MdePkg BaseMemoryLibSse2: Add SSE2 implementation of API IsZeroBuffer()

Add the implementation of API IsZeroBuffer() via assembly in
BaseMemoryLibSse2.

The assembly codes use SSE2 XMM registers and related instructions.

Cc: Michael D Kinney <michael.d.kinney@intel.com>
Cc: Liming Gao <liming.gao@intel.com>
Cc: Jiewen Yao <jiewen.yao@intel.com>
Contributed-under: TianoCore Contribution Agreement 1.0
Signed-off-by: Hao Wu <hao.a.wu@intel.com>
Reviewed-by: Liming Gao <liming.gao@intel.com>

MdePkg/Library/BaseMemoryLibSse2/X64/IsZeroBuffer.nasm

@@ -0,0 +1,76 @@
+;------------------------------------------------------------------------------
+;
+; Copyright (c) 2016, 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:
+;
+;   IsZeroBuffer.nasm
+;
+; Abstract:
+;
+;   IsZeroBuffer function
+;
+; Notes:
+;
+;------------------------------------------------------------------------------
+
+    DEFAULT REL
+    SECTION .text
+
+;------------------------------------------------------------------------------
+;  BOOLEAN
+;  EFIAPI
+;  InternalMemIsZeroBuffer (
+;    IN CONST VOID  *Buffer,
+;    IN UINTN       Length
+;    );
+;------------------------------------------------------------------------------
+global ASM_PFX(InternalMemIsZeroBuffer)
+ASM_PFX(InternalMemIsZeroBuffer):
+    push         rdi
+    mov          rdi, rcx              ; rdi <- Buffer
+    xor          rcx, rcx              ; rcx <- 0
+    sub          rcx, rdi
+    and          rcx, 15               ; rcx + rdi aligns on 16-byte boundary
+    jz           @Is16BytesZero
+    cmp          rcx, rdx              ; Length already in rdx
+    cmova        rcx, rdx              ; bytes before the 16-byte boundary
+    sub          rdx, rcx
+    xor          rax, rax              ; rax <- 0, also set ZF
+    repe         scasb
+    jnz          @ReturnFalse          ; ZF=0 means non-zero element found
+@Is16BytesZero:
+    mov          rcx, rdx
+    and          rdx, 15
+    shr          rcx, 4
+    jz           @IsBytesZero
+.0:
+    pxor         xmm0, xmm0            ; xmm0 <- 0
+    pcmpeqb      xmm0, [rdi]           ; check zero for 16 bytes
+    pmovmskb     eax, xmm0             ; eax <- compare results
+                                       ; nasm doesn't support 64-bit destination
+                                       ; for pmovmskb
+    cmp          eax, 0xffff
+    jnz          @ReturnFalse
+    add          rdi, 16
+    loop         .0
+@IsBytesZero:
+    mov          rcx, rdx
+    xor          rax, rax              ; rax <- 0, also set ZF
+    repe         scasb
+    jnz          @ReturnFalse          ; ZF=0 means non-zero element found
+    pop          rdi
+    mov          rax, 1                ; return TRUE
+    ret
+@ReturnFalse:
+    pop          rdi
+    xor          rax, rax
+    ret                                ; return FALSE
+