问题
I am looking to optimise some SSE code I wrote for converting YUV to RGB (both planar and packed YUV functions).
I am using SSSE3 at the moment, but if there are useful functions from later SSE versions that's ok.
I am mainly interested in how I would work out processor stalls and the like.
Anyone know of any tools that do static analysis of SSE code?
;
; Copyright (C) 2009-2010 David McPaul
;
; All rights reserved. Distributed under the terms of the MIT License.
;
; A rather unoptimised set of ssse3 yuv to rgb converters
; does 8 pixels per loop
; inputer:
; reads 128 bits of yuv 8 bit data and puts
; the y values converted to 16 bit in xmm0
; the u values converted to 16 bit and duplicated into xmm1
; the v values converted to 16 bit and duplicated into xmm2
; conversion:
; does the yuv to rgb conversion using 16 bit integer and the
; results are placed into the following registers as 8 bit clamped values
; r values in xmm3
; g values in xmm4
; b values in xmm5
; outputer:
; writes out the rgba pixels as 8 bit values with 0 for alpha
; xmm6 used for scratch
; xmm7 used for scratch
%macro cglobal 1
global _%1
%define %1 _%1
align 16
%1:
%endmacro
; conversion code
%macro yuv2rgbsse2 0
; u = u - 128
; v = v - 128
; r = y + v + v >> 2 + v >> 3 + v >> 5
; g = y - (u >> 2 + u >> 4 + u >> 5) - (v >> 1 + v >> 3 + v >> 4 + v >> 5)
; b = y + u + u >> 1 + u >> 2 + u >> 6
; subtract 16 from y
movdqa xmm7, [Const16] ; loads a constant using data cache (slower on first fetch but then cached)
psubsw xmm0,xmm7 ; y = y - 16
; subtract 128 from u and v movdqa xmm7, [Const128] ; loads a constant using data cache (slower on first fetch but then cached)
psubsw xmm1,xmm7 ; u = u - 128
psubsw xmm2,xmm7 ; v = v - 128
; load r,b with y
movdqa xmm3,xmm0 ; r = y
pshufd xmm5,xmm0, 0xE4 ; b = y
; r = y + v + v >> 2 + v >> 3 + v >> 5
paddsw xmm3, xmm2 ; add v to r
movdqa xmm7, xmm1 ; move u to scratch
pshufd xmm6, xmm2, 0xE4 ; move v to scratch
psraw xmm6,2 ; divide v by 4
paddsw xmm3, xmm6 ; and add to r
psraw xmm6,1 ; divide v by 2
paddsw xmm3, xmm6 ; and add to r
psraw xmm6,2 ; divide v by 4
paddsw xmm3, xmm6 ; and add to r
; b = y + u + u >> 1 + u >> 2 + u >> 6
paddsw xmm5, xmm1 ; add u to b
psraw xmm7,1 ; divide u by 2
paddsw xmm5, xmm7 ; and add to b
psraw xmm7,1 ; divide u by 2
paddsw xmm5, xmm7 ; and add to b
psraw xmm7,4 ; divide u by 32
paddsw xmm5, xmm7 ; and add to b
; g = y - u >> 2 - u >> 4 - u >> 5 - v >> 1 - v >> 3 - v >> 4 - v >> 5
movdqa xmm7,xmm2 ; move v to scratch
pshufd xmm6,xmm1, 0xE4 ; move u to scratch
movdqa xmm4,xmm0 ; g = y
psraw xmm6,2 ; divide u by 4
psubsw xmm4,xmm6 ; subtract from g
psraw xmm6,2 ; divide u by 4
psubsw xmm4,xmm6 ; subtract from g
psraw xmm6,1 ; divide u by 2
psubsw xmm4,xmm6 ; subtract from g
psraw xmm7,1 ; divide v by 2
psubsw xmm4,xmm7 ; subtract from g
psraw xmm7,2 ; divide v by 4
psubsw xmm4,xmm7 ; subtract from g
psraw xmm7,1 ; divide v by 2
psubsw xmm4,xmm7 ; subtract from g
psraw xmm7,1 ; divide v by 2
psubsw xmm4,xmm7 ; subtract from g
%endmacro
; outputer
%macro rgba32sse2output 0
; clamp values
pxor xmm7,xmm7
packuswb xmm3,xmm7 ; clamp to 0,255 and pack R to 8 bit per pixel
packuswb xmm4,xmm7 ; clamp to 0,255 and pack G to 8 bit per pixel
packuswb xmm5,xmm7 ; clamp to 0,255 and pack B to 8 bit per pixel
; convert to bgra32 packed
punpcklbw xmm5,xmm4 ; bgbgbgbgbgbgbgbg
movdqa xmm0, xmm5 ; save bg values
punpcklbw xmm3,xmm7 ; r0r0r0r0r0r0r0r0
punpcklwd xmm5,xmm3 ; lower half bgr0bgr0bgr0bgr0
punpckhwd xmm0,xmm3 ; upper half bgr0bgr0bgr0bgr0
; write to output ptr
movntdq [edi], xmm5 ; output first 4 pixels bypassing cache
movntdq [edi+16], xmm0 ; output second 4 pixels bypassing cache
%endmacro
SECTION .data align=16
Const16 dw 16
dw 16
dw 16
dw 16
dw 16
dw 16
dw 16
dw 16
Const128 dw 128
dw 128
dw 128
dw 128
dw 128
dw 128
dw 128
dw 128
UMask db 0x01
db 0x80
db 0x01
db 0x80
db 0x05
db 0x80
db 0x05
db 0x80
db 0x09
db 0x80
db 0x09
db 0x80
db 0x0d
db 0x80
db 0x0d
db 0x80
VMask db 0x03
db 0x80
db 0x03
db 0x80
db 0x07
db 0x80
db 0x07
db 0x80
db 0x0b
db 0x80
db 0x0b
db 0x80
db 0x0f
db 0x80
db 0x0f
db 0x80
YMask db 0x00
db 0x80
db 0x02
db 0x80
db 0x04
db 0x80
db 0x06
db 0x80
db 0x08
db 0x80
db 0x0a
db 0x80
db 0x0c
db 0x80
db 0x0e
db 0x80
; void Convert_YUV422_RGBA32_SSSE3(void *fromPtr, void *toPtr, int width)
width equ ebp+16
toPtr equ ebp+12
fromPtr equ ebp+8
; void Convert_YUV420P_RGBA32_SSSE3(void *fromYPtr, void *fromUPtr, void *fromVPtr, void *toPtr, int width)
width1 equ ebp+24
toPtr1 equ ebp+20
fromVPtr equ ebp+16
fromUPtr equ ebp+12
fromYPtr equ ebp+8
SECTION .text align=16
cglobal Convert_YUV422_RGBA32_SSSE3
; reserve variables
push ebp
mov ebp, esp
push edi
push esi
push ecx
mov esi, [fromPtr]
mov edi, [toPtr]
mov ecx, [width]
; loop width / 8 times
shr ecx,3
test ecx,ecx
jng ENDLOOP
REPEATLOOP: ; loop over width / 8
; YUV422 packed inputer
movdqa xmm0, [esi] ; should have yuyv yuyv yuyv yuyv
pshufd xmm1, xmm0, 0xE4 ; copy to xmm1
movdqa xmm2, xmm0 ; copy to xmm2
; extract both y giving y0y0
pshufb xmm0, [YMask]
; extract u and duplicate so each u in yuyv becomes u0u0
pshufb xmm1, [UMask]
; extract v and duplicate so each v in yuyv becomes v0v0
pshufb xmm2, [VMask]
yuv2rgbsse2
rgba32sse2output
; endloop
add edi,32
add esi,16
sub ecx, 1 ; apparently sub is better than dec
jnz REPEATLOOP
ENDLOOP:
; Cleanup
pop ecx
pop esi
pop edi
mov esp, ebp
pop ebp
ret
cglobal Convert_YUV420P_RGBA32_SSSE3
; reserve variables
push ebp
mov ebp, esp
push edi
push esi
push ecx
push eax
push ebx
mov esi, [fromYPtr]
mov eax, [fromUPtr]
mov ebx, [fromVPtr]
mov edi, [toPtr1]
mov ecx, [width1]
; loop width / 8 times
shr ecx,3
test ecx,ecx
jng ENDLOOP1
REPEATLOOP1: ; loop over width / 8
; YUV420 Planar inputer movq xmm0, [esi] ; fetch 8 y values (8 bit) yyyyyyyy00000000
movd xmm1, [eax] ; fetch 4 u values (8 bit) uuuu000000000000
movd xmm2, [ebx] ; fetch 4 v values (8 bit) vvvv000000000000
; extract y
pxor xmm7,xmm7 ; 00000000000000000000000000000000
punpcklbw xmm0,xmm7 ; interleave xmm7 into xmm0 y0y0y0y0y0y0y0y0
; extract u and duplicate so each becomes 0u0u
punpcklbw xmm1,xmm7 ; interleave xmm7 into xmm1 u0u0u0u000000000
punpcklwd xmm1,xmm7 ; interleave again u000u000u000u000
pshuflw xmm1,xmm1, 0xA0 ; copy u values
pshufhw xmm1,xmm1, 0xA0 ; to get u0u0
; extract v
punpcklbw xmm2,xmm7 ; interleave xmm7 into xmm1 v0v0v0v000000000
punpcklwd xmm2,xmm7 ; interleave again v000v000v000v000
pshuflw xmm2,xmm2, 0xA0 ; copy v values
pshufhw xmm2,xmm2, 0xA0 ; to get v0v0
yuv2rgbsse2
rgba32sse2output
; endloop
add edi,32
add esi,8
add eax,4
add ebx,4
sub ecx, 1 ; apparently sub is better than dec
jnz REPEATLOOP1
ENDLOOP1:
; Cleanup
pop ebx
pop eax
pop ecx
pop esi
pop edi
mov esp, ebp
pop ebp
ret
SECTION .note.GNU-stack noalloc noexec nowrite progbits
回答1:
If you keep u & v interleaved in one register, and use 'pmaddwd' and precomputed constants instead of your shift-and-add approach, you can compress the conversion code to about a third, and get rid of most stalls at the same time:
; xmm0 = y y y y y y y y
; xmm3 = u v u v u v u v
psubsw xmm3, [Const128]
psubsw xmm0, [Const16]
movdqa xmm4, xmm3
movdqa xmm5, xmm3
pmaddwd xmm3, [const_1]
pmaddwd xmm4, [const_2]
pmaddwd xmm5, [const_3]
psrad xmm3, 14
psrad xmm4, 14
psrad xmm5, 14
pshufb xmm3, xmm3, [const_4] ; or pshuflw & pshufhw
pshufb xmm4, xmm4, [const_4]
pshufb xmm5, xmm5, [const_4]
paddsw xmm3, xmm0
paddsw xmm4, xmm0
paddsw xmm5, xmm0
If you want it to work even faster, playing with PMADDUBSW should allow you to work on 16 pixels at a time with a small increase in complexity.
Most processors (particularly non-Intels, notorious for not having a well-working hardware prefetcher, but, to a lesser extent, Intels too) will benefit from a prefetchnta [esi+256] thrown inside the loop.
EDIT: the code that uses PMADDUBSW could look like this (correctness not guaranteed):
const a:
times 4 db 1,3
times 4 db 5,7
const b:
times 4 db 9,11
times 4 db 13,15
const_c: times 8 dw 0x00ff
const_d: times 4 dd 0x00ffffff
const_uv_to_rgb_mul:
...
const_uv_to_rgb_add:
...
movdqa xmm4, [esi]
movdqa xmm0, xmm4
movdqa xmm1, xmm4
pshufb xmm0, [const_a]
pshufb xmm1, [const_b]
pand xmm4, [const_c]
; xmm0: uv0 uv0 uv0 uv0 uv2 uv2 uv2 uv2 uv2
; xmm1: uv4 uv4 uv4 uv4 ...
; xmm4: y0 0 y1 0 y2 0 y3 0 y4 0 y5 0 y6 0 y7 0
pmaddubsw xmm0, [const_uv_to_rgb_mul]
pmaddubsw xmm1, [const_uv_to_rgb_mul]
paddsw xmm0, [const_uv_to_rgb_add]
paddsw xmm1, [const_uv_to_rgb_add]
psraw xmm0, 6
psraw xmm1, 6
; r01 g01 b01 0 r23 g23 b23 0
pshufd xmm2, xmm0, 2+3*4+2*16+3*64
pshufd xmm0, xmm0, 0+1*4+0+16+1*64
pshufd xmm3, xmm1, 2+3*4+2*16+3*64
pshufd xmm1, xmm1, 0+1*4+0+16+1*64
; xmm0: r01 g01 b01 0 r01 g01 b01 0
; xmm2: r23 g23 b23 0 r23 g23 b23 0
; xmm1: r45 g45 b45 0 r45 g45 b45 0
paddsw xmm0, xmm4 ; add y
paddsw xmm1, xmm4
paddsw xmm2, xmm4
paddsw xmm3, xmm4
packuswb xmm0, xmm2 ; pack with saturation into 0-255 range
packuswb xmm1, xmm3
pand xmm0, [const_d] ; zero out the alpha byte
pand xmm1, [const_d]
movntdq [edi], xmm0
movntdq [edi+16], xmm1
回答2:
The look up tables work if you use saturating adds, but they limit you to 1 pixel at a time and memory lookups are slow when they cache miss. The 3 pmaddubsw works ok, but the instruction is slow on Core2 and not available on older one's. So 4 pmul's might work better.
回答3:
Given that the source data is only 8-bit per component, have you tried something simple, like:
uint32_t YtoRGBlookupTable[256] = {
/* precomputed table (cut & pasted from a spreadsheet or something) */
};
uint32_t UtoRGBlookupTable[256] = {
/* precomputed table (cut & pasted from a spreadsheet or something) */
};
uint32_t VtoRGBlookupTable[256] = {
/* precomputed table (cut & pasted from a spreadsheet or something) */
};
while(i < something) {
UVtemp = UtoRGBlookupTable[src->u0] + VtoRGBlookupTable[src->v0];
dest[i] = YtoRGBlookupTable[src->y0] + UVtemp;
dest[i+1] = YtoRGBlookupTable[src->y1] + UVtemp;
UVtemp = UtoRGBlookupTable[src->u1] + VtoRGBlookupTable[src->v1];
dest[i+2] = YtoRGBlookupTable[src->y2] + UVtemp;
dest[i+3] = YtoRGBlookupTable[src->y3] + UVtemp;
i += 4;
src++;
}
D'oh - sorry. This won't work because you can't prevent the green from overflowing into the red, and you'd need to handle green separately.
来源：https://stackoverflow.com/questions/4572548/improve-sse-ssse3-yuv-to-rgb-code