diff options
| author | Noah Goldstein <goldstein.w.n@gmail.com> | 2022-06-29 16:07:06 -0700 |
|---|---|---|
| committer | Noah Goldstein <goldstein.w.n@gmail.com> | 2022-07-05 16:42:42 -0700 |
| commit | 37ecc657b22c3367a56df5ebd53908e34e65fa16 (patch) | |
| tree | 6df7e476a885ee4b9e0f89229a2d7bf6a63c9af0 /sysdeps/x86_64/memset.S | |
| parent | b6a02c360655cbb84772bb577fcd8ae54d7f6d82 (diff) | |
| download | glibc-37ecc657b22c3367a56df5ebd53908e34e65fa16.zip glibc-37ecc657b22c3367a56df5ebd53908e34e65fa16.tar.gz glibc-37ecc657b22c3367a56df5ebd53908e34e65fa16.tar.bz2 | |
x86: Add support for building {w}memset{_chk} with explicit ISA level
1. Refactor files so that all implementations are in the multiarch
directory
- Moved the implementation portion of memset sse2 from memset.S to
multiarch/memset-sse2.S
- The non-multiarch file now only includes one of the
implementations in the multiarch directory based on the compiled
ISA level (only used for non-multiarch builds. Otherwise we go
through the ifunc selector).
2. Add ISA level build guards to different implementations.
- I.e memset-avx2-unaligned-erms.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 (memset-evex-unaligned-erms.S).
3. Add new multiarch/rtld-memset.S that just include the
non-multiarch memset.S which will in turn select the best
implementation based on the compiled ISA level.
4. 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/memset.S')
| -rw-r--r-- | sysdeps/x86_64/memset.S | 45 |
1 files changed, 8 insertions, 37 deletions
diff --git a/sysdeps/x86_64/memset.S b/sysdeps/x86_64/memset.S index a6eea61..f4e1bab 100644 --- a/sysdeps/x86_64/memset.S +++ b/sysdeps/x86_64/memset.S @@ -18,47 +18,18 @@ <https://www.gnu.org/licenses/>. */ #include <sysdep.h> -#define USE_WITH_SSE2 1 -#define VEC_SIZE 16 -#define MOV_SIZE 3 -#define RET_SIZE 1 +#define MEMSET_SYMBOL(p,s) memset +#define MEMSET_CHK_SYMBOL(p,s) p -#define VEC(i) xmm##i -#define VMOVU movups -#define VMOVA movaps +#define WMEMSET_SYMBOL(p,s) __wmemset +#define WMEMSET_CHK_SYMBOL(p,s) p -# define MEMSET_SET_VEC0_AND_SET_RETURN(d, r) \ - movd d, %xmm0; \ - movq r, %rax; \ - punpcklbw %xmm0, %xmm0; \ - punpcklwd %xmm0, %xmm0; \ - pshufd $0, %xmm0, %xmm0 +#define DEFAULT_IMPL_V1 "multiarch/memset-sse2-unaligned-erms.S" +#define DEFAULT_IMPL_V3 "multiarch/memset-avx2-unaligned-erms.S" +#define DEFAULT_IMPL_V4 "multiarch/memset-evex-unaligned-erms.S" -# define WMEMSET_SET_VEC0_AND_SET_RETURN(d, r) \ - movd d, %xmm0; \ - pshufd $0, %xmm0, %xmm0; \ - movq r, %rax - -# define MEMSET_VDUP_TO_VEC0_HIGH() -# define MEMSET_VDUP_TO_VEC0_LOW() - -# define WMEMSET_VDUP_TO_VEC0_HIGH() -# define WMEMSET_VDUP_TO_VEC0_LOW() - -#define SECTION(p) p - -#ifndef MEMSET_SYMBOL -# define MEMSET_CHK_SYMBOL(p,s) p -# define MEMSET_SYMBOL(p,s) memset -#endif - -#ifndef WMEMSET_SYMBOL -# define WMEMSET_CHK_SYMBOL(p,s) p -# define WMEMSET_SYMBOL(p,s) __wmemset -#endif - -#include "multiarch/memset-vec-unaligned-erms.S" +#include "isa-default-impl.h" libc_hidden_builtin_def (memset) |