📄 transfer_mmx.asm
字号:
;/**************************************************************************
; *
; * XVID MPEG-4 VIDEO CODEC
; * mmx 8bit<->16bit transfer
; *
; * This program is an implementation of a part of one or more MPEG-4
; * Video tools as specified in ISO/IEC 14496-2 standard. Those intending
; * to use this software module in hardware or software products are
; * advised that its use may infringe existing patents or copyrights, and
; * any such use would be at such party's own risk. The original
; * developer of this software module and his/her company, and subsequent
; * editors and their companies, will have no liability for use of this
; * software or modifications or derivatives thereof.
; *
; * This program is free software; you can redistribute it and/or modify
; * it under the terms of the GNU General Public License as published by
; * the Free Software Foundation; either version 2 of the License, or
; * (at your option) any later version.
; *
; * This program is distributed in the hope that it will be useful,
; * but WITHOUT ANY WARRANTY; without even the implied warranty of
; * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
; * GNU General Public License for more details.
; *
; * You should have received a copy of the GNU General Public License
; * along with this program; if not, write to the Free Software
; * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
; *
; *************************************************************************/
;/**************************************************************************
; *
; * History:
; *
; * 17.11.2001 bug fix: code declared as .data
; * 07.11.2001 initial version; (c)2001 peter ross <pross@cs.rmit.edu.au>
; *
; *************************************************************************/
bits 32
section .text
;===========================================================================
;
; void transfer_8to16copy_mmx(int16_t * const dst,
; const uint8_t * const src,
; uint32_t stride);
;
;===========================================================================
align 16
global _transfer_8to16copy_mmx
_transfer_8to16copy_mmx
push esi
push edi
mov edi, [esp + 8 + 4] ; dst
mov esi, [esp + 8 + 8] ; src
mov ecx, [esp + 8 + 12] ; stride
pxor mm7, mm7 ; mm7 = zero
mov eax, 8
.loop
movq mm0, [esi]
movq mm1, mm0
punpcklbw mm0, mm7 ; mm01 = unpack([src])
punpckhbw mm1, mm7
movq [edi], mm0 ; [dst] = mm01
movq [edi + 8], mm1
add edi, 16
add esi, ecx
dec eax
jnz .loop
pop edi
pop esi
ret
;===========================================================================
;
; void transfer_16to8copy_mmx(uint8_t * const dst,
; const int16_t * const src,
; uint32_t stride);
;
;===========================================================================
align 16
global _transfer_16to8copy_mmx
_transfer_16to8copy_mmx
push esi
push edi
mov edi, [esp + 8 + 4] ; dst
mov esi, [esp + 8 + 8] ; src
mov ecx, [esp + 8 + 12] ; stride
mov eax, 8
.loop
movq mm0, [esi]
packuswb mm0, [esi + 8] ; mm0 = pack([src])
movq [edi], mm0 ; [dst] = mm0
add esi, 16
add edi, ecx
dec eax
jnz .loop
pop edi
pop esi
ret
;===========================================================================
;
; void transfer_16to8add_mmx(uint8_t * const dst,
; const int16_t * const src,
; uint32_t stride);
;
;===========================================================================
align 16
global _transfer_16to8add_mmx
_transfer_16to8add_mmx
push esi
push edi
mov edi, [esp + 8 + 4] ; dst
mov esi, [esp + 8 + 8] ; src
mov ecx, [esp + 8 + 12] ; stride
pxor mm7, mm7
mov eax, 8
.loop
movq mm0, [edi]
movq mm1, mm0
punpcklbw mm0, mm7 ; mm23 = unpack([dst])
punpckhbw mm1, mm7
movq mm2, [esi] ; mm01 = [src]
movq mm3, [esi + 8]
paddsw mm0, mm2 ; mm01 += mm23
paddsw mm1, mm3
packuswb mm0, mm1 ; [dst] = pack(mm01)
movq [edi], mm0
add esi, 16
add edi, ecx
dec eax
jnz .loop
pop edi
pop esi
ret
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -