mirror_edk2/MdePkg/Library/BaseMemoryLibSse2/Ia32/SetMem.nasm
Michael D Kinney 9344f09215 MdePkg: Replace BSD License with BSD+Patent License
https://bugzilla.tianocore.org/show_bug.cgi?id=1373

Replace BSD 2-Clause License with BSD+Patent License.  This change is
based on the following emails:

  https://lists.01.org/pipermail/edk2-devel/2019-February/036260.html
  https://lists.01.org/pipermail/edk2-devel/2018-October/030385.html

RFCs with detailed process for the license change:

  V3: https://lists.01.org/pipermail/edk2-devel/2019-March/038116.html
  V2: https://lists.01.org/pipermail/edk2-devel/2019-March/037669.html
  V1: https://lists.01.org/pipermail/edk2-devel/2019-March/037500.html

Contributed-under: TianoCore Contribution Agreement 1.1
Signed-off-by: Michael D Kinney <michael.d.kinney@intel.com>
Reviewed-by: Liming Gao <liming.gao@intel.com>
2019-04-09 10:58:13 -07:00

68 lines
2.0 KiB
NASM

;------------------------------------------------------------------------------
;
; Copyright (c) 2006, Intel Corporation. All rights reserved.<BR>
; SPDX-License-Identifier: BSD-2-Clause-Patent
;
; 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