diff mbox series

Split vector load from parm_del to elemental loads to avoid STLF stalls.

Message ID 20220331055117.6942-1-hongtao.liu@intel.com
State New
Headers show
Series Split vector load from parm_del to elemental loads to avoid STLF stalls. | expand

Commit Message

liuhongt March 31, 2022, 5:51 a.m. UTC
Since cfg is freed before machine_reorg, just do a rough calculation
of the window according to the layout.
Also according to an experiment on CLX, set window size to 64.

Currently only handle V2DFmode load since it doesn't need any scratch
registers, and it's sufficient to recover cray performance for -O2
compared to GCC11.

Bootstrap and regtest on x86_64-pc-linux-gnu{-m32,}.
No impact for SPEC2017(same binary for both O2 and Ofast).
Ok for trunk?

gcc/ChangeLog:

	PR target/101908
	* config/i386/i386.cc (ix86_split_stlf_stall_load): New
	function
	(ix86_reorg): Call ix86_split_stlf_stall_load.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr101908-1.c: New test.
	* gcc.target/i386/pr101908-2.c: New test.
---
 gcc/config/i386/i386.cc                    | 47 ++++++++++++++++++++++
 gcc/testsuite/gcc.target/i386/pr101908-1.c | 12 ++++++
 gcc/testsuite/gcc.target/i386/pr101908-2.c | 12 ++++++
 3 files changed, 71 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr101908-1.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr101908-2.c

Comments

Richard Biener March 31, 2022, 10:44 a.m. UTC | #1
On Thu, Mar 31, 2022 at 7:51 AM liuhongt <hongtao.liu@intel.com> wrote:
>
> Since cfg is freed before machine_reorg, just do a rough calculation
> of the window according to the layout.
> Also according to an experiment on CLX, set window size to 64.
>
> Currently only handle V2DFmode load since it doesn't need any scratch
> registers, and it's sufficient to recover cray performance for -O2
> compared to GCC11.
>
> Bootstrap and regtest on x86_64-pc-linux-gnu{-m32,}.
> No impact for SPEC2017(same binary for both O2 and Ofast).
> Ok for trunk?
>
> gcc/ChangeLog:
>
>         PR target/101908
>         * config/i386/i386.cc (ix86_split_stlf_stall_load): New
>         function
>         (ix86_reorg): Call ix86_split_stlf_stall_load.
>
> gcc/testsuite/ChangeLog:
>
>         * gcc.target/i386/pr101908-1.c: New test.
>         * gcc.target/i386/pr101908-2.c: New test.
> ---
>  gcc/config/i386/i386.cc                    | 47 ++++++++++++++++++++++
>  gcc/testsuite/gcc.target/i386/pr101908-1.c | 12 ++++++
>  gcc/testsuite/gcc.target/i386/pr101908-2.c | 12 ++++++
>  3 files changed, 71 insertions(+)
>  create mode 100644 gcc/testsuite/gcc.target/i386/pr101908-1.c
>  create mode 100644 gcc/testsuite/gcc.target/i386/pr101908-2.c
>
> diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
> index 5a561966eb4..f9169b04d43 100644
> --- a/gcc/config/i386/i386.cc
> +++ b/gcc/config/i386/i386.cc
> @@ -21933,7 +21933,53 @@ ix86_seh_fixup_eh_fallthru (void)
>        emit_insn_after (gen_nops (const1_rtx), insn);
>      }
>  }
> +/* Split vector load from parm_decl to elemental loads to avoid STLF
> +   stalls.  */
> +static void
> +ix86_split_stlf_stall_load ()
> +{
> +  basic_block bb;
> +  unsigned window = 0;
> +  FOR_EACH_BB_FN (bb, cfun)
> +    {
> +      rtx_insn *insn;
> +      FOR_BB_INSNS (bb, insn)
> +       {
> +         if (!NONDEBUG_INSN_P (insn))
> +           continue;
> +         window++;
> +         /* Insert 64 vaddps %xmm18, %xmm19, %xmm20(no dependence between each
> +            other, just emulate for pipeline) before stalled load, stlf stall
> +            case is as fast as no stall cases on CLX.
> +            Since CFG is freed before machine_reorg, just do a rough
> +            calculation of the window according to the layout.  */
> +         if (window > 64)
> +           return;

I wonder if we should also return for any_uncondjump_p (insn)
(not sure if that captures returnjump_p), or maybe just explicitely
allow any_condjump_p and reject other PC setters.

Likewise we might want to stop at a LABEL that can be backwards reached.

I suppose people more familiar with cfgrtl can suggest something better.

> +         rtx set = single_set (insn);
> +         if (!set)
> +           continue;
> +         rtx src = SET_SRC (set);
> +         if (!MEM_P (src)
> +             /* Only handle V2DFmode load since it doesn't need any scratch
> +                register.  */
> +             || GET_MODE (src) != E_V2DFmode
> +             || !MEM_EXPR (src)
> +             || TREE_CODE (get_base_address (MEM_EXPR (src))) != PARM_DECL)

I wonder if we have (easy) ways to detect whether XEXP (src, 0) is
frame/stack based
rather than requiring a MEM_EXPR.  There is may_be_sp_based_p ()
exported from alias.c
for example, but I'm not sure whether that works after RA & frame elimination.

> +           continue;
> +
> +         rtx zero = CONST0_RTX (V2DFmode);
> +         rtx dest = SET_DEST (set);
> +         rtx m = adjust_address (src, DFmode, 0);
> +         emit_insn_before (gen_sse2_loadlpd (dest, zero, m), insn);

Can SSE1 also do this?

> +         m = adjust_address (src, DFmode, 8);
> +         PATTERN (insn) = gen_sse2_loadhpd (dest, dest, m);
> +         INSN_CODE (insn) = -1;
> +         gcc_assert (recog_memoized (insn) != -1);

I think we want to dump something into dump_file when we split an insn here.

> +       }
> +    }
> +
> +}
>  /* Implement machine specific optimizations.  We implement padding of returns
>     for K8 CPUs and pass to avoid 4 jumps in the single 16 byte window.  */
>  static void
> @@ -21948,6 +21994,7 @@ ix86_reorg (void)
>
>    if (optimize && optimize_function_for_speed_p (cfun))
>      {
> +      ix86_split_stlf_stall_load ();
>        if (TARGET_PAD_SHORT_FUNCTION)
>         ix86_pad_short_function ();

btw. this function suggests we do have edges, so doing something "better"
than FOR_EACH_BB_FN, aka walking blocks in layout order, might be
possible after all.  For example ix86_avoid_jump_mispredicts just walks
the function by looking at get_insns(), that might be more closely what
"as laid out" is.

>        else if (TARGET_PAD_RETURNS)
> diff --git a/gcc/testsuite/gcc.target/i386/pr101908-1.c b/gcc/testsuite/gcc.target/i386/pr101908-1.c
> new file mode 100644
> index 00000000000..33d9684f0ad
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr101908-1.c
> @@ -0,0 +1,12 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -msse2 -mno-avx" } */
> +/* { dg-final { scan-assembler-not {(?n)movhpd[ \t]} } } */
> +
> +struct X { double x[2]; };
> +typedef double v2df __attribute__((vector_size(16)));
> +
> +v2df __attribute__((noipa))
> +foo (struct X* x, struct X* y)
> +{
> +  return (v2df) {x->x[1], x->x[0] } + (v2df) { y->x[1], y->x[0] };
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/pr101908-2.c b/gcc/testsuite/gcc.target/i386/pr101908-2.c
> new file mode 100644
> index 00000000000..45060b73c06
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr101908-2.c
> @@ -0,0 +1,12 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -msse2 -mno-avx" } */
> +/* { dg-final { scan-assembler-times {(?n)movhpd[ \t]+} "2" } }  */
> +
> +struct X { double x[4]; };
> +typedef double v2df __attribute__((vector_size(16)));
> +
> +v2df __attribute__((noipa))
> +foo (struct X x, struct X y)
> +{
> +  return (v2df) {x.x[1], x.x[0] } + (v2df) { y.x[1], y.x[0] };
> +}
> --
> 2.18.1
>
Hongtao Liu April 1, 2022, 6:29 a.m. UTC | #2
On Thu, Mar 31, 2022 at 6:45 PM Richard Biener via Gcc-patches
<gcc-patches@gcc.gnu.org> wrote:
>
> On Thu, Mar 31, 2022 at 7:51 AM liuhongt <hongtao.liu@intel.com> wrote:
> >
> > Since cfg is freed before machine_reorg, just do a rough calculation
> > of the window according to the layout.
> > Also according to an experiment on CLX, set window size to 64.
> >
> > Currently only handle V2DFmode load since it doesn't need any scratch
> > registers, and it's sufficient to recover cray performance for -O2
> > compared to GCC11.
> >
> > Bootstrap and regtest on x86_64-pc-linux-gnu{-m32,}.
> > No impact for SPEC2017(same binary for both O2 and Ofast).
> > Ok for trunk?
> >
> > gcc/ChangeLog:
> >
> >         PR target/101908
> >         * config/i386/i386.cc (ix86_split_stlf_stall_load): New
> >         function
> >         (ix86_reorg): Call ix86_split_stlf_stall_load.
> >
> > gcc/testsuite/ChangeLog:
> >
> >         * gcc.target/i386/pr101908-1.c: New test.
> >         * gcc.target/i386/pr101908-2.c: New test.
> > ---
> >  gcc/config/i386/i386.cc                    | 47 ++++++++++++++++++++++
> >  gcc/testsuite/gcc.target/i386/pr101908-1.c | 12 ++++++
> >  gcc/testsuite/gcc.target/i386/pr101908-2.c | 12 ++++++
> >  3 files changed, 71 insertions(+)
> >  create mode 100644 gcc/testsuite/gcc.target/i386/pr101908-1.c
> >  create mode 100644 gcc/testsuite/gcc.target/i386/pr101908-2.c
> >
> > diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
> > index 5a561966eb4..f9169b04d43 100644
> > --- a/gcc/config/i386/i386.cc
> > +++ b/gcc/config/i386/i386.cc
> > @@ -21933,7 +21933,53 @@ ix86_seh_fixup_eh_fallthru (void)
> >        emit_insn_after (gen_nops (const1_rtx), insn);
> >      }
> >  }
> > +/* Split vector load from parm_decl to elemental loads to avoid STLF
> > +   stalls.  */
> > +static void
> > +ix86_split_stlf_stall_load ()
> > +{
> > +  basic_block bb;
> > +  unsigned window = 0;
> > +  FOR_EACH_BB_FN (bb, cfun)
> > +    {
> > +      rtx_insn *insn;
> > +      FOR_BB_INSNS (bb, insn)
> > +       {
> > +         if (!NONDEBUG_INSN_P (insn))
> > +           continue;
> > +         window++;
> > +         /* Insert 64 vaddps %xmm18, %xmm19, %xmm20(no dependence between each
> > +            other, just emulate for pipeline) before stalled load, stlf stall
> > +            case is as fast as no stall cases on CLX.
> > +            Since CFG is freed before machine_reorg, just do a rough
> > +            calculation of the window according to the layout.  */
> > +         if (window > 64)
> > +           return;
>
> I wonder if we should also return for any_uncondjump_p (insn)
> (not sure if that captures returnjump_p), or maybe just explicitely
> allow any_condjump_p and reject other PC setters.
>
I guess it doesn't include call.
> Likewise we might want to stop at a LABEL that can be backwards reached.
>
I think checking load from parm_decl can somehow avoid split load in a
loop(assume optimizer will hoist that out).
> I suppose people more familiar with cfgrtl can suggest something better.
>
> > +         rtx set = single_set (insn);
> > +         if (!set)
> > +           continue;
> > +         rtx src = SET_SRC (set);
> > +         if (!MEM_P (src)
> > +             /* Only handle V2DFmode load since it doesn't need any scratch
> > +                register.  */
> > +             || GET_MODE (src) != E_V2DFmode
> > +             || !MEM_EXPR (src)
> > +             || TREE_CODE (get_base_address (MEM_EXPR (src))) != PARM_DECL)
>
> I wonder if we have (easy) ways to detect whether XEXP (src, 0) is
> frame/stack based
> rather than requiring a MEM_EXPR.  There is may_be_sp_based_p ()
may_be_sp_based_p just checks stack pointer which is not suitable after RA.
> exported from alias.c
> for example, but I'm not sure whether that works after RA & frame elimination.
>
> > +           continue;
> > +
> > +         rtx zero = CONST0_RTX (V2DFmode);
> > +         rtx dest = SET_DEST (set);
> > +         rtx m = adjust_address (src, DFmode, 0);
> > +         emit_insn_before (gen_sse2_loadlpd (dest, zero, m), insn);
>
> Can SSE1 also do this?
X86 does have movlps and movhps, but the problem is movlps load 64bit
memory to xmm w/o change upper bits which may cause partial register
dependence.
>
> > +         m = adjust_address (src, DFmode, 8);
> > +         PATTERN (insn) = gen_sse2_loadhpd (dest, dest, m);
> > +         INSN_CODE (insn) = -1;
> > +         gcc_assert (recog_memoized (insn) != -1);
>
> I think we want to dump something into dump_file when we split an insn here.
Good idea.
>
> > +       }
> > +    }
> > +
> > +}
> >  /* Implement machine specific optimizations.  We implement padding of returns
> >     for K8 CPUs and pass to avoid 4 jumps in the single 16 byte window.  */
> >  static void
> > @@ -21948,6 +21994,7 @@ ix86_reorg (void)
> >
> >    if (optimize && optimize_function_for_speed_p (cfun))
> >      {
> > +      ix86_split_stlf_stall_load ();
> >        if (TARGET_PAD_SHORT_FUNCTION)
> >         ix86_pad_short_function ();
>
> btw. this function suggests we do have edges, so doing something "better"
> than FOR_EACH_BB_FN, aka walking blocks in layout order, might be
> possible after all.  For example ix86_avoid_jump_mispredicts just walks
> the function by looking at get_insns(), that might be more closely what
> "as laid out" is.
I prefer to use get_insns ().
>
> >        else if (TARGET_PAD_RETURNS)
> > diff --git a/gcc/testsuite/gcc.target/i386/pr101908-1.c b/gcc/testsuite/gcc.target/i386/pr101908-1.c
> > new file mode 100644
> > index 00000000000..33d9684f0ad
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/i386/pr101908-1.c
> > @@ -0,0 +1,12 @@
> > +/* { dg-do compile } */
> > +/* { dg-options "-O2 -msse2 -mno-avx" } */
> > +/* { dg-final { scan-assembler-not {(?n)movhpd[ \t]} } } */
> > +
> > +struct X { double x[2]; };
> > +typedef double v2df __attribute__((vector_size(16)));
> > +
> > +v2df __attribute__((noipa))
> > +foo (struct X* x, struct X* y)
> > +{
> > +  return (v2df) {x->x[1], x->x[0] } + (v2df) { y->x[1], y->x[0] };
> > +}
> > diff --git a/gcc/testsuite/gcc.target/i386/pr101908-2.c b/gcc/testsuite/gcc.target/i386/pr101908-2.c
> > new file mode 100644
> > index 00000000000..45060b73c06
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/i386/pr101908-2.c
> > @@ -0,0 +1,12 @@
> > +/* { dg-do compile } */
> > +/* { dg-options "-O2 -msse2 -mno-avx" } */
> > +/* { dg-final { scan-assembler-times {(?n)movhpd[ \t]+} "2" } }  */
> > +
> > +struct X { double x[4]; };
> > +typedef double v2df __attribute__((vector_size(16)));
> > +
> > +v2df __attribute__((noipa))
> > +foo (struct X x, struct X y)
> > +{
> > +  return (v2df) {x.x[1], x.x[0] } + (v2df) { y.x[1], y.x[0] };
> > +}
> > --
> > 2.18.1
> >
Richard Biener April 1, 2022, 6:47 a.m. UTC | #3
On Fri, Apr 1, 2022 at 8:29 AM Hongtao Liu <crazylht@gmail.com> wrote:
>
> On Thu, Mar 31, 2022 at 6:45 PM Richard Biener via Gcc-patches
> <gcc-patches@gcc.gnu.org> wrote:
> >
> > On Thu, Mar 31, 2022 at 7:51 AM liuhongt <hongtao.liu@intel.com> wrote:
> > >
> > > Since cfg is freed before machine_reorg, just do a rough calculation
> > > of the window according to the layout.
> > > Also according to an experiment on CLX, set window size to 64.
> > >
> > > Currently only handle V2DFmode load since it doesn't need any scratch
> > > registers, and it's sufficient to recover cray performance for -O2
> > > compared to GCC11.
> > >
> > > Bootstrap and regtest on x86_64-pc-linux-gnu{-m32,}.
> > > No impact for SPEC2017(same binary for both O2 and Ofast).
> > > Ok for trunk?
> > >
> > > gcc/ChangeLog:
> > >
> > >         PR target/101908
> > >         * config/i386/i386.cc (ix86_split_stlf_stall_load): New
> > >         function
> > >         (ix86_reorg): Call ix86_split_stlf_stall_load.
> > >
> > > gcc/testsuite/ChangeLog:
> > >
> > >         * gcc.target/i386/pr101908-1.c: New test.
> > >         * gcc.target/i386/pr101908-2.c: New test.
> > > ---
> > >  gcc/config/i386/i386.cc                    | 47 ++++++++++++++++++++++
> > >  gcc/testsuite/gcc.target/i386/pr101908-1.c | 12 ++++++
> > >  gcc/testsuite/gcc.target/i386/pr101908-2.c | 12 ++++++
> > >  3 files changed, 71 insertions(+)
> > >  create mode 100644 gcc/testsuite/gcc.target/i386/pr101908-1.c
> > >  create mode 100644 gcc/testsuite/gcc.target/i386/pr101908-2.c
> > >
> > > diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
> > > index 5a561966eb4..f9169b04d43 100644
> > > --- a/gcc/config/i386/i386.cc
> > > +++ b/gcc/config/i386/i386.cc
> > > @@ -21933,7 +21933,53 @@ ix86_seh_fixup_eh_fallthru (void)
> > >        emit_insn_after (gen_nops (const1_rtx), insn);
> > >      }
> > >  }
> > > +/* Split vector load from parm_decl to elemental loads to avoid STLF
> > > +   stalls.  */
> > > +static void
> > > +ix86_split_stlf_stall_load ()
> > > +{
> > > +  basic_block bb;
> > > +  unsigned window = 0;
> > > +  FOR_EACH_BB_FN (bb, cfun)
> > > +    {
> > > +      rtx_insn *insn;
> > > +      FOR_BB_INSNS (bb, insn)
> > > +       {
> > > +         if (!NONDEBUG_INSN_P (insn))
> > > +           continue;
> > > +         window++;
> > > +         /* Insert 64 vaddps %xmm18, %xmm19, %xmm20(no dependence between each
> > > +            other, just emulate for pipeline) before stalled load, stlf stall
> > > +            case is as fast as no stall cases on CLX.
> > > +            Since CFG is freed before machine_reorg, just do a rough
> > > +            calculation of the window according to the layout.  */
> > > +         if (window > 64)
> > > +           return;
> >
> > I wonder if we should also return for any_uncondjump_p (insn)
> > (not sure if that captures returnjump_p), or maybe just explicitely
> > allow any_condjump_p and reject other PC setters.
> >
> I guess it doesn't include call.
> > Likewise we might want to stop at a LABEL that can be backwards reached.
> >
> I think checking load from parm_decl can somehow avoid split load in a
> loop(assume optimizer will hoist that out).
> > I suppose people more familiar with cfgrtl can suggest something better.
> >
> > > +         rtx set = single_set (insn);
> > > +         if (!set)
> > > +           continue;
> > > +         rtx src = SET_SRC (set);
> > > +         if (!MEM_P (src)
> > > +             /* Only handle V2DFmode load since it doesn't need any scratch
> > > +                register.  */
> > > +             || GET_MODE (src) != E_V2DFmode
> > > +             || !MEM_EXPR (src)
> > > +             || TREE_CODE (get_base_address (MEM_EXPR (src))) != PARM_DECL)
> >
> > I wonder if we have (easy) ways to detect whether XEXP (src, 0) is
> > frame/stack based
> > rather than requiring a MEM_EXPR.  There is may_be_sp_based_p ()
> may_be_sp_based_p just checks stack pointer which is not suitable after RA.
> > exported from alias.c
> > for example, but I'm not sure whether that works after RA & frame elimination.
> >
> > > +           continue;
> > > +
> > > +         rtx zero = CONST0_RTX (V2DFmode);
> > > +         rtx dest = SET_DEST (set);
> > > +         rtx m = adjust_address (src, DFmode, 0);
> > > +         emit_insn_before (gen_sse2_loadlpd (dest, zero, m), insn);
> >
> > Can SSE1 also do this?
> X86 does have movlps and movhps, but the problem is movlps load 64bit
> memory to xmm w/o change upper bits which may cause partial register
> dependence.

So do we need to guard this transform on SSE2 availability then?

> >
> > > +         m = adjust_address (src, DFmode, 8);
> > > +         PATTERN (insn) = gen_sse2_loadhpd (dest, dest, m);
> > > +         INSN_CODE (insn) = -1;
> > > +         gcc_assert (recog_memoized (insn) != -1);
> >
> > I think we want to dump something into dump_file when we split an insn here.
> Good idea.
> >
> > > +       }
> > > +    }
> > > +
> > > +}
> > >  /* Implement machine specific optimizations.  We implement padding of returns
> > >     for K8 CPUs and pass to avoid 4 jumps in the single 16 byte window.  */
> > >  static void
> > > @@ -21948,6 +21994,7 @@ ix86_reorg (void)
> > >
> > >    if (optimize && optimize_function_for_speed_p (cfun))
> > >      {
> > > +      ix86_split_stlf_stall_load ();
> > >        if (TARGET_PAD_SHORT_FUNCTION)
> > >         ix86_pad_short_function ();
> >
> > btw. this function suggests we do have edges, so doing something "better"
> > than FOR_EACH_BB_FN, aka walking blocks in layout order, might be
> > possible after all.  For example ix86_avoid_jump_mispredicts just walks
> > the function by looking at get_insns(), that might be more closely what
> > "as laid out" is.
> I prefer to use get_insns ().
> >
> > >        else if (TARGET_PAD_RETURNS)
> > > diff --git a/gcc/testsuite/gcc.target/i386/pr101908-1.c b/gcc/testsuite/gcc.target/i386/pr101908-1.c
> > > new file mode 100644
> > > index 00000000000..33d9684f0ad
> > > --- /dev/null
> > > +++ b/gcc/testsuite/gcc.target/i386/pr101908-1.c
> > > @@ -0,0 +1,12 @@
> > > +/* { dg-do compile } */
> > > +/* { dg-options "-O2 -msse2 -mno-avx" } */
> > > +/* { dg-final { scan-assembler-not {(?n)movhpd[ \t]} } } */
> > > +
> > > +struct X { double x[2]; };
> > > +typedef double v2df __attribute__((vector_size(16)));
> > > +
> > > +v2df __attribute__((noipa))
> > > +foo (struct X* x, struct X* y)
> > > +{
> > > +  return (v2df) {x->x[1], x->x[0] } + (v2df) { y->x[1], y->x[0] };
> > > +}
> > > diff --git a/gcc/testsuite/gcc.target/i386/pr101908-2.c b/gcc/testsuite/gcc.target/i386/pr101908-2.c
> > > new file mode 100644
> > > index 00000000000..45060b73c06
> > > --- /dev/null
> > > +++ b/gcc/testsuite/gcc.target/i386/pr101908-2.c
> > > @@ -0,0 +1,12 @@
> > > +/* { dg-do compile } */
> > > +/* { dg-options "-O2 -msse2 -mno-avx" } */
> > > +/* { dg-final { scan-assembler-times {(?n)movhpd[ \t]+} "2" } }  */
> > > +
> > > +struct X { double x[4]; };
> > > +typedef double v2df __attribute__((vector_size(16)));
> > > +
> > > +v2df __attribute__((noipa))
> > > +foo (struct X x, struct X y)
> > > +{
> > > +  return (v2df) {x.x[1], x.x[0] } + (v2df) { y.x[1], y.x[0] };
> > > +}
> > > --
> > > 2.18.1
> > >
>
>
>
> --
> BR,
> Hongtao
diff mbox series

Patch

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 5a561966eb4..f9169b04d43 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -21933,7 +21933,53 @@  ix86_seh_fixup_eh_fallthru (void)
       emit_insn_after (gen_nops (const1_rtx), insn);
     }
 }
+/* Split vector load from parm_decl to elemental loads to avoid STLF
+   stalls.  */
+static void
+ix86_split_stlf_stall_load ()
+{
+  basic_block bb;
+  unsigned window = 0;
+  FOR_EACH_BB_FN (bb, cfun)
+    {
+      rtx_insn *insn;
+      FOR_BB_INSNS (bb, insn)
+	{
+	  if (!NONDEBUG_INSN_P (insn))
+	    continue;
+	  window++;
+	  /* Insert 64 vaddps %xmm18, %xmm19, %xmm20(no dependence between each
+	     other, just emulate for pipeline) before stalled load, stlf stall
+	     case is as fast as no stall cases on CLX.
+	     Since CFG is freed before machine_reorg, just do a rough
+	     calculation of the window according to the layout.  */
+	  if (window > 64)
+	    return;
 
+	  rtx set = single_set (insn);
+	  if (!set)
+	    continue;
+	  rtx src = SET_SRC (set);
+	  if (!MEM_P (src)
+	      /* Only handle V2DFmode load since it doesn't need any scratch
+		 register.  */
+	      || GET_MODE (src) != E_V2DFmode
+	      || !MEM_EXPR (src)
+	      || TREE_CODE (get_base_address (MEM_EXPR (src))) != PARM_DECL)
+	    continue;
+
+	  rtx zero = CONST0_RTX (V2DFmode);
+	  rtx dest = SET_DEST (set);
+	  rtx m = adjust_address (src, DFmode, 0);
+	  emit_insn_before (gen_sse2_loadlpd (dest, zero, m), insn);
+	  m = adjust_address (src, DFmode, 8);
+	  PATTERN (insn) = gen_sse2_loadhpd (dest, dest, m);
+	  INSN_CODE (insn) = -1;
+	  gcc_assert (recog_memoized (insn) != -1);
+	}
+    }
+
+}
 /* Implement machine specific optimizations.  We implement padding of returns
    for K8 CPUs and pass to avoid 4 jumps in the single 16 byte window.  */
 static void
@@ -21948,6 +21994,7 @@  ix86_reorg (void)
 
   if (optimize && optimize_function_for_speed_p (cfun))
     {
+      ix86_split_stlf_stall_load ();
       if (TARGET_PAD_SHORT_FUNCTION)
 	ix86_pad_short_function ();
       else if (TARGET_PAD_RETURNS)
diff --git a/gcc/testsuite/gcc.target/i386/pr101908-1.c b/gcc/testsuite/gcc.target/i386/pr101908-1.c
new file mode 100644
index 00000000000..33d9684f0ad
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr101908-1.c
@@ -0,0 +1,12 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2 -mno-avx" } */
+/* { dg-final { scan-assembler-not {(?n)movhpd[ \t]} } } */
+
+struct X { double x[2]; };
+typedef double v2df __attribute__((vector_size(16)));
+
+v2df __attribute__((noipa))
+foo (struct X* x, struct X* y)
+{
+  return (v2df) {x->x[1], x->x[0] } + (v2df) { y->x[1], y->x[0] };
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr101908-2.c b/gcc/testsuite/gcc.target/i386/pr101908-2.c
new file mode 100644
index 00000000000..45060b73c06
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr101908-2.c
@@ -0,0 +1,12 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2 -mno-avx" } */
+/* { dg-final { scan-assembler-times {(?n)movhpd[ \t]+} "2" } }  */
+
+struct X { double x[4]; };
+typedef double v2df __attribute__((vector_size(16)));
+
+v2df __attribute__((noipa))
+foo (struct X x, struct X y)
+{
+  return (v2df) {x.x[1], x.x[0] } + (v2df) { y.x[1], y.x[0] };
+}