diff mbox series

[1/2] Don't issue vzeroupper for vzeroupper call_insn.

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

Commit Message

Liu, Hongtao June 27, 2023, 5:53 a.m. UTC 
Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
Ok for trunk?

gcc/ChangeLog:

	PR target/82735
	* config/i386/i386.cc (ix86_avx_u127_mode_needed): Don't emit
	vzeroupper for vzeroupper call_insn.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/avx-vzeroupper-30.c: New test.
---
 gcc/config/i386/i386.cc                           |  5 +++--
 gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c | 15 +++++++++++++++
 2 files changed, 18 insertions(+), 2 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c

Comments

Uros Bizjak June 27, 2023, 6:04 a.m. UTC | #1 
On Tue, Jun 27, 2023 at 7:55 AM liuhongt <hongtao.liu@intel.com> wrote:
>
> Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
> Ok for trunk?
>
> gcc/ChangeLog:
>
>         PR target/82735
>         * config/i386/i386.cc (ix86_avx_u127_mode_needed): Don't emit
>         vzeroupper for vzeroupper call_insn.
>
> gcc/testsuite/ChangeLog:
>
>         * gcc.target/i386/avx-vzeroupper-30.c: New test.
> ---
>  gcc/config/i386/i386.cc                           |  5 +++--
>  gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c | 15 +++++++++++++++
>  2 files changed, 18 insertions(+), 2 deletions(-)
>  create mode 100644 gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c
>
> diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
> index 0761965344b..caca74d6dec 100644
> --- a/gcc/config/i386/i386.cc
> +++ b/gcc/config/i386/i386.cc
> @@ -14489,8 +14489,9 @@ ix86_avx_u128_mode_needed (rtx_insn *insn)
>          modes wider than 256 bits.  It's only safe to issue a
>          vzeroupper if all SSE registers are clobbered.  */
>        const function_abi &abi = insn_callee_abi (insn);
> -      if (!hard_reg_set_subset_p (reg_class_contents[SSE_REGS],
> -                                 abi.mode_clobbers (V4DImode)))
> +      if (vzeroupper_pattern (PATTERN (insn), VOIDmode)
> +         || !hard_reg_set_subset_p (reg_class_contents[SSE_REGS],
> +                                    abi.mode_clobbers (V4DImode)))
>         return AVX_U128_ANY;

You also want to check for vzeroall_pattern here.

OK with the above change.

Thanks,
Uros.

>
>        return AVX_U128_CLEAN;
> diff --git a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c
> new file mode 100644
> index 00000000000..c1c9baa8fc4
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c
> @@ -0,0 +1,15 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -mavx -mvzeroupper -dp" } */
> +
> +#include <immintrin.h>
> +
> +extern __m256 x, y;
> +
> +void
> +foo ()
> +{
> +  x = y;
> +  _mm256_zeroupper ();
> +}
> +
> +/* { dg-final { scan-assembler-times "avx_vzeroupper" 1 } } */
> --
> 2.39.1.388.g2fc9e9ca3c
>
Hongtao Liu June 27, 2023, 6:07 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:
> >
> > Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
> > Ok for trunk?
> >
> > gcc/ChangeLog:
> >
> >         PR target/82735
> >         * config/i386/i386.cc (ix86_avx_u127_mode_needed): Don't emit
> >         vzeroupper for vzeroupper call_insn.
> >
> > gcc/testsuite/ChangeLog:
> >
> >         * gcc.target/i386/avx-vzeroupper-30.c: New test.
> > ---
> >  gcc/config/i386/i386.cc                           |  5 +++--
> >  gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c | 15 +++++++++++++++
> >  2 files changed, 18 insertions(+), 2 deletions(-)
> >  create mode 100644 gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c
> >
> > diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
> > index 0761965344b..caca74d6dec 100644
> > --- a/gcc/config/i386/i386.cc
> > +++ b/gcc/config/i386/i386.cc
> > @@ -14489,8 +14489,9 @@ ix86_avx_u128_mode_needed (rtx_insn *insn)
> >          modes wider than 256 bits.  It's only safe to issue a
> >          vzeroupper if all SSE registers are clobbered.  */
> >        const function_abi &abi = insn_callee_abi (insn);
> > -      if (!hard_reg_set_subset_p (reg_class_contents[SSE_REGS],
> > -                                 abi.mode_clobbers (V4DImode)))
> > +      if (vzeroupper_pattern (PATTERN (insn), VOIDmode)
> > +         || !hard_reg_set_subset_p (reg_class_contents[SSE_REGS],
> > +                                    abi.mode_clobbers (V4DImode)))
> >         return AVX_U128_ANY;
>
> You also want to check for vzeroall_pattern here.
This is inside
 if (CALL_P (insn))

vzeroupper is defined as special call_insn, but vzeroall is not.
>
> OK with the above change.
>
> Thanks,
> Uros.
>
> >
> >        return AVX_U128_CLEAN;
> > diff --git a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c
> > new file mode 100644
> > index 00000000000..c1c9baa8fc4
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c
> > @@ -0,0 +1,15 @@
> > +/* { dg-do compile } */
> > +/* { dg-options "-O2 -mavx -mvzeroupper -dp" } */
> > +
> > +#include <immintrin.h>
> > +
> > +extern __m256 x, y;
> > +
> > +void
> > +foo ()
> > +{
> > +  x = y;
> > +  _mm256_zeroupper ();
> > +}
> > +
> > +/* { 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 8:08 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:
> > >
> > > Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
> > > Ok for trunk?
> > >
> > > gcc/ChangeLog:
> > >
> > >         PR target/82735
> > >         * config/i386/i386.cc (ix86_avx_u127_mode_needed): Don't emit
> > >         vzeroupper for vzeroupper call_insn.
> > >
> > > gcc/testsuite/ChangeLog:
> > >
> > >         * gcc.target/i386/avx-vzeroupper-30.c: New test.
> > > ---
> > >  gcc/config/i386/i386.cc                           |  5 +++--
> > >  gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c | 15 +++++++++++++++
> > >  2 files changed, 18 insertions(+), 2 deletions(-)
> > >  create mode 100644 gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c
> > >
> > > diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
> > > index 0761965344b..caca74d6dec 100644
> > > --- a/gcc/config/i386/i386.cc
> > > +++ b/gcc/config/i386/i386.cc
> > > @@ -14489,8 +14489,9 @@ ix86_avx_u128_mode_needed (rtx_insn *insn)
> > >          modes wider than 256 bits.  It's only safe to issue a
> > >          vzeroupper if all SSE registers are clobbered.  */
> > >        const function_abi &abi = insn_callee_abi (insn);
> > > -      if (!hard_reg_set_subset_p (reg_class_contents[SSE_REGS],
> > > -                                 abi.mode_clobbers (V4DImode)))
> > > +      if (vzeroupper_pattern (PATTERN (insn), VOIDmode)
> > > +         || !hard_reg_set_subset_p (reg_class_contents[SSE_REGS],
> > > +                                    abi.mode_clobbers (V4DImode)))
> > >         return AVX_U128_ANY;
> >
> > You also want to check for vzeroall_pattern here.
> This is inside
>  if (CALL_P (insn))
>
> vzeroupper is defined as special call_insn, but vzeroall is not.

Indeed. Patch is OK as it is then.

Thanks,
Uros.

> >
> > OK with the above change.
> >
> > Thanks,
> > Uros.
> >
> > >
> > >        return AVX_U128_CLEAN;
> > > diff --git a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c
> > > new file mode 100644
> > > index 00000000000..c1c9baa8fc4
> > > --- /dev/null
> > > +++ b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c
> > > @@ -0,0 +1,15 @@
> > > +/* { dg-do compile } */
> > > +/* { dg-options "-O2 -mavx -mvzeroupper -dp" } */
> > > +
> > > +#include <immintrin.h>
> > > +
> > > +extern __m256 x, y;
> > > +
> > > +void
> > > +foo ()
> > > +{
> > > +  x = y;
> > > +  _mm256_zeroupper ();
> > > +}
> > > +
> > > +/* { 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.cc b/gcc/config/i386/i386.cc
index 0761965344b..caca74d6dec 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -14489,8 +14489,9 @@  ix86_avx_u128_mode_needed (rtx_insn *insn)
 	 modes wider than 256 bits.  It's only safe to issue a
 	 vzeroupper if all SSE registers are clobbered.  */
       const function_abi &abi = insn_callee_abi (insn);
-      if (!hard_reg_set_subset_p (reg_class_contents[SSE_REGS],
-				  abi.mode_clobbers (V4DImode)))
+      if (vzeroupper_pattern (PATTERN (insn), VOIDmode)
+	  || !hard_reg_set_subset_p (reg_class_contents[SSE_REGS],
+				     abi.mode_clobbers (V4DImode)))
 	return AVX_U128_ANY;
 
       return AVX_U128_CLEAN;
diff --git a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c
new file mode 100644
index 00000000000..c1c9baa8fc4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-30.c
@@ -0,0 +1,15 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx -mvzeroupper -dp" } */
+
+#include <immintrin.h>
+
+extern __m256 x, y;
+
+void
+foo ()
+{
+  x = y;
+  _mm256_zeroupper ();
+}
+
+/* { dg-final { scan-assembler-times "avx_vzeroupper" 1 } } */