On Fri, Aug 2, 2019 at 9:54 AM Jakub Jelinek <ja...@redhat.com> wrote:
>
> Hi!
>
> As mentioned in the PR, for SSE4.1 we use pextrb for vec_extractv16qiqi,
> but at least for element 0 we store the vector into memory and load the
> single byte from there and we can just use movd instead.
>
> The following patch does that, just skips it for the case when we know we'll
> go through memory anyway.
>
> Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
>
> For the non-Os case, perhaps we could also handle other (elt & 3) == 0 cases
> which V4SImode ix86_expand_vector_extract also handles through shuffles
> (pshufd or unpck*) before the movd, just not sure if it is a win.
>
> 2019-08-01 Jakub Jelinek <ja...@redhat.com>
>
> PR tree-optimization/91201
> * config/i386/i386-expand.c (ix86_expand_vector_extract): For elt == 0
> V16QImode extraction without sse4.1 try to use V4SImode lowpart
> extraction.
>
> * gcc.target/i386/sse2-pr91201-3.c: New test.
> * gcc.target/i386/sse2-pr91201-4.c: New test.
> * gcc.target/i386/sse2-pr91201-5.c: New test.
> * gcc.target/i386/sse2-pr91201-6.c: New test.
OK.
Thanks,
Uros.
> --- gcc/config/i386/i386-expand.c.jj 2019-07-30 09:12:34.578959902 +0200
> +++ gcc/config/i386/i386-expand.c 2019-08-01 10:41:22.545887899 +0200
> @@ -14706,6 +14706,17 @@ ix86_expand_vector_extract (bool mmx_ok,
>
> case E_V16QImode:
> use_vec_extr = TARGET_SSE4_1;
> + if (!use_vec_extr
> + && TARGET_SSE2
> + && elt == 0
> + && (optimize_insn_for_size_p () ||
> TARGET_INTER_UNIT_MOVES_FROM_VEC))
> + {
> + tmp = gen_reg_rtx (SImode);
> + ix86_expand_vector_extract (false, tmp, gen_lowpart (V4SImode, vec),
> + 0);
> + emit_insn (gen_rtx_SET (target, gen_lowpart (QImode, tmp)));
> + return;
> + }
> break;
>
> case E_V8SFmode:
> --- gcc/testsuite/gcc.target/i386/sse2-pr91201-3.c.jj 2019-08-01
> 10:59:07.508887273 +0200
> +++ gcc/testsuite/gcc.target/i386/sse2-pr91201-3.c 2019-08-01
> 11:07:42.925165205 +0200
> @@ -0,0 +1,13 @@
> +/* PR tree-optimization/91201 */
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -msse2 -mno-sse3 -mtune=generic -masm=att" } */
> +/* { dg-final { scan-assembler "\tmovd\t%xmm0, %eax" } } */
> +/* { dg-final { scan-assembler-not "\\(%" } } */
> +
> +typedef unsigned char V __attribute__((vector_size (16)));
> +
> +unsigned char
> +foo (V x)
> +{
> + return x[0];
> +}
> --- gcc/testsuite/gcc.target/i386/sse2-pr91201-4.c.jj 2019-08-01
> 10:59:33.539497274 +0200
> +++ gcc/testsuite/gcc.target/i386/sse2-pr91201-4.c 2019-08-01
> 11:07:35.304279381 +0200
> @@ -0,0 +1,13 @@
> +/* PR tree-optimization/91201 */
> +/* { dg-do compile } */
> +/* { dg-options "-Os -msse2 -mno-sse3 -mtune=generic -masm=att" } */
> +/* { dg-final { scan-assembler "\tmovd\t%xmm0, %eax" } } */
> +/* { dg-final { scan-assembler-not "\\(%" } } */
> +
> +typedef unsigned char V __attribute__((vector_size (16)));
> +
> +unsigned char
> +foo (V x)
> +{
> + return x[0];
> +}
> --- gcc/testsuite/gcc.target/i386/sse2-pr91201-5.c.jj 2019-08-01
> 11:01:07.994082143 +0200
> +++ gcc/testsuite/gcc.target/i386/sse2-pr91201-5.c 2019-08-01
> 11:07:19.230520198 +0200
> @@ -0,0 +1,13 @@
> +/* PR tree-optimization/91201 */
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -msse2 -mno-sse3 -mtune=k8 -masm=att" } */
> +/* { dg-final { scan-assembler-not "\tmovd\t%xmm0, %eax" } } */
> +/* { dg-final { scan-assembler "\tmov(zbl|b)\t\[^\n\r]*\\(%" } } */
> +
> +typedef unsigned char V __attribute__((vector_size (16)));
> +
> +unsigned char
> +foo (V x)
> +{
> + return x[0];
> +}
> --- gcc/testsuite/gcc.target/i386/sse2-pr91201-6.c.jj 2019-08-01
> 11:03:34.896881216 +0200
> +++ gcc/testsuite/gcc.target/i386/sse2-pr91201-6.c 2019-08-01
> 11:07:27.564395340 +0200
> @@ -0,0 +1,13 @@
> +/* PR tree-optimization/91201 */
> +/* { dg-do compile } */
> +/* { dg-options "-Os -msse2 -mno-sse3 -mtune=k8 -masm=att" } */
> +/* { dg-final { scan-assembler "\tmovd\t%xmm0, %eax" } } */
> +/* { dg-final { scan-assembler-not "\\(%" } } */
> +
> +typedef unsigned char V __attribute__((vector_size (16)));
> +
> +unsigned char
> +foo (V x)
> +{
> + return x[0];
> +}
>
> Jakub
