packages/gcc-12
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

!8 Backport some SPR patches to GCC-12

Browse Source 
From: @github-27907959 
Reviewed-by: @li-yancheng, @eastb233 
Signed-off-by: @eastb233
This commit is contained in:
openeuler-ci-bot 2022-11-16 02:28:02 +00:00 committed by Gitee
commit e586fcabde
No known key found for this signature in database
GPG Key ID: 173E9B9CA92EEF8F
4 changed files with 299 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

77
0002-i386-Add-syscall-to-enable-AMX-for-latest-kernels.patch Normal file
View File

@ -0,0 +1,77 @@
From 5e377d21f1f345d8b157b9bc306e02bb9bd45e01 Mon Sep 17 00:00:00 2001
From: Haochen Jiang <haochen.jiang@intel.com>
Date: Thu, 16 Jun 2022 00:15:53 -0700
Subject: [PATCH] i386: Add syscall to enable AMX for latest kernels
gcc/testsuite/ChangeLog:
* gcc.target/i386/amx-check.h (request_perm_xtile_data):
New function to check if AMX is usable and enable AMX.
(main): Run test if AMX is usable.
---
gcc/testsuite/gcc.target/i386/amx-check.h | 30 +++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/gcc/testsuite/gcc.target/i386/amx-check.h b/gcc/testsuite/gcc.target/i386/amx-check.h
index 434b0e59703..6fff5ff4631 100644
--- a/gcc/testsuite/gcc.target/i386/amx-check.h
+++ b/gcc/testsuite/gcc.target/i386/amx-check.h
@@ -4,11 +4,24 @@
#include <stdlib.h>
#include <string.h>
#include <stdint.h>
+#include <unistd.h>
+#ifdef __linux__
+#include <sys/syscall.h>
+#endif
#ifdef DEBUG
#include <stdio.h>
#endif
#include "cpuid.h"
+#define XFEATURE_XTILECFG 17
+#define XFEATURE_XTILEDATA 18
+#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG)
+#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA)
+#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
+
+#define ARCH_GET_XCOMP_PERM 0x1022
+#define ARCH_REQ_XCOMP_PERM 0x1023
+
/* TODO: The tmm emulation is temporary for current
AMX implementation with no tmm regclass, should
be changed in the future. */
@@ -44,6 +57,20 @@ typedef struct __tile
/* Stride (colum width in byte) used for tileload/store */
#define _STRIDE 64
+#ifdef __linux__
+/* We need syscall to use amx functions */
+int request_perm_xtile_data()
+{
+ unsigned long bitmask;
+
+ if (syscall (SYS_arch_prctl, ARCH_REQ_XCOMP_PERM, XFEATURE_XTILEDATA) ||
+ syscall (SYS_arch_prctl, ARCH_GET_XCOMP_PERM, &bitmask))
+ return 0;
+
+ return (bitmask & XFEATURE_MASK_XTILE) != 0;
+}
+#endif
+
/* Initialize tile config by setting all tmm size to 16x64 */
void init_tile_config (__tilecfg_u *dst)
{
@@ -185,6 +212,9 @@ main ()
#endif
#ifdef AMX_BF16
&& __builtin_cpu_supports ("amx-bf16")
+#endif
+#ifdef __linux__
+ && request_perm_xtile_data ()
#endif
)
{
--
2.18.2

83
0003-Remove-AVX512_VP2INTERSECT-from-PTA_SAPPHIRERAPIDS.patch Normal file
View File

@ -0,0 +1,83 @@
From 11c72f20d4d7ba1862a257cef05dc3a5e84a276d Mon Sep 17 00:00:00 2001
From: "Cui,Lili" <lili.cui@intel.com>
Date: Thu, 29 Sep 2022 14:28:06 +0800
Subject: [PATCH] Remove AVX512_VP2INTERSECT from PTA_SAPPHIRERAPIDS
gcc/ChangeLog:
* config/i386/driver-i386.cc (host_detect_local_cpu):
Move sapphirerapids out of AVX512_VP2INTERSECT.
* config/i386/i386.h: Remove AVX512_VP2INTERSECT from PTA_SAPPHIRERAPIDS
* doc/invoke.texi: Remove AVX512_VP2INTERSECT from SAPPHIRERAPIDS
---
gcc/config/i386/driver-i386.cc | 13 +++++--------
gcc/config/i386/i386.h | 7 +++----
gcc/doc/invoke.texi | 8 ++++----
3 files changed, 12 insertions(+), 16 deletions(-)
diff --git a/gcc/config/i386/driver-i386.cc b/gcc/config/i386/driver-i386.cc
index 3c702fdca33..ef567045c67 100644
--- a/gcc/config/i386/driver-i386.cc
+++ b/gcc/config/i386/driver-i386.cc
@@ -589,15 +589,12 @@ const char *host_detect_local_cpu (int argc, const char **argv)
/* This is unknown family 0x6 CPU. */
if (has_feature (FEATURE_AVX))
{
+ /* Assume Tiger Lake */
if (has_feature (FEATURE_AVX512VP2INTERSECT))
- {
- if (has_feature (FEATURE_TSXLDTRK))
- /* Assume Sapphire Rapids. */
- cpu = "sapphirerapids";
- else
- /* Assume Tiger Lake */
- cpu = "tigerlake";
- }
+ cpu = "tigerlake";
+ /* Assume Sapphire Rapids. */
+ else if (has_feature (FEATURE_TSXLDTRK))
+ cpu = "sapphirerapids";
/* Assume Cooper Lake */
else if (has_feature (FEATURE_AVX512BF16))
cpu = "cooperlake";
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 900a3bc3673..372a2cff8fe 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -2326,10 +2326,9 @@ constexpr wide_int_bitmask PTA_ICELAKE_SERVER = PTA_ICELAKE_CLIENT
constexpr wide_int_bitmask PTA_TIGERLAKE = PTA_ICELAKE_CLIENT | PTA_MOVDIRI
| PTA_MOVDIR64B | PTA_CLWB | PTA_AVX512VP2INTERSECT | PTA_KL | PTA_WIDEKL;
constexpr wide_int_bitmask PTA_SAPPHIRERAPIDS = PTA_ICELAKE_SERVER | PTA_MOVDIRI
- | PTA_MOVDIR64B | PTA_AVX512VP2INTERSECT | PTA_ENQCMD | PTA_CLDEMOTE
- | PTA_PTWRITE | PTA_WAITPKG | PTA_SERIALIZE | PTA_TSXLDTRK | PTA_AMX_TILE
- | PTA_AMX_INT8 | PTA_AMX_BF16 | PTA_UINTR | PTA_AVXVNNI | PTA_AVX512FP16
- | PTA_AVX512BF16;
+ | PTA_MOVDIR64B | PTA_ENQCMD | PTA_CLDEMOTE | PTA_PTWRITE | PTA_WAITPKG
+ | PTA_SERIALIZE | PTA_TSXLDTRK | PTA_AMX_TILE | PTA_AMX_INT8 | PTA_AMX_BF16
+ | PTA_UINTR | PTA_AVXVNNI | PTA_AVX512FP16 | PTA_AVX512BF16;
constexpr wide_int_bitmask PTA_KNL = PTA_BROADWELL | PTA_AVX512PF
| PTA_AVX512ER | PTA_AVX512F | PTA_AVX512CD | PTA_PREFETCHWT1;
constexpr wide_int_bitmask PTA_BONNELL = PTA_CORE2 | PTA_MOVBE;
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 271c8bb8468..a9ecc4426a4 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -32057,11 +32057,11 @@ Intel sapphirerapids CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3,
SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE,
RDRND, F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW,
AES, CLFLUSHOPT, XSAVEC, XSAVES, SGX, AVX512F, AVX512VL, AVX512BW, AVX512DQ,
-AVX512CD, PKU, AVX512VBMI, AVX512IFMA, SHA, AVX512VNNI, GFNI, VAES, AVX512VBMI2
+AVX512CD, PKU, AVX512VBMI, AVX512IFMA, SHA, AVX512VNNI, GFNI, VAES, AVX512VBMI2,
VPCLMULQDQ, AVX512BITALG, RDPID, AVX512VPOPCNTDQ, PCONFIG, WBNOINVD, CLWB,
-MOVDIRI, MOVDIR64B, AVX512VP2INTERSECT, ENQCMD, CLDEMOTE, PTWRITE, WAITPKG,
-SERIALIZE, TSXLDTRK, UINTR, AMX-BF16, AMX-TILE, AMX-INT8, AVX-VNNI, AVX512FP16
-and AVX512BF16 instruction set support.
+MOVDIRI, MOVDIR64B, ENQCMD, CLDEMOTE, PTWRITE, WAITPKG, SERIALIZE, TSXLDTRK,
+UINTR, AMX-BF16, AMX-TILE, AMX-INT8, AVX-VNNI, AVX512FP16 and AVX512BF16
+instruction set support.
@item alderlake
Intel Alderlake CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3,
--
2.18.2

123
0004-Add-attribute-hot-judgement-for-INLINE_HINT_known_ho.patch Normal file
View File

@ -0,0 +1,123 @@
From 1b9a5cc9ec08e9f239dd2096edcc447b7a72f64a Mon Sep 17 00:00:00 2001
From: "Cui,Lili" <lili.cui@intel.com>
Date: Tue, 1 Nov 2022 09:16:49 +0800
Subject: [PATCH] Add attribute hot judgement for INLINE_HINT_known_hot hint.
We set up INLINE_HINT_known_hot hint only when we have profile feedback,
now add function attribute judgement for it, when both caller and callee
have __attribute__((hot)), we will also set up INLINE_HINT_known_hot hint
for it.
With this patch applied,
ADL Multi-copy: 538.imagic_r 16.7%
ICX Multi-copy: 538.imagic_r 15.2%
CLX Multi-copy: 538.imagic_r 12.7%
Znver3 Multi-copy: 538.imagic_r 10.6%
Arm Multi-copy: 538.imagic_r 13.4%
gcc/ChangeLog
* ipa-inline-analysis.cc (do_estimate_edge_time): Add function attribute
judgement for INLINE_HINT_known_hot hint.
gcc/testsuite/ChangeLog:
* gcc.dg/ipa/inlinehint-6.c: New test.
---
gcc/ipa-inline-analysis.cc | 13 ++++---
gcc/testsuite/gcc.dg/ipa/inlinehint-6.c | 47 +++++++++++++++++++++++++
2 files changed, 56 insertions(+), 4 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/ipa/inlinehint-6.c
diff --git a/gcc/ipa-inline-analysis.cc b/gcc/ipa-inline-analysis.cc
index 1ca685d1b0e..7bd29c36590 100644
--- a/gcc/ipa-inline-analysis.cc
+++ b/gcc/ipa-inline-analysis.cc
@@ -48,6 +48,7 @@ along with GCC; see the file COPYING3. If not see
#include "ipa-utils.h"
#include "cfgexpand.h"
#include "gimplify.h"
+#include "attribs.h"
/* Cached node/edge growths. */
fast_call_summary<edge_growth_cache_entry *, va_heap> *edge_growth_cache = NULL;
@@ -249,15 +250,19 @@ do_estimate_edge_time (struct cgraph_edge *edge, sreal *ret_nonspec_time)
hints = estimates.hints;
}
- /* When we have profile feedback, we can quite safely identify hot
- edges and for those we disable size limits. Don't do that when
- probability that caller will call the callee is low however, since it
+ /* When we have profile feedback or function attribute, we can quite safely
+ identify hot edges and for those we disable size limits. Don't do that
+ when probability that caller will call the callee is low however, since it
may hurt optimization of the caller's hot path. */
- if (edge->count.ipa ().initialized_p () && edge->maybe_hot_p ()
+ if ((edge->count.ipa ().initialized_p () && edge->maybe_hot_p ()
&& (edge->count.ipa ().apply_scale (2, 1)
> (edge->caller->inlined_to
? edge->caller->inlined_to->count.ipa ()
: edge->caller->count.ipa ())))
+ || (lookup_attribute ("hot", DECL_ATTRIBUTES (edge->caller->decl))
+ != NULL
+ && lookup_attribute ("hot", DECL_ATTRIBUTES (edge->callee->decl))
+ != NULL))
hints |= INLINE_HINT_known_hot;
gcc_checking_assert (size >= 0);
diff --git a/gcc/testsuite/gcc.dg/ipa/inlinehint-6.c b/gcc/testsuite/gcc.dg/ipa/inlinehint-6.c
new file mode 100644
index 00000000000..1f3be641c6d
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/ipa/inlinehint-6.c
@@ -0,0 +1,47 @@
+/* { dg-options "-O3 -c -fdump-ipa-inline-details -fno-early-inlining -fno-ipa-cp" } */
+/* { dg-add-options bind_pic_locally } */
+
+#define size_t long long int
+
+struct A
+{
+ size_t f1, f2, f3, f4;
+};
+struct C
+{
+ struct A a;
+ size_t b;
+};
+struct C x;
+
+__attribute__((hot)) struct C callee (struct A *a, struct C *c)
+{
+ c->a=(*a);
+
+ if((c->b + 7) & 17)
+ {
+ c->a.f1 = c->a.f2 + c->a.f1;
+ c->a.f2 = c->a.f3 - c->a.f2;
+ c->a.f3 = c->a.f2 + c->a.f3;
+ c->a.f4 = c->a.f2 - c->a.f4;
+ c->b = c->a.f2;
+
+ }
+ return *c;
+}
+
+__attribute__((hot)) struct C caller (size_t d, size_t e, size_t f, size_t g, struct C *c)
+{
+ struct A a;
+ a.f1 = 1 + d;
+ a.f2 = e;
+ a.f3 = 12 + f;
+ a.f4 = 68 + g;
+ if (c->b > 0)
+ return callee (&a, c);
+ else
+ return *c;
+}
+
+/* { dg-final { scan-ipa-dump "known_hot" "inline" } } */
+
--
2.18.2

17
gcc-12.spec
View File

@ -84,7 +84,7 @@
Summary: Various compilers (C, C++, Objective-C, ...)
Name: %{?scl_prefix}gcc
Version: 12.2.1
Release: 5
Release: 8
# libgcc, libgfortran, libgomp, libstdc++ and crtstuff have
# GCC Runtime Exception.
License: GPLv3+ and GPLv3+ with exceptions and GPLv2+ with exceptions and LGPLv2+ and BSD
@ -133,6 +133,9 @@ Provides: %{?scl_prefix}gcc(major) = %{gcc_major}
Patch0: 0001-change-gcc-version.patch
Patch1: 0002-i386-Add-syscall-to-enable-AMX-for-latest-kernels.patch
Patch2: 0003-Remove-AVX512_VP2INTERSECT-from-PTA_SAPPHIRERAPIDS.patch
Patch3: 0004-Add-attribute-hot-judgement-for-INLINE_HINT_known_ho.patch
# On ARM EABI systems, we do want -gnueabi to be part of the
@ -591,6 +594,9 @@ not stable, so plugins must be rebuilt any time GCC is updated.
%setup -q -n gcc-12.2.0
%patch0 -p1
%patch1 -p1
%patch2 -p1
%patch3 -p1
echo 'openEuler %{version}-%{release}' > gcc/DEV-PHASE
@ -2647,6 +2653,15 @@ end
%doc rpm.doc/changelogs/libcc1/ChangeLog*
%changelog
* Wed Nov 09 2022 Cui Lili <lili.cui@intel.com> 12.2.1-8
- Add attribute hot judgement for INLINE_HINT_known_hot hint
* Wed Nov 09 2022 Cui Lili <lili.cui@intel.com> 12.2.1-7
- Remove AVX512_VP2INTERSECT from PTA_SAPPHIRERAPIDS
* Wed Nov 09 2022 Haochen Jiang <haochen.jiang@intel.com> 12.2.1-6
- i386: Add syscall to enable AMX for latest kernels
* Wed Nov 02 2022 liyancheng <412998149@qq.com> 12.2.1-5
- Change isl dependency from Source to BuildRequire