[mirror_edk2.git] / MdePkg / Library / BaseMemoryLibSse2 / X64 / SetMem.S

#
# ConvertAsm.py: Automatically generated from SetMem.asm
#
#------------------------------------------------------------------------------
#
# Copyright (c) 2006, Intel Corporation
# All rights reserved. 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.S
#
# Abstract:
#
#   SetMem function
#
# Notes:
#
#------------------------------------------------------------------------------


#------------------------------------------------------------------------------
#  VOID *
#  EFIAPI
#  InternalMemSetMem (
#    IN VOID   *Buffer,
#    IN UINTN  Count,
#    IN UINT8  Value
#    )
#------------------------------------------------------------------------------
.intel_syntax noprefix
.globl 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      L0
    cmp     rcx, rdx
    cmova   rcx, rdx
    sub     rdx, rcx
    rep     stosb
L0:
    mov     rcx, rdx
    and     rdx, 15
    shr     rcx, 4
    jz      L_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
L1:
    movntdq [rdi], xmm0                 # rdi should be 16-byte aligned
    add     rdi, 16
    loop    L1
    mfence
    movdqa  xmm0, [rsp + 0x10]          # restore xmm0
L_SetBytes:
    mov     ecx, edx                    # high 32 bits of rcx are always zero
    rep     stosb
    mov     rax, r9                     # rax <- Return value
    pop     rdi
    ret
Commit	Line	Data
4df876ad	1	#
	2	# ConvertAsm.py: Automatically generated from SetMem.asm
	3	#
	4	#------------------------------------------------------------------------------
	5	#
	6	# Copyright (c) 2006, Intel Corporation
	7	# All rights reserved. This program and the accompanying materials
	8	# are licensed and made available under the terms and conditions of the BSD License
	9	# which accompanies this distribution. The full text of the license may be found at
	10	# http://opensource.org/licenses/bsd-license.php
	11	#
	12	# THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,
	13	# WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.
	14	#
	15	# Module Name:
	16	#
	17	# SetMem.S
	18	#
	19	# Abstract:
	20	#
	21	# SetMem function
	22	#
	23	# Notes:
	24	#
	25	#------------------------------------------------------------------------------
	26
	27
	28	#------------------------------------------------------------------------------
	29	# VOID *
	30	# EFIAPI
	31	# InternalMemSetMem (
	32	# IN VOID *Buffer,
	33	# IN UINTN Count,
	34	# IN UINT8 Value
	35	# )
	36	#------------------------------------------------------------------------------
	37	.intel_syntax noprefix
	38	.globl ASM_PFX(InternalMemSetMem)
	39	ASM_PFX(InternalMemSetMem):
	40	push rdi
	41	mov rdi, rcx # rdi <- Buffer
	42	mov al, r8b # al <- Value
	43	mov r9, rdi # r9 <- Buffer as return value
	44	xor rcx, rcx
	45	sub rcx, rdi
	46	and rcx, 15 # rcx + rdi aligns on 16-byte boundary
	47	jz L0
	48	cmp rcx, rdx
	49	cmova rcx, rdx
	50	sub rdx, rcx
	51	rep stosb
	52	L0:
	53	mov rcx, rdx
	54	and rdx, 15
	55	shr rcx, 4
852f5d96	56	jz L_SetBytes
4df876ad	57	mov ah, al # ax <- Value repeats twice
852f5d96	58	movdqa [rsp + 0x10], xmm0 # save xmm0
4df876ad	59	movd xmm0, eax # xmm0[0..16] <- Value repeats twice
	60	pshuflw xmm0, xmm0, 0 # xmm0[0..63] <- Value repeats 8 times
	61	movlhps xmm0, xmm0 # xmm0 <- Value repeats 16 times
	62	L1:
	63	movntdq [rdi], xmm0 # rdi should be 16-byte aligned
	64	add rdi, 16
	65	loop L1
	66	mfence
852f5d96	67	movdqa xmm0, [rsp + 0x10] # restore xmm0
852f5d96	68	L_SetBytes:
4df876ad	69	mov ecx, edx # high 32 bits of rcx are always zero
	70	rep stosb
	71	mov rax, r9 # rax <- Return value
	72	pop rdi
	73	ret