x86-64: Optimize wmemset with SSE2/AVX2/AVX512

The difference between memset and wmemset is byte vs int.  Add stubs
to SSE2/AVX2/AVX512 memset for wmemset with updated constant and size:

SSE2 wmemset:
	shl    $0x2,%rdx
	movd   %esi,%xmm0
	mov    %rdi,%rax
	pshufd $0x0,%xmm0,%xmm0
	jmp	entry_from_wmemset

SSE2 memset:
	movd   %esi,%xmm0
	mov    %rdi,%rax
	punpcklbw %xmm0,%xmm0
	punpcklwd %xmm0,%xmm0
	pshufd $0x0,%xmm0,%xmm0
entry_from_wmemset:

Since the ERMS versions of wmemset requires "rep stosl" instead of
"rep stosb", only the vector store stubs of SSE2/AVX2/AVX512 wmemset
are added.  The SSE2 wmemset is about 3X faster and the AVX2 wmemset
is about 6X faster on Haswell.

	* include/wchar.h (__wmemset_chk): New.
	* sysdeps/x86_64/memset.S (VDUP_TO_VEC0_AND_SET_RETURN): Renamed
	to MEMSET_VDUP_TO_VEC0_AND_SET_RETURN.
	(WMEMSET_VDUP_TO_VEC0_AND_SET_RETURN): New.
	(WMEMSET_CHK_SYMBOL): Likewise.
	(WMEMSET_SYMBOL): Likewise.
	(__wmemset): Add hidden definition.
	(wmemset): Add weak hidden definition.
	* sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Add
	wmemset_chk-nonshared.
	* sysdeps/x86_64/multiarch/ifunc-impl-list.c
	(__libc_ifunc_impl_list): Add __wmemset_sse2_unaligned,
	__wmemset_avx2_unaligned, __wmemset_avx512_unaligned,
	__wmemset_chk_sse2_unaligned, __wmemset_chk_avx2_unaligned
	and __wmemset_chk_avx512_unaligned.
	* sysdeps/x86_64/multiarch/memset-avx2-unaligned-erms.S
	(VDUP_TO_VEC0_AND_SET_RETURN): Renamed to ...
	(MEMSET_VDUP_TO_VEC0_AND_SET_RETURN): This.
	(WMEMSET_VDUP_TO_VEC0_AND_SET_RETURN): New.
	(WMEMSET_SYMBOL): Likewise.
	* sysdeps/x86_64/multiarch/memset-avx512-unaligned-erms.S
	(VDUP_TO_VEC0_AND_SET_RETURN): Renamed to ...
	(MEMSET_VDUP_TO_VEC0_AND_SET_RETURN): This.
	(WMEMSET_VDUP_TO_VEC0_AND_SET_RETURN): New.
	(WMEMSET_SYMBOL): Likewise.
	* sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S: Updated.
	(WMEMSET_CHK_SYMBOL): New.
	(WMEMSET_CHK_SYMBOL (__wmemset_chk, unaligned)): Likewise.
	(WMEMSET_SYMBOL (__wmemset, unaligned)): Likewise.
	* sysdeps/x86_64/multiarch/memset.S (WMEMSET_SYMBOL): New.
	(libc_hidden_builtin_def): Also define __GI_wmemset and
	__GI___wmemset.
	(weak_alias): New.
	* sysdeps/x86_64/multiarch/wmemset.c: New file.
	* sysdeps/x86_64/multiarch/wmemset.h: Likewise.
	* sysdeps/x86_64/multiarch/wmemset_chk-nonshared.S: Likewise.
	* sysdeps/x86_64/multiarch/wmemset_chk.c: Likewise.
	* sysdeps/x86_64/wmemset.c: Likewise.
	* sysdeps/x86_64/wmemset_chk.c: Likewise.

1 files changed, 10 insertions, 3 deletions

diff --git a/sysdeps/x86_64/multiarch/memset.S b/sysdeps/x86_64/multiarch/memset.S
index 9d33118..11f2737 100644
--- a/sysdeps/x86_64/multiarch/memset.S
+++ b/sysdeps/x86_64/multiarch/memset.S
@@ -58,16 +58,23 @@ END(memset)
 
 #if IS_IN (libc)
 # define MEMSET_SYMBOL(p,s)	p##_sse2_##s
+# define WMEMSET_SYMBOL(p,s)	p##_sse2_##s
 
 # ifdef SHARED
-# undef libc_hidden_builtin_def
+#  undef libc_hidden_builtin_def
 /* It doesn't make sense to send libc-internal memset calls through a PLT.
    The speedup we get from using SSE2 instructions is likely eaten away
    by the indirect call in the PLT.  */
-# define libc_hidden_builtin_def(name) \
-	.globl __GI_memset; __GI_memset = __memset_sse2_unaligned
+#  define libc_hidden_builtin_def(name) \
+	.globl __GI_memset; __GI_memset = __memset_sse2_unaligned; \
+	.globl __GI_wmemset; __GI_wmemset = __wmemset_sse2_unaligned; \
+	.globl __GI___wmemset; __GI___wmemset = __wmemset_sse2_unaligned
 # endif
 
+# undef weak_alias
+# define weak_alias(original, alias) \
+	.weak bzero; bzero = __bzero
+
 # undef strong_alias
 # define strong_alias(original, alias)
 #endif