diff options
author | Noah Goldstein <goldstein.w.n@gmail.com> | 2022-07-13 16:32:59 -0700 |
---|---|---|
committer | Noah Goldstein <goldstein.w.n@gmail.com> | 2022-07-16 03:07:59 -0700 |
commit | ceabdcd130ca7043b0fcf2676183d79431d10493 (patch) | |
tree | f6ced435023b66ac1f3b519e5b26a60ef8f479dd /sysdeps/x86_64/multiarch/strcmp-sse2-unaligned.S | |
parent | c353689e49e72f3aafa1a9e68d4f7a4f33a79cbe (diff) | |
download | glibc-ceabdcd130ca7043b0fcf2676183d79431d10493.tar.gz glibc-ceabdcd130ca7043b0fcf2676183d79431d10493.tar.xz glibc-ceabdcd130ca7043b0fcf2676183d79431d10493.zip |
x86: Add support to build strcmp/strlen/strchr with explicit ISA level
1. Add default ISA level selection in non-multiarch/rtld implementations. 2. Add ISA level build guards to different implementations. - I.e strcmp-avx2.S which is ISA level 3 will only build if compiled ISA level <= 3. Otherwise there is no reason to include it as we will always use one of the ISA level 4 implementations (strcmp-evex.S). 3. Refactor the ifunc selector and ifunc implementation list to use the ISA level aware wrapper macros that allow functions below the compiled ISA level (with a guranteed replacement) to be skipped. Tested with and without multiarch on x86_64 for ISA levels: {generic, x86-64-v2, x86-64-v3, x86-64-v4} And m32 with and without multiarch.
Diffstat (limited to 'sysdeps/x86_64/multiarch/strcmp-sse2-unaligned.S')
-rw-r--r-- | sysdeps/x86_64/multiarch/strcmp-sse2-unaligned.S | 18 |
1 files changed, 13 insertions, 5 deletions
diff --git a/sysdeps/x86_64/multiarch/strcmp-sse2-unaligned.S b/sysdeps/x86_64/multiarch/strcmp-sse2-unaligned.S index 0d691b78a8..33c18a28e8 100644 --- a/sysdeps/x86_64/multiarch/strcmp-sse2-unaligned.S +++ b/sysdeps/x86_64/multiarch/strcmp-sse2-unaligned.S @@ -16,11 +16,20 @@ License along with the GNU C Library; if not, see <https://www.gnu.org/licenses/>. */ -#if IS_IN (libc) +#include <isa-level.h> -#include "sysdep.h" +/* Continue building as ISA level 2. We use this as ISA V2 default + because strcmp-sse42 uses pcmpstri (slow on some SSE4.2 + processors) and this implementation is potenially faster than + strcmp-sse42 (aside from the slower page cross case). */ +#if ISA_SHOULD_BUILD (2) -ENTRY ( __strcmp_sse2_unaligned) +# define STRCMP_ISA _sse2_unaligned +# include "strcmp-naming.h" + +# include "sysdep.h" + +ENTRY (STRCMP) movl %edi, %eax xorl %edx, %edx pxor %xmm7, %xmm7 @@ -208,6 +217,5 @@ L(cross_page): L(different): subl %ecx, %eax ret -END (__strcmp_sse2_unaligned) - +END (STRCMP) #endif |