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

[Sync] Sync patch from openeuler/gcc

Browse Source
This commit is contained in:
wangding16 2024-04-24 12:45:54 +08:00
parent 2707dd6474
commit 4c67342df6
4 changed files with 929 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

142
0072-Disable-FMADD-in-chains-for-Zen4-and-generic.patch Normal file
View File

@ -0,0 +1,142 @@
From 19ee37b11702c86d7ed271e9e1d00e23cc4ab93c Mon Sep 17 00:00:00 2001
From: Jan Hubicka <jh@suse.cz>
Date: Fri, 29 Dec 2023 23:51:03 +0100
Subject: [PATCH 17/32] Disable FMADD in chains for Zen4 and generic
this patch disables use of FMA in matrix multiplication loop for generic (for
x86-64-v3) and zen4. I tested this on zen4 and Xenon Gold Gold 6212U.
For Intel this is neutral both on the matrix multiplication microbenchmark
(attached) and spec2k17 where the difference was within noise for Core.
On core the micro-benchmark runs as follows:
With FMA:
578,500,241 cycles:u # 3.645 GHz
( +- 0.12% )
753,318,477 instructions:u # 1.30 insn per
cycle ( +- 0.00% )
125,417,701 branches:u # 790.227 M/sec
( +- 0.00% )
0.159146 +- 0.000363 seconds time elapsed ( +- 0.23% )
No FMA:
577,573,960 cycles:u # 3.514 GHz
( +- 0.15% )
878,318,479 instructions:u # 1.52 insn per
cycle ( +- 0.00% )
125,417,702 branches:u # 763.035 M/sec
( +- 0.00% )
0.164734 +- 0.000321 seconds time elapsed ( +- 0.19% )
So the cycle count is unchanged and discrete multiply+add takes same time as
FMA.
While on zen:
With FMA:
484875179 cycles:u # 3.599 GHz
( +- 0.05% ) (82.11%)
752031517 instructions:u # 1.55 insn per
cycle
125106525 branches:u # 928.712 M/sec
( +- 0.03% ) (85.09%)
128356 branch-misses:u # 0.10% of all
branches ( +- 0.06% ) (83.58%)
No FMA:
375875209 cycles:u # 3.592 GHz
( +- 0.08% ) (80.74%)
875725341 instructions:u # 2.33 insn per
cycle
124903825 branches:u # 1.194 G/sec
( +- 0.04% ) (84.59%)
0.105203 +- 0.000188 seconds time elapsed ( +- 0.18% )
The diffrerence is that Cores understand the fact that fmadd does not need
all three parameters to start computation, while Zen cores doesn't.
Since this seems noticeable win on zen and not loss on Core it seems like good
default for generic.
float a[SIZE][SIZE];
float b[SIZE][SIZE];
float c[SIZE][SIZE];
void init(void)
{
int i, j, k;
for(i=0; i<SIZE; ++i)
{
for(j=0; j<SIZE; ++j)
{
a[i][j] = (float)i + j;
b[i][j] = (float)i - j;
c[i][j] = 0.0f;
}
}
}
void mult(void)
{
int i, j, k;
for(i=0; i<SIZE; ++i)
{
for(j=0; j<SIZE; ++j)
{
for(k=0; k<SIZE; ++k)
{
c[i][j] += a[i][k] * b[k][j];
}
}
}
}
int main(void)
{
clock_t s, e;
init();
s=clock();
mult();
e=clock();
printf(" mult took %10d clocks\n", (int)(e-s));
return 0;
}
gcc/ChangeLog:
* config/i386/x86-tune.def (X86_TUNE_AVOID_128FMA_CHAINS,
X86_TUNE_AVOID_256FMA_CHAINS): Enable for znver4 and Core.
---
gcc/config/i386/x86-tune.def | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index bdb455d20..fd095f3ec 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -499,12 +499,13 @@ DEF_TUNE (X86_TUNE_USE_SCATTER_8PARTS, "use_scatter_8parts",
/* X86_TUNE_AVOID_128FMA_CHAINS: Avoid creating loops with tight 128bit or
smaller FMA chain. */
-DEF_TUNE (X86_TUNE_AVOID_128FMA_CHAINS, "avoid_fma_chains", m_ZNVER1 | m_ZNVER2 | m_ZNVER3)
+DEF_TUNE (X86_TUNE_AVOID_128FMA_CHAINS, "avoid_fma_chains", m_ZNVER1 | m_ZNVER2
+ | m_ZNVER3 | m_ZNVER4 | m_GENERIC)
/* X86_TUNE_AVOID_256FMA_CHAINS: Avoid creating loops with tight 256bit or
smaller FMA chain. */
DEF_TUNE (X86_TUNE_AVOID_256FMA_CHAINS, "avoid_fma256_chains", m_ZNVER2 | m_ZNVER3
- | m_ALDERLAKE | m_SAPPHIRERAPIDS)
+ | m_ZNVER4 | m_ALDERLAKE | m_SAPPHIRERAPIDS | m_GENERIC)
/* X86_TUNE_AVOID_512FMA_CHAINS: Avoid creating loops with tight 512bit or
smaller FMA chain. */
--
2.28.0.windows.1

47
0073-Initial-Raptorlake-Support.patch Normal file
View File

@ -0,0 +1,47 @@
From 411d1f0bcc0d1c8018fdf5fe84ad2404929556ec Mon Sep 17 00:00:00 2001
From: Haochen Jiang <haochen.jiang@intel.com>
Date: Fri, 16 Sep 2022 13:59:01 +0800
Subject: [PATCH 18/32] Initial Raptorlake Support
gcc/ChangeLog:
* common/config/i386/cpuinfo.h:
(get_intel_cpu): Handle Raptorlake.
* common/config/i386/i386-common.cc:
(processor_alias_table): Add Raptorlake.
(cherry picked from commit 470a0659b508d684148f362c4dc0eccf5a83a23e)
---
gcc/common/config/i386/cpuinfo.h | 2 ++
gcc/common/config/i386/i386-common.cc | 2 ++
2 files changed, 4 insertions(+)
diff --git a/gcc/common/config/i386/cpuinfo.h b/gcc/common/config/i386/cpuinfo.h
index 316ad3cb3..13d0f4cd8 100644
--- a/gcc/common/config/i386/cpuinfo.h
+++ b/gcc/common/config/i386/cpuinfo.h
@@ -508,6 +508,8 @@ get_intel_cpu (struct __processor_model *cpu_model,
case 0x97:
case 0x9a:
/* Alder Lake. */
+ case 0xb7:
+ /* Raptor Lake. */
cpu = "alderlake";
CHECK___builtin_cpu_is ("corei7");
CHECK___builtin_cpu_is ("alderlake");
diff --git a/gcc/common/config/i386/i386-common.cc b/gcc/common/config/i386/i386-common.cc
index f650e255f..c1d700f89 100644
--- a/gcc/common/config/i386/i386-common.cc
+++ b/gcc/common/config/i386/i386-common.cc
@@ -1939,6 +1939,8 @@ const pta processor_alias_table[] =
M_CPU_SUBTYPE (INTEL_COREI7_SAPPHIRERAPIDS), P_PROC_AVX512F},
{"alderlake", PROCESSOR_ALDERLAKE, CPU_HASWELL, PTA_ALDERLAKE,
M_CPU_SUBTYPE (INTEL_COREI7_ALDERLAKE), P_PROC_AVX2},
+ {"raptorlake", PROCESSOR_ALDERLAKE, CPU_HASWELL, PTA_ALDERLAKE,
+ M_CPU_SUBTYPE (INTEL_COREI7_ALDERLAKE), P_PROC_AVX2},
{"bonnell", PROCESSOR_BONNELL, CPU_ATOM, PTA_BONNELL,
M_CPU_TYPE (INTEL_BONNELL), P_PROC_SSSE3},
{"atom", PROCESSOR_BONNELL, CPU_ATOM, PTA_BONNELL,
--
2.28.0.windows.1

49
0074-Initial-Meteorlake-Support.patch Normal file
View File

@ -0,0 +1,49 @@
From 87cea29ede520f4a5af01dff7071ab1d23bd47b5 Mon Sep 17 00:00:00 2001
From: "Hu, Lin1" <lin1.hu@intel.com>
Date: Fri, 16 Sep 2022 11:25:13 +0800
Subject: [PATCH 19/32] Initial Meteorlake Support
gcc/ChangeLog:
* common/config/i386/cpuinfo.h:
(get_intel_cpu): Handle Meteorlake.
* common/config/i386/i386-common.cc:
(processor_alias_table): Add Meteorlake.
(cherry picked from commit fd206f0e95fb6f41b96eaaaab1dc0c30378e5e08)
---
gcc/common/config/i386/cpuinfo.h | 4 ++++
gcc/common/config/i386/i386-common.cc | 2 ++
2 files changed, 6 insertions(+)
diff --git a/gcc/common/config/i386/cpuinfo.h b/gcc/common/config/i386/cpuinfo.h
index 13d0f4cd8..37af92d6b 100644
--- a/gcc/common/config/i386/cpuinfo.h
+++ b/gcc/common/config/i386/cpuinfo.h
@@ -510,6 +510,10 @@ get_intel_cpu (struct __processor_model *cpu_model,
/* Alder Lake. */
case 0xb7:
/* Raptor Lake. */
+ case 0xb5:
+ case 0xaa:
+ case 0xac:
+ /* Meteor Lake. */
cpu = "alderlake";
CHECK___builtin_cpu_is ("corei7");
CHECK___builtin_cpu_is ("alderlake");
diff --git a/gcc/common/config/i386/i386-common.cc b/gcc/common/config/i386/i386-common.cc
index c1d700f89..cfee672fb 100644
--- a/gcc/common/config/i386/i386-common.cc
+++ b/gcc/common/config/i386/i386-common.cc
@@ -1941,6 +1941,8 @@ const pta processor_alias_table[] =
M_CPU_SUBTYPE (INTEL_COREI7_ALDERLAKE), P_PROC_AVX2},
{"raptorlake", PROCESSOR_ALDERLAKE, CPU_HASWELL, PTA_ALDERLAKE,
M_CPU_SUBTYPE (INTEL_COREI7_ALDERLAKE), P_PROC_AVX2},
+ {"meteorlake", PROCESSOR_ALDERLAKE, CPU_HASWELL, PTA_ALDERLAKE,
+ M_CPU_SUBTYPE (INTEL_COREI7_ALDERLAKE), P_PROC_AVX2},
{"bonnell", PROCESSOR_BONNELL, CPU_ATOM, PTA_BONNELL,
M_CPU_TYPE (INTEL_BONNELL), P_PROC_SSSE3},
{"atom", PROCESSOR_BONNELL, CPU_ATOM, PTA_BONNELL,
--
2.28.0.windows.1

691
0075-Support-Intel-AMX-FP16-ISA.patch Normal file
View File

@ -0,0 +1,691 @@
From c11301c7780213ddf46a0bcdb06079af485f431c Mon Sep 17 00:00:00 2001
From: Hongyu Wang <hongyu.wang@intel.com>
Date: Fri, 4 Nov 2022 15:50:55 +0800
Subject: [PATCH 20/32] Support Intel AMX-FP16 ISA
gcc/ChangeLog:
* common/config/i386/cpuinfo.h (get_available_features): Detect
amx-fp16.
* common/config/i386/i386-common.cc (OPTION_MASK_ISA2_AMX_FP16_SET,
OPTION_MASK_ISA2_AMX_FP16_UNSET): New macros.
(ix86_handle_option): Handle -mamx-fp16.
* common/config/i386/i386-cpuinfo.h (enum processor_features):
Add FEATURE_AMX_FP16.
* common/config/i386/i386-isas.h: Add ISA_NAME_TABLE_ENTRY for
amx-fp16.
* config.gcc: Add amxfp16intrin.h.
* config/i386/cpuid.h (bit_AMX_FP16): New.
* config/i386/i386-c.cc (ix86_target_macros_internal): Define
__AMX_FP16__.
* config/i386/i386-isa.def: Add DEF_PTA for AMX_FP16.
* config/i386/i386-options.cc (isa2_opts): Add -mamx-fp16.
(ix86_valid_target_attribute_inner_p): Add new ATTR.
(ix86_option_override_internal): Handle AMX-FP16.
* config/i386/i386.opt: Add -mamx-fp16.
* config/i386/immintrin.h: Include amxfp16intrin.h.
* doc/extend.texi: Document -mamx-fp16.
* doc/invoke.texi: Document amx-fp16.
* doc/sourcebuild.texi: Document amx_fp16.
* config/i386/amxfp16intrin.h: New file.
gcc/testsuite/ChangeLog:
* g++.dg/other/i386-2.C: Add -mamx-fp16.
* g++.dg/other/i386-3.C: Ditto.
* gcc.target/i386/sse-12.c: Ditto.
* gcc.target/i386/sse-13.c: Ditto.
* gcc.target/i386/sse-14.c: Ditto.
* gcc.target/i386/sse-22.c: Ditto.
* gcc.target/i386/sse-23.c: Ditto.
* lib/target-supports.exp: (check_effective_target_amx_fp16):
New proc.
* gcc.target/i386/funcspec-56.inc: Add new target attribute.
* gcc.target/i386/amx-check.h: Add AMX_FP16.
* gcc.target/i386/amx-helper.h: New file to support amx-fp16.
* gcc.target/i386/amxfp16-asmatt-1.c: New test.
* gcc.target/i386/amxfp16-asmintel-1.c: Ditto.
* gcc.target/i386/amxfp16-dpfp16ps-2.c: Ditto.
Co-authored-by: Haochen Jiang <haochen.jiang@intel.com>
(cherry picked from commit 2b4a03962a0fe18cadc944d90f1fb85a40004226)
---
gcc/common/config/i386/cpuinfo.h | 5 ++
gcc/common/config/i386/i386-common.cc | 15 +++++
gcc/common/config/i386/i386-cpuinfo.h | 1 +
gcc/common/config/i386/i386-isas.h | 1 +
gcc/config.gcc | 3 +-
gcc/config/i386/amxfp16intrin.h | 46 ++++++++++++++
gcc/config/i386/cpuid.h | 1 +
gcc/config/i386/i386-c.cc | 2 +
gcc/config/i386/i386-isa.def | 1 +
gcc/config/i386/i386-options.cc | 4 +-
gcc/config/i386/i386.opt | 4 ++
gcc/config/i386/immintrin.h | 2 +
gcc/doc/extend.texi | 5 ++
gcc/doc/invoke.texi | 9 ++-
gcc/doc/sourcebuild.texi | 3 +
gcc/testsuite/g++.dg/other/i386-2.C | 2 +-
gcc/testsuite/g++.dg/other/i386-3.C | 2 +-
gcc/testsuite/gcc.target/i386/amx-check.h | 3 +
gcc/testsuite/gcc.target/i386/amx-helper.h | 61 +++++++++++++++++++
.../gcc.target/i386/amxfp16-asmatt-1.c | 13 ++++
.../gcc.target/i386/amxfp16-asmintel-1.c | 10 +++
.../gcc.target/i386/amxfp16-dpfp16ps-2.c | 57 +++++++++++++++++
gcc/testsuite/gcc.target/i386/funcspec-56.inc | 2 +
gcc/testsuite/gcc.target/i386/sse-12.c | 2 +-
gcc/testsuite/gcc.target/i386/sse-13.c | 2 +-
gcc/testsuite/gcc.target/i386/sse-14.c | 2 +-
gcc/testsuite/gcc.target/i386/sse-22.c | 4 +-
gcc/testsuite/gcc.target/i386/sse-23.c | 2 +-
gcc/testsuite/lib/target-supports.exp | 11 ++++
29 files changed, 262 insertions(+), 13 deletions(-)
create mode 100644 gcc/config/i386/amxfp16intrin.h
create mode 100644 gcc/testsuite/gcc.target/i386/amx-helper.h
create mode 100644 gcc/testsuite/gcc.target/i386/amxfp16-asmatt-1.c
create mode 100644 gcc/testsuite/gcc.target/i386/amxfp16-asmintel-1.c
create mode 100644 gcc/testsuite/gcc.target/i386/amxfp16-dpfp16ps-2.c
diff --git a/gcc/common/config/i386/cpuinfo.h b/gcc/common/config/i386/cpuinfo.h
index 37af92d6b..5951a30aa 100644
--- a/gcc/common/config/i386/cpuinfo.h
+++ b/gcc/common/config/i386/cpuinfo.h
@@ -783,6 +783,11 @@ get_available_features (struct __processor_model *cpu_model,
set_feature (FEATURE_AVX512BF16);
}
}
+ if (amx_usable)
+ {
+ if (eax & bit_AMX_FP16)
+ set_feature (FEATURE_AMX_FP16);
+ }
}
/* Get Advanced Features at level 0xd (eax = 0xd, ecx = 1). */
diff --git a/gcc/common/config/i386/i386-common.cc b/gcc/common/config/i386/i386-common.cc
index cfee672fb..922db33ee 100644
--- a/gcc/common/config/i386/i386-common.cc
+++ b/gcc/common/config/i386/i386-common.cc
@@ -107,6 +107,7 @@ along with GCC; see the file COPYING3. If not see
#define OPTION_MASK_ISA2_AMX_TILE_SET OPTION_MASK_ISA2_AMX_TILE
#define OPTION_MASK_ISA2_AMX_INT8_SET OPTION_MASK_ISA2_AMX_INT8
#define OPTION_MASK_ISA2_AMX_BF16_SET OPTION_MASK_ISA2_AMX_BF16
+#define OPTION_MASK_ISA2_AMX_FP16_SET OPTION_MASK_ISA2_AMX_FP16
/* SSE4 includes both SSE4.1 and SSE4.2. -msse4 should be the same
as -msse4.2. */
@@ -275,6 +276,7 @@ along with GCC; see the file COPYING3. If not see
#define OPTION_MASK_ISA2_KL_UNSET \
(OPTION_MASK_ISA2_KL | OPTION_MASK_ISA2_WIDEKL_UNSET)
#define OPTION_MASK_ISA2_WIDEKL_UNSET OPTION_MASK_ISA2_WIDEKL
+#define OPTION_MASK_ISA2_AMX_FP16_UNSET OPTION_MASK_ISA2_AMX_FP16
/* SSE4 includes both SSE4.1 and SSE4.2. -mno-sse4 should the same
as -mno-sse4.1. */
@@ -1125,6 +1127,19 @@ ix86_handle_option (struct gcc_options *opts,
}
return true;
+ case OPT_mamx_fp16:
+ if (value)
+ {
+ opts->x_ix86_isa_flags2 |= OPTION_MASK_ISA2_AMX_FP16_SET;
+ opts->x_ix86_isa_flags2_explicit |= OPTION_MASK_ISA2_AMX_FP16_SET;
+ }
+ else
+ {
+ opts->x_ix86_isa_flags2 &= ~OPTION_MASK_ISA2_AMX_FP16_UNSET;
+ opts->x_ix86_isa_flags2_explicit |= OPTION_MASK_ISA2_AMX_FP16_UNSET;
+ }
+ return true;
+
case OPT_mfma:
if (value)
{
diff --git a/gcc/common/config/i386/i386-cpuinfo.h b/gcc/common/config/i386/i386-cpuinfo.h
index 82996ebb3..8f22897de 100644
--- a/gcc/common/config/i386/i386-cpuinfo.h
+++ b/gcc/common/config/i386/i386-cpuinfo.h
@@ -240,6 +240,7 @@ enum processor_features
FEATURE_X86_64_V2,
FEATURE_X86_64_V3,
FEATURE_X86_64_V4,
+ FEATURE_AMX_FP16,
CPU_FEATURE_MAX
};
diff --git a/gcc/common/config/i386/i386-isas.h b/gcc/common/config/i386/i386-isas.h
index 2d0646a68..95bab6da2 100644
--- a/gcc/common/config/i386/i386-isas.h
+++ b/gcc/common/config/i386/i386-isas.h
@@ -175,4 +175,5 @@ ISA_NAMES_TABLE_START
ISA_NAMES_TABLE_ENTRY("x86-64-v2", FEATURE_X86_64_V2, P_X86_64_V2, NULL)
ISA_NAMES_TABLE_ENTRY("x86-64-v3", FEATURE_X86_64_V3, P_X86_64_V3, NULL)
ISA_NAMES_TABLE_ENTRY("x86-64-v4", FEATURE_X86_64_V4, P_X86_64_V4, NULL)
+ ISA_NAMES_TABLE_ENTRY("amx-fp16", FEATURE_AMX_FP16, P_NONE, "-mamx-fp16")
ISA_NAMES_TABLE_END
diff --git a/gcc/config.gcc b/gcc/config.gcc
index 4a0ae9328..e2b4a23dc 100644
--- a/gcc/config.gcc
+++ b/gcc/config.gcc
@@ -423,7 +423,8 @@ i[34567]86-*-* | x86_64-*-*)
tsxldtrkintrin.h amxtileintrin.h amxint8intrin.h
amxbf16intrin.h x86gprintrin.h uintrintrin.h
hresetintrin.h keylockerintrin.h avxvnniintrin.h
- mwaitintrin.h avx512fp16intrin.h avx512fp16vlintrin.h"
+ mwaitintrin.h avx512fp16intrin.h avx512fp16vlintrin.h
+ amxfp16intrin.h"
;;
ia64-*-*)
extra_headers=ia64intrin.h
diff --git a/gcc/config/i386/amxfp16intrin.h b/gcc/config/i386/amxfp16intrin.h
new file mode 100644
index 000000000..6a114741a
--- /dev/null
+++ b/gcc/config/i386/amxfp16intrin.h
@@ -0,0 +1,46 @@
+/* Copyright (C) 2020 Free Software Foundation, Inc.
+
+ This file is part of GCC.
+
+ GCC is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3, or (at your option)
+ any later version.
+
+ GCC is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ Under Section 7 of GPL version 3, you are granted additional
+ permissions described in the GCC Runtime Library Exception, version
+ 3.1, as published by the Free Software Foundation.
+
+ You should have received a copy of the GNU General Public License and
+ a copy of the GCC Runtime Library Exception along with this program;
+ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+ <http://www.gnu.org/licenses/>. */
+
+#if !defined _IMMINTRIN_H_INCLUDED
+#error "Never use <amxfp16intrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef _AMXFP16INTRIN_H_INCLUDED
+#define _AMXFP16INTRIN_H_INCLUDED
+
+#if defined(__x86_64__)
+#define _tile_dpfp16ps_internal(dst,src1,src2) \
+ __asm__ volatile \
+ ("{tdpfp16ps\t%%tmm"#src2", %%tmm"#src1", %%tmm"#dst"|tdpfp16ps\t%%tmm"#dst", %%tmm"#src1", %%tmm"#src2"}" ::)
+
+#define _tile_dpfp16ps(dst,src1,src2) \
+ _tile_dpfp16ps_internal (dst,src1,src2)
+
+#endif
+
+#ifdef __DISABLE_AMX_FP16__
+#undef __DISABLE_AMX_FP16__
+#pragma GCC pop_options
+#endif /* __DISABLE_AMX_FP16__ */
+
+#endif /* _AMXFP16INTRIN_H_INCLUDED */
diff --git a/gcc/config/i386/cpuid.h b/gcc/config/i386/cpuid.h
index 8b3dc2b1d..d6cd8d1bf 100644
--- a/gcc/config/i386/cpuid.h
+++ b/gcc/config/i386/cpuid.h
@@ -27,6 +27,7 @@
/* %eax */
#define bit_AVXVNNI (1 << 4)
#define bit_AVX512BF16 (1 << 5)
+#define bit_AMX_FP16 (1 << 21)
#define bit_HRESET (1 << 22)
/* %ecx */
diff --git a/gcc/config/i386/i386-c.cc b/gcc/config/i386/i386-c.cc
index 3fec4c7e2..4269f29e6 100644
--- a/gcc/config/i386/i386-c.cc
+++ b/gcc/config/i386/i386-c.cc
@@ -633,6 +633,8 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
def_or_undef (parse_in, "__WIDEKL__");
if (isa_flag2 & OPTION_MASK_ISA2_AVXVNNI)
def_or_undef (parse_in, "__AVXVNNI__");
+ if (isa_flag2 & OPTION_MASK_ISA2_AMX_FP16)
+ def_or_undef (parse_in, "__AMX_FP16__");
if (TARGET_IAMCU)
{
def_or_undef (parse_in, "__iamcu");
diff --git a/gcc/config/i386/i386-isa.def b/gcc/config/i386/i386-isa.def
index 83659d0be..c7305c01b 100644
--- a/gcc/config/i386/i386-isa.def
+++ b/gcc/config/i386/i386-isa.def
@@ -109,3 +109,4 @@ DEF_PTA(KL)
DEF_PTA(WIDEKL)
DEF_PTA(AVXVNNI)
DEF_PTA(AVX512FP16)
+DEF_PTA(AMX_FP16)
diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
index 3df1f0c41..3edb7094e 100644
--- a/gcc/config/i386/i386-options.cc
+++ b/gcc/config/i386/i386-options.cc
@@ -230,7 +230,8 @@ static struct ix86_target_opts isa2_opts[] =
{ "-mkl", OPTION_MASK_ISA2_KL },
{ "-mwidekl", OPTION_MASK_ISA2_WIDEKL },
{ "-mavxvnni", OPTION_MASK_ISA2_AVXVNNI },
- { "-mavx512fp16", OPTION_MASK_ISA2_AVX512FP16 }
+ { "-mavx512fp16", OPTION_MASK_ISA2_AVX512FP16 },
+ { "-mamx-fp16", OPTION_MASK_ISA2_AMX_FP16 }
};
static struct ix86_target_opts isa_opts[] =
{
@@ -1074,6 +1075,7 @@ ix86_valid_target_attribute_inner_p (tree fndecl, tree args, char *p_strings[],
IX86_ATTR_ISA ("hreset", OPT_mhreset),
IX86_ATTR_ISA ("avxvnni", OPT_mavxvnni),
IX86_ATTR_ISA ("avx512fp16", OPT_mavx512fp16),
+ IX86_ATTR_ISA ("amx-fp16", OPT_mamx_fp16),
/* enum options */
IX86_ATTR_ENUM ("fpmath=", OPT_mfpmath_),
diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt
index b154110d8..52c6f02ee 100644
--- a/gcc/config/i386/i386.opt
+++ b/gcc/config/i386/i386.opt
@@ -1226,3 +1226,7 @@ Enable conservative small loop unrolling.
mscatter
Target Alias(mtune-ctrl=, use_scatter, ^use_scatter)
Enable vectorization for scatter instruction.
+
+mamx-fp16
+Target Mask(ISA2_AMX_FP16) Var(ix86_isa_flags2) Save
+Support AMX-FP16 built-in functions and code generation.
diff --git a/gcc/config/i386/immintrin.h b/gcc/config/i386/immintrin.h
index 6afd78c2b..0447ca4b2 100644
--- a/gcc/config/i386/immintrin.h
+++ b/gcc/config/i386/immintrin.h
@@ -128,4 +128,6 @@
#include <keylockerintrin.h>
+#include <amxfp16intrin.h>
+
#endif /* _IMMINTRIN_H_INCLUDED */
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index 33a776a79..4ba9d34cd 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -7038,6 +7038,11 @@ Enable/disable the generation of the WIDEKL instructions.
@cindex @code{target("avxvnni")} function attribute, x86
Enable/disable the generation of the AVXVNNI instructions.
+@item amx-fp16
+@itemx no-amx-fp16
+@cindex @code{target("amx-fp16")} function attribute, x86
+Enable/disable the generation of the AMX-FP16 instructions.
+
@item cld
@itemx no-cld
@cindex @code{target("cld")} function attribute, x86
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 3a48655e5..d25f13217 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -1428,7 +1428,7 @@ See RS/6000 and PowerPC Options.
-mavx5124fmaps -mavx512vnni -mavx5124vnniw -mprfchw -mrdpid @gol
-mrdseed -msgx -mavx512vp2intersect -mserialize -mtsxldtrk@gol
-mamx-tile -mamx-int8 -mamx-bf16 -muintr -mhreset -mavxvnni@gol
--mavx512fp16 @gol
+-mavx512fp16 -mamx-fp16 @gol
-mcldemote -mms-bitfields -mno-align-stringops -minline-all-stringops @gol
-minline-stringops-dynamically -mstringop-strategy=@var{alg} @gol
-mkl -mwidekl @gol
@@ -32442,6 +32442,9 @@ preferred alignment to @option{-mpreferred-stack-boundary=2}.
@need 200
@itemx -mwidekl
@opindex mwidekl
+@need 200
+@itemx -mamx-fp16
+@opindex mamx-fp16
These switches enable the use of instructions in the MMX, SSE,
SSE2, SSE3, SSSE3, SSE4, SSE4A, SSE4.1, SSE4.2, AVX, AVX2, AVX512F, AVX512PF,
AVX512ER, AVX512CD, AVX512VL, AVX512BW, AVX512DQ, AVX512IFMA, AVX512VBMI, SHA,
@@ -32451,8 +32454,8 @@ WBNOINVD, FMA4, PREFETCHW, RDPID, PREFETCHWT1, RDSEED, SGX, XOP, LWP,
XSAVEOPT, XSAVEC, XSAVES, RTM, HLE, TBM, MWAITX, CLZERO, PKU, AVX512VBMI2,
GFNI, VAES, WAITPKG, VPCLMULQDQ, AVX512BITALG, MOVDIRI, MOVDIR64B, AVX512BF16,
ENQCMD, AVX512VPOPCNTDQ, AVX5124FMAPS, AVX512VNNI, AVX5124VNNIW, SERIALIZE,
-UINTR, HRESET, AMXTILE, AMXINT8, AMXBF16, KL, WIDEKL, AVXVNNI, AVX512-FP16
-or CLDEMOTE extended instruction sets. Each has a corresponding
+UINTR, HRESET, AMXTILE, AMXINT8, AMXBF16, KL, WIDEKL, AVXVNNI, AVX512-FP16,
+AMX-FP16 or CLDEMOTE extended instruction sets. Each has a corresponding
@option{-mno-} option to disable use of these instructions.
These extensions are also available as built-in functions: see
diff --git a/gcc/doc/sourcebuild.texi b/gcc/doc/sourcebuild.texi
index 71c04841d..b64b62dee 100644
--- a/gcc/doc/sourcebuild.texi
+++ b/gcc/doc/sourcebuild.texi
@@ -2472,6 +2472,9 @@ Target supports the execution of @code{amx-int8} instructions.
@item amx_bf16
Target supports the execution of @code{amx-bf16} instructions.
+@item amx_fp16
+Target supports the execution of @code{amx-fp16} instructions.
+
@item cell_hw
Test system can execute AltiVec and Cell PPU instructions.
diff --git a/gcc/testsuite/g++.dg/other/i386-2.C b/gcc/testsuite/g++.dg/other/i386-2.C
index fba3d1ac6..57a6357aa 100644
--- a/gcc/testsuite/g++.dg/other/i386-2.C
+++ b/gcc/testsuite/g++.dg/other/i386-2.C
@@ -1,5 +1,5 @@
/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
-/* { dg-options "-O -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx512vbmi2 -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd -mavx512vp2intersect -mserialize -mtsxldtrk -mamx-tile -mamx-int8 -mamx-bf16 -mkl -mwidekl -mavxvnni -mavx512fp16" } */
+/* { dg-options "-O -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx512vbmi2 -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd -mavx512vp2intersect -mserialize -mtsxldtrk -mamx-tile -mamx-int8 -mamx-bf16 -mkl -mwidekl -mavxvnni -mavx512fp16 -mamx-fp16" } */
/* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, mm3dnow.h, fma4intrin.h,
xopintrin.h, abmintrin.h, bmiintrin.h, tbmintrin.h, lwpintrin.h,
diff --git a/gcc/testsuite/g++.dg/other/i386-3.C b/gcc/testsuite/g++.dg/other/i386-3.C
index 5cc0fa834..1947547d6 100644
--- a/gcc/testsuite/g++.dg/other/i386-3.C
+++ b/gcc/testsuite/g++.dg/other/i386-3.C
@@ -1,5 +1,5 @@
/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
-/* { dg-options "-O -fkeep-inline-functions -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx512vbmi2 -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd -mavx512vp2intersect -mserialize -mtsxldtrk -mamx-tile -mamx-int8 -mamx-bf16 -mkl -mwidekl -mavxvnni -mavx512fp16" } */
+/* { dg-options "-O -fkeep-inline-functions -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx512vbmi2 -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd -mavx512vp2intersect -mserialize -mtsxldtrk -mamx-tile -mamx-int8 -mamx-bf16 -mkl -mwidekl -mavxvnni -mavx512fp16 -mamx-fp16" } */
/* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, mm3dnow.h, fma4intrin.h,
xopintrin.h, abmintrin.h, bmiintrin.h, tbmintrin.h, lwpintrin.h,
diff --git a/gcc/testsuite/gcc.target/i386/amx-check.h b/gcc/testsuite/gcc.target/i386/amx-check.h
index 6fff5ff46..27dd37bf9 100644
--- a/gcc/testsuite/gcc.target/i386/amx-check.h
+++ b/gcc/testsuite/gcc.target/i386/amx-check.h
@@ -213,6 +213,9 @@ main ()
#ifdef AMX_BF16
&& __builtin_cpu_supports ("amx-bf16")
#endif
+#ifdef AMX_FP16
+ && __builtin_cpu_supports ("amx-fp16")
+#endif
#ifdef __linux__
&& request_perm_xtile_data ()
#endif
diff --git a/gcc/testsuite/gcc.target/i386/amx-helper.h b/gcc/testsuite/gcc.target/i386/amx-helper.h
new file mode 100644
index 000000000..fe24d7067
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/amx-helper.h
@@ -0,0 +1,61 @@
+#ifndef AMX_HELPER_H_INCLUDED
+#define AMX_HELPER_H_INCLUDED
+#if defined(AMX_FP16)
+#include <immintrin.h>
+#include <xmmintrin.h>
+#endif
+#include "amx-check.h"
+
+typedef union
+{
+ _Float16 f16;
+ uint16_t u;
+} union16f_uw;
+
+#if defined(AMX_FP16)
+/* Transformation functions between fp16/float */
+static uint16_t make_f32_fp16 (float f)
+{
+ union16f_uw tmp;
+ __m128 b = _mm_set_ss (f);
+ __m128h a;
+ tmp.f16 = _mm_cvtsh_h (_mm_cvtss_sh (a, b));
+ return tmp.u;
+}
+
+static float make_fp16_f32 (uint16_t fp)
+{
+ union16f_uw tmp;
+ tmp.u = fp;
+ __m128h b = _mm_set_sh (tmp.f16);
+ __m128 a;
+ return _mm_cvtss_f32 (_mm_cvtsh_ss (a, b));
+}
+
+/* Init tile buffer with fp16 pairs */
+void init_fp16_max_tile_buffer (uint8_t* buf)
+{
+ int i, j;
+ uint16_t* ptr = (uint16_t *) buf;
+
+ for (i = 0; i < 16; i++)
+ for (j = 0; j < 32; j++)
+ {
+ float f = 2.5f * i + 1.25f * j;
+ ptr[i * 32 + j] = make_f32_fp16 (f);
+ }
+}
+
+/* Init tile fp16 pair buffer with zero */
+void init_fp16_max_tile_zero_buffer (uint8_t* buf)
+{
+ int i, j;
+ uint16_t* ptr = (uint16_t *) buf;
+
+ for (i = 0; i < 16; i++)
+ for (j = 0; j < 32; j++)
+ ptr[i * 32 + j] = make_f32_fp16 (0.0f);
+}
+#endif
+
+#endif
diff --git a/gcc/testsuite/gcc.target/i386/amxfp16-asmatt-1.c b/gcc/testsuite/gcc.target/i386/amxfp16-asmatt-1.c
new file mode 100644
index 000000000..09ae6d408
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/amxfp16-asmatt-1.c
@@ -0,0 +1,13 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mamx-fp16" } */
+/* { dg-final { scan-assembler "tdpfp16ps\[ \\t]+\[^\n\]*%tmm3+\[^\n\]*%tmm2+\[^\n\]*%tmm1" } } */
+#include <immintrin.h>
+
+#define TMM1 1
+#define TMM2 2
+#define TMM3 3
+
+void TEST ()
+{
+ _tile_dpfp16ps (TMM1, TMM2, TMM3);
+}
diff --git a/gcc/testsuite/gcc.target/i386/amxfp16-asmintel-1.c b/gcc/testsuite/gcc.target/i386/amxfp16-asmintel-1.c
new file mode 100644
index 000000000..a8dff945f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/amxfp16-asmintel-1.c
@@ -0,0 +1,10 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-require-effective-target masm_intel } */
+/* { dg-options "-O2 -mamx-fp16 -masm=intel" } */
+/* { dg-final { scan-assembler "tdpfp16ps\[ \\t]+\[^\n\]*%tmm1+\[^\n\]*%tmm2+\[^\n\]*%tmm3" } } */
+#include <immintrin.h>
+
+void TEST ()
+{
+ _tile_dpfp16ps (1, 2, 3);
+}
diff --git a/gcc/testsuite/gcc.target/i386/amxfp16-dpfp16ps-2.c b/gcc/testsuite/gcc.target/i386/amxfp16-dpfp16ps-2.c
new file mode 100644
index 000000000..2d359a689
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/amxfp16-dpfp16ps-2.c
@@ -0,0 +1,57 @@
+/* { dg-do run { target { ! ia32 } } } */
+/* { dg-require-effective-target amx_tile } */
+/* { dg-require-effective-target amx_fp16 } */
+/* { dg-require-effective-target avx512fp16 } */
+/* { dg-options "-O2 -mamx-tile -mamx-fp16 -mavx512fp16" } */
+#define AMX_FP16
+#define DO_TEST test_amx_fp16_dpfp16ps
+void test_amx_fp16_dpfp16ps ();
+#include "amx-helper.h"
+
+void calc_matrix_dpfp16ps (__tile *dst, __tile *src1, __tile *src2)
+{
+ uint16_t *src1_buf = (uint16_t *)src1->buf;
+ uint16_t *src2_buf = (uint16_t *)src2->buf;
+ float *dst_buf = (float *)dst->buf;
+
+ int M = src1->rows;
+ int N = src1->colsb / 4;
+ int K = src2->colsb / 4;
+ int i, j, k, t;
+
+ for (i = 0; i < M; i++)
+ for (j = 0; j < N; j++)
+ for (k = 0; k < K; k++)
+ for (t = 0; t < 2; t+=2)
+ {
+ dst_buf[i * K + k] +=
+ (make_fp16_f32 (src1_buf[i * 2 * N + 2 * j + t]) *
+ make_fp16_f32 (src2_buf[j * 2 * K + 2 * k + t])) +
+ (make_fp16_f32 (src1_buf[i * 2 * N + 2 * j + t + 1]) *
+ make_fp16_f32 (src2_buf[j * 2 * K + 2 * k + t + 1]));
+ }
+
+}
+
+void test_amx_fp16_dpfp16ps ()
+{
+ __tilecfg_u cfg;
+ __tile dst, dst_ref, src1, src2;
+ uint8_t tmp_dst_buf[1024], tmp_dst_zero_buf[1024];
+
+ init_fp16_max_tile_buffer (tmp_dst_buf);
+ init_fp16_max_tile_zero_buffer (tmp_dst_zero_buf);
+
+ init_tile_config (&cfg);
+ init_tile_reg_and_src_with_buffer (1, dst, tmp_dst_zero_buf);
+ init_tile_reg_and_src_with_buffer (2, src1, tmp_dst_buf);
+ init_tile_reg_and_src_with_buffer (3, src2, tmp_dst_buf);
+
+ calc_matrix_dpfp16ps (&dst, &src1, &src2);
+
+ _tile_dpfp16ps (1, 2, 3);
+ _tile_stored (1, dst_ref.buf, _STRIDE);
+
+ if (!check_float_tile_register (&dst_ref, &dst))
+ abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/funcspec-56.inc b/gcc/testsuite/gcc.target/i386/funcspec-56.inc
index f34e7a977..b00cfff03 100644
--- a/gcc/testsuite/gcc.target/i386/funcspec-56.inc
+++ b/gcc/testsuite/gcc.target/i386/funcspec-56.inc
@@ -80,6 +80,7 @@ extern void test_keylocker (void) __attribute__((__target__("kl")));
extern void test_widekl (void) __attribute__((__target__("widekl")));
extern void test_avxvnni (void) __attribute__((__target__("avxvnni")));
extern void test_avx512fp16 (void) __attribute__((__target__("avx512fp16")));
+extern void test_amx_fp16 (void) __attribute__((__target__("amx-fp16")));
extern void test_no_sgx (void) __attribute__((__target__("no-sgx")));
extern void test_no_avx5124fmaps(void) __attribute__((__target__("no-avx5124fmaps")));
@@ -161,6 +162,7 @@ extern void test_no_keylocker (void) __attribute__((__target__("no-kl")));
extern void test_no_widekl (void) __attribute__((__target__("no-widekl")));
extern void test_no_avxvnni (void) __attribute__((__target__("no-avxvnni")));
extern void test_no_avx512fp16 (void) __attribute__((__target__("no-avx512fp16")));
+extern void test_no_amx_fp16 (void) __attribute__((__target__("no-amx-fp16")));
extern void test_arch_nocona (void) __attribute__((__target__("arch=nocona")));
extern void test_arch_core2 (void) __attribute__((__target__("arch=core2")));
diff --git a/gcc/testsuite/gcc.target/i386/sse-12.c b/gcc/testsuite/gcc.target/i386/sse-12.c
index 375d4d1b4..9ab4a7e0c 100644
--- a/gcc/testsuite/gcc.target/i386/sse-12.c
+++ b/gcc/testsuite/gcc.target/i386/sse-12.c
@@ -3,7 +3,7 @@
popcntintrin.h gfniintrin.h and mm_malloc.h are usable
with -O -std=c89 -pedantic-errors. */
/* { dg-do compile } */
-/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512bw -mavx512dq -mavx512vl -mavx512vbmi -mavx512vbmi2 -mavx512ifma -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd -mavx512vp2intersect -mserialize -mtsxldtrk -mamx-tile -mamx-int8 -mamx-bf16 -mkl -mwidekl -mavxvnni" } */
+/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512bw -mavx512dq -mavx512vl -mavx512vbmi -mavx512vbmi2 -mavx512ifma -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd -mavx512vp2intersect -mserialize -mtsxldtrk -mamx-tile -mamx-int8 -mamx-bf16 -mkl -mwidekl -mavxvnni -mamx-fp16" } */
#include <x86intrin.h>
diff --git a/gcc/testsuite/gcc.target/i386/sse-13.c b/gcc/testsuite/gcc.target/i386/sse-13.c
index e285c307d..a1e453a98 100644
--- a/gcc/testsuite/gcc.target/i386/sse-13.c
+++ b/gcc/testsuite/gcc.target/i386/sse-13.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -Werror-implicit-function-declaration -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vbmi2 -mavx512ifma -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mavx512vp2intersect -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd -mserialize -mtsxldtrk -mamx-tile -mamx-int8 -mamx-bf16 -mkl -mwidekl -mavxvnni -mavx512fp16" } */
+/* { dg-options "-O2 -Werror-implicit-function-declaration -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vbmi2 -mavx512ifma -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mavx512vp2intersect -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd -mserialize -mtsxldtrk -mamx-tile -mamx-int8 -mamx-bf16 -mkl -mwidekl -mavxvnni -mavx512fp16 -mamx-fp16" } */
/* { dg-add-options bind_pic_locally } */
#include <mm_malloc.h>
diff --git a/gcc/testsuite/gcc.target/i386/sse-14.c b/gcc/testsuite/gcc.target/i386/sse-14.c
index f41493b93..eaa1a8d81 100644
--- a/gcc/testsuite/gcc.target/i386/sse-14.c
+++ b/gcc/testsuite/gcc.target/i386/sse-14.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O0 -Werror-implicit-function-declaration -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx512vbmi2 -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mpconfig -mwbnoinvd -mavx512vl -mavx512bf16 -menqcmd -mavx512vp2intersect -mserialize -mtsxldtrk -mamx-tile -mamx-int8 -mamx-bf16 -mkl -mwidekl -mavxvnni -mavx512fp16" } */
+/* { dg-options "-O0 -Werror-implicit-function-declaration -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx512vbmi2 -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mpconfig -mwbnoinvd -mavx512vl -mavx512bf16 -menqcmd -mavx512vp2intersect -mserialize -mtsxldtrk -mamx-tile -mamx-int8 -mamx-bf16 -mkl -mwidekl -mavxvnni -mavx512fp16 -mamx-fp16" } */
/* { dg-add-options bind_pic_locally } */
#include <mm_malloc.h>
diff --git a/gcc/testsuite/gcc.target/i386/sse-22.c b/gcc/testsuite/gcc.target/i386/sse-22.c
index 31492ef36..19afe639d 100644
--- a/gcc/testsuite/gcc.target/i386/sse-22.c
+++ b/gcc/testsuite/gcc.target/i386/sse-22.c
@@ -103,7 +103,7 @@
#ifndef DIFFERENT_PRAGMAS
-#pragma GCC target ("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,avx512f,avx512er,avx512cd,avx512pf,sha,prefetchwt1,avx512vl,avx512bw,avx512dq,avx512vbmi,avx512vbmi2,avx512ifma,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,gfni,avx512bitalg,avx512bf16,avx512vp2intersect,serialize,tsxldtrk,amx-tile,amx-int8,amx-bf16,kl,widekl,avxvnni,avx512fp16")
+#pragma GCC target ("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,avx512f,avx512er,avx512cd,avx512pf,sha,prefetchwt1,avx512vl,avx512bw,avx512dq,avx512vbmi,avx512vbmi2,avx512ifma,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,gfni,avx512bitalg,avx512bf16,avx512vp2intersect,serialize,tsxldtrk,amx-tile,amx-int8,amx-bf16,kl,widekl,avxvnni,avx512fp16,amx-fp16")
#endif
/* Following intrinsics require immediate arguments. They
@@ -220,7 +220,7 @@ test_4 (_mm_cmpestrz, int, __m128i, int, __m128i, int, 1)
/* immintrin.h (AVX/AVX2/RDRND/FSGSBASE/F16C/RTM/AVX512F/SHA) */
#ifdef DIFFERENT_PRAGMAS
-#pragma GCC target ("avx,avx2,rdrnd,fsgsbase,f16c,rtm,avx512f,avx512er,avx512cd,avx512pf,sha,avx512vl,avx512bw,avx512dq,avx512ifma,avx512vbmi,avx512vbmi2,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,gfni,avx512bitalg,avx512bf16,avx512vp2intersect,serialize,tsxldtrk,amx-tile,amx-int8,amx-bf16,kl,widekl,avxvnni,avx512fp16")
+#pragma GCC target ("avx,avx2,rdrnd,fsgsbase,f16c,rtm,avx512f,avx512er,avx512cd,avx512pf,sha,avx512vl,avx512bw,avx512dq,avx512ifma,avx512vbmi,avx512vbmi2,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,gfni,avx512bitalg,avx512bf16,avx512vp2intersect,serialize,tsxldtrk,amx-tile,amx-int8,amx-bf16,kl,widekl,avxvnni,avx512fp16,amx-fp16")
#endif
#include <immintrin.h>
test_1 (_cvtss_sh, unsigned short, float, 1)
diff --git a/gcc/testsuite/gcc.target/i386/sse-23.c b/gcc/testsuite/gcc.target/i386/sse-23.c
index b398fd144..151201d97 100644
--- a/gcc/testsuite/gcc.target/i386/sse-23.c
+++ b/gcc/testsuite/gcc.target/i386/sse-23.c
@@ -843,6 +843,6 @@
#define __builtin_ia32_vpclmulqdq_v2di(A, B, C) __builtin_ia32_vpclmulqdq_v2di(A, B, 1)
#define __builtin_ia32_vpclmulqdq_v8di(A, B, C) __builtin_ia32_vpclmulqdq_v8di(A, B, 1)
-#pragma GCC target ("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,fma,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,avx512f,avx512er,avx512cd,avx512pf,sha,prefetchwt1,xsavec,xsaves,clflushopt,avx512bw,avx512dq,avx512vl,avx512vbmi,avx512ifma,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,clwb,mwaitx,clzero,pku,sgx,rdpid,gfni,avx512vbmi2,vpclmulqdq,avx512bitalg,pconfig,wbnoinvd,avx512bf16,enqcmd,avx512vp2intersect,serialize,tsxldtrk,amx-tile,amx-int8,amx-bf16,kl,widekl,avxvnni,avx512fp16")
+#pragma GCC target ("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,fma,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,avx512f,avx512er,avx512cd,avx512pf,sha,prefetchwt1,xsavec,xsaves,clflushopt,avx512bw,avx512dq,avx512vl,avx512vbmi,avx512ifma,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,clwb,mwaitx,clzero,pku,sgx,rdpid,gfni,avx512vbmi2,vpclmulqdq,avx512bitalg,pconfig,wbnoinvd,avx512bf16,enqcmd,avx512vp2intersect,serialize,tsxldtrk,amx-tile,amx-int8,amx-bf16,kl,widekl,avxvnni,avx512fp16,amx-fp16")
#include <x86intrin.h>
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index c858bd93b..0d83c780c 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -9972,6 +9972,17 @@ proc check_effective_target_amx_bf16 { } {
} "-mamx-bf16" ]
}
+# Return 1 if amx-fp16 instructions can be compiled.
+proc check_effective_target_amx_fp16 { } {
+ return [check_no_compiler_messages amx_fp16 object {
+ void
+ foo ()
+ {
+ __asm__ volatile ("tdpfp16ps\t%%tmm1, %%tmm2, %%tmm3" ::);
+ }
+ } "-mamx-fp16" ]
+}
+
# Return 1 if vpclmulqdq instructions can be compiled.
proc check_effective_target_vpclmulqdq { } {
return [check_no_compiler_messages vpclmulqdq object {
--
2.28.0.windows.1