3 files changed, 113 insertions, 0 deletions
diff --git a/src/string/x86_64/memcpy.s b/src/string/x86_64/memcpy.s
new file mode 100644
index 0000000..3d960ef
--- /dev/null
+++ b/src/string/x86_64/memcpy.s
@@ -0,0 +1,25 @@
+.global memcpy
+.global __memcpy_fwd
+.hidden __memcpy_fwd
+.type memcpy,@function
+memcpy:
+__memcpy_fwd:
+	mov %rdi,%rax
+	cmp $8,%rdx
+	jc 1f
+	test $7,%edi
+	jz 1f
+2:	movsb
+	dec %rdx
+	test $7,%edi
+	jnz 2b
+1:	mov %rdx,%rcx
+	shr $3,%rcx
+	rep
+	movsq
+	and $7,%edx
+	jz 1f
+2:	movsb
+	dec %edx
+	jnz 2b
+1:	ret
diff --git a/src/string/x86_64/memmove.s b/src/string/x86_64/memmove.s
new file mode 100644
index 0000000..172c025
--- /dev/null
+++ b/src/string/x86_64/memmove.s
@@ -0,0 +1,16 @@
+.global memmove
+.type memmove,@function
+memmove:
+	mov %rdi,%rax
+	sub %rsi,%rax
+	cmp %rdx,%rax
+.hidden __memcpy_fwd
+	jae __memcpy_fwd
+	mov %rdx,%rcx
+	lea -1(%rdi,%rdx),%rdi
+	lea -1(%rsi,%rdx),%rsi
+	std
+	rep movsb
+	cld
+	lea 1(%rdi),%rax
+	ret
diff --git a/src/string/x86_64/memset.s b/src/string/x86_64/memset.s
new file mode 100644
index 0000000..2d3f5e5
--- /dev/null
+++ b/src/string/x86_64/memset.s
@@ -0,0 +1,72 @@
+.global memset
+.type memset,@function
+memset:
+	movzbq %sil,%rax
+	mov $0x101010101010101,%r8
+	imul %r8,%rax
+
+	cmp $126,%rdx
+	ja 2f
+
+	test %edx,%edx
+	jz 1f
+
+	mov %sil,(%rdi)
+	mov %sil,-1(%rdi,%rdx)
+	cmp $2,%edx
+	jbe 1f
+
+	mov %ax,1(%rdi)
+	mov %ax,(-1-2)(%rdi,%rdx)
+	cmp $6,%edx
+	jbe 1f
+
+	mov %eax,(1+2)(%rdi)
+	mov %eax,(-1-2-4)(%rdi,%rdx)
+	cmp $14,%edx
+	jbe 1f
+
+	mov %rax,(1+2+4)(%rdi)
+	mov %rax,(-1-2-4-8)(%rdi,%rdx)
+	cmp $30,%edx
+	jbe 1f
+
+	mov %rax,(1+2+4+8)(%rdi)
+	mov %rax,(1+2+4+8+8)(%rdi)
+	mov %rax,(-1-2-4-8-16)(%rdi,%rdx)
+	mov %rax,(-1-2-4-8-8)(%rdi,%rdx)
+	cmp $62,%edx
+	jbe 1f
+
+	mov %rax,(1+2+4+8+16)(%rdi)
+	mov %rax,(1+2+4+8+16+8)(%rdi)
+	mov %rax,(1+2+4+8+16+16)(%rdi)
+	mov %rax,(1+2+4+8+16+24)(%rdi)
+	mov %rax,(-1-2-4-8-16-32)(%rdi,%rdx)
+	mov %rax,(-1-2-4-8-16-24)(%rdi,%rdx)
+	mov %rax,(-1-2-4-8-16-16)(%rdi,%rdx)
+	mov %rax,(-1-2-4-8-16-8)(%rdi,%rdx)
+
+1:	mov %rdi,%rax
+	ret
+
+2:	test $15,%edi
+	mov %rdi,%r8
+	mov %rax,-8(%rdi,%rdx)
+	mov %rdx,%rcx
+	jnz 2f
+
+1:	shr $3,%rcx
+	rep
+	stosq
+	mov %r8,%rax
+	ret
+
+2:	xor %edx,%edx
+	sub %edi,%edx
+	and $15,%edx
+	mov %rax,(%rdi)
+	mov %rax,8(%rdi)
+	sub %rdx,%rcx
+	add %rdx,%rdi
+	jmp 1b