MdePkg BaseMemoryLibSse2: Convert X64/SetMem.asm to NASM

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

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

MdePkg/Library/BaseMemoryLibSse2/BaseMemoryLibSse2.inf

@@ -109,6 +109,7 @@
   X64/SetMem32.asm
   X64/SetMem16.nasm
   X64/SetMem16.asm
+  X64/SetMem.nasm
   X64/SetMem.asm
   X64/CopyMem.asm
   X64/ScanMem64.nasm
@@ -129,6 +130,7 @@
   X64/SetMem32.S
   X64/SetMem16.nasm
   X64/SetMem16.S
+  X64/SetMem.nasm
   X64/SetMem.S
   X64/CopyMem.S
 

MdePkg/Library/BaseMemoryLibSse2/X64/SetMem.nasm

@@ -0,0 +1,71 @@
+;------------------------------------------------------------------------------
+;
+; 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:
+;
+;------------------------------------------------------------------------------
+
+    DEFAULT REL
+    SECTION .text
+
+;------------------------------------------------------------------------------
+;  VOID *
+;  InternalMemSetMem (
+;    IN VOID   *Buffer,
+;    IN UINTN  Count,
+;    IN UINT8  Value
+;    )
+;------------------------------------------------------------------------------
+global 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      .0
+    cmp     rcx, rdx
+    cmova   rcx, rdx
+    sub     rdx, rcx
+    rep     stosb
+.0:
+    mov     rcx, rdx
+    and     rdx, 15
+    shr     rcx, 4
+    jz      @SetBytes
+    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
+.1:
+    movntdq [rdi], xmm0                 ; rdi should be 16-byte aligned
+    add     rdi, 16
+    loop    .1
+    mfence
+    movdqa  xmm0, [rsp + 0x10]           ; restore xmm0
+@SetBytes:
+    mov     ecx, edx                    ; high 32 bits of rcx are always zero
+    rep     stosb
+    mov     rax, r9                     ; rax <- Return value
+    pop     rdi
+    ret
+