src/third_party/libvpx/vp8/common/x86/recon_mmx.asm

;
;  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
;
;  Use of this source code is governed by a BSD-style license
;  that can be found in the LICENSE file in the root of the source
;  tree. An additional intellectual property rights grant can be found
;  in the file PATENTS.  All contributing project authors may
;  be found in the AUTHORS file in the root of the source tree.
;


%include "vpx_ports/x86_abi_support.asm"

SECTION .text

;void copy_mem8x8_mmx(
;    unsigned char *src,
;    int src_stride,
;    unsigned char *dst,
;    int dst_stride
;    )
globalsym(vp8_copy_mem8x8_mmx)
sym(vp8_copy_mem8x8_mmx):
    push        rbp
    mov         rbp, rsp
    SHADOW_ARGS_TO_STACK 4
    push        rsi
    push        rdi
    ; end prolog

        mov         rsi,        arg(0) ;src;
        movq        mm0,        [rsi]

        movsxd      rax,        dword ptr arg(1) ;src_stride;
        mov         rdi,        arg(2) ;dst;

        movq        mm1,        [rsi+rax]
        movq        mm2,        [rsi+rax*2]

        movsxd      rcx,        dword ptr arg(3) ;dst_stride
        lea         rsi,        [rsi+rax*2]

        movq        [rdi],      mm0
        add         rsi,        rax

        movq        [rdi+rcx],      mm1
        movq        [rdi+rcx*2],    mm2


        lea         rdi,        [rdi+rcx*2]
        movq        mm3,        [rsi]

        add         rdi,        rcx
        movq        mm4,        [rsi+rax]

        movq        mm5,        [rsi+rax*2]
        movq        [rdi],      mm3

        lea         rsi,        [rsi+rax*2]
        movq        [rdi+rcx],  mm4

        movq        [rdi+rcx*2],    mm5
        lea         rdi,        [rdi+rcx*2]

        movq        mm0,        [rsi+rax]
        movq        mm1,        [rsi+rax*2]

        movq        [rdi+rcx],  mm0
        movq        [rdi+rcx*2],mm1

    ; begin epilog
    pop rdi
    pop rsi
    UNSHADOW_ARGS
    pop         rbp
    ret


;void copy_mem8x4_mmx(
;    unsigned char *src,
;    int src_stride,
;    unsigned char *dst,
;    int dst_stride
;    )
globalsym(vp8_copy_mem8x4_mmx)
sym(vp8_copy_mem8x4_mmx):
    push        rbp
    mov         rbp, rsp
    SHADOW_ARGS_TO_STACK 4
    push        rsi
    push        rdi
    ; end prolog

        mov         rsi,        arg(0) ;src;
        movq        mm0,        [rsi]

        movsxd      rax,        dword ptr arg(1) ;src_stride;
        mov         rdi,        arg(2) ;dst;

        movq        mm1,        [rsi+rax]
        movq        mm2,        [rsi+rax*2]

        movsxd      rcx,        dword ptr arg(3) ;dst_stride
        lea         rsi,        [rsi+rax*2]

        movq        [rdi],      mm0
        movq        [rdi+rcx],      mm1

        movq        [rdi+rcx*2],    mm2
        lea         rdi,        [rdi+rcx*2]

        movq        mm3,        [rsi+rax]
        movq        [rdi+rcx],      mm3

    ; begin epilog
    pop rdi
    pop rsi
    UNSHADOW_ARGS
    pop         rbp
    ret