On Mon, Jan 27, 2020 at 12:26 PM Uros Bizjak <ubiz...@gmail.com> wrote:
>
> On Mon, Jan 27, 2020 at 7:23 PM H.J. Lu <hjl.to...@gmail.com> wrote:
> >
> > movaps/movups is one byte shorter than movdaq/movdqu. But it isn't the
> > case for AVX nor AVX512. We should disable TARGET_SSE_TYPELESS_STORES
> > for TARGET_AVX.
> >
> > gcc/
> >
> > PR target/91461
> > * config/i386/i386.h (TARGET_SSE_TYPELESS_STORES): Disable for
> > TARGET_AVX.
> > * config/i386/i386.md (*movoi_internal_avx): Remove
> > TARGET_SSE_TYPELESS_STORES check.
> >
> > gcc/testsuite/
> >
> > PR target/91461
> > * gcc.target/i386/pr91461-1.c: New test.
> > * gcc.target/i386/pr91461-2.c: Likewise.
> > * gcc.target/i386/pr91461-3.c: Likewise.
> > * gcc.target/i386/pr91461-4.c: Likewise.
> > * gcc.target/i386/pr91461-5.c: Likewise.
> > ---
> > gcc/config/i386/i386.h | 4 +-
> > gcc/config/i386/i386.md | 4 +-
> > gcc/testsuite/gcc.target/i386/pr91461-1.c | 66 ++++++++++++++++++++
> > gcc/testsuite/gcc.target/i386/pr91461-2.c | 19 ++++++
> > gcc/testsuite/gcc.target/i386/pr91461-3.c | 76 +++++++++++++++++++++++
> > gcc/testsuite/gcc.target/i386/pr91461-4.c | 21 +++++++
> > gcc/testsuite/gcc.target/i386/pr91461-5.c | 17 +++++
> > 7 files changed, 203 insertions(+), 4 deletions(-)
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr91461-1.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr91461-2.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr91461-3.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr91461-4.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr91461-5.c
> >
> > diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
> > index 943e9a5c783..c134b04c5c4 100644
> > --- a/gcc/config/i386/i386.h
> > +++ b/gcc/config/i386/i386.h
> > @@ -516,8 +516,10 @@ extern unsigned char ix86_tune_features[X86_TUNE_LAST];
> > #define TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL \
> > ix86_tune_features[X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL]
> > #define TARGET_SSE_SPLIT_REGS ix86_tune_features[X86_TUNE_SSE_SPLIT_REGS]
> > +/* NB: movaps/movups is one byte shorter than movdaq/movdqu. But it
> > + isn't the case for AVX nor AVX512. */
> > #define TARGET_SSE_TYPELESS_STORES \
> > - ix86_tune_features[X86_TUNE_SSE_TYPELESS_STORES]
> > + (!TARGET_AVX && ix86_tune_features[X86_TUNE_SSE_TYPELESS_STORES])
>
> This is wrong place to disable the feature.
Like this?
diff --git a/gcc/config/i386/i386-options.c b/gcc/config/i386/i386-options.c
index 2acc9fb0cfe..639969d736d 100644
--- a/gcc/config/i386/i386-options.c
+++ b/gcc/config/i386/i386-options.c
@@ -1597,6 +1597,11 @@ set_ix86_tune_features (enum processor_type
ix86_tune, bool dump)
= !!(initial_ix86_tune_features[i] & ix86_tune_mask);
}
+ /* NB: movaps/movups is one byte shorter than movdaq/movdqu. But it
+ isn't the case for AVX nor AVX512. */
+ if (TARGET_AVX)
+ ix86_tune_features[X86_TUNE_SSE_TYPELESS_STORES] = 0;
+
if (dump)
{
fprintf (stderr, "List of x86 specific tuning parameter names:\n");
--
H.J.
