[PATCH] Align ix86_{move_max,store_max} with vectorizer.
Hongtao Liu
crazylht@gmail.com
Wed Aug 21 09:24:52 GMT 2024
On Wed, Aug 21, 2024 at 4:49 PM Richard Biener
<richard.guenther@gmail.com> wrote:
>
> On Wed, Aug 21, 2024 at 7:40 AM liuhongt <hongtao.liu@intel.com> wrote:
> >
> > When none of mprefer-vector-width, avx256_optimal/avx128_optimal,
> > avx256_store_by_pieces/avx512_store_by_pieces is specified, GCC will
> > set ix86_{move_max,store_max} as max available vector length except
> > for AVX part.
> >
> > if (TARGET_AVX512F_P (opts->x_ix86_isa_flags)
> > && TARGET_EVEX512_P (opts->x_ix86_isa_flags2))
> > opts->x_ix86_move_max = PVW_AVX512;
> > else
> > opts->x_ix86_move_max = PVW_AVX128;
> >
> > So for -mavx2, vectorizer will choose 256-bit for vectorization, but
> > 128-bit is used for struct copy, there could be a potential STLF issue
> > due to this "misalign".
> >
> > The patch fixes that and improved 538.imagick_r by ~30% for -march=x86-64-v3 -O2.
> > Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
> > Any comments?
>
> Should we look at the avx128_optimal tune and/or avx256_split_regs and
> avx256_optimal
> also for 512? Because IIRC the vectorizers default looks at that as
> well (OTOH larger
> stores should be fine for STLF).
For Double Pumped processors, i.e. SRF, there's no STLF issue for
128-bit store and 256-bit load since the 256-bit load is teared down
to 2 128-bit load.
I guess it should be similar for Znver1/Znve4, so it should be fine
with the mismatch between struct copy and vectorizer size.
One exception is that we use 256-bit for vectorization and 512-bit for
struct copy on SPR, it could be an issue when the struct copy is after
the vectorization.
But I didn't observe any cases yet, and for not-STLF-stall case,
512-bit copy should be better than 256-bit copy on SPR, So I'll leave
it there.(There's a plan to enable 512-bit vectorization for SPR by
default, it's ongoing).
>
> > gcc/ChangeLog:
> >
> > * config/i386/i386-options.cc (ix86_option_override_internal):
> > set ix86_{move_max,store_max} to PVW_AVX256 when TARGET_AVX
> > instead of PVW_AVX128.
> >
> > gcc/testsuite/ChangeLog:
> > * gcc.target/i386/pieces-memcpy-10.c: Add -mprefer-vector-width=128.
> > * gcc.target/i386/pieces-memcpy-6.c: Ditto.
> > * gcc.target/i386/pieces-memset-38.c: Ditto.
> > * gcc.target/i386/pieces-memset-40.c: Ditto.
> > * gcc.target/i386/pieces-memset-41.c: Ditto.
> > * gcc.target/i386/pieces-memset-42.c: Ditto.
> > * gcc.target/i386/pieces-memset-43.c: Ditto.
> > * gcc.target/i386/pieces-strcpy-2.c: Ditto.
> > * gcc.target/i386/pieces-memcpy-22.c: New test.
> > * gcc.target/i386/pieces-memset-51.c: New test.
> > * gcc.target/i386/pieces-strcpy-3.c: New test.
> > ---
> > gcc/config/i386/i386-options.cc | 6 ++++++
> > gcc/testsuite/gcc.target/i386/pieces-memcpy-10.c | 2 +-
> > gcc/testsuite/gcc.target/i386/pieces-memcpy-22.c | 12 ++++++++++++
> > gcc/testsuite/gcc.target/i386/pieces-memcpy-6.c | 2 +-
> > gcc/testsuite/gcc.target/i386/pieces-memset-38.c | 2 +-
> > gcc/testsuite/gcc.target/i386/pieces-memset-40.c | 2 +-
> > gcc/testsuite/gcc.target/i386/pieces-memset-41.c | 2 +-
> > gcc/testsuite/gcc.target/i386/pieces-memset-42.c | 2 +-
> > gcc/testsuite/gcc.target/i386/pieces-memset-43.c | 2 +-
> > gcc/testsuite/gcc.target/i386/pieces-memset-51.c | 12 ++++++++++++
> > gcc/testsuite/gcc.target/i386/pieces-strcpy-2.c | 2 +-
> > gcc/testsuite/gcc.target/i386/pieces-strcpy-3.c | 15 +++++++++++++++
> > 12 files changed, 53 insertions(+), 8 deletions(-)
> > create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memcpy-22.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-51.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pieces-strcpy-3.c
> >
> > diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
> > index f423455b363..f79257cc764 100644
> > --- a/gcc/config/i386/i386-options.cc
> > +++ b/gcc/config/i386/i386-options.cc
> > @@ -3023,6 +3023,9 @@ ix86_option_override_internal (bool main_args_p,
> > if (TARGET_AVX512F_P (opts->x_ix86_isa_flags)
> > && TARGET_EVEX512_P (opts->x_ix86_isa_flags2))
> > opts->x_ix86_move_max = PVW_AVX512;
> > + /* Align with vectorizer to avoid potential STLF issue. */
> > + else if (TARGET_AVX_P (opts->x_ix86_isa_flags))
> > + opts->x_ix86_move_max = PVW_AVX256;
> > else
> > opts->x_ix86_move_max = PVW_AVX128;
> > }
> > @@ -3047,6 +3050,9 @@ ix86_option_override_internal (bool main_args_p,
> > if (TARGET_AVX512F_P (opts->x_ix86_isa_flags)
> > && TARGET_EVEX512_P (opts->x_ix86_isa_flags2))
> > opts->x_ix86_store_max = PVW_AVX512;
> > + /* Align with vectorizer to avoid potential STLF issue. */
> > + else if (TARGET_AVX_P (opts->x_ix86_isa_flags))
> > + opts->x_ix86_store_max = PVW_AVX256;
> > else
> > opts->x_ix86_store_max = PVW_AVX128;
> > }
> > diff --git a/gcc/testsuite/gcc.target/i386/pieces-memcpy-10.c b/gcc/testsuite/gcc.target/i386/pieces-memcpy-10.c
> > index 5faee21f9b9..53ad0b3be44 100644
> > --- a/gcc/testsuite/gcc.target/i386/pieces-memcpy-10.c
> > +++ b/gcc/testsuite/gcc.target/i386/pieces-memcpy-10.c
> > @@ -1,5 +1,5 @@
> > /* { dg-do compile } */
> > -/* { dg-options "-O2 -mno-avx2 -mavx -mtune=sandybridge" } */
> > +/* { dg-options "-O2 -mno-avx2 -mavx -mprefer-vector-width=128 -mtune=sandybridge" } */
> >
> > extern char *dst, *src;
> >
> > diff --git a/gcc/testsuite/gcc.target/i386/pieces-memcpy-22.c b/gcc/testsuite/gcc.target/i386/pieces-memcpy-22.c
> > new file mode 100644
> > index 00000000000..605b3623ffc
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/i386/pieces-memcpy-22.c
> > @@ -0,0 +1,12 @@
> > +/* { dg-do compile { target { ! ia32 } } } */
> > +/* { dg-options "-O2 -mno-avx2 -mavx -mtune=generic" } */
> > +
> > +extern char *dst, *src;
> > +
> > +void
> > +foo (void)
> > +{
> > + __builtin_memcpy (dst, src, 33);
> > +}
> > +
> > +/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 2 } } */
> > diff --git a/gcc/testsuite/gcc.target/i386/pieces-memcpy-6.c b/gcc/testsuite/gcc.target/i386/pieces-memcpy-6.c
> > index 5f99cc98c47..cfd2a86cf33 100644
> > --- a/gcc/testsuite/gcc.target/i386/pieces-memcpy-6.c
> > +++ b/gcc/testsuite/gcc.target/i386/pieces-memcpy-6.c
> > @@ -1,5 +1,5 @@
> > /* { dg-do compile { target { ! ia32 } } } */
> > -/* { dg-options "-O2 -mno-avx2 -mavx -mtune=sandybridge" } */
> > +/* { dg-options "-O2 -mno-avx2 -mavx -mprefer-vector-width=128 -mtune=sandybridge" } */
> >
> > extern char *dst, *src;
> >
> > diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-38.c b/gcc/testsuite/gcc.target/i386/pieces-memset-38.c
> > index ed4a24a54fd..ddd194debd5 100644
> > --- a/gcc/testsuite/gcc.target/i386/pieces-memset-38.c
> > +++ b/gcc/testsuite/gcc.target/i386/pieces-memset-38.c
> > @@ -1,5 +1,5 @@
> > /* { dg-do compile } */
> > -/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune=sandybridge" } */
> > +/* { dg-options "-O2 -mno-avx512f -mavx2 -mprefer-vector-width=128 -mtune=sandybridge" } */
> >
> > extern char *dst;
> >
> > diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-40.c b/gcc/testsuite/gcc.target/i386/pieces-memset-40.c
> > index 86358c99a83..5878876550c 100644
> > --- a/gcc/testsuite/gcc.target/i386/pieces-memset-40.c
> > +++ b/gcc/testsuite/gcc.target/i386/pieces-memset-40.c
> > @@ -1,5 +1,5 @@
> > /* { dg-do compile } */
> > -/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune=sandybridge" } */
> > +/* { dg-options "-O2 -mno-avx512f -mavx2 -mprefer-vector-width=128 -mtune=sandybridge" } */
> > /* Cope with --enable-frame-pointer, Solaris/x86 -mstackrealign default. */
> > /* { dg-additional-options "-fomit-frame-pointer -mno-stackrealign" } */
> >
> > diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-41.c b/gcc/testsuite/gcc.target/i386/pieces-memset-41.c
> > index d7a27f52983..27a6c8ad139 100644
> > --- a/gcc/testsuite/gcc.target/i386/pieces-memset-41.c
> > +++ b/gcc/testsuite/gcc.target/i386/pieces-memset-41.c
> > @@ -1,5 +1,5 @@
> > /* { dg-do compile } */
> > -/* { dg-options "-O2 -mno-avx2 -mavx -mtune=sandybridge -mno-stackrealign" } */
> > +/* { dg-options "-O2 -mno-avx2 -mavx -mprefer-vector-width=128 -mtune=sandybridge -mno-stackrealign" } */
> > /* Cope with --enable-frame-pointer. */
> > /* { dg-additional-options "-fomit-frame-pointer" } */
> >
> > diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-42.c b/gcc/testsuite/gcc.target/i386/pieces-memset-42.c
> > index df0c122aae7..103da699ae5 100644
> > --- a/gcc/testsuite/gcc.target/i386/pieces-memset-42.c
> > +++ b/gcc/testsuite/gcc.target/i386/pieces-memset-42.c
> > @@ -1,5 +1,5 @@
> > /* { dg-do compile } */
> > -/* { dg-options "-O2 -mno-avx2 -mavx -mtune=sandybridge" } */
> > +/* { dg-options "-O2 -mno-avx2 -mavx -mprefer-vector-width=128 -mtune=sandybridge" } */
> >
> > extern char *dst;
> >
> > diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-43.c b/gcc/testsuite/gcc.target/i386/pieces-memset-43.c
> > index 2f2179c2df9..f1494e17610 100644
> > --- a/gcc/testsuite/gcc.target/i386/pieces-memset-43.c
> > +++ b/gcc/testsuite/gcc.target/i386/pieces-memset-43.c
> > @@ -1,5 +1,5 @@
> > /* { dg-do compile } */
> > -/* { dg-options "-O2 -mno-avx2 -mavx -mtune=sandybridge" } */
> > +/* { dg-options "-O2 -mno-avx2 -mavx -mprefer-vector-width=128 -mtune=sandybridge" } */
> >
> > extern char *dst;
> >
> > diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-51.c b/gcc/testsuite/gcc.target/i386/pieces-memset-51.c
> > new file mode 100644
> > index 00000000000..192ec0d1647
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/i386/pieces-memset-51.c
> > @@ -0,0 +1,12 @@
> > +/* { dg-do compile } */
> > +/* { dg-options "-O2 -mno-avx2 -mavx -mtune=generic" } */
> > +
> > +extern char *dst;
> > +
> > +void
> > +foo (int x)
> > +{
> > + __builtin_memset (dst, x, 64);
> > +}
> > +
> > +/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 2 } } */
> > diff --git a/gcc/testsuite/gcc.target/i386/pieces-strcpy-2.c b/gcc/testsuite/gcc.target/i386/pieces-strcpy-2.c
> > index 90446edb4f3..9bb94b7419b 100644
> > --- a/gcc/testsuite/gcc.target/i386/pieces-strcpy-2.c
> > +++ b/gcc/testsuite/gcc.target/i386/pieces-strcpy-2.c
> > @@ -1,5 +1,5 @@
> > /* { dg-do compile { target { ! ia32 } } } */
> > -/* { dg-options "-O2 -mno-avx2 -mavx -mtune=sandybridge" } */
> > +/* { dg-options "-O2 -mno-avx2 -mavx -mprefer-vector-width=128 -mtune=sandybridge" } */
> >
> > extern char *strcpy (char *, const char *);
> >
> > diff --git a/gcc/testsuite/gcc.target/i386/pieces-strcpy-3.c b/gcc/testsuite/gcc.target/i386/pieces-strcpy-3.c
> > new file mode 100644
> > index 00000000000..df7571b547f
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/i386/pieces-strcpy-3.c
> > @@ -0,0 +1,15 @@
> > +/* { dg-do compile { target { ! ia32 } } } */
> > +/* { dg-options "-O2 -mno-avx2 -mavx -mtune=generic" } */
> > +
> > +extern char *strcpy (char *, const char *);
> > +
> > +void
> > +foo (char *s)
> > +{
> > + strcpy (s,
> > + "1234567890abcdef123456abcdef5678123456abcdef567abcdef678"
> > + "1234567");
> > +}
> > +
> > +/* { dg-final { scan-assembler-times "vmovdqa\[ \\t\]+\[^\n\]*%ymm" 2 } } */
> > +/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 2 } } */
> > --
> > 2.31.1
> >
--
BR,
Hongtao
More information about the Gcc-patches
mailing list