On Fri, Nov 21, 2014 at 12:45 PM, Ilya Tocar <tocarip.in...@gmail.com> wrote:
> On 20 Nov 09:43, Uros Bizjak wrote:
>> On Wed, Nov 19, 2014 at 6:32 PM, Ilya Tocar <tocarip.in...@gmail.com> wrote:
>> > Hi,
>> >
>> > New revision of Intel ISA reference [1] has new instructions:
>> > Clwb, pcommit and new flavors of AVX512. Patch bellow adds them.
>> > I understand that stage 1 is closed, however those changes shouldn't
>> > affect anything outside if i386 backend. And are extremely unlikely to
>> > break existing functionality, and I personally think it's desirable for
>> > newest GCC to support newest spec.
>> > Bootstrapped/regtestsed on x86_64-unknown-linux-gnu.
>> > Ok for trunk?
>>
>> Please split the patch into patch series, like it was done previously
>> for AVX512F patches.
>>
>> Uros.
>>
> Done. This part adds clwb.
> Bootstrapped/passes make-check.
> Ok for trunk?
>
> gcc/
>
> * common/config/i386/i386-common.c (OPTION_MASK_ISA_CLWB_UNSET,
> OPTION_MASK_ISA_CLWB_SET): New.
> (ix86_handle_option): Handle OPT_mclwb.
> * config.gcc: Add clwbintrin.h.
> * config/i386/clwbintrin.h: New file.
> * config/i386/cpuid.h (bit_CLWB): Define.
> * config/i386/driver-i386.c (host_detect_local_cpu): Detect clwb.
> * config/i386/i386-c.c (ix86_target_macros_internal): Define
> __CLWB__.
> * config/i386/i386.c (ix86_target_string): Add -mclwb.
> (PTA_CLWB): Define.
> (ix86_option_override_internal): Handle new option.
> (ix86_valid_target_attribute_inner_p): Add clwb.
> (ix86_builtins): Add IX86_BUILTIN_CLWB.
> (ix86_init_mmx_sse_builtins): Add __builtin_ia32_clwb.
> (ix86_expand_builtin): Handle IX86_BUILTIN_CLWB.
> * config/i386/i386.h (TARGET_CLWB, TARGET_CLWB_P): Define.
> * config/i386/i386.md (unspecv): Add UNSPECV_CLWB.
> (clwb): New instruction.
> * config/i386/i386.opt: Add mclwb.
> * config/i386/x86intrin.h: Include clwbintrin.h.
>
> gcc/testsuite/
>
> * g++.dg/other/i386-2.C: Add -mclwb.
> * g++.dg/other/i386-3.C: Ditto.
> * gcc.target/i386/clwb-1.c: New test.
> * gcc.target/i386/sse-12.c: Add new options.
> * 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.
OK.
Thanks,
Uros.
> ---
> gcc/common/config/i386/i386-common.c | 15 +++++++++++
> gcc/config.gcc | 4 +--
> gcc/config/i386/clwbintrin.h | 49
> ++++++++++++++++++++++++++++++++++
> gcc/config/i386/cpuid.h | 1 +
> gcc/config/i386/driver-i386.c | 6 +++--
> gcc/config/i386/i386-c.c | 2 ++
> gcc/config/i386/i386.c | 23 ++++++++++++++++
> gcc/config/i386/i386.h | 2 ++
> gcc/config/i386/i386.md | 12 +++++++++
> gcc/config/i386/i386.opt | 4 +++
> gcc/config/i386/x86intrin.h | 2 ++
> gcc/testsuite/g++.dg/other/i386-2.C | 2 +-
> gcc/testsuite/g++.dg/other/i386-3.C | 2 +-
> gcc/testsuite/gcc.target/i386/clwb-1.c | 11 ++++++++
> 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 | 2 +-
> gcc/testsuite/gcc.target/i386/sse-23.c | 2 +-
> 19 files changed, 134 insertions(+), 11 deletions(-)
> create mode 100644 gcc/config/i386/clwbintrin.h
> create mode 100644 gcc/testsuite/gcc.target/i386/clwb-1.c
>
> diff --git a/gcc/common/config/i386/i386-common.c
> b/gcc/common/config/i386/i386-common.c
> index 1c4f15e..bad0988 100644
> --- a/gcc/common/config/i386/i386-common.c
> +++ b/gcc/common/config/i386/i386-common.c
> @@ -85,6 +85,7 @@ along with GCC; see the file COPYING3. If not see
> (OPTION_MASK_ISA_XSAVES | OPTION_MASK_ISA_XSAVE)
> #define OPTION_MASK_ISA_XSAVEC_SET \
> (OPTION_MASK_ISA_XSAVEC | OPTION_MASK_ISA_XSAVE)
> +#define OPTION_MASK_ISA_CLWB_SET OPTION_MASK_ISA_CLWB
>
> /* SSE4 includes both SSE4.1 and SSE4.2. -msse4 should be the same
> as -msse4.2. */
> @@ -181,6 +182,7 @@ along with GCC; see the file COPYING3. If not see
> #define OPTION_MASK_ISA_CLFLUSHOPT_UNSET OPTION_MASK_ISA_CLFLUSHOPT
> #define OPTION_MASK_ISA_XSAVEC_UNSET OPTION_MASK_ISA_XSAVEC
> #define OPTION_MASK_ISA_XSAVES_UNSET OPTION_MASK_ISA_XSAVES
> +#define OPTION_MASK_ISA_CLWB_UNSET OPTION_MASK_ISA_CLWB
>
> /* SSE4 includes both SSE4.1 and SSE4.2. -mno-sse4 should the same
> as -mno-sse4.1. */
> @@ -901,6 +903,19 @@ ix86_handle_option (struct gcc_options *opts,
> }
> return true;
>
> + case OPT_mclwb:
> + if (value)
> + {
> + opts->x_ix86_isa_flags |= OPTION_MASK_ISA_CLWB_SET;
> + opts->x_ix86_isa_flags_explicit |= OPTION_MASK_ISA_CLWB_SET;
> + }
> + else
> + {
> + opts->x_ix86_isa_flags &= ~OPTION_MASK_ISA_CLWB_UNSET;
> + opts->x_ix86_isa_flags_explicit |= OPTION_MASK_ISA_CLWB_UNSET;
> + }
> + return true;
> +
> /* Comes from final.c -- no real reason to change it. */
> #define MAX_CODE_ALIGN 16
>
> diff --git a/gcc/config.gcc b/gcc/config.gcc
> index da2a723..766f13b 100644
> --- a/gcc/config.gcc
> +++ b/gcc/config.gcc
> @@ -369,7 +369,7 @@ i[34567]86-*-*)
> xsavesintrin.h avx512dqintrin.h avx512bwintrin.h
> avx512vlintrin.h avx512vlbwintrin.h avx512vldqintrin.h
> avx512ifmaintrin.h avx512ifmavlintrin.h
> avx512vbmiintrin.h
> - avx512vbmivlintrin.h"
> + avx512vbmivlintrin.h clwbintrin.h"
> ;;
> x86_64-*-*)
> cpu_type=i386
> @@ -390,7 +390,7 @@ x86_64-*-*)
> xsavesintrin.h avx512dqintrin.h avx512bwintrin.h
> avx512vlintrin.h avx512vlbwintrin.h avx512vldqintrin.h
> avx512ifmaintrin.h avx512ifmavlintrin.h
> avx512vbmiintrin.h
> - avx512vbmivlintrin.h"
> + avx512vbmivlintrin.h clwbintrin.h"
> ;;
> ia64-*-*)
> extra_headers=ia64intrin.h
> diff --git a/gcc/config/i386/clwbintrin.h b/gcc/config/i386/clwbintrin.h
> new file mode 100644
> index 0000000..9020c95
> --- /dev/null
> +++ b/gcc/config/i386/clwbintrin.h
> @@ -0,0 +1,49 @@
> +/* Copyright (C) 2013 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 _X86INTRIN_H_INCLUDED
> +# error "Never use <clwbintrin.h> directly; include <x86intrin.h> instead."
> +#endif
> +
> +#ifndef _CLWBINTRIN_H_INCLUDED
> +#define _CLWBINTRIN_H_INCLUDED
> +
> +#ifndef __CLWB__
> +#pragma GCC push_options
> +#pragma GCC target("clwb")
> +#define __DISABLE_CLWB__
> +#endif /* __CLWB__ */
> +
> +extern __inline void
> +__attribute__((__gnu_inline__, __always_inline__, __artificial__))
> +_mm_clwb (void *__A)
> +{
> + __builtin_ia32_clwb (__A);
> +}
> +
> +#ifdef __DISABLE_CLWB__
> +#undef __DISABLE_CLWB__
> +#pragma GCC pop_options
> +#endif /* __DISABLE_CLWB__ */
> +
> +#endif /* _CLWBINTRIN_H_INCLUDED */
> diff --git a/gcc/config/i386/cpuid.h b/gcc/config/i386/cpuid.h
> index 0efb1a4..6ee928b 100644
> --- a/gcc/config/i386/cpuid.h
> +++ b/gcc/config/i386/cpuid.h
> @@ -78,6 +78,7 @@
> #define bit_ADX (1 << 19)
> #define bit_AVX512IFMA (1 << 21)
> #define bit_CLFLUSHOPT (1 << 23)
> +#define bit_CLWB (1 << 24)
> #define bit_AVX512PF (1 << 26)
> #define bit_AVX512ER (1 << 27)
> #define bit_AVX512CD (1 << 28)
> diff --git a/gcc/config/i386/driver-i386.c b/gcc/config/i386/driver-i386.c
> index 72dfd04..c7acfba 100644
> --- a/gcc/config/i386/driver-i386.c
> +++ b/gcc/config/i386/driver-i386.c
> @@ -412,7 +412,7 @@ const char *host_detect_local_cpu (int argc, const char
> **argv)
> unsigned int has_avx512f = 0, has_sha = 0, has_prefetchwt1 = 0;
> unsigned int has_clflushopt = 0, has_xsavec = 0, has_xsaves = 0;
> unsigned int has_avx512dq = 0, has_avx512bw = 0, has_avx512vl = 0;
> - unsigned int has_avx512vbmi = 0, has_avx512ifma = 0;
> + unsigned int has_avx512vbmi = 0, has_avx512ifma = 0, has_clwb = 0;
>
> bool arch;
>
> @@ -491,6 +491,7 @@ const char *host_detect_local_cpu (int argc, const char
> **argv)
> has_avx512cd = ebx & bit_AVX512CD;
> has_sha = ebx & bit_SHA;
> has_clflushopt = ebx & bit_CLFLUSHOPT;
> + has_clwb = ebx & bit_CLWB;
> has_avx512dq = ebx & bit_AVX512DQ;
> has_avx512bw = ebx & bit_AVX512BW;
> has_avx512vl = ebx & bit_AVX512VL;
> @@ -930,6 +931,7 @@ const char *host_detect_local_cpu (int argc, const char
> **argv)
> const char *avx512vl = has_avx512vl ? " -mavx512vl" : " -mno-avx512vl";
> const char *avx512ifma = has_avx512ifma ? " -mavx512ifma" : "
> -mno-avx512ifma";
> const char *avx512vbmi = has_avx512vbmi ? " -mavx512vbmi" : "
> -mno-avx512vbmi";
> + const char *clwb = has_clwb ? " -mclwb" : " -mno-clwb";
>
> options = concat (options, mmx, mmx3dnow, sse, sse2, sse3, ssse3,
> sse4a, cx16, sahf, movbe, aes, sha, pclmul,
> @@ -939,7 +941,7 @@ const char *host_detect_local_cpu (int argc, const char
> **argv)
> fxsr, xsave, xsaveopt, avx512f, avx512er,
> avx512cd, avx512pf, prefetchwt1, clflushopt,
> xsavec, xsaves, avx512dq, avx512bw, avx512vl,
> - avx512ifma, avx512vbmi, NULL);
> + avx512ifma, avx512vbmi, clwb, NULL);
> }
>
> done:
> diff --git a/gcc/config/i386/i386-c.c b/gcc/config/i386/i386-c.c
> index 798eaa6..9742536 100644
> --- a/gcc/config/i386/i386-c.c
> +++ b/gcc/config/i386/i386-c.c
> @@ -411,6 +411,8 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
> def_or_undef (parse_in, "__XSAVES__");
> if (isa_flag & OPTION_MASK_ISA_MPX)
> def_or_undef (parse_in, "__MPX__");
> + if (isa_flag & OPTION_MASK_ISA_CLWB)
> + def_or_undef (parse_in, "__CLWB__");
> }
>
>
> diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
> index baf3166..e470b48 100644
> --- a/gcc/config/i386/i386.c
> +++ b/gcc/config/i386/i386.c
> @@ -2657,6 +2657,7 @@ ix86_target_string (HOST_WIDE_INT isa, int flags, const
> char *arch,
> { "-mxsavec", OPTION_MASK_ISA_XSAVEC },
> { "-mxsaves", OPTION_MASK_ISA_XSAVES },
> { "-mmpx", OPTION_MASK_ISA_MPX },
> + { "-mclwb", OPTION_MASK_ISA_CLWB },
> };
>
> /* Flag options. */
> @@ -3157,6 +3158,7 @@ ix86_option_override_internal (bool main_args_p,
> #define PTA_AVX512VL (HOST_WIDE_INT_1 << 52)
> #define PTA_AVX512IFMA (HOST_WIDE_INT_1 << 53)
> #define PTA_AVX512VBMI (HOST_WIDE_INT_1 << 54)
> +#define PTA_CLWB (HOST_WIDE_INT_1 << 55)
>
> #define PTA_CORE2 \
> (PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3 | PTA_SSSE3 \
> @@ -3716,6 +3718,9 @@ ix86_option_override_internal (bool main_args_p,
> if (processor_alias_table[i].flags & PTA_PREFETCHWT1
> && !(opts->x_ix86_isa_flags_explicit &
> OPTION_MASK_ISA_PREFETCHWT1))
> opts->x_ix86_isa_flags |= OPTION_MASK_ISA_PREFETCHWT1;
> + if (processor_alias_table[i].flags & PTA_CLWB
> + && !(opts->x_ix86_isa_flags_explicit & OPTION_MASK_ISA_CLWB))
> + opts->x_ix86_isa_flags |= OPTION_MASK_ISA_CLWB;
> if (processor_alias_table[i].flags & PTA_CLFLUSHOPT
> && !(opts->x_ix86_isa_flags_explicit &
> OPTION_MASK_ISA_CLFLUSHOPT))
> opts->x_ix86_isa_flags |= OPTION_MASK_ISA_CLFLUSHOPT;
> @@ -4661,6 +4666,7 @@ ix86_valid_target_attribute_inner_p (tree args, char
> *p_strings[],
> IX86_ATTR_ISA ("xsaves", OPT_mxsaves),
> IX86_ATTR_ISA ("avx512vbmi", OPT_mavx512vbmi),
> IX86_ATTR_ISA ("avx512ifma", OPT_mavx512ifma),
> + IX86_ATTR_ISA ("clwb", OPT_mclwb),
>
> /* enum options */
> IX86_ATTR_ENUM ("fpmath=", OPT_mfpmath_),
> @@ -30096,6 +30102,9 @@ enum ix86_builtins
> IX86_BUILTIN_SHA256MSG2,
> IX86_BUILTIN_SHA256RNDS2,
>
> + /* CLWB instructions. */
> + IX86_BUILTIN_CLWB,
> +
> /* CLFLUSHOPT instructions. */
> IX86_BUILTIN_CLFLUSHOPT,
>
> @@ -33956,6 +33965,10 @@ ix86_init_mmx_sse_builtins (void)
> def_builtin (OPTION_MASK_ISA_CLFLUSHOPT, "__builtin_ia32_clflushopt",
> VOID_FTYPE_PCVOID, IX86_BUILTIN_CLFLUSHOPT);
>
> + /* CLWB. */
> + def_builtin (OPTION_MASK_ISA_CLWB, "__builtin_ia32_clwb",
> + VOID_FTYPE_PCVOID, IX86_BUILTIN_CLWB);
> +
> /* Add FMA4 multi-arg argument instructions */
> for (i = 0, d = bdesc_multi_arg; i < ARRAY_SIZE (bdesc_multi_arg); i++,
> d++)
> {
> @@ -38675,6 +38688,16 @@ ix86_expand_builtin (tree exp, rtx target, rtx
> subtarget,
> emit_insn (gen_sse2_clflush (op0));
> return 0;
>
> + case IX86_BUILTIN_CLWB:
> + arg0 = CALL_EXPR_ARG (exp, 0);
> + op0 = expand_normal (arg0);
> + icode = CODE_FOR_clwb;
> + if (!insn_data[icode].operand[0].predicate (op0, Pmode))
> + op0 = ix86_zero_extend_to_Pmode (op0);
> +
> + emit_insn (gen_clwb (op0));
> + return 0;
> +
> case IX86_BUILTIN_CLFLUSHOPT:
> arg0 = CALL_EXPR_ARG (exp, 0);
> op0 = expand_normal (arg0);
> diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
> index 2596f81..03d1b06 100644
> --- a/gcc/config/i386/i386.h
> +++ b/gcc/config/i386/i386.h
> @@ -150,6 +150,8 @@ see the files COPYING3 and COPYING.RUNTIME respectively.
> If not, see
> #define TARGET_PREFETCHWT1_P(x) TARGET_ISA_PREFETCHWT1_P(x)
> #define TARGET_MPX TARGET_ISA_MPX
> #define TARGET_MPX_P(x) TARGET_ISA_MPX_P(x)
> +#define TARGET_CLWB TARGET_ISA_CLWB
> +#define TARGET_CLWB_P(x) TARGET_ISA_CLWB_P(x)
>
> #define TARGET_LP64 TARGET_ABI_64
> #define TARGET_LP64_P(x) TARGET_ABI_64_P(x)
> diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
> index 203db11..a60e2de 100644
> --- a/gcc/config/i386/i386.md
> +++ b/gcc/config/i386/i386.md
> @@ -253,6 +253,9 @@
>
> UNSPECV_NLGR
>
> + ;; For CLWB support
> + UNSPECV_CLWB
> +
> ;; For CLFLUSHOPT support
> UNSPECV_CLFLUSHOPT
> ])
> @@ -18668,6 +18671,15 @@
> [(set_attr "type" "other")
> (set_attr "length" "3")])
>
> +(define_insn "clwb"
> + [(unspec_volatile [(match_operand 0 "address_operand" "p")]
> + UNSPECV_CLWB)]
> + "TARGET_CLWB"
> + "clwb\t%a0"
> + [(set_attr "type" "sse")
> + (set_attr "atom_sse_attr" "fence")
> + (set_attr "memory" "unknown")])
> +
> (define_insn "clflushopt"
> [(unspec_volatile [(match_operand 0 "address_operand" "p")]
> UNSPECV_CLFLUSHOPT)]
> diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt
> index f6ba8a7..9c18173 100644
> --- a/gcc/config/i386/i386.opt
> +++ b/gcc/config/i386/i386.opt
> @@ -721,6 +721,10 @@ mclflushopt
> Target Report Mask(ISA_CLFLUSHOPT) Var(ix86_isa_flags) Save
> Support CLFLUSHOPT instructions
>
> +mclwb
> +Target Report Mask(ISA_CLWB) Var(ix86_isa_flags) Save
> +Support CLWB instructions
> +
> mfxsr
> Target Report Mask(ISA_FXSR) Var(ix86_isa_flags) Save
> Support FXSAVE and FXRSTOR instructions
> diff --git a/gcc/config/i386/x86intrin.h b/gcc/config/i386/x86intrin.h
> index c84ab88..7f9a519 100644
> --- a/gcc/config/i386/x86intrin.h
> +++ b/gcc/config/i386/x86intrin.h
> @@ -75,6 +75,8 @@
>
> #include <adxintrin.h>
>
> +#include <clwbintrin.h>
> +
> #include <clflushoptintrin.h>
>
> #include <xsavesintrin.h>
> diff --git a/gcc/testsuite/g++.dg/other/i386-2.C
> b/gcc/testsuite/g++.dg/other/i386-2.C
> index 0368d35..dbbe0bc 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" } */
> +/* { 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 -mclwb" } */
>
> /* 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 3a3d5ff..185f403 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" } */
> +/* { 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 -mclwb" } */
>
> /* 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/clwb-1.c
> b/gcc/testsuite/gcc.target/i386/clwb-1.c
> new file mode 100644
> index 0000000..d6f5023
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/clwb-1.c
> @@ -0,0 +1,11 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -mclwb" } */
> +/* { dg-final { scan-assembler "clwb\[ \\t\]" } } */
> +
> +#include "x86intrin.h"
> +
> +void
> +test_clwb (void *__A)
> +{
> + _mm_clwb (__A);
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/sse-12.c
> b/gcc/testsuite/gcc.target/i386/sse-12.c
> index a83db92..9af6f70 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 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 -mavx512ifma" } */
> +/* { 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 -mavx512ifma -mclwb" } */
>
> #include <x86intrin.h>
>
> diff --git a/gcc/testsuite/gcc.target/i386/sse-13.c
> b/gcc/testsuite/gcc.target/i386/sse-13.c
> index f1d9157..98b0936 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 -mavx512ifma" } */
> +/* { 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 -mavx512ifma -mclwb" } */
>
> #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 bc10109..3c462c0 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" } */
> +/* { 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 -mclwb" } */
> /* { 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 d54d1db..b1def10 100644
> --- a/gcc/testsuite/gcc.target/i386/sse-22.c
> +++ b/gcc/testsuite/gcc.target/i386/sse-22.c
> @@ -695,7 +695,7 @@ test_2 (_mm_clmulepi64_si128, __m128i, __m128i, __m128i,
> 1)
>
> /* x86intrin.h (FMA4/XOP/LWP/BMI/BMI2/TBM/LZCNT/FMA). */
> #ifdef DIFFERENT_PRAGMAS
> -#pragma GCC target
> ("fma4,xop,lwp,bmi,bmi2,tbm,lzcnt,fma,rdseed,prfchw,adx,fxsr,xsaveopt,xsavec,xsaves,clflushopt")
> +#pragma GCC target
> ("fma4,xop,lwp,bmi,bmi2,tbm,lzcnt,fma,rdseed,prfchw,adx,fxsr,xsaveopt,xsavec,xsaves,clflushopt,clwb")
> #endif
> #include <x86intrin.h>
> /* xopintrin.h */
> diff --git a/gcc/testsuite/gcc.target/i386/sse-23.c
> b/gcc/testsuite/gcc.target/i386/sse-23.c
> index e699bd3..5f149cb 100644
> --- a/gcc/testsuite/gcc.target/i386/sse-23.c
> +++ b/gcc/testsuite/gcc.target/i386/sse-23.c
> @@ -594,7 +594,7 @@
> #define __builtin_ia32_extracti64x2_256_mask(A, E, C, D)
> __builtin_ia32_extracti64x2_256_mask(A, 1, C, D)
> #define __builtin_ia32_extractf64x2_256_mask(A, E, C, D)
> __builtin_ia32_extractf64x2_256_mask(A, 1, C, D)
>
> -#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")
> +#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,clwb")
> #include <wmmintrin.h>
> #include <smmintrin.h>
> #include <mm3dnow.h>
> --
> 1.8.3.1
>
