add corresponding .S files for BaseMemoryLibXXX X64 arch. Note that we use ".intel_syntax noprefix" directive to simplify the .S implementation.

git-svn-id: https://edk2.svn.sourceforge.net/svnroot/edk2/trunk/edk2@6184 6f19259b-4bc3-4df7-8a09-765794883524

MdePkg/Library/BaseMemoryLibSse2/X64/SetMem.S

@@ -0,0 +1,73 @@
+#
+# ConvertAsm.py: Automatically generated from SetMem.asm
+#
+#------------------------------------------------------------------------------
+#
+# Copyright (c) 2006, Intel Corporation
+# All rights reserved. This program and the accompanying materials
+# are licensed and made available under the terms and conditions of the BSD License
+# which accompanies this distribution.  The full text of the license may be found at
+# http://opensource.org/licenses/bsd-license.php
+#
+# THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,
+# WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.
+#
+# Module Name:
+#
+#   SetMem.S
+#
+# Abstract:
+#
+#   SetMem function
+#
+# Notes:
+#
+#------------------------------------------------------------------------------
+
+
+#------------------------------------------------------------------------------
+#  VOID *
+#  EFIAPI
+#  InternalMemSetMem (
+#    IN VOID   *Buffer,
+#    IN UINTN  Count,
+#    IN UINT8  Value
+#    )
+#------------------------------------------------------------------------------
+.intel_syntax noprefix
+.globl ASM_PFX(InternalMemSetMem)
+ASM_PFX(InternalMemSetMem):
+    push    rdi
+    mov     rdi, rcx                    # rdi <- Buffer
+    mov     al, r8b                     # al <- Value
+    mov     r9, rdi                     # r9 <- Buffer as return value
+    xor     rcx, rcx
+    sub     rcx, rdi
+    and     rcx, 15                     # rcx + rdi aligns on 16-byte boundary
+    jz      L0
+    cmp     rcx, rdx
+    cmova   rcx, rdx
+    sub     rdx, rcx
+    rep     stosb
+L0:
+    mov     rcx, rdx
+    and     rdx, 15
+    shr     rcx, 4
+    jz      _SetBytes_L2
+    mov     ah, al                      # ax <- Value repeats twice
+    movdqa  [rsp + 0x10], xmm0           # save xmm0
+    movd    xmm0, eax                   # xmm0[0..16] <- Value repeats twice
+    pshuflw xmm0, xmm0, 0               # xmm0[0..63] <- Value repeats 8 times
+    movlhps xmm0, xmm0                  # xmm0 <- Value repeats 16 times
+L1:
+    movntdq [rdi], xmm0                 # rdi should be 16-byte aligned
+    add     rdi, 16
+    loop    L1
+    mfence
+    movdqa  xmm0, [rsp + 0x10]           # restore xmm0
+_SetBytes_L2:
+    mov     ecx, edx                    # high 32 bits of rcx are always zero
+    rep     stosb
+    mov     rax, r9                     # rax <- Return value
+    pop     rdi
+    ret