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, 21 insertions, 3 deletions

diff --git a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S
index 704eed9a3f..2eb9e3744e 100644
--- a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S
+++ b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S
@@ -30,6 +30,10 @@
 # define MEMSET_CHK_SYMBOL(p,s)		MEMSET_SYMBOL(p, s)
 #endif
 
+#ifndef WMEMSET_CHK_SYMBOL
+# define WMEMSET_CHK_SYMBOL(p,s)	WMEMSET_SYMBOL(p, s)
+#endif
+
 #ifndef VZEROUPPER
 # if VEC_SIZE > 16
 #  define VZEROUPPER			vzeroupper
@@ -79,6 +83,21 @@ END (__bzero)
 weak_alias (__bzero, bzero)
 #endif
 
+#if IS_IN (libc)
+# if defined SHARED
+ENTRY_CHK (WMEMSET_CHK_SYMBOL (__wmemset_chk, unaligned))
+	cmpq	%rdx, %rcx
+	jb	HIDDEN_JUMPTARGET (__chk_fail)
+END_CHK (WMEMSET_CHK_SYMBOL (__wmemset_chk, unaligned))
+# endif
+
+ENTRY (WMEMSET_SYMBOL (__wmemset, unaligned))
+	shlq	$2, %rdx
+	WMEMSET_VDUP_TO_VEC0_AND_SET_RETURN (%esi, %rdi)
+	jmp	L(entry_from_bzero)
+END (WMEMSET_SYMBOL (__wmemset, unaligned))
+#endif
+
 #if defined SHARED && IS_IN (libc)
 ENTRY_CHK (MEMSET_CHK_SYMBOL (__memset_chk, unaligned))
 	cmpq	%rdx, %rcx
@@ -87,8 +106,7 @@ END_CHK (MEMSET_CHK_SYMBOL (__memset_chk, unaligned))
 #endif
 
 ENTRY (MEMSET_SYMBOL (__memset, unaligned))
-L(memset_entry):
-	VDUP_TO_VEC0_AND_SET_RETURN (%esi, %rdi)
+	MEMSET_VDUP_TO_VEC0_AND_SET_RETURN (%esi, %rdi)
 L(entry_from_bzero):
 	cmpq	$VEC_SIZE, %rdx
 	jb	L(less_vec)
@@ -132,7 +150,7 @@ END_CHK (MEMSET_CHK_SYMBOL (__memset_chk, unaligned_erms))
 # endif
 
 ENTRY (MEMSET_SYMBOL (__memset, unaligned_erms))
-	VDUP_TO_VEC0_AND_SET_RETURN (%esi, %rdi)
+	MEMSET_VDUP_TO_VEC0_AND_SET_RETURN (%esi, %rdi)
 	cmpq	$VEC_SIZE, %rdx
 	jb	L(less_vec)
 	cmpq	$(VEC_SIZE * 2), %rdx