On Sun, Feb 20, 2022 at 6:01 PM Hongtao Liu <crazy...@gmail.com> wrote:
>
> On Thu, Feb 17, 2022 at 9:56 PM H.J. Lu <hjl.to...@gmail.com> wrote:
> >
> > On Thu, Feb 17, 2022 at 08:51:31AM +0100, Uros Bizjak wrote:
> > > On Thu, Feb 17, 2022 at 6:25 AM Hongtao Liu via Gcc-patches
> > > <gcc-patches@gcc.gnu.org> wrote:
> > > >
> > > > On Thu, Feb 17, 2022 at 12:26 PM H.J. Lu via Gcc-patches
> > > > <gcc-patches@gcc.gnu.org> wrote:
> > > > >
> > > > > Reading YMM registers with all zero bits needs VZEROUPPER on Sandy
> > > > > Bride,
> > > > > Ivy Bridge, Haswell, Broadwell and Alder Lake to avoid SSE <-> AVX
> > > > > transition penalty. Add TARGET_READ_ZERO_YMM_ZMM_NEED_VZEROUPPER to
> > > > > generate vzeroupper instruction after loading all-zero YMM/YMM
> > > > > registers
> > > > > and enable it by default.
> > > > Shouldn't TARGET_READ_ZERO_YMM_ZMM_NONEED_VZEROUPPER sounds a bit
> > > > smoother?
> > > > Because originally we needed to add vzeroupper to all avx<->sse cases,
> > > > now it's a tune to indicate that we don't need to add it in some
> > >
> > > Perhaps we should go from the other side and use
> > > X86_TUNE_OPTIMIZE_AVX_READ for new processors?
> > >
> >
> > Here is the v2 patch to add TARGET_OMIT_VZEROUPPER_AFTER_AVX_READ_ZERO.
> >
> The patch LGTM in general, but please rebase against
> https://gcc.gnu.org/pipermail/gcc-patches/2022-February/590541.html
> and resend the patch, also wait a couple days in case Uros(and others)
> have any comments.
I am dropping my patch since it causes the compile-time regression.
> >
> > H.J.
> > ---
> > Reading YMM registers with all zero bits needs VZEROUPPER on Sandy Bride,
> > Ivy Bridge, Haswell, Broadwell and Alder Lake to avoid SSE <-> AVX
> > transition penalty. Add TARGET_OMIT_VZEROUPPER_AFTER_AVX_READ_ZERO to
> > omit vzeroupper instruction after loading all-zero YMM/ZMM registers.
> >
> > gcc/
> >
> > PR target/101456
> > * config/i386/i386.cc (ix86_avx_u128_mode_needed): Omit
> > vzeroupper after reading all-zero YMM/ZMM registers for
> > TARGET_OMIT_VZEROUPPER_AFTER_AVX_READ_ZERO.
> > * config/i386/i386.h (TARGET_OMIT_VZEROUPPER_AFTER_AVX_READ_ZERO):
> > New.
> > * config/i386/x86-tune.def
> > (X86_TUNE_OMIT_VZEROUPPER_AFTER_AVX_READ_ZERO): New.
> >
> > gcc/testsuite/
> >
> > PR target/101456
> > * gcc.target/i386/pr101456-1.c (dg-options): Add
> > -mtune-ctrl=-mtune-ctrl=omit_vzeroupper_after_avx_read_zero.
> > * gcc.target/i386/pr101456-2.c: Likewise.
> > * gcc.target/i386/pr101456-3.c: New test.
> > * gcc.target/i386/pr101456-4.c: Likewise.
> > ---
> > gcc/config/i386/i386.cc | 51 ++++++++++++----------
> > gcc/config/i386/i386.h | 2 +
> > gcc/config/i386/x86-tune.def | 5 +++
> > gcc/testsuite/gcc.target/i386/pr101456-1.c | 2 +-
> > gcc/testsuite/gcc.target/i386/pr101456-2.c | 2 +-
> > gcc/testsuite/gcc.target/i386/pr101456-3.c | 33 ++++++++++++++
> > gcc/testsuite/gcc.target/i386/pr101456-4.c | 33 ++++++++++++++
> > 7 files changed, 103 insertions(+), 25 deletions(-)
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr101456-3.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr101456-4.c
> >
> > diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
> > index cf246e74e57..60c72ceb72d 100644
> > --- a/gcc/config/i386/i386.cc
> > +++ b/gcc/config/i386/i386.cc
> > @@ -14502,33 +14502,38 @@ ix86_avx_u128_mode_needed (rtx_insn *insn)
> >
> > subrtx_iterator::array_type array;
> >
> > - rtx set = single_set (insn);
> > - if (set)
> > + if (TARGET_OMIT_VZEROUPPER_AFTER_AVX_READ_ZERO)
> > {
> > - rtx dest = SET_DEST (set);
> > - rtx src = SET_SRC (set);
> > - if (ix86_check_avx_upper_register (dest))
> > + /* Perform this vzeroupper optimization if target doesn't need
> > + vzeroupper after reading all-zero YMM/YMM registers. */
> > + rtx set = single_set (insn);
> > + if (set)
> > {
> > - /* This is an YMM/ZMM load. Return AVX_U128_DIRTY if the
> > - source isn't zero. */
> > - if (standard_sse_constant_p (src, GET_MODE (dest)) != 1)
> > - return AVX_U128_DIRTY;
> > + rtx dest = SET_DEST (set);
> > + rtx src = SET_SRC (set);
> > + if (ix86_check_avx_upper_register (dest))
> > + {
> > + /* This is an YMM/ZMM load. Return AVX_U128_DIRTY if the
> > + source isn't zero. */
> > + if (standard_sse_constant_p (src, GET_MODE (dest)) != 1)
> > + return AVX_U128_DIRTY;
> > + else
> > + return AVX_U128_ANY;
> > + }
> > else
> > - return AVX_U128_ANY;
> > - }
> > - else
> > - {
> > - FOR_EACH_SUBRTX (iter, array, src, NONCONST)
> > - if (ix86_check_avx_upper_register (*iter))
> > - {
> > - int status = ix86_avx_u128_mode_source (insn, *iter);
> > - if (status == AVX_U128_DIRTY)
> > - return status;
> > - }
> > - }
> > + {
> > + FOR_EACH_SUBRTX (iter, array, src, NONCONST)
> > + if (ix86_check_avx_upper_register (*iter))
> > + {
> > + int status = ix86_avx_u128_mode_source (insn, *iter);
> > + if (status == AVX_U128_DIRTY)
> > + return status;
> > + }
> > + }
> >
> > - /* This isn't YMM/ZMM load/store. */
> > - return AVX_U128_ANY;
> > + /* This isn't YMM/ZMM load/store. */
> > + return AVX_U128_ANY;
> > + }
> > }
> >
> > /* Require DIRTY mode if a 256bit or 512bit AVX register is referenced.
> > diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
> > index f41e0908250..46379d2231b 100644
> > --- a/gcc/config/i386/i386.h
> > +++ b/gcc/config/i386/i386.h
> > @@ -425,6 +425,8 @@ extern unsigned char ix86_tune_features[X86_TUNE_LAST];
> > #define TARGET_AVOID_MFENCE ix86_tune_features[X86_TUNE_AVOID_MFENCE]
> > #define TARGET_EMIT_VZEROUPPER \
> > ix86_tune_features[X86_TUNE_EMIT_VZEROUPPER]
> > +#define TARGET_OMIT_VZEROUPPER_AFTER_AVX_READ_ZERO \
> > + ix86_tune_features[X86_TUNE_OMIT_VZEROUPPER_AFTER_AVX_READ_ZERO]
> > #define TARGET_EXPAND_ABS \
> > ix86_tune_features[X86_TUNE_EXPAND_ABS]
> > #define TARGET_V2DF_REDUCTION_PREFER_HADDPD \
> > diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
> > index 82ca0ae63ac..132de2db2eb 100644
> > --- a/gcc/config/i386/x86-tune.def
> > +++ b/gcc/config/i386/x86-tune.def
> > @@ -649,3 +649,8 @@ DEF_TUNE (X86_TUNE_PROMOTE_QI_REGS, "promote_qi_regs",
> > m_NONE)
> > /* X86_TUNE_EMIT_VZEROUPPER: This enables vzeroupper instruction insertion
> > before a transfer of control flow out of the function. */
> > DEF_TUNE (X86_TUNE_EMIT_VZEROUPPER, "emit_vzeroupper", ~m_KNL)
> > +
> > +/* X86_TUNE_OMIT_VZEROUPPER_AFTER_AVX_READ_ZERO: This omits vzeroupper
> > + instruction after reading all-zero YMM/ZMM registers. */
> > +DEF_TUNE (X86_TUNE_OMIT_VZEROUPPER_AFTER_AVX_READ_ZERO,
> > + "omit_vzeroupper_after_avx_read_zero", 0)
> > diff --git a/gcc/testsuite/gcc.target/i386/pr101456-1.c
> > b/gcc/testsuite/gcc.target/i386/pr101456-1.c
> > index 803fc6e0207..f653197da7c 100644
> > --- a/gcc/testsuite/gcc.target/i386/pr101456-1.c
> > +++ b/gcc/testsuite/gcc.target/i386/pr101456-1.c
> > @@ -1,5 +1,5 @@
> > /* { dg-do compile } */
> > -/* { dg-options "-O2 -march=skylake" } */
> > +/* { dg-options "-O2 -march=skylake
> > -mtune-ctrl=omit_vzeroupper_after_avx_read_zero" } */
> >
> > #include <x86intrin.h>
> >
> > diff --git a/gcc/testsuite/gcc.target/i386/pr101456-2.c
> > b/gcc/testsuite/gcc.target/i386/pr101456-2.c
> > index 554a0f1702c..9aac3ece14d 100644
> > --- a/gcc/testsuite/gcc.target/i386/pr101456-2.c
> > +++ b/gcc/testsuite/gcc.target/i386/pr101456-2.c
> > @@ -1,5 +1,5 @@
> > /* { dg-do compile } */
> > -/* { dg-options "-O2 -march=skylake" } */
> > +/* { dg-options "-O2 -march=skylake
> > -mtune-ctrl=omit_vzeroupper_after_avx_read_zero" } */
> >
> > #include <x86intrin.h>
> >
> > diff --git a/gcc/testsuite/gcc.target/i386/pr101456-3.c
> > b/gcc/testsuite/gcc.target/i386/pr101456-3.c
> > new file mode 100644
> > index 00000000000..8389d18ed6c
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/i386/pr101456-3.c
> > @@ -0,0 +1,33 @@
> > +/* { dg-do compile } */
> > +/* { dg-options "-O2 -march=skylake -mtune=alderlake" } */
> > +
> > +#include <x86intrin.h>
> > +
> > +extern __m256 x1;
> > +extern __m256d x2;
> > +extern __m256i x3;
> > +
> > +extern void bar (void);
> > +
> > +void
> > +foo1 (void)
> > +{
> > + x1 = _mm256_setzero_ps ();
> > + bar ();
> > +}
> > +
> > +void
> > +foo2 (void)
> > +{
> > + x2 = _mm256_setzero_pd ();
> > + bar ();
> > +}
> > +
> > +void
> > +foo3 (void)
> > +{
> > + x3 = _mm256_setzero_si256 ();
> > + bar ();
> > +}
> > +
> > +/* { dg-final { scan-assembler-times "vzeroupper" 3 } } */
> > diff --git a/gcc/testsuite/gcc.target/i386/pr101456-4.c
> > b/gcc/testsuite/gcc.target/i386/pr101456-4.c
> > new file mode 100644
> > index 00000000000..3e4cdcc4d28
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/i386/pr101456-4.c
> > @@ -0,0 +1,33 @@
> > +/* { dg-do compile } */
> > +/* { dg-options "-O2 -march=haswell" } */
> > +
> > +#include <x86intrin.h>
> > +
> > +extern __m256 x1;
> > +extern __m256d x2;
> > +extern __m256i x3;
> > +
> > +extern void bar (void);
> > +
> > +void
> > +foo1 (void)
> > +{
> > + x1 = _mm256_setzero_ps ();
> > + bar ();
> > +}
> > +
> > +void
> > +foo2 (void)
> > +{
> > + x2 = _mm256_setzero_pd ();
> > + bar ();
> > +}
> > +
> > +void
> > +foo3 (void)
> > +{
> > + x3 = _mm256_setzero_si256 ();
> > + bar ();
> > +}
> > +
> > +/* { dg-final { scan-assembler-times "vzeroupper" 3 } } */
> > --
> > 2.35.1
> >
>
>
> --
> BR,
> Hongtao
--
H.J.
