> -----Original Message-----
> From: H.J. Lu <hjl.to...@gmail.com>
> Sent: Wednesday, September 15, 2021 10:14 PM
> To: Cui, Lili <lili....@intel.com>
> Cc: Uros Bizjak <ubiz...@gmail.com>; GCC Patches <gcc-
> patc...@gcc.gnu.org>; Liu, Hongtao <hongtao....@intel.com>
> Subject: Re: [PATCH 4/4] [PATCH 4/4] x86: Add
> TARGET_SSE_PARTIAL_REG_[FP_]CONVERTS_DEPENDENCY
> 
> There is no need to add [PATCH N/4] in the first line of the git commit
> message.  "git format-patch" or "git send-email" will add them automatically.
> 
Thanks for the reminder, I didn't notice it before.

> On Wed, Sep 15, 2021 at 1:10 AM <lili....@intel.com> wrote:
> >
> > From: "H.J. Lu" <hjl.to...@gmail.com>
> >
> > 1. Replace TARGET_SSE_PARTIAL_REG_DEPENDENCY with
> > TARGET_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY in SSE FP to FP
> splitters.
> > 2. Replace TARGET_SSE_PARTIAL_REG_DEPENDENCY with
> > TARGET_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY in SSE INT to FP
> splitters.
> > 3.  Also check TARGET_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY
> and
> > TARGET_SSE_PARTIAL_REG_DEPENDENCY when handling
> avx_partial_xmm_update
> > attribute.  Don't convert AVX partial XMM register update if there is
> > no partial SSE register dependency for SSE conversion.
> >
> > gcc/
> >
> >         * config/i386/i386-features.c (remove_partial_avx_dependency):
> >         Also check TARGET_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY
> and
> >         and TARGET_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY before
> generating
> >         vxorps.
> >         * config/i386/i386.h
> (TARGET_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY):
> >         New.
> >         (TARGET_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY): Likewise.
> >         * config/i386/i386.md (SSE FP to FP splitters): Replace
> >         TARGET_SSE_PARTIAL_REG_DEPENDENCY with
> >         TARGET_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY.
> >         (SSE INT to FP splitter): Replace
> TARGET_SSE_PARTIAL_REG_DEPENDENCY
> >         with TARGET_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY.
> >         * config/i386/x86-tune.def
> >         (X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY): New.
> >         (X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY): Likewise.
> >
> > gcc/testsuite/
> >
> >         * gcc.target/i386/avx-covert-1.c: New file.
> >         * gcc.target/i386/avx-fp-covert-1.c: Likewise.
> >         * gcc.target/i386/avx-int-covert-1.c: Likewise.
> >         * gcc.target/i386/sse-covert-1.c: Likewise.
> >         * gcc.target/i386/sse-fp-covert-1.c: Likewise.
> >         * gcc.target/i386/sse-int-covert-1.c: Likewise.
> > ---
> >  gcc/config/i386/i386-features.c               |  6 ++++--
> >  gcc/config/i386/i386.h                        |  4 ++++
> >  gcc/config/i386/i386.md                       |  9 ++++++---
> >  gcc/config/i386/x86-tune.def                  | 15 +++++++++++++++
> >  gcc/testsuite/gcc.target/i386/avx-covert-1.c  | 19 +++++++++++++++++++
> >  .../gcc.target/i386/avx-fp-covert-1.c         | 15 +++++++++++++++
> >  .../gcc.target/i386/avx-int-covert-1.c        | 14 ++++++++++++++
> >  gcc/testsuite/gcc.target/i386/sse-covert-1.c  | 19 +++++++++++++++++++
> >  .../gcc.target/i386/sse-fp-covert-1.c         | 15 +++++++++++++++
> >  .../gcc.target/i386/sse-int-covert-1.c        | 14 ++++++++++++++
> >  10 files changed, 125 insertions(+), 5 deletions(-)  create mode
> > 100644 gcc/testsuite/gcc.target/i386/avx-covert-1.c
> >  create mode 100644 gcc/testsuite/gcc.target/i386/avx-fp-covert-1.c
> >  create mode 100644 gcc/testsuite/gcc.target/i386/avx-int-covert-1.c
> >  create mode 100644 gcc/testsuite/gcc.target/i386/sse-covert-1.c
> >  create mode 100644 gcc/testsuite/gcc.target/i386/sse-fp-covert-1.c
> >  create mode 100644 gcc/testsuite/gcc.target/i386/sse-int-covert-1.c
> >
> > diff --git a/gcc/config/i386/i386-features.c
> > b/gcc/config/i386/i386-features.c index ae5ea02a002..91bfa06d4bf
> > 100644
> > --- a/gcc/config/i386/i386-features.c
> > +++ b/gcc/config/i386/i386-features.c
> > @@ -2218,14 +2218,16 @@ remove_partial_avx_dependency (void)
> >           machine_mode dest_mode = GET_MODE (dest);
> >           machine_mode src_mode;
> >
> > -         if (TARGET_USE_VECTOR_FP_CONVERTS)
> > +         if (TARGET_USE_VECTOR_FP_CONVERTS
> > +             || !TARGET_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY)
> >             {
> >               src_mode = GET_MODE (XEXP (src, 0));
> >               if (src_mode == E_SFmode || src_mode == E_DFmode)
> >                 continue;
> >             }
> >
> > -         if (TARGET_USE_VECTOR_CONVERTS)
> > +         if (TARGET_USE_VECTOR_CONVERTS
> > +             || !TARGET_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY)
> >             {
> >               src_mode = GET_MODE (XEXP (src, 0));
> >               if (src_mode == E_SImode || src_mode == E_DImode) diff
> > --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h index
> > e76bb55c080..ec60b89753e 100644
> > --- a/gcc/config/i386/i386.h
> > +++ b/gcc/config/i386/i386.h
> > @@ -334,6 +334,10 @@ extern unsigned char
> ix86_tune_features[X86_TUNE_LAST];
> >         ix86_tune_features[X86_TUNE_PARTIAL_REG_DEPENDENCY]
> >  #define TARGET_SSE_PARTIAL_REG_DEPENDENCY \
> >         ix86_tune_features[X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY]
> > +#define TARGET_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY \
> > +
> >
> +ix86_tune_features[X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDE
> NCY]
> > +#define TARGET_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY \
> > +
> >
> +ix86_tune_features[X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENC
> Y]
> >  #define TARGET_SSE_UNALIGNED_LOAD_OPTIMAL \
> >         ix86_tune_features[X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL]
> >  #define TARGET_SSE_UNALIGNED_STORE_OPTIMAL \ diff --git
> > a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md index
> > 13f6f57cdcc..c82a9dc1f67 100644
> > --- a/gcc/config/i386/i386.md
> > +++ b/gcc/config/i386/i386.md
> > @@ -4535,7 +4535,8 @@
> >          (float_extend:DF
> >            (match_operand:SF 1 "nonimmediate_operand")))]
> >    "!TARGET_AVX
> > -   && TARGET_SSE_PARTIAL_REG_DEPENDENCY && epilogue_completed
> > +   && TARGET_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY
> > +   && epilogue_completed
> >     && optimize_function_for_speed_p (cfun)
> >     && (!REG_P (operands[1])
> >         || (!TARGET_AVX && REGNO (operands[0]) != REGNO
> > (operands[1]))) @@ -4708,7 +4709,8 @@
> >          (float_truncate:SF
> >           (match_operand:DF 1 "nonimmediate_operand")))]
> >    "!TARGET_AVX
> > -   && TARGET_SSE_PARTIAL_REG_DEPENDENCY && epilogue_completed
> > +   && TARGET_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY
> > +   && epilogue_completed
> >     && optimize_function_for_speed_p (cfun)
> >     && (!REG_P (operands[1])
> >         || (!TARGET_AVX && REGNO (operands[0]) != REGNO
> > (operands[1]))) @@ -5243,7 +5245,8 @@
> >    [(set (match_operand:MODEF 0 "sse_reg_operand")
> >         (float:MODEF (match_operand:SWI48 1 "nonimmediate_operand")))]
> >    "!TARGET_AVX
> > -   && TARGET_SSE_PARTIAL_REG_DEPENDENCY && epilogue_completed
> > +   && TARGET_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY
> > +   && epilogue_completed
> >     && optimize_function_for_speed_p (cfun)
> >     && (!EXT_REX_SSE_REG_P (operands[0])
> >         || TARGET_AVX512VL)"
> > diff --git a/gcc/config/i386/x86-tune.def
> > b/gcc/config/i386/x86-tune.def index 088edb6c4ca..58e8ead56b4 100644
> > --- a/gcc/config/i386/x86-tune.def
> > +++ b/gcc/config/i386/x86-tune.def
> > @@ -64,6 +64,21 @@ DEF_TUNE
> (X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY, "sse_partial_reg_dependency",
> >            m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL |
> m_AMDFAM10
> >           | m_BDVER | m_ZNVER | m_TREMONT | m_GENERIC)
> >
> > +/* X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY: This knob
> avoids
> > +   partial write to the destination in scalar SSE conversion from FP
> > +   to FP.  */
> > +DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY,
> > +         "sse_partial_reg_fp_converts_dependency",
> > +         m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL |
> m_AMDFAM10
> > +         | m_BDVER | m_ZNVER | m_GENERIC)
> 
> I thought we wanted to enable this for Tremont.
> 
From the latest test, enabling Tremont here will cause a 2.8% regression to 
538.imagic_r.

Thanks,
Lili.

> > +
> > +/* X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY: This knob
> avoids partial
> > +   write to the destination in scalar SSE conversion from integer to
> > +FP.  */ DEF_TUNE
> (X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY,
> > +         "sse_partial_reg_converts_dependency",
> > +         m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL |
> m_AMDFAM10
> > +         | m_BDVER | m_ZNVER | m_GENERIC)
> > +
> >  /* X86_TUNE_SSE_SPLIT_REGS: Set for machines where the type and
> dependencies
> >     are resolved on SSE register parts instead of whole registers, so we may
> >     maintain just lower part of scalar values in proper format leaving
> > the
> 
> --
> H.J.

Reply via email to