I am currently doing a color conversion routine in order to convert from YUY2 to NV12. I have a function which is quite fast, but not as fast as I would expect, mainly due to cache misses.
void convert_hd(uint8_t *orig, uint8_t *result) {
uint32_t width = 1280;
uint32_t height = 720;
uint8_t *lineOdd = orig;
uint8_t *lineEven = orig + width*2;
uint8_t *resultYOdd = result;
uint8_t *resultYEven = result + width;
uint8_t *resultUV = result + height*width;
uint32_t totalLoop = height/2;
while (totalLoop-- > 0) {
uint32_t lineLoop = 1280/32; // Bytes length: width*2, read by iter 16Bytes
while(lineLoop-- > 0) {
__asm__ __volatile__(
"pld [%[lineOdd]] \n\t"
"vld4.8 {d0, d1, d2, d3}, [%[lineOdd],:128]! \n\t" // d0:Y d1:U0 d2:Y d3:V0
"pld [%[lineEven]] \n\t"
"vld4.8 {d4, d5, d6, d7}, [%[lineOdd],:128]! \n\t" // d4:Y d5:U1 d6:Y d7:V1
"vld4.8 {d8, d9, d10, d11}, [%[lineEven],:128]! \n\t" // d8:Y d9:U0' d10:Y d11:V0'
"vld4.8 {d12, d13, d14, d15}, [%[lineEven],:128]! \n\t" // d12:Y d13:U1' d14:Y d15:V1'
"vhadd.u8 d1, d1, d9 \n\t" // (U0+U0') / 2
"vhadd.u8 d3, d3, d11 \n\t" // (V0+V0') / 2
"vhadd.u8 d5, d5, d13 \n\t" // (U1+U1') / 2
"vhadd.u8 d7, d7, d15 \n\t" // (V1+V1') / 2
// Save
"vst2.8 {d0, d2}, [%[resultYOdd],:128]! \n\t"
"vst2.8 {d4, d6}, [%[resultYOdd],:128]! \n\t"
"vst2.8 {d8, d10}, [%[resultYEven],:128]! \n\t"
"vst2.8 {d12, d14}, [%[resultYEven],:128]! \n\t"
"vst2.8 {d1, d3}, [%[resultUV],:128]! \n\t"
"vst2.8 {d5, d7}, [%[resultUV],:128]! \n\t"
: [lineOdd]"+r"(lineOdd), [lineEven]"+r"(lineEven), [resultYOdd]"+r"(resultYOdd), [resultYEven]"+r"(resultYEven), [resultUV]"+r"(resultUV)
:
: "memory"
);
}
lineOdd += width*2;
lineEven += width*2;
resultYOdd += width;
resultYEven += width;
}
}
When I ask oprofile what is taking time, it says the following :
: 220c: add r2, r0, #2560 ;
: 2210: add r3, r1, #1280 ;
: 2214: add ip, r1, #921600 ;
: 2218: push {r4, lr}
: 221c: mov r4, #360 ;
6 0.1243 10 0.5787 4 0.4561 : 2220: mov lr, #40 ; 0x28
9 0.1864 5 0.2894 0 0 : 2224: pld [r0]
45 0.9321 7 0.4051 3 0.3421 : 2228: vld4.8 {d0-d3}, [r0 :128]!
51 1.0563 7 0.4051 1 0.1140 : 222c: pld [r2]
1 0.0207 1 0.0579 0 0 : 2230: vld4.8 {d4-d7}, [r0 :128]!
1360 28.1690 770 44.5602 463 52.7936 : 2234: vld4.8 {d8-d11}, [r2 :128]!
980 20.2983 329 19.0394 254 28.9624 : 2238: vld4.8 {d12-d15}, [r2 :128]!
: 223c: vhadd.u8 d1, d1, d9
1000 20.7125 170 9.8380 104 11.8586 : 2240: vhadd.u8 d3, d3, d11
: 2244: vhadd.u8 d5, d5, d13
5 0.1036 2 0.1157 2 0.2281 : 2248: vhadd.u8 d7, d7, d15
: 224c: vst2.8 {d0,d2}, [r1 :128]!
1125 23.3016 293 16.9560 15 1.7104 : 2250: vst2.8 {d4,d6}, [r1 :128]!
34 0.7042 41 2.3727 0 0 : 2254: vst2.8 {d8,d10}, [r3 :128]!
74 1.5327 8 0.4630 0 0 : 2258: vst2.8 {d12,d14}, [r3 :128]!
60 1.2428 39 2.2569 6 0.6842 : 225c: vst2.8 {d1,d3}, [ip :128]!
53 1.0978 24 1.3889 14 1.5964 : 2260: vst2.8 {d5,d7}, [ip :128]!
: 2264: subs lr, lr, #1
0 0 0 0 1 0.1140 : 2268: bne 2224 <convert_hd+0x18>
11 0.2278 14 0.8102 10 1.1403 : 226c: subs r4, r4, #1
: 2270: add r0, r0, #2560 ;
: 2274: add r2, r2, #2560 ;
2 0.0414 6 0.3472 0 0 : 2278: add r1, r1, #1280 ;
: 227c: add r3, r3, #1280 ;
2 0.0414 1 0.0579 0 0 : 2280: bne 2220 <convert_hd+0x14>
: 2284: pop {r4, pc}
- the first two columns are the cycle count (absolute and relative)
- the two next ones are L1 cache miss (absolute and relative)
- the last ones are L2 cache miss (absolute and relative)
Any help would be appreciated, as this is a quite difficult task right now to find out ideas and avoid cache misses...
Thanks !