From: H.J. Lu Date: Fri, 16 Jul 2021 17:29:46 +0000 (-0700) Subject: x86: Use XMM31 for scratch SSE register X-Git-Tag: basepoints/gcc-13~5616 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=98d7f305d5081bc91c16b9d2b4d62196b86bca86;p=thirdparty%2Fgcc.git 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. --- diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c index 842eb0e6786b..ec0690876b71 100644 --- a/gcc/config/i386/i386.c +++ b/gcc/config/i386/i386.c @@ -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); } diff --git a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-14.c b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-14.c index a31b4a2a63aa..9590f25da225 100644 --- a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-14.c +++ b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-14.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-O2 -mavx -mtune=generic -dp" } */ +/* { dg-options "-O2 -mavx -mno-avx512f -mtune=generic -dp" } */ #include diff --git a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-15.c b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-15.c index 803936eef01e..36dcf7367f1d 100644 --- a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-15.c +++ b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-15.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-O2 -mavx -mtune=generic -dp" } */ +/* { dg-options "-O2 -mavx -mno-avx512f -mtune=generic -dp" } */ #include diff --git a/gcc/testsuite/gcc.target/i386/pr100865-10b.c b/gcc/testsuite/gcc.target/i386/pr100865-10b.c index e5616d8d2587..77ace86ffe85 100644 --- a/gcc/testsuite/gcc.target/i386/pr100865-10b.c +++ b/gcc/testsuite/gcc.target/i386/pr100865-10b.c @@ -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" } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr100865-11b.c b/gcc/testsuite/gcc.target/i386/pr100865-11b.c index 12d55b9a6424..7e458e85cdd4 100644 --- a/gcc/testsuite/gcc.target/i386/pr100865-11b.c +++ b/gcc/testsuite/gcc.target/i386/pr100865-11b.c @@ -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 } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr100865-12b.c b/gcc/testsuite/gcc.target/i386/pr100865-12b.c index 63a5629b90c1..dee0cfb016a1 100644 --- a/gcc/testsuite/gcc.target/i386/pr100865-12b.c +++ b/gcc/testsuite/gcc.target/i386/pr100865-12b.c @@ -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 } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr100865-4b.c b/gcc/testsuite/gcc.target/i386/pr100865-4b.c index 8e8a7eaaaff3..80e9fdb12ea9 100644 --- a/gcc/testsuite/gcc.target/i386/pr100865-4b.c +++ b/gcc/testsuite/gcc.target/i386/pr100865-4b.c @@ -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" } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr100865-6b.c b/gcc/testsuite/gcc.target/i386/pr100865-6b.c index 44e74c64e559..35f2e961d259 100644 --- a/gcc/testsuite/gcc.target/i386/pr100865-6b.c +++ b/gcc/testsuite/gcc.target/i386/pr100865-6b.c @@ -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" } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr100865-7b.c b/gcc/testsuite/gcc.target/i386/pr100865-7b.c index 0a68820aa327..ad267c43891e 100644 --- a/gcc/testsuite/gcc.target/i386/pr100865-7b.c +++ b/gcc/testsuite/gcc.target/i386/pr100865-7b.c @@ -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" } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr100865-8b.c b/gcc/testsuite/gcc.target/i386/pr100865-8b.c index 99a10ad83bd0..4b7dd7cee3e3 100644 --- a/gcc/testsuite/gcc.target/i386/pr100865-8b.c +++ b/gcc/testsuite/gcc.target/i386/pr100865-8b.c @@ -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 } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr100865-9b.c b/gcc/testsuite/gcc.target/i386/pr100865-9b.c index 146962485258..a315dde7c520 100644 --- a/gcc/testsuite/gcc.target/i386/pr100865-9b.c +++ b/gcc/testsuite/gcc.target/i386/pr100865-9b.c @@ -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 } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr82941-1.c b/gcc/testsuite/gcc.target/i386/pr82941-1.c index d7e530d51161..c3be2f5b7977 100644 --- a/gcc/testsuite/gcc.target/i386/pr82941-1.c +++ b/gcc/testsuite/gcc.target/i386/pr82941-1.c @@ -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 } } } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr82942-1.c b/gcc/testsuite/gcc.target/i386/pr82942-1.c index 9cdf81a9d603..29ead049a67f 100644 --- a/gcc/testsuite/gcc.target/i386/pr82942-1.c +++ b/gcc/testsuite/gcc.target/i386/pr82942-1.c @@ -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 } } } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr82990-1.c b/gcc/testsuite/gcc.target/i386/pr82990-1.c index ff1d6d40eb26..bbf580fea77a 100644 --- a/gcc/testsuite/gcc.target/i386/pr82990-1.c +++ b/gcc/testsuite/gcc.target/i386/pr82990-1.c @@ -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 } } } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr82990-3.c b/gcc/testsuite/gcc.target/i386/pr82990-3.c index 201fa98d8d41..89ddb20adb32 100644 --- a/gcc/testsuite/gcc.target/i386/pr82990-3.c +++ b/gcc/testsuite/gcc.target/i386/pr82990-3.c @@ -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 } } } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr82990-5.c b/gcc/testsuite/gcc.target/i386/pr82990-5.c index 9932bdc53756..b9da0e706b1c 100644 --- a/gcc/testsuite/gcc.target/i386/pr82990-5.c +++ b/gcc/testsuite/gcc.target/i386/pr82990-5.c @@ -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 } } } } */