Hi Mike,
on 2023/7/11 03:50, Michael Meissner wrote:
> This patch optimizes cases like:
>
> vector double v1, v2;
> /* ... */
> v2 = vec_splats (vec_extract (v1, 0); /* or */
> v2 = vec_splats (vec_extract (v1, 1);
>
> Previously:
>
> vector long long
> splat_dup_l_0 (vector long long v)
> {
> return __builtin_vec_splats (__builtin_vec_extract (v, 0));
> }
>
> would generate:
>
> mfvsrld 9,34
> mtvsrdd 34,9,9
> blr
>
> With this patch, GCC generates:
>
> xxpermdi 34,34,34,3
> blr
> > 2023-07-10 Michael Meissner
>
> gcc/
>
> PR target/99293
> * gcc/config/rs6000/vsx.md (vsx_splat_extract_): New combiner
> insn.
>
> gcc/testsuite/
>
> PR target/108958
> * gcc.target/powerpc/pr99293.c: New test.
> * gcc.target/powerpc/builtins-1.c: Update insn count.
> ---
> gcc/config/rs6000/vsx.md | 18 ++
> gcc/testsuite/gcc.target/powerpc/builtins-1.c | 2 +-
> gcc/testsuite/gcc.target/powerpc/pr99293.c| 55 +++
> 3 files changed, 74 insertions(+), 1 deletion(-)
> create mode 100644 gcc/testsuite/gcc.target/powerpc/pr99293.c
>
> diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
> index 0c269e4e8d9..d34c3b21abe 100644
> --- a/gcc/config/rs6000/vsx.md
> +++ b/gcc/config/rs6000/vsx.md
> @@ -4600,6 +4600,24 @@ (define_insn "vsx_splat__mem"
>"lxvdsx %x0,%y1"
>[(set_attr "type" "vecload")])
>
> +;; Optimize SPLAT of an extract from a V2DF/V2DI vector with a constant
> element
> +(define_insn "*vsx_splat_extract_"
> + [(set (match_operand:VSX_D 0 "vsx_register_operand" "=wa")
> + (vec_duplicate:VSX_D
> + (vec_select:
> + (match_operand:VSX_D 1 "vsx_register_operand" "wa")
> + (parallel [(match_operand 2 "const_0_to_1_operand" "n")]]
> + "VECTOR_MEM_VSX_P (mode)"
> +{
> + int which_word = INTVAL (operands[2]);
> + if (!BYTES_BIG_ENDIAN)
> +which_word = 1 - which_word;
> +
> + operands[3] = GEN_INT (which_word ? 3 : 0);
> + return "xxpermdi %x0,%x1,%x1,%3";
> +}
> + [(set_attr "type" "vecperm")])
> +
> ;; V4SI splat support
> (define_insn "vsx_splat_v4si"
>[(set (match_operand:V4SI 0 "vsx_register_operand" "=wa,wa")
> diff --git a/gcc/testsuite/gcc.target/powerpc/builtins-1.c
> b/gcc/testsuite/gcc.target/powerpc/builtins-1.c
> index 28cd1aa6b1a..98783668bce 100644
> --- a/gcc/testsuite/gcc.target/powerpc/builtins-1.c
> +++ b/gcc/testsuite/gcc.target/powerpc/builtins-1.c
> @@ -1035,4 +1035,4 @@ foo156 (vector unsigned short usa)
> /* { dg-final { scan-assembler-times {\mvmrglb\M} 3 } } */
> /* { dg-final { scan-assembler-times {\mvmrgew\M} 4 } } */
> /* { dg-final { scan-assembler-times {\mvsplth|xxsplth\M} 4 } } */
> -/* { dg-final { scan-assembler-times {\mxxpermdi\M} 44 } } */
> +/* { dg-final { scan-assembler-times {\mxxpermdi\M} 42 } } */
> diff --git a/gcc/testsuite/gcc.target/powerpc/pr99293.c
> b/gcc/testsuite/gcc.target/powerpc/pr99293.c
> new file mode 100644
> index 000..e5f44bd7346
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/pr99293.c
> @@ -0,0 +1,55 @@
> +/* { dg-require-effective-target powerpc_p8vector_ok } */
> +/* { dg-options "-O2 -mpower8-vector" } */
Nit: IMHO -mdejagnu-cpu=power8 is preferred against -mpower8-vector which is
considered as a workaround option, and we plan to make it go away.
> +
> +/* Test for PR 99263, which wants to do:
> + __builtin_vec_splats (__builtin_vec_extract (v, n))
Nit: Maybe remove all "__builtin_" prefixes since vec_splats and vec_extract
are defined in PVIPR without __builtin_.
This is also applied for the others below.
> +
> + where v is a V2DF or V2DI vector and n is either 0 or 1. Previously the
> GCC
> + compiler would do a direct move to the GPR registers to select the item
> and a
> + direct move from the GPR registers to do the splat.
> +
> + Before the patch, splat_dup_ll_0 or splat_dup_dbl_0 below would generate:
> +
> +mfvsrld 9,34
> +mtvsrdd 34,9,9
> +blr
> +
> + and now it generates:
> +
> +xxpermdi 34,34,34,3
> +blr */
> +
> +#include
> +
> +vector long long
> +splat_dup_ll_0 (vector long long v)
> +{
> + /* xxpermdi 34,34,34,3 */
> + return __builtin_vec_splats (vec_extract (v, 0));
> +}
> +
> +vector double
> +splat_dup_dbl_0 (vector double v)
> +{
> + /* xxpermdi 34,34,34,3 */
> + return __builtin_vec_splats (vec_extract (v, 0));
> +}
> +
> +vector long long
> +splat_dup_ll_1 (vector long long v)
> +{
> + /* xxpermdi 34,34,34,0 */
> + return __builtin_vec_splats (vec_extract (v, 1));
> +}
> +
> +vector double
> +splat_dup_dbl_1 (vector double v)
> +{
> + /* xxpermdi 34,34,34,0 */
> + return __builtin_vec_splats (vec_extract (v, 1));
> +}
> +
> +/* { dg-final { scan-assembler-times "xxpermdi" 4 } } */
Nit: It's good to add \m..\M like the others, i.e.
/* { dg-final { scan-assembler-times {\mxxpermdi\M} 4