MdePkg BaseMemoryLibSse2: Convert Ia32/SetMem.asm to NASM

The BaseTools/Scripts/ConvertMasmToNasm.py script was used to convert
Ia32/SetMem.asm to Ia32/SetMem.nasm

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

MdePkg/Library/BaseMemoryLibSse2/BaseMemoryLibSse2.inf

@@ -63,6 +63,7 @@
   Ia32/SetMem32.S
   Ia32/SetMem16.nasm
   Ia32/SetMem16.S
+  Ia32/SetMem.nasm
   Ia32/SetMem.S
   Ia32/CopyMem.S
   Ia32/ScanMem64.nasm
@@ -83,6 +84,7 @@
   Ia32/SetMem32.asm
   Ia32/SetMem16.nasm
   Ia32/SetMem16.asm
+  Ia32/SetMem.nasm
   Ia32/SetMem.asm
   Ia32/CopyMem.asm
 

MdePkg/Library/BaseMemoryLibSse2/Ia32/SetMem.nasm

@@ -0,0 +1,73 @@
+;------------------------------------------------------------------------------
+;
+; 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:
+;
+;   SetMem.nasm
+;
+; Abstract:
+;
+;   SetMem function
+;
+; Notes:
+;
+;------------------------------------------------------------------------------
+
+    SECTION .text
+
+;------------------------------------------------------------------------------
+;  VOID *
+;  EFIAPI
+;  InternalMemSetMem (
+;    IN VOID   *Buffer,
+;    IN UINTN  Count,
+;    IN UINT8  Value
+;    );
+;------------------------------------------------------------------------------
+global ASM_PFX(InternalMemSetMem)
+ASM_PFX(InternalMemSetMem):
+    push    edi
+    mov     edx, [esp + 12]             ; edx <- Count
+    mov     edi, [esp + 8]              ; edi <- Buffer
+    mov     al, [esp + 16]              ; al <- Value
+    xor     ecx, ecx
+    sub     ecx, edi
+    and     ecx, 15                     ; ecx + edi aligns on 16-byte boundary
+    jz      .0
+    cmp     ecx, edx
+    cmova   ecx, edx
+    sub     edx, ecx
+    rep     stosb
+.0:
+    mov     ecx, edx
+    and     edx, 15
+    shr     ecx, 4                      ; ecx <- # of DQwords to set
+    jz      @SetBytes
+    mov     ah, al                      ; ax <- Value | (Value << 8)
+    add     esp, -16
+    movdqu  [esp], xmm0                 ; save xmm0
+    movd    xmm0, eax
+    pshuflw xmm0, xmm0, 0               ; xmm0[0..63] <- Value repeats 8 times
+    movlhps xmm0, xmm0                  ; xmm0 <- Value repeats 16 times
+.1:
+    movntdq [edi], xmm0                 ; edi should be 16-byte aligned
+    add     edi, 16
+    loop    .1
+    mfence
+    movdqu  xmm0, [esp]                 ; restore xmm0
+    add     esp, 16                     ; stack cleanup
+@SetBytes:
+    mov     ecx, edx
+    rep     stosb
+    mov     eax, [esp + 8]              ; eax <- Buffer as return value
+    pop     edi
+    ret
+