diff mbox series

[2/2] Make option mvzeroupper independent of optimization level.

Message ID 20230627055312.2881827-2-hongtao.liu@intel.com
State New
Headers show
Series [1/2] Don't issue vzeroupper for vzeroupper call_insn. | expand

Commit Message

liuhongt June 27, 2023, 5:53 a.m. UTC 
pass_insert_vzeroupper is under condition

TARGET_AVX && TARGET_VZEROUPPER
&& flag_expensive_optimizations && !optimize_size

But the document of mvzeroupper doesn't mention the insertion
required -O2 and above, it may confuse users when they explicitly
use -Os -mvzeroupper.

------------
mvzeroupper
Target Mask(VZEROUPPER) Save
Generate vzeroupper instruction before a transfer of control flow out of
the function.
------------

The patch moves flag_expensive_optimizations && !optimize_size to
ix86_option_override_internal. It makes -mvzeroupper independent of
optimization level, but still keeps the behavior of architecture
tuning(emit_vzeroupper) unchanged.

Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
Ok for trunk?

gcc/ChangeLog:

	* config/i386/i386-features.cc (pass_insert_vzeroupper:gate):
	Move flag_expensive_optimizations && !optimize_size to ..
	* config/i386/i386-options.cc (ix86_option_override_internal):
	.. this, it makes -mvzeroupper independent of optimization
	level, but still keeps the behavior of architecture
	tuning(emit_vzeroupper) unchanged.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/avx-vzeroupper-29.c: New testcase.
---
 gcc/config/i386/i386-features.cc                  |  3 +--
 gcc/config/i386/i386-options.cc                   |  4 +++-
 gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c | 14 ++++++++++++++
 3 files changed, 18 insertions(+), 3 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c

Comments

Uros Bizjak June 27, 2023, 6:05 a.m. UTC | #1 
On Tue, Jun 27, 2023 at 7:55 AM liuhongt <hongtao.liu@intel.com> wrote:
>
> pass_insert_vzeroupper is under condition
>
> TARGET_AVX && TARGET_VZEROUPPER
> && flag_expensive_optimizations && !optimize_size
>
> But the document of mvzeroupper doesn't mention the insertion
> required -O2 and above, it may confuse users when they explicitly
> use -Os -mvzeroupper.
>
> ------------
> mvzeroupper
> Target Mask(VZEROUPPER) Save
> Generate vzeroupper instruction before a transfer of control flow out of
> the function.
> ------------
>
> The patch moves flag_expensive_optimizations && !optimize_size to
> ix86_option_override_internal. It makes -mvzeroupper independent of
> optimization level, but still keeps the behavior of architecture
> tuning(emit_vzeroupper) unchanged.
>
> Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
> Ok for trunk?
>
> gcc/ChangeLog:
>
>         * config/i386/i386-features.cc (pass_insert_vzeroupper:gate):
>         Move flag_expensive_optimizations && !optimize_size to ..
>         * config/i386/i386-options.cc (ix86_option_override_internal):
>         .. this, it makes -mvzeroupper independent of optimization
>         level, but still keeps the behavior of architecture
>         tuning(emit_vzeroupper) unchanged.
>
> gcc/testsuite/ChangeLog:
>
>         * gcc.target/i386/avx-vzeroupper-29.c: New testcase.

OK.

Thanks,
Uros.

> ---
>  gcc/config/i386/i386-features.cc                  |  3 +--
>  gcc/config/i386/i386-options.cc                   |  4 +++-
>  gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c | 14 ++++++++++++++
>  3 files changed, 18 insertions(+), 3 deletions(-)
>  create mode 100644 gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c
>
> diff --git a/gcc/config/i386/i386-features.cc b/gcc/config/i386/i386-features.cc
> index 4a3b07ae045..92ae08d442e 100644
> --- a/gcc/config/i386/i386-features.cc
> +++ b/gcc/config/i386/i386-features.cc
> @@ -2489,8 +2489,7 @@ public:
>    /* opt_pass methods: */
>    bool gate (function *) final override
>      {
> -      return TARGET_AVX && TARGET_VZEROUPPER
> -       && flag_expensive_optimizations && !optimize_size;
> +      return TARGET_AVX && TARGET_VZEROUPPER;
>      }
>
>    unsigned int execute (function *) final override
> diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
> index 2cb0bddcd35..f76e7c5947b 100644
> --- a/gcc/config/i386/i386-options.cc
> +++ b/gcc/config/i386/i386-options.cc
> @@ -2727,7 +2727,9 @@ ix86_option_override_internal (bool main_args_p,
>      sorry ("%<-mcall-ms2sysv-xlogues%> isn%'t currently supported with SEH");
>
>    if (!(opts_set->x_target_flags & MASK_VZEROUPPER)
> -      && TARGET_EMIT_VZEROUPPER)
> +      && TARGET_EMIT_VZEROUPPER
> +      && flag_expensive_optimizations
> +      && !optimize_size)
>      opts->x_target_flags |= MASK_VZEROUPPER;
>    if (!(opts_set->x_target_flags & MASK_STV))
>      opts->x_target_flags |= MASK_STV;
> diff --git a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c
> new file mode 100644
> index 00000000000..4af637757f7
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c
> @@ -0,0 +1,14 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O0 -mavx -mtune=generic -mvzeroupper -dp" } */
> +
> +#include <immintrin.h>
> +
> +extern __m256 x, y;
> +
> +void
> +foo ()
> +{
> +  x = y;
> +}
> +
> +/* { dg-final { scan-assembler-times "avx_vzeroupper" 1 } } */
> --
> 2.39.1.388.g2fc9e9ca3c
>
Hongtao Liu June 27, 2023, 6:08 a.m. UTC | #2 
On Tue, Jun 27, 2023 at 2:05 PM Uros Bizjak <ubizjak@gmail.com> wrote:
>
> On Tue, Jun 27, 2023 at 7:55 AM liuhongt <hongtao.liu@intel.com> wrote:
> >
> > pass_insert_vzeroupper is under condition
> >
> > TARGET_AVX && TARGET_VZEROUPPER
> > && flag_expensive_optimizations && !optimize_size
> >
> > But the document of mvzeroupper doesn't mention the insertion
> > required -O2 and above, it may confuse users when they explicitly
> > use -Os -mvzeroupper.
> >
> > ------------
> > mvzeroupper
> > Target Mask(VZEROUPPER) Save
> > Generate vzeroupper instruction before a transfer of control flow out of
> > the function.
> > ------------
> >
> > The patch moves flag_expensive_optimizations && !optimize_size to
> > ix86_option_override_internal. It makes -mvzeroupper independent of
> > optimization level, but still keeps the behavior of architecture
> > tuning(emit_vzeroupper) unchanged.
> >
> > Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
> > Ok for trunk?
> >
> > gcc/ChangeLog:
> >
> >         * config/i386/i386-features.cc (pass_insert_vzeroupper:gate):
> >         Move flag_expensive_optimizations && !optimize_size to ..
> >         * config/i386/i386-options.cc (ix86_option_override_internal):
> >         .. this, it makes -mvzeroupper independent of optimization
> >         level, but still keeps the behavior of architecture
> >         tuning(emit_vzeroupper) unchanged.
> >
> > gcc/testsuite/ChangeLog:
> >
> >         * gcc.target/i386/avx-vzeroupper-29.c: New testcase.
>
> OK.
I'd like to backport this patch to GCC10/GCC11/GCC12/GCC13.
>
> Thanks,
> Uros.
>
> > ---
> >  gcc/config/i386/i386-features.cc                  |  3 +--
> >  gcc/config/i386/i386-options.cc                   |  4 +++-
> >  gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c | 14 ++++++++++++++
> >  3 files changed, 18 insertions(+), 3 deletions(-)
> >  create mode 100644 gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c
> >
> > diff --git a/gcc/config/i386/i386-features.cc b/gcc/config/i386/i386-features.cc
> > index 4a3b07ae045..92ae08d442e 100644
> > --- a/gcc/config/i386/i386-features.cc
> > +++ b/gcc/config/i386/i386-features.cc
> > @@ -2489,8 +2489,7 @@ public:
> >    /* opt_pass methods: */
> >    bool gate (function *) final override
> >      {
> > -      return TARGET_AVX && TARGET_VZEROUPPER
> > -       && flag_expensive_optimizations && !optimize_size;
> > +      return TARGET_AVX && TARGET_VZEROUPPER;
> >      }
> >
> >    unsigned int execute (function *) final override
> > diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
> > index 2cb0bddcd35..f76e7c5947b 100644
> > --- a/gcc/config/i386/i386-options.cc
> > +++ b/gcc/config/i386/i386-options.cc
> > @@ -2727,7 +2727,9 @@ ix86_option_override_internal (bool main_args_p,
> >      sorry ("%<-mcall-ms2sysv-xlogues%> isn%'t currently supported with SEH");
> >
> >    if (!(opts_set->x_target_flags & MASK_VZEROUPPER)
> > -      && TARGET_EMIT_VZEROUPPER)
> > +      && TARGET_EMIT_VZEROUPPER
> > +      && flag_expensive_optimizations
> > +      && !optimize_size)
> >      opts->x_target_flags |= MASK_VZEROUPPER;
> >    if (!(opts_set->x_target_flags & MASK_STV))
> >      opts->x_target_flags |= MASK_STV;
> > diff --git a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c
> > new file mode 100644
> > index 00000000000..4af637757f7
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c
> > @@ -0,0 +1,14 @@
> > +/* { dg-do compile } */
> > +/* { dg-options "-O0 -mavx -mtune=generic -mvzeroupper -dp" } */
> > +
> > +#include <immintrin.h>
> > +
> > +extern __m256 x, y;
> > +
> > +void
> > +foo ()
> > +{
> > +  x = y;
> > +}
> > +
> > +/* { dg-final { scan-assembler-times "avx_vzeroupper" 1 } } */
> > --
> > 2.39.1.388.g2fc9e9ca3c
> >
Uros Bizjak June 27, 2023, 6:11 a.m. UTC | #3 
On Tue, Jun 27, 2023 at 8:09 AM Hongtao Liu <crazylht@gmail.com> wrote:
>
> On Tue, Jun 27, 2023 at 2:05 PM Uros Bizjak <ubizjak@gmail.com> wrote:
> >
> > On Tue, Jun 27, 2023 at 7:55 AM liuhongt <hongtao.liu@intel.com> wrote:
> > >
> > > pass_insert_vzeroupper is under condition
> > >
> > > TARGET_AVX && TARGET_VZEROUPPER
> > > && flag_expensive_optimizations && !optimize_size
> > >
> > > But the document of mvzeroupper doesn't mention the insertion
> > > required -O2 and above, it may confuse users when they explicitly
> > > use -Os -mvzeroupper.
> > >
> > > ------------
> > > mvzeroupper
> > > Target Mask(VZEROUPPER) Save
> > > Generate vzeroupper instruction before a transfer of control flow out of
> > > the function.
> > > ------------
> > >
> > > The patch moves flag_expensive_optimizations && !optimize_size to
> > > ix86_option_override_internal. It makes -mvzeroupper independent of
> > > optimization level, but still keeps the behavior of architecture
> > > tuning(emit_vzeroupper) unchanged.
> > >
> > > Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
> > > Ok for trunk?
> > >
> > > gcc/ChangeLog:
> > >
> > >         * config/i386/i386-features.cc (pass_insert_vzeroupper:gate):
> > >         Move flag_expensive_optimizations && !optimize_size to ..
> > >         * config/i386/i386-options.cc (ix86_option_override_internal):
> > >         .. this, it makes -mvzeroupper independent of optimization
> > >         level, but still keeps the behavior of architecture
> > >         tuning(emit_vzeroupper) unchanged.
> > >
> > > gcc/testsuite/ChangeLog:
> > >
> > >         * gcc.target/i386/avx-vzeroupper-29.c: New testcase.
> >
> > OK.
> I'd like to backport this patch to GCC10/GCC11/GCC12/GCC13.

Also OK.

Thanks,
Uros.

> >
> > Thanks,
> > Uros.
> >
> > > ---
> > >  gcc/config/i386/i386-features.cc                  |  3 +--
> > >  gcc/config/i386/i386-options.cc                   |  4 +++-
> > >  gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c | 14 ++++++++++++++
> > >  3 files changed, 18 insertions(+), 3 deletions(-)
> > >  create mode 100644 gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c
> > >
> > > diff --git a/gcc/config/i386/i386-features.cc b/gcc/config/i386/i386-features.cc
> > > index 4a3b07ae045..92ae08d442e 100644
> > > --- a/gcc/config/i386/i386-features.cc
> > > +++ b/gcc/config/i386/i386-features.cc
> > > @@ -2489,8 +2489,7 @@ public:
> > >    /* opt_pass methods: */
> > >    bool gate (function *) final override
> > >      {
> > > -      return TARGET_AVX && TARGET_VZEROUPPER
> > > -       && flag_expensive_optimizations && !optimize_size;
> > > +      return TARGET_AVX && TARGET_VZEROUPPER;
> > >      }
> > >
> > >    unsigned int execute (function *) final override
> > > diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
> > > index 2cb0bddcd35..f76e7c5947b 100644
> > > --- a/gcc/config/i386/i386-options.cc
> > > +++ b/gcc/config/i386/i386-options.cc
> > > @@ -2727,7 +2727,9 @@ ix86_option_override_internal (bool main_args_p,
> > >      sorry ("%<-mcall-ms2sysv-xlogues%> isn%'t currently supported with SEH");
> > >
> > >    if (!(opts_set->x_target_flags & MASK_VZEROUPPER)
> > > -      && TARGET_EMIT_VZEROUPPER)
> > > +      && TARGET_EMIT_VZEROUPPER
> > > +      && flag_expensive_optimizations
> > > +      && !optimize_size)
> > >      opts->x_target_flags |= MASK_VZEROUPPER;
> > >    if (!(opts_set->x_target_flags & MASK_STV))
> > >      opts->x_target_flags |= MASK_STV;
> > > diff --git a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c
> > > new file mode 100644
> > > index 00000000000..4af637757f7
> > > --- /dev/null
> > > +++ b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c
> > > @@ -0,0 +1,14 @@
> > > +/* { dg-do compile } */
> > > +/* { dg-options "-O0 -mavx -mtune=generic -mvzeroupper -dp" } */
> > > +
> > > +#include <immintrin.h>
> > > +
> > > +extern __m256 x, y;
> > > +
> > > +void
> > > +foo ()
> > > +{
> > > +  x = y;
> > > +}
> > > +
> > > +/* { dg-final { scan-assembler-times "avx_vzeroupper" 1 } } */
> > > --
> > > 2.39.1.388.g2fc9e9ca3c
> > >
>
>
>
> --
> BR,
> Hongtao
diff mbox series

Patch

diff --git a/gcc/config/i386/i386-features.cc b/gcc/config/i386/i386-features.cc
index 4a3b07ae045..92ae08d442e 100644
--- a/gcc/config/i386/i386-features.cc
+++ b/gcc/config/i386/i386-features.cc
@@ -2489,8 +2489,7 @@  public:
   /* opt_pass methods: */
   bool gate (function *) final override
     {
-      return TARGET_AVX && TARGET_VZEROUPPER
-	&& flag_expensive_optimizations && !optimize_size;
+      return TARGET_AVX && TARGET_VZEROUPPER;
     }
 
   unsigned int execute (function *) final override
diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
index 2cb0bddcd35..f76e7c5947b 100644
--- a/gcc/config/i386/i386-options.cc
+++ b/gcc/config/i386/i386-options.cc
@@ -2727,7 +2727,9 @@  ix86_option_override_internal (bool main_args_p,
     sorry ("%<-mcall-ms2sysv-xlogues%> isn%'t currently supported with SEH");
 
   if (!(opts_set->x_target_flags & MASK_VZEROUPPER)
-      && TARGET_EMIT_VZEROUPPER)
+      && TARGET_EMIT_VZEROUPPER
+      && flag_expensive_optimizations
+      && !optimize_size)
     opts->x_target_flags |= MASK_VZEROUPPER;
   if (!(opts_set->x_target_flags & MASK_STV))
     opts->x_target_flags |= MASK_STV;
diff --git a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c
new file mode 100644
index 00000000000..4af637757f7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c
@@ -0,0 +1,14 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O0 -mavx -mtune=generic -mvzeroupper -dp" } */
+
+#include <immintrin.h>
+
+extern __m256 x, y;
+
+void
+foo ()
+{
+  x = y;
+}
+
+/* { dg-final { scan-assembler-times "avx_vzeroupper" 1 } } */