On Thu, Jun 27, 2024 at 10:30 AM liuhongt <hongtao....@intel.com> wrote:
>
> > Richard suggests that we implement the "obvious" transforms like
> > inversion in the middle-end but if for example unsigned compares
> > are not supported the us_minus + eq + negative trick isn't on
> > that list.
> >
> > The main reason to restrict vec_cmp would be to avoid
> > a <= b ? c : d going with an unsupported vec_cmp but instead
> > do a > b ? d : c - the alternative is trying to fix this
> > on the RTL side via combine.  I understand the non-native
>
> Yes, I have a patch which can fix most regressions via pattern match
> in combine.
> Still there is a situation that is difficult to deal with, mainly the
> optimization w/o sse4.1 . Because pblendvb/blendvps/blendvpd only
> exists under sse4.1, w/o sse4.1, it takes 3
> instructions (pand,pandn,por) to simulate the vcond_mask, and the
> combine matches up to 4 instructions, which makes it currently
> impossible to use the combine to recover those optimizations in the
> vcond{,u,eq}.i.e min/max.
>
> In the case of sse 4.1 and above, there is basically no regression anymore.

So for SSE 4.1 you could mark the compares as not available - I'll
note this might
have fallout since not all middle-end code using expand_vec_cmp_expr_p handles
emulating it via inversion.  So an alternative to outright disabling
might be for
ISEL to resort to an alternate way to see that swapping cond arms is a
good idea,
for example by having different rtx/insn_cost?  I'm not sure using rtx
costing is
good here, one could think of an additional target hook indicating a compare op
is emulated?

OTOH dealing with the fallout of disabling not supported compare ops
would be good
anyway.

> the regression testcases w/o sse4.1
>
> FAIL: g++.target/i386/pr100637-1b.C  -std=gnu++14  scan-assembler-times 
> pcmpeqb 2
> FAIL: g++.target/i386/pr100637-1b.C  -std=gnu++17  scan-assembler-times 
> pcmpeqb 2
> FAIL: g++.target/i386/pr100637-1b.C  -std=gnu++20  scan-assembler-times 
> pcmpeqb 2
> FAIL: g++.target/i386/pr100637-1b.C  -std=gnu++98  scan-assembler-times 
> pcmpeqb 2
> FAIL: g++.target/i386/pr100637-1w.C  -std=gnu++14  scan-assembler-times 
> pcmpeqw 2
> FAIL: g++.target/i386/pr100637-1w.C  -std=gnu++17  scan-assembler-times 
> pcmpeqw 2
> FAIL: g++.target/i386/pr100637-1w.C  -std=gnu++20  scan-assembler-times 
> pcmpeqw 2
> FAIL: g++.target/i386/pr100637-1w.C  -std=gnu++98  scan-assembler-times 
> pcmpeqw 2
> FAIL: g++.target/i386/pr103861-1.C  -std=gnu++14  scan-assembler-times 
> pcmpeqb 2
> FAIL: g++.target/i386/pr103861-1.C  -std=gnu++17  scan-assembler-times 
> pcmpeqb 2
> FAIL: g++.target/i386/pr103861-1.C  -std=gnu++20  scan-assembler-times 
> pcmpeqb 2
> FAIL: g++.target/i386/pr103861-1.C  -std=gnu++98  scan-assembler-times 
> pcmpeqb 2
> FAIL: gcc.target/i386/pr88540.c scan-assembler minpd
>
> gcc/testsuite/ChangeLog:
>
>         PR target/115517
>         * g++.target/i386/pr100637-1b.C: Add xfail and -mno-sse4.1.
>         * g++.target/i386/pr100637-1w.C: Ditto.
>         * g++.target/i386/pr103861-1.C: Ditto.
>         * gcc.target/i386/pr88540.c: Ditto.
>         * gcc.target/i386/pr103941-2.c: Add -mno-avx512f.
>         * g++.target/i386/sse4_1-pr100637-1b.C: New test.
>         * g++.target/i386/sse4_1-pr100637-1w.C: New test.
>         * g++.target/i386/sse4_1-pr103861-1.C: New test.
>         * gcc.target/i386/sse4_1-pr88540.c: New test.
> ---
>  gcc/testsuite/g++.target/i386/pr100637-1b.C     |  4 ++--
>  gcc/testsuite/g++.target/i386/pr100637-1w.C     |  4 ++--
>  gcc/testsuite/g++.target/i386/pr103861-1.C      |  4 ++--
>  .../g++.target/i386/sse4_1-pr100637-1b.C        | 17 +++++++++++++++++
>  .../g++.target/i386/sse4_1-pr100637-1w.C        | 17 +++++++++++++++++
>  .../g++.target/i386/sse4_1-pr103861-1.C         | 17 +++++++++++++++++
>  gcc/testsuite/gcc.target/i386/pr103941-2.c      |  2 +-
>  gcc/testsuite/gcc.target/i386/pr88540.c         |  4 ++--
>  gcc/testsuite/gcc.target/i386/sse4_1-pr88540.c  | 10 ++++++++++
>  9 files changed, 70 insertions(+), 9 deletions(-)
>  create mode 100644 gcc/testsuite/g++.target/i386/sse4_1-pr100637-1b.C
>  create mode 100644 gcc/testsuite/g++.target/i386/sse4_1-pr100637-1w.C
>  create mode 100644 gcc/testsuite/g++.target/i386/sse4_1-pr103861-1.C
>  create mode 100644 gcc/testsuite/gcc.target/i386/sse4_1-pr88540.c
>
> diff --git a/gcc/testsuite/g++.target/i386/pr100637-1b.C 
> b/gcc/testsuite/g++.target/i386/pr100637-1b.C
> index 35b5df7c9dd..dccb8f5e712 100644
> --- a/gcc/testsuite/g++.target/i386/pr100637-1b.C
> +++ b/gcc/testsuite/g++.target/i386/pr100637-1b.C
> @@ -1,6 +1,6 @@
>  /* PR target/100637 */
>  /* { dg-do compile } */
> -/* { dg-options "-O2 -msse2" } */
> +/* { dg-options "-O2 -msse2 -mno-sse4.1" } */
>
>  typedef unsigned char __attribute__((__vector_size__ (4))) __v4qu;
>  typedef char __attribute__((__vector_size__ (4))) __v4qi;
> @@ -13,5 +13,5 @@ __v4qu us (__v4qi a, __v4qi b) { return (a > b) ? au : bu; }
>  __v4qi su (__v4qu a, __v4qu b) { return (a > b) ? as : bs; }
>  __v4qi ss (__v4qi a, __v4qi b) { return (a > b) ? as : bs; }
>
> -/* { dg-final { scan-assembler-times "pcmpeqb" 2 } } */
> +/* { dg-final { scan-assembler-times "pcmpeqb" 2 { xfail *-*-* } } } */
>  /* { dg-final { scan-assembler-times "pcmpgtb" 2 } } */
> diff --git a/gcc/testsuite/g++.target/i386/pr100637-1w.C 
> b/gcc/testsuite/g++.target/i386/pr100637-1w.C
> index a3ed06fddee..a0aab62db33 100644
> --- a/gcc/testsuite/g++.target/i386/pr100637-1w.C
> +++ b/gcc/testsuite/g++.target/i386/pr100637-1w.C
> @@ -1,6 +1,6 @@
>  /* PR target/100637 */
>  /* { dg-do compile } */
> -/* { dg-options "-O2 -msse2" } */
> +/* { dg-options "-O2 -msse2 -mno-sse4.1" } */
>
>  typedef unsigned short __attribute__((__vector_size__ (4))) __v2hu;
>  typedef short __attribute__((__vector_size__ (4))) __v2hi;
> @@ -13,5 +13,5 @@ __v2hu us (__v2hi a, __v2hi b) { return (a > b) ? au : bu; }
>  __v2hi su (__v2hu a, __v2hu b) { return (a > b) ? as : bs; }
>  __v2hi ss (__v2hi a, __v2hi b) { return (a > b) ? as : bs; }
>
> -/* { dg-final { scan-assembler-times "pcmpeqw" 2 } } */
> +/* { dg-final { scan-assembler-times "pcmpeqw" 2 { xfail *-*-* } } } */
>  /* { dg-final { scan-assembler-times "pcmpgtw" 2 } } */
> diff --git a/gcc/testsuite/g++.target/i386/pr103861-1.C 
> b/gcc/testsuite/g++.target/i386/pr103861-1.C
> index 6475728991e..3b282a7dca2 100644
> --- a/gcc/testsuite/g++.target/i386/pr103861-1.C
> +++ b/gcc/testsuite/g++.target/i386/pr103861-1.C
> @@ -1,6 +1,6 @@
>  /* PR target/103861 */
>  /* { dg-do compile } */
> -/* { dg-options "-O2 -msse2" } */
> +/* { dg-options "-O2 -msse2 -mno-sse4.1" } */
>
>  typedef unsigned char __attribute__((__vector_size__ (2))) __v2qu;
>  typedef char __attribute__((__vector_size__ (2))) __v2qi;
> @@ -13,5 +13,5 @@ __v2qu us (__v2qi a, __v2qi b) { return (a > b) ? au : bu; }
>  __v2qi su (__v2qu a, __v2qu b) { return (a > b) ? as : bs; }
>  __v2qi ss (__v2qi a, __v2qi b) { return (a > b) ? as : bs; }
>
> -/* { dg-final { scan-assembler-times "pcmpeqb" 2 } } */
> +/* { dg-final { scan-assembler-times "pcmpeqb" 2 { xfail *-*-* } } } */
>  /* { dg-final { scan-assembler-times "pcmpgtb" 2 } } */
> diff --git a/gcc/testsuite/g++.target/i386/sse4_1-pr100637-1b.C 
> b/gcc/testsuite/g++.target/i386/sse4_1-pr100637-1b.C
> new file mode 100644
> index 00000000000..3230a4ee563
> --- /dev/null
> +++ b/gcc/testsuite/g++.target/i386/sse4_1-pr100637-1b.C
> @@ -0,0 +1,17 @@
> +/* PR target/100637 */
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -msse4.1" } */
> +
> +typedef unsigned char __attribute__((__vector_size__ (4))) __v4qu;
> +typedef char __attribute__((__vector_size__ (4))) __v4qi;
> +
> +__v4qu au, bu;
> +__v4qi as, bs;
> +
> +__v4qu uu (__v4qu a, __v4qu b) { return (a > b) ? au : bu; }
> +__v4qu us (__v4qi a, __v4qi b) { return (a > b) ? au : bu; }
> +__v4qi su (__v4qu a, __v4qu b) { return (a > b) ? as : bs; }
> +__v4qi ss (__v4qi a, __v4qi b) { return (a > b) ? as : bs; }
> +
> +/* { dg-final { scan-assembler-times "pcmpeqb" 2 } } */
> +/* { dg-final { scan-assembler-times "pcmpgtb" 2 } } */
> diff --git a/gcc/testsuite/g++.target/i386/sse4_1-pr100637-1w.C 
> b/gcc/testsuite/g++.target/i386/sse4_1-pr100637-1w.C
> new file mode 100644
> index 00000000000..9036ea5429d
> --- /dev/null
> +++ b/gcc/testsuite/g++.target/i386/sse4_1-pr100637-1w.C
> @@ -0,0 +1,17 @@
> +/* PR target/100637 */
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -msse4.1" } */
> +
> +typedef unsigned short __attribute__((__vector_size__ (4))) __v2hu;
> +typedef short __attribute__((__vector_size__ (4))) __v2hi;
> +
> +__v2hu au, bu;
> +__v2hi as, bs;
> +
> +__v2hu uu (__v2hu a, __v2hu b) { return (a > b) ? au : bu; }
> +__v2hu us (__v2hi a, __v2hi b) { return (a > b) ? au : bu; }
> +__v2hi su (__v2hu a, __v2hu b) { return (a > b) ? as : bs; }
> +__v2hi ss (__v2hi a, __v2hi b) { return (a > b) ? as : bs; }
> +
> +/* { dg-final { scan-assembler-times "pcmpeqw" 2 } } */
> +/* { dg-final { scan-assembler-times "pcmpgtw" 2 } } */
> diff --git a/gcc/testsuite/g++.target/i386/sse4_1-pr103861-1.C 
> b/gcc/testsuite/g++.target/i386/sse4_1-pr103861-1.C
> new file mode 100644
> index 00000000000..a2b74898db9
> --- /dev/null
> +++ b/gcc/testsuite/g++.target/i386/sse4_1-pr103861-1.C
> @@ -0,0 +1,17 @@
> +/* PR target/103861 */
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -msse4.1" } */
> +
> +typedef unsigned char __attribute__((__vector_size__ (2))) __v2qu;
> +typedef char __attribute__((__vector_size__ (2))) __v2qi;
> +
> +__v2qu au, bu;
> +__v2qi as, bs;
> +
> +__v2qu uu (__v2qu a, __v2qu b) { return (a > b) ? au : bu; }
> +__v2qu us (__v2qi a, __v2qi b) { return (a > b) ? au : bu; }
> +__v2qi su (__v2qu a, __v2qu b) { return (a > b) ? as : bs; }
> +__v2qi ss (__v2qi a, __v2qi b) { return (a > b) ? as : bs; }
> +
> +/* { dg-final { scan-assembler-times "pcmpeqb" 2 } } */
> +/* { dg-final { scan-assembler-times "pcmpgtb" 2 } } */
> diff --git a/gcc/testsuite/gcc.target/i386/pr103941-2.c 
> b/gcc/testsuite/gcc.target/i386/pr103941-2.c
> index 972a32be997..9b24a10c63d 100644
> --- a/gcc/testsuite/gcc.target/i386/pr103941-2.c
> +++ b/gcc/testsuite/gcc.target/i386/pr103941-2.c
> @@ -1,5 +1,5 @@
>  /* { dg-do compile } */
> -/* { dg-options "-O2 -msse2" } */
> +/* { dg-options "-O2 -msse2 -mno-avx512f" } */
>
>  void foo (int *c, float *x, float *y)
>  {
> diff --git a/gcc/testsuite/gcc.target/i386/pr88540.c 
> b/gcc/testsuite/gcc.target/i386/pr88540.c
> index b927d0c57d5..a22744763b5 100644
> --- a/gcc/testsuite/gcc.target/i386/pr88540.c
> +++ b/gcc/testsuite/gcc.target/i386/pr88540.c
> @@ -1,5 +1,5 @@
>  /* { dg-do compile } */
> -/* { dg-options "-O2 -msse2" } */
> +/* { dg-options "-O2 -msse2 -mno-sse4.1" } */
>
>  void test(double* __restrict d1, double* __restrict d2, double* __restrict 
> d3)
>  {
> @@ -7,4 +7,4 @@ void test(double* __restrict d1, double* __restrict d2, 
> double* __restrict d3)
>      d3[n] = d1[n] < d2[n] ? d1[n] : d2[n];
>  }
>
> -/* { dg-final { scan-assembler "minpd" } } */
> +/* { dg-final { scan-assembler "minpd" { xfail *-*-* } } } */
> diff --git a/gcc/testsuite/gcc.target/i386/sse4_1-pr88540.c 
> b/gcc/testsuite/gcc.target/i386/sse4_1-pr88540.c
> new file mode 100644
> index 00000000000..31565a69db5
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/sse4_1-pr88540.c
> @@ -0,0 +1,10 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -msse4.1" } */
> +
> +void test(double* __restrict d1, double* __restrict d2, double* __restrict 
> d3)
> +{
> +  for (int n = 0; n < 2; ++n)
> +    d3[n] = d1[n] < d2[n] ? d1[n] : d2[n];
> +}
> +
> +/* { dg-final { scan-assembler "minpd" } } */
> --
> 2.31.1
>

Reply via email to