diff options
| author | H.J. Lu <hjl.tools@gmail.com> | 2016-04-06 09:10:18 -0700 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2016-04-06 09:10:35 -0700 |
| commit | 4af1bb06c59d24f35bf8dc55897838d926c05892 (patch) | |
| tree | 905c9d344060fde892d029d30015883fc4d2798a | |
| parent | a25322f4e855eb5b24c63c2395c941c3327627ca (diff) | |
| download | glibc-4af1bb06c59d24f35bf8dc55897838d926c05892.tar.gz glibc-4af1bb06c59d24f35bf8dc55897838d926c05892.tar.xz glibc-4af1bb06c59d24f35bf8dc55897838d926c05892.zip | |
X86-64: Prepare memset-vec-unaligned-erms.S
Prepare memset-vec-unaligned-erms.S to make the SSE2 version as the default memset. * sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S (MEMSET_CHK_SYMBOL): New. Define if not defined. (__bzero): Check VEC_SIZE == 16 instead of USE_MULTIARCH. Disabled fro now. Replace MEMSET_SYMBOL with MEMSET_CHK_SYMBOL on __memset_chk symbols. Properly check USE_MULTIARCH on __memset symbols.
| -rw-r--r-- | ChangeLog | 9 | ||||
| -rw-r--r-- | sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S | 32 |
2 files changed, 28 insertions, 13 deletions
diff --git a/ChangeLog b/ChangeLog index 4ba9309333..c801aff3f3 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,5 +1,14 @@ 2016-04-06 H.J. Lu <hongjiu.lu@intel.com> + * sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S + (MEMSET_CHK_SYMBOL): New. Define if not defined. + (__bzero): Check VEC_SIZE == 16 instead of USE_MULTIARCH. + Disabled fro now. + Replace MEMSET_SYMBOL with MEMSET_CHK_SYMBOL on __memset_chk + symbols. Properly check USE_MULTIARCH on __memset symbols. + +2016-04-06 H.J. Lu <hongjiu.lu@intel.com> + * benchtests/Makefile (string-benchset): Add memcpy-large, memmove-large and memset-large. * benchtests/bench-memcpy-large.c: New file. diff --git a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S index fe0f74516d..578a5ae0a2 100644 --- a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S +++ b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S @@ -28,6 +28,10 @@ #include <sysdep.h> +#ifndef MEMSET_CHK_SYMBOL +# define MEMSET_CHK_SYMBOL(p,s) MEMSET_SYMBOL(p, s) +#endif + #ifndef VZEROUPPER # if VEC_SIZE > 16 # define VZEROUPPER vzeroupper @@ -66,8 +70,8 @@ # error SECTION is not defined! #endif -#if !defined USE_MULTIARCH && IS_IN (libc) .section SECTION(.text),"ax",@progbits +#if VEC_SIZE == 16 && IS_IN (libc) && 0 ENTRY (__bzero) movq %rdi, %rax /* Set return value. */ movq %rsi, %rdx /* Set n. */ @@ -78,10 +82,10 @@ weak_alias (__bzero, bzero) #endif #if defined SHARED && IS_IN (libc) -ENTRY_CHK (MEMSET_SYMBOL (__memset_chk, unaligned)) +ENTRY_CHK (MEMSET_CHK_SYMBOL (__memset_chk, unaligned)) cmpq %rdx, %rcx jb HIDDEN_JUMPTARGET (__chk_fail) -END_CHK (MEMSET_SYMBOL (__memset_chk, unaligned)) +END_CHK (MEMSET_CHK_SYMBOL (__memset_chk, unaligned)) #endif ENTRY (MEMSET_SYMBOL (__memset, unaligned)) @@ -97,15 +101,16 @@ L(entry_from_bzero): VMOVU %VEC(0), (%rdi) VZEROUPPER ret +#if defined USE_MULTIARCH && IS_IN (libc) END (MEMSET_SYMBOL (__memset, unaligned)) -#if VEC_SIZE == 16 +# if VEC_SIZE == 16 /* Only used to measure performance of REP STOSB. */ ENTRY (__memset_erms) -#else +# else /* Provide a symbol to debugger. */ ENTRY (MEMSET_SYMBOL (__memset, erms)) -#endif +# endif L(stosb): movq %rdx, %rcx movzbl %sil, %eax @@ -113,18 +118,18 @@ L(stosb): rep stosb movq %rdx, %rax ret -#if VEC_SIZE == 16 +# if VEC_SIZE == 16 END (__memset_erms) -#else +# else END (MEMSET_SYMBOL (__memset, erms)) -#endif +# endif -#if defined SHARED && IS_IN (libc) -ENTRY_CHK (MEMSET_SYMBOL (__memset_chk, unaligned_erms)) +# if defined SHARED && IS_IN (libc) +ENTRY_CHK (MEMSET_CHK_SYMBOL (__memset_chk, unaligned_erms)) cmpq %rdx, %rcx jb HIDDEN_JUMPTARGET (__chk_fail) -END_CHK (MEMSET_SYMBOL (__memset_chk, unaligned_erms)) -#endif +END_CHK (MEMSET_CHK_SYMBOL (__memset_chk, unaligned_erms)) +# endif ENTRY (MEMSET_SYMBOL (__memset, unaligned_erms)) VDUP_TO_VEC0_AND_SET_RETURN (%esi, %rdi) @@ -144,6 +149,7 @@ L(stosb_more_2x_vec): /* Force 32-bit displacement to avoid long nop between instructions. */ ja.d32 L(stosb) +#endif .p2align 4 L(more_2x_vec): cmpq $(VEC_SIZE * 4), %rdx |