Re: [PATCH] Optimize vec_splats of vec_extract for V2DI/V2DF (PR target/99293)

["Kewen.Lin" <linkw@linux.ibm.com>]

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  <meissner@linux.ibm.com>
> 
> gcc/
> 
> 	PR target/99293
> 	* gcc/config/rs6000/vsx.md (vsx_splat_extract_<mode>): 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_<mode>_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_<mode>"
> +  [(set (match_operand:VSX_D 0 "vsx_register_operand" "=wa")
> +	(vec_duplicate:VSX_D
> +	 (vec_select:<VEC_base>
> +	  (match_operand:VSX_D 1 "vsx_register_operand" "wa")
> +	  (parallel [(match_operand 2 "const_0_to_1_operand" "n")]))))]
> +  "VECTOR_MEM_VSX_P (<MODE>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 00000000000..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 <altivec.h>
> +
> +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 } } */

..., same for the below ones. 

> +/* { dg-final { scan-assembler-not   "mfvsrd"     } } */
> +/* { dg-final { scan-assembler-not   "mfvsrld"    } } */
> +/* { dg-final { scan-assembler-not   "mtvsrdd"    } } */

This patch is okay for trunk with these nits tweaked,
thanks!

BR,
Kewen