Optimize A < B ? A : B to MIN_EXPR.
Checks
Commit Message
> I wonder if you can amend the existing patterns instead by iterating
> over cond/vec_cond. There are quite some (look for uses of
> minmax_from_comparison) that could be adapted to vectors.
>
> The ones matching the simple form you match are
>
> #if GIMPLE
> /* A >= B ? A : B -> max (A, B) and friends. The code is still
> in fold_cond_expr_with_comparison for GENERIC folding with
> some extra constraints. */
> (for cmp (eq ne le lt unle unlt ge gt unge ungt uneq ltgt)
> (simplify
> (cond (cmp:c (nop_convert1?@c0 @0) (nop_convert2?@c1 @1))
> (convert3? @0) (convert4? @1))
> (if (!HONOR_SIGNED_ZEROS (type)
> ...
This pattern is a conditional operation that treats a vector as a complete
unit, it's more like cbranchm which is different from vec_cond_expr.
So I add my patterns after this.
>
> I think. Consider at least placing the new patterns next to that.
Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
Ok for trunk?
Similar for A < B ? B : A to MAX_EXPR.
There're codes in the frontend to optimize such pattern but failed to
handle testcase in the PR since it's exposed at gimple level when
folding backend builtins.
pr95906 now can be optimized to MAX_EXPR as it's commented in the
testcase.
// FIXME: this should further optimize to a MAX_EXPR
typedef signed char v16i8 __attribute__((vector_size(16)));
v16i8 f(v16i8 a, v16i8 b)
gcc/ChangeLog:
PR target/104401
* match.pd (VEC_COND_EXPR: A < B ? A : B -> MIN_EXPR): New patten match.
gcc/testsuite/ChangeLog:
* gcc.target/i386/pr104401.c: New test.
* gcc.dg/tree-ssa/pr95906.c: Adjust testcase.
---
gcc/match.pd | 21 ++++++++++++++++++
gcc/testsuite/gcc.dg/tree-ssa/pr95906.c | 3 +--
gcc/testsuite/gcc.target/i386/pr104401.c | 27 ++++++++++++++++++++++++
3 files changed, 49 insertions(+), 2 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/i386/pr104401.c
Comments
On Tue, Jan 9, 2024 at 11:48 AM liuhongt <hongtao.liu@intel.com> wrote:
>
> > I wonder if you can amend the existing patterns instead by iterating
> > over cond/vec_cond. There are quite some (look for uses of
> > minmax_from_comparison) that could be adapted to vectors.
> >
> > The ones matching the simple form you match are
> >
> > #if GIMPLE
> > /* A >= B ? A : B -> max (A, B) and friends. The code is still
> > in fold_cond_expr_with_comparison for GENERIC folding with
> > some extra constraints. */
> > (for cmp (eq ne le lt unle unlt ge gt unge ungt uneq ltgt)
> > (simplify
> > (cond (cmp:c (nop_convert1?@c0 @0) (nop_convert2?@c1 @1))
> > (convert3? @0) (convert4? @1))
> > (if (!HONOR_SIGNED_ZEROS (type)
> > ...
> This pattern is a conditional operation that treats a vector as a complete
> unit, it's more like cbranchm which is different from vec_cond_expr.
> So I add my patterns after this.
> >
> > I think. Consider at least placing the new patterns next to that.
>
>
> Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
> Ok for trunk?
OK.
Richard.
> Similar for A < B ? B : A to MAX_EXPR.
> There're codes in the frontend to optimize such pattern but failed to
> handle testcase in the PR since it's exposed at gimple level when
> folding backend builtins.
>
> pr95906 now can be optimized to MAX_EXPR as it's commented in the
> testcase.
>
> // FIXME: this should further optimize to a MAX_EXPR
> typedef signed char v16i8 __attribute__((vector_size(16)));
> v16i8 f(v16i8 a, v16i8 b)
>
> gcc/ChangeLog:
>
> PR target/104401
> * match.pd (VEC_COND_EXPR: A < B ? A : B -> MIN_EXPR): New patten match.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/i386/pr104401.c: New test.
> * gcc.dg/tree-ssa/pr95906.c: Adjust testcase.
> ---
> gcc/match.pd | 21 ++++++++++++++++++
> gcc/testsuite/gcc.dg/tree-ssa/pr95906.c | 3 +--
> gcc/testsuite/gcc.target/i386/pr104401.c | 27 ++++++++++++++++++++++++
> 3 files changed, 49 insertions(+), 2 deletions(-)
> create mode 100644 gcc/testsuite/gcc.target/i386/pr104401.c
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index 7b4b15acc41..d8e2009a83f 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -5672,6 +5672,27 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> (if (VECTOR_TYPE_P (type))
> (view_convert @c0)
> (convert @c0))))))))
> +
> +/* This is for VEC_COND_EXPR
> + Optimize A < B ? A : B to MIN (A, B)
> + A > B ? A : B to MAX (A, B). */
> +(for cmp (lt le ungt unge gt ge unlt unle)
> + minmax (min min min min max max max max)
> + MINMAX (MIN_EXPR MIN_EXPR MIN_EXPR MIN_EXPR MAX_EXPR MAX_EXPR MAX_EXPR MAX_EXPR)
> + (simplify
> + (vec_cond (cmp @0 @1) @0 @1)
> + (if (VECTOR_INTEGER_TYPE_P (type)
> + && target_supports_op_p (type, MINMAX, optab_vector))
> + (minmax @0 @1))))
> +
> +(for cmp (lt le ungt unge gt ge unlt unle)
> + minmax (max max max max min min min min)
> + MINMAX (MAX_EXPR MAX_EXPR MAX_EXPR MAX_EXPR MIN_EXPR MIN_EXPR MIN_EXPR MIN_EXPR)
> + (simplify
> + (vec_cond (cmp @0 @1) @1 @0)
> + (if (VECTOR_INTEGER_TYPE_P (type)
> + && target_supports_op_p (type, MINMAX, optab_vector))
> + (minmax @0 @1))))
> #endif
>
> (for cnd (cond vec_cond)
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr95906.c b/gcc/testsuite/gcc.dg/tree-ssa/pr95906.c
> index 3d820a58e93..d15670f3e9e 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/pr95906.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr95906.c
> @@ -1,7 +1,6 @@
> /* { dg-do compile } */
> /* { dg-options "-O2 -fdump-tree-forwprop3-raw -w -Wno-psabi" } */
>
> -// FIXME: this should further optimize to a MAX_EXPR
> typedef signed char v16i8 __attribute__((vector_size(16)));
> v16i8 f(v16i8 a, v16i8 b)
> {
> @@ -10,4 +9,4 @@ v16i8 f(v16i8 a, v16i8 b)
> }
>
> /* { dg-final { scan-tree-dump-not "bit_(and|ior)_expr" "forwprop3" } } */
> -/* { dg-final { scan-tree-dump-times "vec_cond_expr" 1 "forwprop3" } } */
> +/* { dg-final { scan-tree-dump-times "max_expr" 1 "forwprop3" } } */
> diff --git a/gcc/testsuite/gcc.target/i386/pr104401.c b/gcc/testsuite/gcc.target/i386/pr104401.c
> new file mode 100644
> index 00000000000..8ce7ff88d9e
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr104401.c
> @@ -0,0 +1,27 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -msse4.1" } */
> +/* { dg-final { scan-assembler-times "pminsd" 2 } } */
> +/* { dg-final { scan-assembler-times "pmaxsd" 2 } } */
> +
> +#include <smmintrin.h>
> +
> +__m128i min32(__m128i value, __m128i input)
> +{
> + return _mm_blendv_epi8(input, value, _mm_cmplt_epi32(value, input));
> +}
> +
> +__m128i max32(__m128i value, __m128i input)
> +{
> + return _mm_blendv_epi8(input, value, _mm_cmpgt_epi32(value, input));
> +}
> +
> +__m128i min32_1(__m128i value, __m128i input)
> +{
> + return _mm_blendv_epi8(input, value, _mm_cmpgt_epi32(input, value));
> +}
> +
> +__m128i max32_1(__m128i value, __m128i input)
> +{
> + return _mm_blendv_epi8(input, value, _mm_cmplt_epi32(input, value));
> +}
> +
> --
> 2.31.1
>
@@ -5672,6 +5672,27 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(if (VECTOR_TYPE_P (type))
(view_convert @c0)
(convert @c0))))))))
+
+/* This is for VEC_COND_EXPR
+ Optimize A < B ? A : B to MIN (A, B)
+ A > B ? A : B to MAX (A, B). */
+(for cmp (lt le ungt unge gt ge unlt unle)
+ minmax (min min min min max max max max)
+ MINMAX (MIN_EXPR MIN_EXPR MIN_EXPR MIN_EXPR MAX_EXPR MAX_EXPR MAX_EXPR MAX_EXPR)
+ (simplify
+ (vec_cond (cmp @0 @1) @0 @1)
+ (if (VECTOR_INTEGER_TYPE_P (type)
+ && target_supports_op_p (type, MINMAX, optab_vector))
+ (minmax @0 @1))))
+
+(for cmp (lt le ungt unge gt ge unlt unle)
+ minmax (max max max max min min min min)
+ MINMAX (MAX_EXPR MAX_EXPR MAX_EXPR MAX_EXPR MIN_EXPR MIN_EXPR MIN_EXPR MIN_EXPR)
+ (simplify
+ (vec_cond (cmp @0 @1) @1 @0)
+ (if (VECTOR_INTEGER_TYPE_P (type)
+ && target_supports_op_p (type, MINMAX, optab_vector))
+ (minmax @0 @1))))
#endif
(for cnd (cond vec_cond)
@@ -1,7 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O2 -fdump-tree-forwprop3-raw -w -Wno-psabi" } */
-// FIXME: this should further optimize to a MAX_EXPR
typedef signed char v16i8 __attribute__((vector_size(16)));
v16i8 f(v16i8 a, v16i8 b)
{
@@ -10,4 +9,4 @@ v16i8 f(v16i8 a, v16i8 b)
}
/* { dg-final { scan-tree-dump-not "bit_(and|ior)_expr" "forwprop3" } } */
-/* { dg-final { scan-tree-dump-times "vec_cond_expr" 1 "forwprop3" } } */
+/* { dg-final { scan-tree-dump-times "max_expr" 1 "forwprop3" } } */
new file mode 100644
@@ -0,0 +1,27 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse4.1" } */
+/* { dg-final { scan-assembler-times "pminsd" 2 } } */
+/* { dg-final { scan-assembler-times "pmaxsd" 2 } } */
+
+#include <smmintrin.h>
+
+__m128i min32(__m128i value, __m128i input)
+{
+ return _mm_blendv_epi8(input, value, _mm_cmplt_epi32(value, input));
+}
+
+__m128i max32(__m128i value, __m128i input)
+{
+ return _mm_blendv_epi8(input, value, _mm_cmpgt_epi32(value, input));
+}
+
+__m128i min32_1(__m128i value, __m128i input)
+{
+ return _mm_blendv_epi8(input, value, _mm_cmpgt_epi32(input, value));
+}
+
+__m128i max32_1(__m128i value, __m128i input)
+{
+ return _mm_blendv_epi8(input, value, _mm_cmplt_epi32(input, value));
+}
+