MdePkg BaseMemoryLibSse2: Convert X64/CopyMem.asm to NASM

The BaseTools/Scripts/ConvertMasmToNasm.py script was used to convert
X64/CopyMem.asm to X64/CopyMem.nasm

Contributed-under: TianoCore Contribution Agreement 1.0
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>

MdePkg/Library/BaseMemoryLibSse2/BaseMemoryLibSse2.inf

@@ -111,6 +111,7 @@
   X64/SetMem16.asm
   X64/SetMem.nasm
   X64/SetMem.asm
+  X64/CopyMem.nasm
   X64/CopyMem.asm
   X64/ScanMem64.nasm
   X64/ScanMem64.S
@@ -132,6 +133,7 @@
   X64/SetMem16.S
   X64/SetMem.nasm
   X64/SetMem.S
+  X64/CopyMem.nasm
   X64/CopyMem.S
 
 [Packages]

MdePkg/Library/BaseMemoryLibSse2/X64/CopyMem.nasm

@@ -0,0 +1,83 @@
+;------------------------------------------------------------------------------
+;
+; Copyright (c) 2006, Intel Corporation. All rights reserved.<BR>
+; 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.nasm
+;
+; Abstract:
+;
+;   CopyMem function
+;
+; Notes:
+;
+;------------------------------------------------------------------------------
+
+    DEFAULT REL
+    SECTION .text
+
+;------------------------------------------------------------------------------
+;  VOID *
+;  EFIAPI
+;  InternalMemCopyMem (
+;    IN VOID   *Destination,
+;    IN VOID   *Source,
+;    IN UINTN  Count
+;    );
+;------------------------------------------------------------------------------
+global 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     .0                          ; Copy forward if Source > Destination
+    cmp     r9, rdi                     ; Overlapped?
+    jae     @CopyBackward               ; Copy backward if overlapped
+.0:
+    xor     rcx, rcx
+    sub     rcx, rdi                    ; rcx <- -rdi
+    and     rcx, 15                     ; rcx + rsi should be 16 bytes aligned
+    jz      .1                          ; skip if rcx == 0
+    cmp     rcx, r8
+    cmova   rcx, r8
+    sub     r8, rcx
+    rep     movsb
+.1:
+    mov     rcx, r8
+    and     r8, 15
+    shr     rcx, 4                      ; rcx <- # of DQwords to copy
+    jz      @CopyBytes
+    movdqa  [rsp + 0x18], xmm0           ; save xmm0 on stack
+.2:
+    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    .2
+    mfence
+    movdqa  xmm0, [rsp + 0x18]           ; restore xmm0
+    jmp     @CopyBytes                  ; copy remaining bytes
+@CopyBackward:
+    mov     rsi, r9                     ; rsi <- Last byte of Source
+    lea     rdi, [rdi + r8 - 1]         ; rdi <- Last byte of Destination
+    std
+@CopyBytes:
+    mov     rcx, r8
+    rep     movsb
+    cld
+    pop     rdi
+    pop     rsi
+    ret
+