Re: [PATCH 1/5] x86: Add -mmwait for -mgeneral-regs-only

[Richard Biener <richard.guenther@gmail.com>]

On Fri, Aug 13, 2021 at 3:51 PM H.J. Lu <hjl.tools@gmail.com> wrote:
>
> Add -mmwait so that the MWAIT and MONITOR intrinsics can be used with
> -mgeneral-regs-only and make -msse3 to imply -mmwait.

Adding new options requires to bump the LTO streaming minor version
(I know we forgot it once on the branch already when adding a new --param).

Please take care of this when backporting.

Richard.

> gcc/
>
>         * config.gcc: Install mwaitintrin.h for i[34567]86-*-* and
>         x86_64-*-* targets.
>         * common/config/i386/i386-common.c (OPTION_MASK_ISA2_MWAIT_SET):
>         New.
>         (OPTION_MASK_ISA2_MWAIT_UNSET): Likewise.
>         (ix86_handle_option): Handle -mmwait.
>         * config/i386/i386-builtins.c (ix86_init_mmx_sse_builtins):
>         Replace OPTION_MASK_ISA_SSE3 with OPTION_MASK_ISA2_MWAIT on
>         __builtin_ia32_monitor and __builtin_ia32_mwait.
>         * config/i386/i386-options.c (isa2_opts): Add -mmwait.
>         (ix86_valid_target_attribute_inner_p): Likewise.
>         (ix86_option_override_internal): Enable mwait/monitor
>         instructions for -msse3.
>         * config/i386/i386.h (TARGET_MWAIT): New.
>         (TARGET_MWAIT_P): Likewise.
>         * config/i386/i386.opt: Add -mmwait.
>         * config/i386/mwaitintrin.h: New file.
>         * config/i386/pmmintrin.h: Include <mwaitintrin.h>.
>         * config/i386/sse.md (sse3_mwait): Replace TARGET_SSE3 with
>         TARGET_MWAIT.
>         (@sse3_monitor_<mode>): Likewise.
>         * config/i386/x86gprintrin.h: Include <mwaitintrin.h>.
>         * doc/extend.texi: Document mwait target attribute.
>         * doc/invoke.texi: Document -mmwait.
>
> gcc/testsuite/
>
>         * gcc.target/i386/monitor-2.c: New test.
>
> (cherry picked from commit d8c6cc2ca35489bc41bb58ec96c1195928826922)
> ---
>  gcc/common/config/i386/i386-common.c      | 15 +++++++
>  gcc/config.gcc                            |  6 ++-
>  gcc/config/i386/i386-builtins.c           |  4 +-
>  gcc/config/i386/i386-options.c            |  7 +++
>  gcc/config/i386/i386.h                    |  2 +
>  gcc/config/i386/i386.opt                  |  4 ++
>  gcc/config/i386/mwaitintrin.h             | 52 +++++++++++++++++++++++
>  gcc/config/i386/pmmintrin.h               | 13 +-----
>  gcc/config/i386/sse.md                    |  4 +-
>  gcc/config/i386/x86gprintrin.h            |  2 +
>  gcc/doc/extend.texi                       |  5 +++
>  gcc/doc/invoke.texi                       |  8 +++-
>  gcc/testsuite/gcc.target/i386/monitor-2.c | 27 ++++++++++++
>  13 files changed, 130 insertions(+), 19 deletions(-)
>  create mode 100644 gcc/config/i386/mwaitintrin.h
>  create mode 100644 gcc/testsuite/gcc.target/i386/monitor-2.c
>
> diff --git a/gcc/common/config/i386/i386-common.c b/gcc/common/config/i386/i386-common.c
> index 6a7b5c8312f..e156cc34584 100644
> --- a/gcc/common/config/i386/i386-common.c
> +++ b/gcc/common/config/i386/i386-common.c
> @@ -150,6 +150,7 @@ along with GCC; see the file COPYING3.  If not see
>  #define OPTION_MASK_ISA_F16C_SET \
>    (OPTION_MASK_ISA_F16C | OPTION_MASK_ISA_AVX_SET)
>  #define OPTION_MASK_ISA2_MWAITX_SET OPTION_MASK_ISA2_MWAITX
> +#define OPTION_MASK_ISA2_MWAIT_SET OPTION_MASK_ISA2_MWAIT
>  #define OPTION_MASK_ISA2_CLZERO_SET OPTION_MASK_ISA2_CLZERO
>  #define OPTION_MASK_ISA_PKU_SET OPTION_MASK_ISA_PKU
>  #define OPTION_MASK_ISA2_RDPID_SET OPTION_MASK_ISA2_RDPID
> @@ -245,6 +246,7 @@ along with GCC; see the file COPYING3.  If not see
>  #define OPTION_MASK_ISA_XSAVES_UNSET OPTION_MASK_ISA_XSAVES
>  #define OPTION_MASK_ISA_CLWB_UNSET OPTION_MASK_ISA_CLWB
>  #define OPTION_MASK_ISA2_MWAITX_UNSET OPTION_MASK_ISA2_MWAITX
> +#define OPTION_MASK_ISA2_MWAIT_UNSET OPTION_MASK_ISA2_MWAIT
>  #define OPTION_MASK_ISA2_CLZERO_UNSET OPTION_MASK_ISA2_CLZERO
>  #define OPTION_MASK_ISA_PKU_UNSET OPTION_MASK_ISA_PKU
>  #define OPTION_MASK_ISA2_RDPID_UNSET OPTION_MASK_ISA2_RDPID
> @@ -1546,6 +1548,19 @@ ix86_handle_option (struct gcc_options *opts,
>         }
>        return true;
>
> +    case OPT_mmwait:
> +      if (value)
> +       {
> +         opts->x_ix86_isa_flags2 |= OPTION_MASK_ISA2_MWAIT_SET;
> +         opts->x_ix86_isa_flags2_explicit |= OPTION_MASK_ISA2_MWAIT_SET;
> +       }
> +      else
> +       {
> +         opts->x_ix86_isa_flags2 &= ~OPTION_MASK_ISA2_MWAIT_UNSET;
> +         opts->x_ix86_isa_flags2_explicit |= OPTION_MASK_ISA2_MWAIT_UNSET;
> +       }
> +      return true;
> +
>      case OPT_mclzero:
>        if (value)
>         {
> diff --git a/gcc/config.gcc b/gcc/config.gcc
> index 357b0bed067..a020e0808c9 100644
> --- a/gcc/config.gcc
> +++ b/gcc/config.gcc
> @@ -414,7 +414,8 @@ i[34567]86-*-*)
>                        avx512vp2intersectintrin.h avx512vp2intersectvlintrin.h
>                        tsxldtrkintrin.h amxtileintrin.h amxint8intrin.h
>                        amxbf16intrin.h x86gprintrin.h uintrintrin.h
> -                      hresetintrin.h keylockerintrin.h avxvnniintrin.h"
> +                      hresetintrin.h keylockerintrin.h avxvnniintrin.h
> +                      mwaitintrin.h"
>         ;;
>  x86_64-*-*)
>         cpu_type=i386
> @@ -451,7 +452,8 @@ x86_64-*-*)
>                        avx512vp2intersectintrin.h avx512vp2intersectvlintrin.h
>                        tsxldtrkintrin.h amxtileintrin.h amxint8intrin.h
>                        amxbf16intrin.h x86gprintrin.h uintrintrin.h
> -                      hresetintrin.h keylockerintrin.h avxvnniintrin.h"
> +                      hresetintrin.h keylockerintrin.h avxvnniintrin.h
> +                      mwaitintrin.h"
>         ;;
>  ia64-*-*)
>         extra_headers=ia64intrin.h
> diff --git a/gcc/config/i386/i386-builtins.c b/gcc/config/i386/i386-builtins.c
> index 4fcdf4b89ee..128bd39816c 100644
> --- a/gcc/config/i386/i386-builtins.c
> +++ b/gcc/config/i386/i386-builtins.c
> @@ -628,9 +628,9 @@ ix86_init_mmx_sse_builtins (void)
>                             VOID_FTYPE_VOID, IX86_BUILTIN_MFENCE);
>
>    /* SSE3.  */
> -  def_builtin (OPTION_MASK_ISA_SSE3, 0, "__builtin_ia32_monitor",
> +  def_builtin (0, OPTION_MASK_ISA2_MWAIT, "__builtin_ia32_monitor",
>                VOID_FTYPE_PCVOID_UNSIGNED_UNSIGNED, IX86_BUILTIN_MONITOR);
> -  def_builtin (OPTION_MASK_ISA_SSE3, 0, "__builtin_ia32_mwait",
> +  def_builtin (0, OPTION_MASK_ISA2_MWAIT, "__builtin_ia32_mwait",
>                VOID_FTYPE_UNSIGNED_UNSIGNED, IX86_BUILTIN_MWAIT);
>
>    /* AES */
> diff --git a/gcc/config/i386/i386-options.c b/gcc/config/i386/i386-options.c
> index 18d2c0b9f99..7ecd0cf8b8c 100644
> --- a/gcc/config/i386/i386-options.c
> +++ b/gcc/config/i386/i386-options.c
> @@ -207,6 +207,7 @@ static struct ix86_target_opts isa2_opts[] =
>    { "-mmovbe",         OPTION_MASK_ISA2_MOVBE },
>    { "-mclzero",                OPTION_MASK_ISA2_CLZERO },
>    { "-mmwaitx",                OPTION_MASK_ISA2_MWAITX },
> +  { "-mmwait",         OPTION_MASK_ISA2_MWAIT },
>    { "-mmovdir64b",     OPTION_MASK_ISA2_MOVDIR64B },
>    { "-mwaitpkg",       OPTION_MASK_ISA2_WAITPKG },
>    { "-mcldemote",      OPTION_MASK_ISA2_CLDEMOTE },
> @@ -1015,6 +1016,7 @@ ix86_valid_target_attribute_inner_p (tree fndecl, tree args, char *p_strings[],
>      IX86_ATTR_ISA ("fsgsbase", OPT_mfsgsbase),
>      IX86_ATTR_ISA ("rdrnd",    OPT_mrdrnd),
>      IX86_ATTR_ISA ("mwaitx",   OPT_mmwaitx),
> +    IX86_ATTR_ISA ("mwait",    OPT_mmwait),
>      IX86_ATTR_ISA ("clzero",   OPT_mclzero),
>      IX86_ATTR_ISA ("pku",      OPT_mpku),
>      IX86_ATTR_ISA ("lwp",      OPT_mlwp),
> @@ -2612,6 +2614,11 @@ ix86_option_override_internal (bool main_args_p,
>        || TARGET_PREFETCHWT1_P (opts->x_ix86_isa_flags))
>      ix86_prefetch_sse = true;
>
> +  /* Enable mwait/monitor instructions for -msse3.  */
> +  if (TARGET_SSE3_P (opts->x_ix86_isa_flags))
> +    opts->x_ix86_isa_flags2
> +      |= OPTION_MASK_ISA2_MWAIT & ~opts->x_ix86_isa_flags2_explicit;
> +
>    /* Enable popcnt instruction for -msse4.2 or -mabm.  */
>    if (TARGET_SSE4_2_P (opts->x_ix86_isa_flags)
>        || TARGET_ABM_P (opts->x_ix86_isa_flags))
> diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
> index 5583ec6881a..73e118900f7 100644
> --- a/gcc/config/i386/i386.h
> +++ b/gcc/config/i386/i386.h
> @@ -181,6 +181,8 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
>  #define TARGET_CLWB_P(x)       TARGET_ISA_CLWB_P(x)
>  #define TARGET_MWAITX  TARGET_ISA2_MWAITX
>  #define TARGET_MWAITX_P(x)     TARGET_ISA2_MWAITX_P(x)
> +#define TARGET_MWAIT   TARGET_ISA2_MWAIT
> +#define TARGET_MWAIT_P(x)      TARGET_ISA2_MWAIT_P(x)
>  #define TARGET_PKU     TARGET_ISA_PKU
>  #define TARGET_PKU_P(x)        TARGET_ISA_PKU_P(x)
>  #define TARGET_SHSTK   TARGET_ISA_SHSTK
> diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt
> index c781fdc8278..7b8547bb1c3 100644
> --- a/gcc/config/i386/i386.opt
> +++ b/gcc/config/i386/i386.opt
> @@ -1162,3 +1162,7 @@ AVXVNNI built-in functions and code generation.
>  mneeded
>  Target Var(ix86_needed) Save
>  Emit GNU_PROPERTY_X86_ISA_1_NEEDED GNU property.
> +
> +mmwait
> +Target Mask(ISA2_MWAIT) Var(ix86_isa_flags2) Save
> +Support MWAIT and MONITOR built-in functions and code generation.
> diff --git a/gcc/config/i386/mwaitintrin.h b/gcc/config/i386/mwaitintrin.h
> new file mode 100644
> index 00000000000..1ecbc4abb69
> --- /dev/null
> +++ b/gcc/config/i386/mwaitintrin.h
> @@ -0,0 +1,52 @@
> +/* Copyright (C) 2021 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/>.  */
> +
> +#ifndef _MWAITINTRIN_H_INCLUDED
> +#define _MWAITINTRIN_H_INCLUDED
> +
> +#ifndef __MWAIT__
> +#pragma GCC push_options
> +#pragma GCC target("mwait")
> +#define __DISABLE_MWAIT__
> +#endif /* __MWAIT__ */
> +
> +extern __inline void
> +__attribute__((__gnu_inline__, __always_inline__, __artificial__))
> +_mm_monitor (void const * __P, unsigned int __E, unsigned int __H)
> +{
> +  __builtin_ia32_monitor (__P, __E, __H);
> +}
> +
> +extern __inline void
> +__attribute__((__gnu_inline__, __always_inline__, __artificial__))
> +_mm_mwait (unsigned int __E, unsigned int __H)
> +{
> +  __builtin_ia32_mwait (__E, __H);
> +}
> +
> +#ifdef __DISABLE_MWAIT__
> +#undef __DISABLE_MWAIT__
> +#pragma GCC pop_options
> +#endif /* __DISABLE_MWAIT__ */
> +
> +#endif /* _MWAITINTRIN_H_INCLUDED */
> diff --git a/gcc/config/i386/pmmintrin.h b/gcc/config/i386/pmmintrin.h
> index fa9c5bb8b9f..f8102d2be23 100644
> --- a/gcc/config/i386/pmmintrin.h
> +++ b/gcc/config/i386/pmmintrin.h
> @@ -29,6 +29,7 @@
>
>  /* We need definitions from the SSE2 and SSE header files*/
>  #include <emmintrin.h>
> +#include <mwaitintrin.h>
>
>  #ifndef __SSE3__
>  #pragma GCC push_options
> @@ -112,18 +113,6 @@ _mm_lddqu_si128 (__m128i const *__P)
>    return (__m128i) __builtin_ia32_lddqu ((char const *)__P);
>  }
>
> -extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_monitor (void const * __P, unsigned int __E, unsigned int __H)
> -{
> -  __builtin_ia32_monitor (__P, __E, __H);
> -}
> -
> -extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_mwait (unsigned int __E, unsigned int __H)
> -{
> -  __builtin_ia32_mwait (__E, __H);
> -}
> -
>  #ifdef __DISABLE_SSE3__
>  #undef __DISABLE_SSE3__
>  #pragma GCC pop_options
> diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
> index 3f81abc7804..43afe3dabed 100644
> --- a/gcc/config/i386/sse.md
> +++ b/gcc/config/i386/sse.md
> @@ -16593,7 +16593,7 @@ (define_insn "sse3_mwait"
>    [(unspec_volatile [(match_operand:SI 0 "register_operand" "c")
>                      (match_operand:SI 1 "register_operand" "a")]
>                     UNSPECV_MWAIT)]
> -  "TARGET_SSE3"
> +  "TARGET_MWAIT"
>  ;; 64bit version is "mwait %rax,%rcx". But only lower 32bits are used.
>  ;; Since 32bit register operands are implicitly zero extended to 64bit,
>  ;; we only need to set up 32bit registers.
> @@ -16605,7 +16605,7 @@ (define_insn "@sse3_monitor_<mode>"
>                      (match_operand:SI 1 "register_operand" "c")
>                      (match_operand:SI 2 "register_operand" "d")]
>                     UNSPECV_MONITOR)]
> -  "TARGET_SSE3"
> +  "TARGET_MWAIT"
>  ;; 64bit version is "monitor %rax,%rcx,%rdx". But only lower 32bits in
>  ;; RCX and RDX are used.  Since 32bit register operands are implicitly
>  ;; zero extended to 64bit, we only need to set up 32bit registers.
> diff --git a/gcc/config/i386/x86gprintrin.h b/gcc/config/i386/x86gprintrin.h
> index ceda501252c..7793032ba90 100644
> --- a/gcc/config/i386/x86gprintrin.h
> +++ b/gcc/config/i386/x86gprintrin.h
> @@ -56,6 +56,8 @@
>
>  #include <movdirintrin.h>
>
> +#include <mwaitintrin.h>
> +
>  #include <mwaitxintrin.h>
>
>  #include <pconfigintrin.h>
> diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
> index 1bc66cce2b8..1acfaf1d345 100644
> --- a/gcc/doc/extend.texi
> +++ b/gcc/doc/extend.texi
> @@ -6665,6 +6665,11 @@ Enable/disable the generation of the MOVDIR64B instructions.
>  @cindex @code{target("movdiri")} function attribute, x86
>  Enable/disable the generation of the MOVDIRI instructions.
>
> +@item mwait
> +@itemx no-mwait
> +@cindex @code{target("mwait")} function attribute, x86
> +Enable/disable the generation of the MWAIT and MONITOR instructions.
> +
>  @item mwaitx
>  @itemx no-mwaitx
>  @cindex @code{target("mwaitx")} function attribute, x86
> diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
> index 7f13ffb79e1..3e1f0bc8fad 100644
> --- a/gcc/doc/invoke.texi
> +++ b/gcc/doc/invoke.texi
> @@ -1371,7 +1371,7 @@ See RS/6000 and PowerPC Options.
>  -mno-wide-multiply  -mrtd  -malign-double @gol
>  -mpreferred-stack-boundary=@var{num} @gol
>  -mincoming-stack-boundary=@var{num} @gol
> --mcld  -mcx16  -msahf  -mmovbe  -mcrc32 @gol
> +-mcld  -mcx16  -msahf  -mmovbe  -mcrc32 -mmwait @gol
>  -mrecip  -mrecip=@var{opt} @gol
>  -mvzeroupper  -mprefer-avx128  -mprefer-vector-width=@var{opt} @gol
>  -mmmx  -msse  -msse2  -msse3  -mssse3  -msse4.1  -msse4.2  -msse4  -mavx @gol
> @@ -31159,6 +31159,12 @@ This option enables built-in functions @code{__builtin_ia32_crc32qi},
>  @code{__builtin_ia32_crc32hi}, @code{__builtin_ia32_crc32si} and
>  @code{__builtin_ia32_crc32di} to generate the @code{crc32} machine instruction.
>
> +@item -mmwait
> +@opindex mmwait
> +This option enables built-in functions @code{__builtin_ia32_monitor},
> +and @code{__builtin_ia32_mwait} to generate the @code{monitor} and
> +@code{mwait} machine instructions.
> +
>  @item -mrecip
>  @opindex mrecip
>  This option enables use of @code{RCPSS} and @code{RSQRTSS} instructions
> diff --git a/gcc/testsuite/gcc.target/i386/monitor-2.c b/gcc/testsuite/gcc.target/i386/monitor-2.c
> new file mode 100644
> index 00000000000..96eeec070f0
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/monitor-2.c
> @@ -0,0 +1,27 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -mmwait -mgeneral-regs-only" } */
> +
> +/* Verify that they work in both 32bit and 64bit.  */
> +
> +#include <x86gprintrin.h>
> +
> +void
> +foo (char *p, int x, int y, int z)
> +{
> +   _mm_monitor (p, y, x);
> +   _mm_mwait (z, y);
> +}
> +
> +void
> +bar (char *p, long x, long y, long z)
> +{
> +   _mm_monitor (p, y, x);
> +   _mm_mwait (z, y);
> +}
> +
> +void
> +foo1 (char *p)
> +{
> +   _mm_monitor (p, 0, 0);
> +   _mm_mwait (0, 0);
> +}
> --
> 2.31.1
>