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/CopyMem.S

@@ -0,0 +1,84 @@
+#
+# ConvertAsm.py: Automatically generated from CopyMem.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:
+#
+#   CopyMem.S
+#
+# Abstract:
+#
+#   CopyMem function
+#
+# Notes:
+#
+#------------------------------------------------------------------------------
+
+
+#------------------------------------------------------------------------------
+#  VOID *
+#  EFIAPI
+#  InternalMemCopyMem (
+#    IN VOID   *Destination,
+#    IN VOID   *Source,
+#    IN UINTN  Count
+#    )
+#------------------------------------------------------------------------------
+.intel_syntax noprefix
+.globl ASM_PFX(InternalMemCopyMem)
+ASM_PFX(InternalMemCopyMem):
+    push    rsi
+    push    rdi
+    mov     rsi, rdx                    # rsi <- Source
+    mov     rdi, rcx                    # rdi <- Destination
+    lea     r9, [rsi + r8 - 1]          # r9 <- Last byte of Source
+    cmp     rsi, rdi                    
+    mov     rax, rdi                    # rax <- Destination as return value
+    jae     _InternalMemCopyMem_al_0000 # Copy forward if Source > Destination
+    cmp     r9, rdi                     # Overlapped?
+    jae     _atSym_CopyBackward         # Copy backward if overlapped
+_InternalMemCopyMem_al_0000:            
+    xor     rcx, rcx                    
+    sub     rcx, rdi                    # rcx <- -rdi
+    and     rcx, 15                     # rcx + rsi should be 16 bytes aligned
+    jz      _InternalMemCopyMem_al_0001 # skip if rcx == 0
+    cmp     rcx, r8
+    cmova   rcx, r8
+    sub     r8, rcx
+    rep     movsb
+_InternalMemCopyMem_al_0001:
+    mov     rcx, r8
+    and     r8, 15
+    shr     rcx, 4                      # rcx <- # of DQwords to copy
+    jz      _atSym_CopyBytes
+    movdqa  [rsp + 0x18], xmm0           # save xmm0 on stack
+_InternalMemCopyMem_al_0002:
+    movdqu  xmm0, [rsi]                 # rsi may not be 16-byte aligned
+    movntdq [rdi], xmm0                 # rdi should be 16-byte aligned
+    add     rsi, 16
+    add     rdi, 16
+    loop    _InternalMemCopyMem_al_0002
+    mfence
+    movdqa  xmm0, [rsp + 0x18]           # restore xmm0
+    jmp     _atSym_CopyBytes            # copy remaining bytes
+_atSym_CopyBackward:
+    mov     rsi, r9                     # rsi <- Last byte of Source
+    lea     rdi, [rdi + r8 - 1]         # rdi <- Last byte of Destination
+    std
+_atSym_CopyBytes:
+    mov     rcx, r8
+    rep     movsb
+    cld
+    pop     rdi
+    pop     rsi
+    ret