generic-library/vpx
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
e5f7139951
vpx/vp8/encoder/x86/sad_sse3.asm
Fritz Koenig e180255375 Remove stack shadowing for x86-x64 for SAD functions. 
x86-64 passes arguments in registers.  There is no need to push
them to the stack before using them.

This fixes 15acc84f10 where ebx
was not getting preserved on x86.

Change-Id: I1214b5f818a0201f75ab6ad7d5c6f448e09b16c2
2010-11-15 10:56:02 -08:00

898 lines
27 KiB
NASM
Raw Blame History

;
; 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"
%macro STACK_FRAME_CREATE_X3 0
%if ABI_IS_32BIT
%define src_ptr rsi
%define src_stride rax
%define ref_ptr rdi
%define ref_stride rdx
%define end_ptr rcx
%define ret_var rbx
%define result_ptr arg(4)
%define max_err arg(4)
push rbp
mov rbp, rsp
push rsi
push rdi
push rbx
mov rsi, arg(0) ; src_ptr
mov rdi, arg(2) ; ref_ptr
movsxd rax, dword ptr arg(1) ; src_stride
movsxd rdx, dword ptr arg(3) ; ref_stride
%else
%ifidn __OUTPUT_FORMAT__,x64
%define src_ptr rcx
%define src_stride rdx
%define ref_ptr r8
%define ref_stride r9
%define end_ptr r10
%define ret_var r11
%define result_ptr [rsp+8+4*8]
%define max_err [rsp+8+4*8]
%else
%define src_ptr rdi
%define src_stride rsi
%define ref_ptr rdx
%define ref_stride rcx
%define end_ptr r9
%define ret_var r10
%define result_ptr r8
%define max_err r8
%endif
%endif
%endmacro
%macro STACK_FRAME_DESTROY_X3 0
%define src_ptr
%define src_stride
%define ref_ptr
%define ref_stride
%define end_ptr
%define ret_var
%define result_ptr
%define max_err
%if ABI_IS_32BIT
pop rbx
pop rdi
pop rsi
pop rbp
%else
%ifidn __OUTPUT_FORMAT__,x64
%endif
%endif
ret
%endmacro
%macro STACK_FRAME_CREATE_X4 0
%if ABI_IS_32BIT
%define src_ptr rsi
%define src_stride rax
%define r0_ptr rcx
%define r1_ptr rdx
%define r2_ptr rbx
%define r3_ptr rdi
%define ref_stride rbp
%define result_ptr arg(4)
push rbp
mov rbp, rsp
push rsi
push rdi
push rbx
push rbp
mov rdi, arg(2) ; ref_ptr_base
LOAD_X4_ADDRESSES rdi, rcx, rdx, rax, rdi
mov rsi, arg(0) ; src_ptr
movsxd rbx, dword ptr arg(1) ; src_stride
movsxd rbp, dword ptr arg(3) ; ref_stride
xchg rbx, rax
%else
%ifidn __OUTPUT_FORMAT__,x64
%define src_ptr rcx
%define src_stride rdx
%define r0_ptr rsi
%define r1_ptr r10
%define r2_ptr r11
%define r3_ptr r8
%define ref_stride r9
%define result_ptr [rsp+16+4*8]
push rsi
LOAD_X4_ADDRESSES r8, r0_ptr, r1_ptr, r2_ptr, r3_ptr
%else
%define src_ptr rdi
%define src_stride rsi
%define r0_ptr r9
%define r1_ptr r10
%define r2_ptr r11
%define r3_ptr rdx
%define ref_stride rcx
%define result_ptr r8
LOAD_X4_ADDRESSES rdx, r0_ptr, r1_ptr, r2_ptr, r3_ptr
%endif
%endif
%endmacro
%macro STACK_FRAME_DESTROY_X4 0
%define src_ptr
%define src_stride
%define r0_ptr
%define r1_ptr
%define r2_ptr
%define r3_ptr
%define ref_stride
%define result_ptr
%if ABI_IS_32BIT
pop rbx
pop rdi
pop rsi
pop rbp
%else
%ifidn __OUTPUT_FORMAT__,x64
pop rsi
%endif
%endif
ret
%endmacro
%macro PROCESS_16X2X3 5
%if %1==0
movdqa xmm0, XMMWORD PTR [%2]
lddqu xmm5, XMMWORD PTR [%3]
lddqu xmm6, XMMWORD PTR [%3+1]
lddqu xmm7, XMMWORD PTR [%3+2]
psadbw xmm5, xmm0
psadbw xmm6, xmm0
psadbw xmm7, xmm0
%else
movdqa xmm0, XMMWORD PTR [%2]
lddqu xmm1, XMMWORD PTR [%3]
lddqu xmm2, XMMWORD PTR [%3+1]
lddqu xmm3, XMMWORD PTR [%3+2]
psadbw xmm1, xmm0
psadbw xmm2, xmm0
psadbw xmm3, xmm0
paddw xmm5, xmm1
paddw xmm6, xmm2
paddw xmm7, xmm3
%endif
movdqa xmm0, XMMWORD PTR [%2+%4]
lddqu xmm1, XMMWORD PTR [%3+%5]
lddqu xmm2, XMMWORD PTR [%3+%5+1]
lddqu xmm3, XMMWORD PTR [%3+%5+2]
%if %1==0 || %1==1
lea %2, [%2+%4*2]
lea %3, [%3+%5*2]
%endif
psadbw xmm1, xmm0
psadbw xmm2, xmm0
psadbw xmm3, xmm0
paddw xmm5, xmm1
paddw xmm6, xmm2
paddw xmm7, xmm3
%endmacro
%macro PROCESS_8X2X3 5
%if %1==0
movq mm0, QWORD PTR [%2]
movq mm5, QWORD PTR [%3]
movq mm6, QWORD PTR [%3+1]
movq mm7, QWORD PTR [%3+2]
psadbw mm5, mm0
psadbw mm6, mm0
psadbw mm7, mm0
%else
movq mm0, QWORD PTR [%2]
movq mm1, QWORD PTR [%3]
movq mm2, QWORD PTR [%3+1]
movq mm3, QWORD PTR [%3+2]
psadbw mm1, mm0
psadbw mm2, mm0
psadbw mm3, mm0
paddw mm5, mm1
paddw mm6, mm2
paddw mm7, mm3
%endif
movq mm0, QWORD PTR [%2+%4]
movq mm1, QWORD PTR [%3+%5]
movq mm2, QWORD PTR [%3+%5+1]
movq mm3, QWORD PTR [%3+%5+2]
%if %1==0 || %1==1
lea %2, [%2+%4*2]
lea %3, [%3+%5*2]
%endif
psadbw mm1, mm0
psadbw mm2, mm0
psadbw mm3, mm0
paddw mm5, mm1
paddw mm6, mm2
paddw mm7, mm3
%endmacro
%macro LOAD_X4_ADDRESSES 5
mov %2, [%1+REG_SZ_BYTES*0]
mov %3, [%1+REG_SZ_BYTES*1]
mov %4, [%1+REG_SZ_BYTES*2]
mov %5, [%1+REG_SZ_BYTES*3]
%endmacro
%macro PROCESS_16X2X4 8
%if %1==0
movdqa xmm0, XMMWORD PTR [%2]
lddqu xmm4, XMMWORD PTR [%3]
lddqu xmm5, XMMWORD PTR [%4]
lddqu xmm6, XMMWORD PTR [%5]
lddqu xmm7, XMMWORD PTR [%6]
psadbw xmm4, xmm0
psadbw xmm5, xmm0
psadbw xmm6, xmm0
psadbw xmm7, xmm0
%else
movdqa xmm0, XMMWORD PTR [%2]
lddqu xmm1, XMMWORD PTR [%3]
lddqu xmm2, XMMWORD PTR [%4]
lddqu xmm3, XMMWORD PTR [%5]
psadbw xmm1, xmm0
psadbw xmm2, xmm0
psadbw xmm3, xmm0
paddw xmm4, xmm1
lddqu xmm1, XMMWORD PTR [%6]
paddw xmm5, xmm2
paddw xmm6, xmm3
psadbw xmm1, xmm0
paddw xmm7, xmm1
%endif
movdqa xmm0, XMMWORD PTR [%2+%7]
lddqu xmm1, XMMWORD PTR [%3+%8]
lddqu xmm2, XMMWORD PTR [%4+%8]
lddqu xmm3, XMMWORD PTR [%5+%8]
psadbw xmm1, xmm0
psadbw xmm2, xmm0
psadbw xmm3, xmm0
paddw xmm4, xmm1
lddqu xmm1, XMMWORD PTR [%6+%8]
paddw xmm5, xmm2
paddw xmm6, xmm3
%if %1==0 || %1==1
lea %2, [%2+%7*2]
lea %3, [%3+%8*2]
lea %4, [%4+%8*2]
lea %5, [%5+%8*2]
lea %6, [%6+%8*2]
%endif
psadbw xmm1, xmm0
paddw xmm7, xmm1
%endmacro
%macro PROCESS_8X2X4 8
%if %1==0
movq mm0, QWORD PTR [%2]
movq mm4, QWORD PTR [%3]
movq mm5, QWORD PTR [%4]
movq mm6, QWORD PTR [%5]
movq mm7, QWORD PTR [%6]
psadbw mm4, mm0
psadbw mm5, mm0
psadbw mm6, mm0
psadbw mm7, mm0
%else
movq mm0, QWORD PTR [%2]
movq mm1, QWORD PTR [%3]
movq mm2, QWORD PTR [%4]
movq mm3, QWORD PTR [%5]
psadbw mm1, mm0
psadbw mm2, mm0
psadbw mm3, mm0
paddw mm4, mm1
movq mm1, QWORD PTR [%6]
paddw mm5, mm2
paddw mm6, mm3
psadbw mm1, mm0
paddw mm7, mm1
%endif
movq mm0, QWORD PTR [%2+%7]
movq mm1, QWORD PTR [%3+%8]
movq mm2, QWORD PTR [%4+%8]
movq mm3, QWORD PTR [%5+%8]
psadbw mm1, mm0
psadbw mm2, mm0
psadbw mm3, mm0
paddw mm4, mm1
movq mm1, QWORD PTR [%6+%8]
paddw mm5, mm2
paddw mm6, mm3
%if %1==0 || %1==1
lea %2, [%2+%7*2]
lea %3, [%3+%8*2]
lea %4, [%4+%8*2]
lea %5, [%5+%8*2]
lea %6, [%6+%8*2]
%endif
psadbw mm1, mm0
paddw mm7, mm1
%endmacro
;void int vp8_sad16x16x3_sse3(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr,
; int ref_stride,
; int *results)
global sym(vp8_sad16x16x3_sse3)
sym(vp8_sad16x16x3_sse3):
STACK_FRAME_CREATE_X3
PROCESS_16X2X3 0, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_16X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_16X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_16X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_16X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_16X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_16X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_16X2X3 2, src_ptr, ref_ptr, src_stride, ref_stride
mov rcx, result_ptr
movq xmm0, xmm5
psrldq xmm5, 8
paddw xmm0, xmm5
movd [rcx], xmm0
;-
movq xmm0, xmm6
psrldq xmm6, 8
paddw xmm0, xmm6
movd [rcx+4], xmm0
;-
movq xmm0, xmm7
psrldq xmm7, 8
paddw xmm0, xmm7
movd [rcx+8], xmm0
STACK_FRAME_DESTROY_X3
;void int vp8_sad16x8x3_sse3(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr,
; int ref_stride,
; int *results)
global sym(vp8_sad16x8x3_sse3)
sym(vp8_sad16x8x3_sse3):
STACK_FRAME_CREATE_X3
PROCESS_16X2X3 0, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_16X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_16X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_16X2X3 2, src_ptr, ref_ptr, src_stride, ref_stride
mov rcx, result_ptr
movq xmm0, xmm5
psrldq xmm5, 8
paddw xmm0, xmm5
movd [rcx], xmm0
;-
movq xmm0, xmm6
psrldq xmm6, 8
paddw xmm0, xmm6
movd [rcx+4], xmm0
;-
movq xmm0, xmm7
psrldq xmm7, 8
paddw xmm0, xmm7
movd [rcx+8], xmm0
STACK_FRAME_DESTROY_X3
;void int vp8_sad8x16x3_sse3(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr,
; int ref_stride,
; int *results)
global sym(vp8_sad8x16x3_sse3)
sym(vp8_sad8x16x3_sse3):
STACK_FRAME_CREATE_X3
PROCESS_8X2X3 0, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_8X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_8X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_8X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_8X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_8X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_8X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_8X2X3 2, src_ptr, ref_ptr, src_stride, ref_stride
mov rcx, result_ptr
punpckldq mm5, mm6
movq [rcx], mm5
movd [rcx+8], mm7
STACK_FRAME_DESTROY_X3
;void int vp8_sad8x8x3_sse3(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr,
; int ref_stride,
; int *results)
global sym(vp8_sad8x8x3_sse3)
sym(vp8_sad8x8x3_sse3):
STACK_FRAME_CREATE_X3
PROCESS_8X2X3 0, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_8X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_8X2X3 1, src_ptr, ref_ptr, src_stride, ref_stride
PROCESS_8X2X3 2, src_ptr, ref_ptr, src_stride, ref_stride
mov rcx, result_ptr
punpckldq mm5, mm6
movq [rcx], mm5
movd [rcx+8], mm7
STACK_FRAME_DESTROY_X3
;void int vp8_sad4x4x3_sse3(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr,
; int ref_stride,
; int *results)
global sym(vp8_sad4x4x3_sse3)
sym(vp8_sad4x4x3_sse3):
STACK_FRAME_CREATE_X3
movd mm0, DWORD PTR [src_ptr]
movd mm1, DWORD PTR [ref_ptr]
movd mm2, DWORD PTR [src_ptr+src_stride]
movd mm3, DWORD PTR [ref_ptr+ref_stride]
punpcklbw mm0, mm2
punpcklbw mm1, mm3
movd mm4, DWORD PTR [ref_ptr+1]
movd mm5, DWORD PTR [ref_ptr+2]
movd mm2, DWORD PTR [ref_ptr+ref_stride+1]
movd mm3, DWORD PTR [ref_ptr+ref_stride+2]
psadbw mm1, mm0
punpcklbw mm4, mm2
punpcklbw mm5, mm3
psadbw mm4, mm0
psadbw mm5, mm0
lea src_ptr, [src_ptr+src_stride*2]
lea ref_ptr, [ref_ptr+ref_stride*2]
movd mm0, DWORD PTR [src_ptr]
movd mm2, DWORD PTR [ref_ptr]
movd mm3, DWORD PTR [src_ptr+src_stride]
movd mm6, DWORD PTR [ref_ptr+ref_stride]
punpcklbw mm0, mm3
punpcklbw mm2, mm6
movd mm3, DWORD PTR [ref_ptr+1]
movd mm7, DWORD PTR [ref_ptr+2]
psadbw mm2, mm0
paddw mm1, mm2
movd mm2, DWORD PTR [ref_ptr+ref_stride+1]
movd mm6, DWORD PTR [ref_ptr+ref_stride+2]
punpcklbw mm3, mm2
punpcklbw mm7, mm6
psadbw mm3, mm0
psadbw mm7, mm0
paddw mm3, mm4
paddw mm7, mm5
mov rcx, result_ptr
punpckldq mm1, mm3
movq [rcx], mm1
movd [rcx+8], mm7
STACK_FRAME_DESTROY_X3
;unsigned int vp8_sad16x16_sse3(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr,
; int ref_stride,
; int max_err)
;%define lddqu movdqu
global sym(vp8_sad16x16_sse3)
sym(vp8_sad16x16_sse3):
STACK_FRAME_CREATE_X3
lea end_ptr, [src_ptr+src_stride*8]
lea end_ptr, [end_ptr+src_stride*8]
pxor mm7, mm7
.vp8_sad16x16_sse3_loop:
movq ret_var, mm7
cmp ret_var, max_err
jg .vp8_sad16x16_early_exit
movq mm0, QWORD PTR [src_ptr]
movq mm2, QWORD PTR [src_ptr+8]
movq mm1, QWORD PTR [ref_ptr]
movq mm3, QWORD PTR [ref_ptr+8]
movq mm4, QWORD PTR [src_ptr+src_stride]
movq mm5, QWORD PTR [ref_ptr+ref_stride]
psadbw mm0, mm1
psadbw mm2, mm3
movq mm1, QWORD PTR [src_ptr+src_stride+8]
movq mm3, QWORD PTR [ref_ptr+ref_stride+8]
psadbw mm4, mm5
psadbw mm1, mm3
lea src_ptr, [src_ptr+src_stride*2]
lea ref_ptr, [ref_ptr+ref_stride*2]
paddw mm0, mm2
paddw mm4, mm1
paddw mm7, mm0
paddw mm7, mm4
cmp src_ptr, end_ptr
jne .vp8_sad16x16_sse3_loop
movq ret_var, mm7
.vp8_sad16x16_early_exit:
mov rax, ret_var
STACK_FRAME_DESTROY_X3
;void vp8_sad16x16x4d_sse3(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr_base,
; int ref_stride,
; int *results)
global sym(vp8_sad16x16x4d_sse3)
sym(vp8_sad16x16x4d_sse3):
STACK_FRAME_CREATE_X4
PROCESS_16X2X4 0, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_16X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_16X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_16X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_16X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_16X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_16X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_16X2X4 2, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
%if ABI_IS_32BIT
pop rbp
%endif
mov rcx, result_ptr
movq xmm0, xmm4
psrldq xmm4, 8
paddw xmm0, xmm4
movd [rcx], xmm0
;-
movq xmm0, xmm5
psrldq xmm5, 8
paddw xmm0, xmm5
movd [rcx+4], xmm0
;-
movq xmm0, xmm6
psrldq xmm6, 8
paddw xmm0, xmm6
movd [rcx+8], xmm0
;-
movq xmm0, xmm7
psrldq xmm7, 8
paddw xmm0, xmm7
movd [rcx+12], xmm0
STACK_FRAME_DESTROY_X4
;void vp8_sad16x8x4d_sse3(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr_base,
; int ref_stride,
; int *results)
global sym(vp8_sad16x8x4d_sse3)
sym(vp8_sad16x8x4d_sse3):
STACK_FRAME_CREATE_X4
PROCESS_16X2X4 0, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_16X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_16X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_16X2X4 2, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
%if ABI_IS_32BIT
pop rbp
%endif
mov rcx, result_ptr
movq xmm0, xmm4
psrldq xmm4, 8
paddw xmm0, xmm4
movd [rcx], xmm0
;-
movq xmm0, xmm5
psrldq xmm5, 8
paddw xmm0, xmm5
movd [rcx+4], xmm0
;-
movq xmm0, xmm6
psrldq xmm6, 8
paddw xmm0, xmm6
movd [rcx+8], xmm0
;-
movq xmm0, xmm7
psrldq xmm7, 8
paddw xmm0, xmm7
movd [rcx+12], xmm0
STACK_FRAME_DESTROY_X4
;void int vp8_sad8x16x4d_sse3(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr,
; int ref_stride,
; int *results)
global sym(vp8_sad8x16x4d_sse3)
sym(vp8_sad8x16x4d_sse3):
STACK_FRAME_CREATE_X4
PROCESS_8X2X4 0, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_8X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_8X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_8X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_8X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_8X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_8X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_8X2X4 2, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
%if ABI_IS_32BIT
pop rbp
%endif
mov rcx, result_ptr
punpckldq mm4, mm5
punpckldq mm6, mm7
movq [rcx], mm4
movq [rcx+8], mm6
STACK_FRAME_DESTROY_X4
;void int vp8_sad8x8x4d_sse3(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr,
; int ref_stride,
; int *results)
global sym(vp8_sad8x8x4d_sse3)
sym(vp8_sad8x8x4d_sse3):
STACK_FRAME_CREATE_X4
PROCESS_8X2X4 0, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_8X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_8X2X4 1, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
PROCESS_8X2X4 2, src_ptr, r0_ptr, r1_ptr, r2_ptr, r3_ptr, src_stride, ref_stride
%if ABI_IS_32BIT
pop rbp
%endif
mov rcx, result_ptr
punpckldq mm4, mm5
punpckldq mm6, mm7
movq [rcx], mm4
movq [rcx+8], mm6
STACK_FRAME_DESTROY_X4
;void int vp8_sad4x4x4d_sse3(
; unsigned char *src_ptr,
; int src_stride,
; unsigned char *ref_ptr,
; int ref_stride,
; int *results)
global sym(vp8_sad4x4x4d_sse3)
sym(vp8_sad4x4x4d_sse3):
STACK_FRAME_CREATE_X4
movd mm0, DWORD PTR [src_ptr]
movd mm1, DWORD PTR [r0_ptr]
movd mm2, DWORD PTR [src_ptr+src_stride]
movd mm3, DWORD PTR [r0_ptr+ref_stride]
punpcklbw mm0, mm2
punpcklbw mm1, mm3
movd mm4, DWORD PTR [r1_ptr]
movd mm5, DWORD PTR [r2_ptr]
movd mm6, DWORD PTR [r3_ptr]
movd mm2, DWORD PTR [r1_ptr+ref_stride]
movd mm3, DWORD PTR [r2_ptr+ref_stride]
movd mm7, DWORD PTR [r3_ptr+ref_stride]
psadbw mm1, mm0
punpcklbw mm4, mm2
punpcklbw mm5, mm3
punpcklbw mm6, mm7
psadbw mm4, mm0
psadbw mm5, mm0
psadbw mm6, mm0
lea src_ptr, [src_ptr+src_stride*2]
lea r0_ptr, [r0_ptr+ref_stride*2]
lea r1_ptr, [r1_ptr+ref_stride*2]
lea r2_ptr, [r2_ptr+ref_stride*2]
lea r3_ptr, [r3_ptr+ref_stride*2]
movd mm0, DWORD PTR [src_ptr]
movd mm2, DWORD PTR [r0_ptr]
movd mm3, DWORD PTR [src_ptr+src_stride]
movd mm7, DWORD PTR [r0_ptr+ref_stride]
punpcklbw mm0, mm3
punpcklbw mm2, mm7
movd mm3, DWORD PTR [r1_ptr]
movd mm7, DWORD PTR [r2_ptr]
psadbw mm2, mm0
%if ABI_IS_32BIT
mov rax, rbp
pop rbp
%define ref_stride rax
%endif
mov rsi, result_ptr
paddw mm1, mm2
movd [rsi], mm1
movd mm2, DWORD PTR [r1_ptr+ref_stride]
movd mm1, DWORD PTR [r2_ptr+ref_stride]
punpcklbw mm3, mm2
punpcklbw mm7, mm1
psadbw mm3, mm0
psadbw mm7, mm0
movd mm2, DWORD PTR [r3_ptr]
movd mm1, DWORD PTR [r3_ptr+ref_stride]
paddw mm3, mm4
paddw mm7, mm5
movd [rsi+4], mm3
punpcklbw mm2, mm1
movd [rsi+8], mm7
psadbw mm2, mm0
paddw mm2, mm6
movd [rsi+12], mm2
STACK_FRAME_DESTROY_X4
Reference in New Issue View Git Blame Copy Permalink