-not "vmovdqa" } } */

View file

@ -4,4 +4,4 @@
#include "pr100865-8a.c"
/* { dg-final { scan-assembler-times "vpbroadcastd\[\\t \]+%(?:r|e)\[^\n\]*, %xmm\[0-9\]+" 1 } } */
/* { dg-final { scan-assembler-times "vmovdqa\[\\t \]%xmm\[0-9\]+, " 16 } } */
/* { dg-final { scan-assembler-times "vmovdqa64\[\\t \]%xmm\[0-9\]+, " 16 } } */

View file

@ -4,4 +4,4 @@
#include "pr100865-9a.c"
/* { dg-final { scan-assembler-times "vpbroadcastw\[\\t \]+%(?:r|e)\[^\n\]*, %xmm\[0-9\]+" 1 } } */
/* { dg-final { scan-assembler-times "vmovdqa\[\\t \]%xmm\[0-9\]+, " 16 } } */
/* { dg-final { scan-assembler-times "vmovdqa64\[\\t \]%xmm\[0-9\]+, " 16 } } */

View file

@ -11,4 +11,5 @@ pr82941 ()
z = y;
}
/* { dg-final { scan-assembler-times "vzeroupper" 1 } } */
/* { dg-final { scan-assembler-times "vzeroupper" 1 { target ia32 } } } */
/* { dg-final { scan-assembler-not "vzeroupper" { target { ! ia32 } } } } */

View file

@ -3,4 +3,5 @@
#include "pr82941-1.c"
/* { dg-final { scan-assembler-times "vzeroupper" 1 } } */
/* { dg-final { scan-assembler-times "vzeroupper" 1 { target ia32 } } } */
/* { dg-final { scan-assembler-not "vzeroupper" { target { ! ia32 } } } } */

View file

@ -11,4 +11,5 @@ pr82941 ()
z = y;
}
/* { dg-final { scan-assembler-times "vzeroupper" 1 } } */
/* { dg-final { scan-assembler-times "vzeroupper" 1 { target ia32 } } } */
/* { dg-final { scan-assembler-not "vzeroupper" { target { ! ia32 } } } } */

View file

@ -3,4 +3,5 @@
#include "pr82941-1.c"
/* { dg-final { scan-assembler-times "vzeroupper" 1 } } */
/* { dg-final { scan-assembler-times "vzeroupper" 1 { target ia32 } } } */
/* { dg-final { scan-assembler-not "vzeroupper" { target { ! ia32 } } } } */

View file

@ -11,4 +11,5 @@ pr82941 ()
z = y;
}
/* { dg-final { scan-assembler-times "vzeroupper" 1 } } */
/* { dg-final { scan-assembler-times "vzeroupper" 1 { target ia32 } } } */
/* { dg-final { scan-assembler-not "vzeroupper" { target { ! ia32 } } } } */