On Fri, 4 Nov 2022 at 05:36, Hongyu Wang via Gcc-patches
<gcc-patches@gcc.gnu.org> wrote:
>
> Hi,
>
> This is a follow-up patch for PR98167
>
> The sequence
> c1 = VEC_PERM_EXPR (a, a, mask)
> c2 = VEC_PERM_EXPR (b, b, mask)
> c3 = c1 op c2
> can be optimized to
> c = a op b
> c3 = VEC_PERM_EXPR (c, c, mask)
> for all integer vector operation, and float operation with
> full permutation.
>
> Bootstrapped & regrtested on x86_64-pc-linux-gnu.
>
> Ok for trunk?
>
> gcc/ChangeLog:
>
> PR target/98167
> * match.pd: New perm + vector op patterns for int and fp vector.
>
> gcc/testsuite/ChangeLog:
>
> PR target/98167
> * gcc.target/i386/pr98167.c: New test.
> ---
> gcc/match.pd | 49 +++++++++++++++++++++++++
> gcc/testsuite/gcc.target/i386/pr98167.c | 44 ++++++++++++++++++++++
> 2 files changed, 93 insertions(+)
> create mode 100644 gcc/testsuite/gcc.target/i386/pr98167.c
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index 194ba8f5188..b85ad34f609 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -8189,3 +8189,52 @@ and,
> (bit_and (negate @0) integer_onep@1)
> (if (!TYPE_OVERFLOW_SANITIZED (type))
> (bit_and @0 @1)))
> +
> +/* Optimize
> + c1 = VEC_PERM_EXPR (a, a, mask)
> + c2 = VEC_PERM_EXPR (b, b, mask)
> + c3 = c1 op c2
> + -->
> + c = a op b
> + c3 = VEC_PERM_EXPR (c, c, mask)
> + For all integer non-div operations. */
> +(for op (plus minus mult bit_and bit_ior bit_xor
> + lshift rshift)
> + (simplify
> + (op (vec_perm @0 @0 VECTOR_CST@2) (vec_perm @1 @1 VECTOR_CST@2))
> + (if (VECTOR_INTEGER_TYPE_P (type))
> + (vec_perm (op @0 @1) (op @0 @1) @2))))
Just wondering, why should mask be CST here ?
I guess the transform should work as long as mask is same for both
vectors even if it's
not constant ?
> +
> +/* Similar for float arithmetic when permutation constant covers
> + all vector elements. */
> +(for op (plus minus mult)
> + (simplify
> + (op (vec_perm @0 @0 VECTOR_CST@2) (vec_perm @1 @1 VECTOR_CST@2))
> + (if (VECTOR_FLOAT_TYPE_P (type))
> + (with
> + {
> + tree perm_cst = @2;
> + vec_perm_builder builder;
> + bool full_perm_p = false;
> + if (tree_to_vec_perm_builder (&builder, perm_cst))
> + {
> + /* Create a vec_perm_indices for the integer vector. */
> + int nelts = TYPE_VECTOR_SUBPARTS (type).to_constant ();
If this transform is meant only for VLS vectors, I guess you should
bail out if TYPE_VECTOR_SUBPARTS is not constant,
otherwise it will crash for VLA vectors.
Thanks,
Prathamesh
> + vec_perm_indices sel (builder, 1, nelts);
> +
> + /* Check if perm indices covers all vector elements. */
> + int count = 0, i, j;
> + for (i = 0; i < nelts; i++)
> + for (j = 0; j < nelts; j++)
> + {
> + if (sel[j].to_constant () == i)
> + {
> + count++;
> + break;
> + }
> + }
> + full_perm_p = count == nelts;
> + }
> + }
> + (if (full_perm_p)
> + (vec_perm (op @0 @1) (op @0 @1) @2))))))
> diff --git a/gcc/testsuite/gcc.target/i386/pr98167.c
> b/gcc/testsuite/gcc.target/i386/pr98167.c
> new file mode 100644
> index 00000000000..40e0ac11332
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr98167.c
> @@ -0,0 +1,44 @@
> +/* PR target/98167 */
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -mavx2" } */
> +
> +/* { dg-final { scan-assembler-times "vpshufd\t" 8 } } */
> +/* { dg-final { scan-assembler-times "vpermilps\t" 3 } } */
> +
> +#define VEC_PERM_4 \
> + 2, 3, 1, 0
> +#define VEC_PERM_8 \
> + 4, 5, 6, 7, 3, 2, 1, 0
> +#define VEC_PERM_16 \
> + 8, 9, 10, 11, 12, 13, 14, 15, 7, 6, 5, 4, 3, 2, 1, 0
> +
> +#define TYPE_PERM_OP(type, size, op, name) \
> + typedef type v##size##s##type __attribute__ ((vector_size(4*size))); \
> + v##size##s##type type##foo##size##i_##name (v##size##s##type a, \
> + v##size##s##type b) \
> + { \
> + v##size##s##type a1 = __builtin_shufflevector (a, a, \
> + VEC_PERM_##size); \
> + v##size##s##type b1 = __builtin_shufflevector (b, b, \
> + VEC_PERM_##size); \
> + return a1 op b1; \
> + }
> +
> +#define INT_PERMS(op, name) \
> + TYPE_PERM_OP (int, 4, op, name) \
> +
> +#define FP_PERMS(op, name) \
> + TYPE_PERM_OP (float, 4, op, name) \
> +
> +INT_PERMS (+, add)
> +INT_PERMS (-, sub)
> +INT_PERMS (*, mul)
> +INT_PERMS (|, ior)
> +INT_PERMS (^, xor)
> +INT_PERMS (&, and)
> +INT_PERMS (<<, shl)
> +INT_PERMS (>>, shr)
> +FP_PERMS (+, add)
> +FP_PERMS (-, sub)
> +FP_PERMS (*, mul)
> +
> --
> 2.18.1
>
