git
/
gcc
mirror of git://gcc.gnu.org/git/gcc.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Remove SPR/GNR/DMR from avx512_{move,store}_by pieces tune. 

Align move_max with prefer_vector_width for SPR/GNR/DMR similar as
below commit.

commit 6ea25c0419
Author: liuhongt <hongtao.liu@intel.com>
Date:   Thu Aug 15 12:54:07 2024 +0800

    Align ix86_{move_max,store_max} with vectorizer.

    When none of mprefer-vector-width, avx256_optimal/avx128_optimal,
    avx256_store_by_pieces/avx512_store_by_pieces is specified, GCC will
    set ix86_{move_max,store_max} as max available vector length except
    for AVX part.

                  if (TARGET_AVX512F_P (opts->x_ix86_isa_flags)
                      && TARGET_EVEX512_P (opts->x_ix86_isa_flags2))
                    opts->x_ix86_move_max = PVW_AVX512;
                  else
                    opts->x_ix86_move_max = PVW_AVX128;

    So for -mavx2, vectorizer will choose 256-bit for vectorization, but
    128-bit is used for struct copy, there could be a potential STLF issue
    due to this "misalign".

gcc/ChangeLog:

	* config/i386/x86-tune.def (X86_TUNE_AVX512_MOVE_BY_PIECES):
	Remove SPR/GNR/DMR.
	(X86_TUNE_AVX512_STORE_BY_PIECES): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pieces-memcpy-18.c: Use -mtune=znver5
	instead of -mtune=sapphirerapids.
	* gcc.target/i386/pieces-memcpy-21.c: Ditto.
	* gcc.target/i386/pieces-memset-46.c: Ditto.
	* gcc.target/i386/pieces-memset-49.c: Ditto.
This commit is contained in:
hongtao.liu 2025-09-16 03:23:45 +02:00 committed by liuhongt
parent 9bd24f83a1
commit dd713d0f3f
5 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
gcc/config/i386/x86-tune.def
View File

@ -612,6 +612,8 @@ DEF_TUNE (X86_TUNE_AVX256_AVOID_VEC_PERM,
/* X86_TUNE_AVX256_SPLIT_REGS: if true, AVX512 ops are split into two AVX256 ops. */
DEF_TUNE (X86_TUNE_AVX512_SPLIT_REGS, "avx512_split_regs", m_ZNVER4)
/* It's better to align MOVE_MAX with prefer_vector_width to reduce
risk of STLF stalls(small store followed by big load.) */
/* X86_TUNE_AVX256_MOVE_BY_PIECES: Optimize move_by_pieces with 256-bit
AVX instructions. */
DEF_TUNE (X86_TUNE_AVX256_MOVE_BY_PIECES, "avx256_move_by_pieces",
@ -625,14 +627,12 @@ DEF_TUNE (X86_TUNE_AVX256_STORE_BY_PIECES, "avx256_store_by_pieces",
/* X86_TUNE_AVX512_MOVE_BY_PIECES: Optimize move_by_pieces with 512-bit
AVX instructions. */
DEF_TUNE (X86_TUNE_AVX512_MOVE_BY_PIECES, "avx512_move_by_pieces",
m_SAPPHIRERAPIDS | m_GRANITERAPIDS | m_GRANITERAPIDS_D
| m_DIAMONDRAPIDS | m_ZNVER4 | m_ZNVER5)
m_ZNVER4 | m_ZNVER5)
/* X86_TUNE_AVX512_STORE_BY_PIECES: Optimize store_by_pieces with 512-bit
AVX instructions. */
DEF_TUNE (X86_TUNE_AVX512_STORE_BY_PIECES, "avx512_store_by_pieces",
m_SAPPHIRERAPIDS | m_GRANITERAPIDS | m_GRANITERAPIDS_D
| m_DIAMONDRAPIDS | m_ZNVER4 | m_ZNVER5)
m_ZNVER4 | m_ZNVER5)
/* X86_TUNE_AVX512_TWO_EPILOGUES: Use two vector epilogues for 512-bit
vectorized loops. */

2
gcc/testsuite/gcc.target/i386/pieces-memcpy-18.c
View File

@ -1,5 +1,5 @@
/* { dg-do compile } */
/* { dg-options "-O2 -march=sapphirerapids" } */
/* { dg-options "-O2 -march=znver5" } */
extern char *dst, *src;

2
gcc/testsuite/gcc.target/i386/pieces-memcpy-21.c
View File

@ -1,5 +1,5 @@
/* { dg-do compile } */
/* { dg-options "-O2 -mtune=sapphirerapids -march=x86-64 -mavx2" } */
/* { dg-options "-O2 -mtune=znver5 -march=x86-64 -mavx2" } */
extern char *dst, *src;

2
gcc/testsuite/gcc.target/i386/pieces-memset-46.c
View File

@ -1,5 +1,5 @@
/* { dg-do compile } */
/* { dg-options "-O2 -march=sapphirerapids" } */
/* { dg-options "-O2 -march=znver5" } */
extern char *dst;

2
gcc/testsuite/gcc.target/i386/pieces-memset-49.c
View File

@ -1,5 +1,5 @@
/* { dg-do compile } */
/* { dg-options "-O2 -mtune=sapphirerapids -march=x86-64 -mavx2" } */
/* { dg-options "-O2 -mtune=znver5 -march=x86-64 -mavx2" } */
extern char *dst;