PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
24156 (vs. 24239, 0.34%↓) |
156472 (vs. 156472, 0.00%) |
416325 (vs. 416325, 0.00%) |
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
34581 (vs. 31417, 10.07%↑) |
208680 (vs. 208680, 0.00%) |
10430021 (vs. 10430021, 0.00%) |
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
31915 (vs. 26046, 22.53%↑) |
141096 (vs. 141096, 0.00%) |
2922117 (vs. 2922117, 0.00%) |
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
59710 (vs. 59051, 1.12%↑) |
503736 (vs. 503880, 0.03%↓) |
5538501 (vs. 5538629, 0.00%↓) |
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
22076 (vs. 24155, 8.61%↓) |
86864 (vs. 88320, 1.65%↓) |
17003205 (vs. 17004677, 0.01%↓) |
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
33371 (vs. 29868, 11.73%↑) |
142248 (vs. 142248, 0.00%) |
14125509 (vs. 14125509, 0.00%) |
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
65629 (vs. 70359, 6.72%↓) |
476664 (vs. 476664, 0.00%) |
4129413 (vs. 4129413, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
46661 (vs. 39419, 18.37%↑) |
247112 (vs. 247112, 0.00%) |
18187077 (vs. 18187077, 0.00%) |
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
13441 (vs. 15268, 11.97%↓) |
83672 (vs. 83672, 0.00%) |
5136709 (vs. 5136709, 0.00%) |
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
53747 (vs. 53724, 0.04%↑) |
77424 (vs. 79072, 2.08%↓) |
99934981 (vs. 99936645, 0.00%↓) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
43447 (vs. 51847, 16.20%↓) |
80672 (vs. 82336, 2.02%↓) |
98479237 (vs. 98480901, 0.00%↓) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
326475 (vs. 317458, 2.84%↑) |
5986048 (vs. 5987712, 0.03%↓) |
31195141 (vs. 31196805, 0.01%↓) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
93488 (vs. 88918, 5.14%↑) |
234872 (vs. 235000, 0.05%↓) |
164123089 (vs. 164123217, 0.00%↓) |
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
30873 (vs. 32152, 3.98%↓) |
64288 (vs. 66032, 2.64%↓) |
133764500 (vs. 133766228, 0.00%↓) |
Resnet50TFBatch1(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
42625 (vs. 46785, 8.89%↓) |
135768 (vs. 135896, 0.09%↓) |
137643197 (vs. 137643325, 0.00%↓) |
EfficientNetV2SPT(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
92174 (vs. 79732, 15.60%↑) |
398672 (vs. 397536, 0.29%↑) |
86910469 (vs. 86909381, 0.00%↑) |
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
34816 (vs. 32346, 7.64%↑) |
58800 (vs. 60256, 2.42%↓) |
438457937 (vs. 438459409, 0.00%↓) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
31943 (vs. 29001, 10.14%↑) |
56880 (vs. 58384, 2.58%↓) |
1336031051 (vs. 1336032523, 0.00%↓) |
EfficientNetB7PT(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,compile-stats] |
136267 (vs. 114701, 18.80%↑) |
576080 (vs. 581120, 0.87%↓) |
267314821 (vs. 267319877, 0.00%↓) |
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
25856 (vs. 21681, 19.26%↑) |
158456 (vs. 158456, 0.00%) |
415429 (vs. 415429, 0.00%) |
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
27908 (vs. 27768, 0.50%↑) |
207032 (vs. 207032, 0.00%) |
10426757 (vs. 10426757, 0.00%) |
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
22013 (vs. 21968, 0.20%↑) |
146440 (vs. 146440, 0.00%) |
2922501 (vs. 2922501, 0.00%) |
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
63785 (vs. 61476, 3.76%↑) |
515912 (vs. 516056, 0.03%↓) |
5546629 (vs. 5546821, 0.00%↓) |
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
22898 (vs. 24467, 6.41%↓) |
149192 (vs. 149192, 0.00%) |
14127749 (vs. 14127749, 0.00%) |
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
67313 (vs. 69919, 3.73%↓) |
476664 (vs. 476664, 0.00%) |
4129413 (vs. 4129413, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
44105 (vs. 37756, 16.82%↑) |
254792 (vs. 254792, 0.00%) |
18189381 (vs. 18189381, 0.00%) |
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
17976 (vs. 12174, 47.66%↑) |
86216 (vs. 86216, 0.00%) |
5134789 (vs. 5134789, 0.00%) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
55185 (vs. 50085, 10.18%↑) |
80672 (vs. 82336, 2.02%↓) |
98479237 (vs. 98480901, 0.00%↓) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
346621 (vs. 341110, 1.62%↑) |
5986048 (vs. 5987712, 0.03%↓) |
31195141 (vs. 31196805, 0.01%↓) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
98325 (vs. 90020, 9.23%↑) |
229560 (vs. 229688, 0.06%↓) |
164113809 (vs. 164113937, 0.00%↓) |
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
33962 (vs. 33037, 2.80%↑) |
64288 (vs. 66032, 2.64%↓) |
133764500 (vs. 133766228, 0.00%↓) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,fuse-padding,compile-stats] |
32928 (vs. 32280, 2.01%↑) |
56880 (vs. 58384, 2.58%↓) |
1336031051 (vs. 1336032523, 0.00%↓) |
EfficientNetV2STF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
97259 (vs. 95164, 2.20%↑) |
944068 (vs. 944068, 0.00%) |
164907877 (vs. 164907877, 0.00%) |
MiniLML12H384Uncased(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
32175 (vs. 35054, 8.21%↓) |
159016 (vs. 159016, 0.00%) |
133877563 (vs. 133877563, 0.00%) |
BertForMaskedLMTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
31074 (vs. 31532, 1.45%↓) |
204014 (vs. 204014, 0.00%) |
438620817 (vs. 438620817, 0.00%) |
BertLargeTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
33318 (vs. 28528, 16.79%↑) |
142970 (vs. 142970, 0.00%) |
1336122859 (vs. 1336122859, 0.00%) |
ClipTextSeqLen64PT(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
81946 (vs. 68672, 19.33%↑) |
88394 (vs. 88394, 0.00%) |
492381747 (vs. 492381747, 0.00%) |
Unet2dPT(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
237185 (vs. 237469, 0.12%↓) |
1746196 (vs. 1746196, 0.00%) |
3440116838 (vs. 3440116838, 0.00%) |
EfficientNetB7PT(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
84960 (vs. 90904, 6.54%↓) |
2701600 (vs. 2701600, 0.00%) |
269500177 (vs. 269500177, 0.00%) |
matmul_3456x1024x2048_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1040 (vs. 923, 12.68%↑) |
34574 (vs. 34574, 0.00%) |
44977 (vs. 44977, 0.00%) |
matmul_3456x1024x2048_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1364 (vs. 1376, 0.87%↓) |
41782 (vs. 41782, 0.00%) |
52185 (vs. 52185, 0.00%) |
matmul_2560x2560x2560_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1032 (vs. 860, 20.00%↑) |
33642 (vs. 33642, 0.00%) |
43981 (vs. 43981, 0.00%) |
matmul_2560x2560x2560_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1354 (vs. 1341, 0.97%↑) |
40506 (vs. 40506, 0.00%) |
50845 (vs. 50845, 0.00%) |
matmul_128x256x8192_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,splitk,compile-stats] |
481 (vs. 444, 8.33%↑) |
9464 (vs. 9464, 0.00%) |
26635 (vs. 26635, 0.00%) |
matmul_128x256x8192_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,splitk,compile-stats] |
503 (vs. 494, 1.82%↑) |
10252 (vs. 10252, 0.00%) |
27411 (vs. 27411, 0.00%) |
Resnet50TFBatch1(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
40002 (vs. 42268, 5.36%↓) |
394080 (vs. 394080, 0.00%) |
137932747 (vs. 137932747, 0.00%) |
Resnet50TFBatch8(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
45041 (vs. 37773, 19.24%↑) |
382630 (vs. 382630, 0.00%) |
103165825 (vs. 103165825, 0.00%) |
Resnet50TFBatch64(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
41970 (vs. 44767, 6.25%↓) |
433070 (vs. 433070, 0.00%) |
103216193 (vs. 103216193, 0.00%) |
Resnet50TFBatch128(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
43178 (vs. 41646, 3.68%↑) |
433710 (vs. 433710, 0.00%) |
103216833 (vs. 103216833, 0.00%) |
Resnet50TFBatch256(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
42948 (vs. 45787, 6.20%↓) |
433722 (vs. 433722, 0.00%) |
103216897 (vs. 103216897, 0.00%) |
Resnet50TFBatch2048(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
41163 (vs. 46393, 11.27%↓) |
434226 (vs. 434226, 0.00%) |
103217345 (vs. 103217345, 0.00%) |
BertLargeTFBatch1(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
78263 (vs. 60929, 28.45%↑) |
114680 (vs. 114680, 0.00%) |
1337218466 (vs. 1337218466, 0.00%) |
BertLargeTFBatch16(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
70288 (vs. 71603, 1.84%↓) |
438030 (vs. 438030, 0.00%) |
1337545102 (vs. 1337545102, 0.00%) |
BertLargeTFBatch24(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
85805 (vs. 71237, 20.45%↑) |
438374 (vs. 438374, 0.00%) |
1337545422 (vs. 1337545422, 0.00%) |
BertLargeTFBatch32(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
70394 (vs. 67034, 5.01%↑) |
438466 (vs. 438466, 0.00%) |
1337545486 (vs. 1337545486, 0.00%) |
BertLargeTFBatch48(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
86280 (vs. 67609, 27.62%↑) |
438466 (vs. 438466, 0.00%) |
1337545550 (vs. 1337545550, 0.00%) |
BertLargeTFBatch64(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
73675 (vs. 79710, 7.57%↓) |
438514 (vs. 438514, 0.00%) |
1337545614 (vs. 1337545614, 0.00%) |
BertLargeTFBatch512(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
75482 (vs. 71160, 6.07%↑) |
438738 (vs. 438738, 0.00%) |
1337545870 (vs. 1337545870, 0.00%) |
BertLargeTFBatch1024(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
86514 (vs. 68723, 25.89%↑) |
438782 (vs. 438782, 0.00%) |
1337545806 (vs. 1337545806, 0.00%) |
BertLargeTFBatch1280(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
68242 (vs. 67615, 0.93%↑) |
438782 (vs. 438782, 0.00%) |
1337545870 (vs. 1337545870, 0.00%) |
T5LargeTFBatch1(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
131523 (vs. 108163, 21.60%↑) |
119084 (vs. 119084, 0.00%) |
2954683426 (vs. 2954683426, 0.00%) |
T5LargeTFBatch16(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
119960 (vs. 121663, 1.40%↓) |
275464 (vs. 275464, 0.00%) |
2953798014 (vs. 2953798014, 0.00%) |
T5LargeTFBatch24(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
117786 (vs. 119834, 1.71%↓) |
275548 (vs. 275548, 0.00%) |
2953798206 (vs. 2953798206, 0.00%) |
T5LargeTFBatch32(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
121296 (vs. 101920, 19.01%↑) |
275548 (vs. 275548, 0.00%) |
2953798142 (vs. 2953798142, 0.00%) |
T5LargeTFBatch48(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
141014 (vs. 107000, 31.79%↑) |
275548 (vs. 275548, 0.00%) |
2953798142 (vs. 2953798142, 0.00%) |
T5LargeTFBatch64(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
137661 (vs. 119508, 15.19%↑) |
275604 (vs. 275604, 0.00%) |
2953798270 (vs. 2953798270, 0.00%) |
T5LargeTFBatch512(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
134445 (vs. 125049, 7.51%↑) |
274268 (vs. 274268, 0.00%) |
2953796542 (vs. 2953796542, 0.00%) |
BertLargePTBatch1(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
204350 (vs. 205108, 0.37%↓) |
113038 (vs. 113038, 0.00%) |
1336569944 (vs. 1336569944, 0.00%) |
BertLargePTBatch16(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
229904 (vs. 201667, 14.00%↑) |
490282 (vs. 490282, 0.00%) |
1336958672 (vs. 1336958672, 0.00%) |
BertLargePTBatch24(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
231657 (vs. 212749, 8.89%↑) |
490682 (vs. 490682, 0.00%) |
1336959120 (vs. 1336959120, 0.00%) |
BertLargePTBatch32(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
218822 (vs. 188177, 16.29%↑) |
490774 (vs. 490774, 0.00%) |
1336959120 (vs. 1336959120, 0.00%) |
BertLargePTBatch48(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
187248 (vs. 176801, 5.91%↑) |
490774 (vs. 490774, 0.00%) |
1336959184 (vs. 1336959184, 0.00%) |
BertLargePTBatch64(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
198344 (vs. 192764, 2.89%↑) |
490802 (vs. 490802, 0.00%) |
1336959248 (vs. 1336959248, 0.00%) |
BertLargePTBatch512(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
234688 (vs. 207508, 13.10%↑) |
490994 (vs. 490994, 0.00%) |
1336959440 (vs. 1336959440, 0.00%) |
BertLargePTBatch1024(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
206482 (vs. 211797, 2.51%↓) |
491038 (vs. 491038, 0.00%) |
1336959376 (vs. 1336959376, 0.00%) |
BertLargePTBatch1280(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
228993 (vs. 199613, 14.72%↑) |
491042 (vs. 491042, 0.00%) |
1336959504 (vs. 1336959504, 0.00%) |
Resnet50PTBatch1(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
27526 (vs. 30388, 9.42%↓) |
616424 (vs. 616424, 0.00%) |
103088167 (vs. 103088167, 0.00%) |
Resnet50PTBatch8(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
28148 (vs. 21538, 30.69%↑) |
299342 (vs. 299342, 0.00%) |
102771221 (vs. 102771221, 0.00%) |
Resnet50PTBatch64(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
23946 (vs. 19728, 21.38%↑) |
353858 (vs. 353858, 0.00%) |
102825749 (vs. 102825749, 0.00%) |
Resnet50PTBatch128(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
28313 (vs. 26006, 8.87%↑) |
354338 (vs. 354338, 0.00%) |
102826133 (vs. 102826133, 0.00%) |
Resnet50PTBatch256(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
24840 (vs. 28185, 11.87%↓) |
354370 (vs. 354370, 0.00%) |
102826197 (vs. 102826197, 0.00%) |
Resnet50PTBatch2048(linalg) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
27618 (vs. 25817, 6.98%↑) |
354862 (vs. 354862, 0.00%) |
102826709 (vs. 102826709, 0.00%) |
DeepLabV3_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
24615 (vs. 15288, 61.01%↑) |
48152 (vs. 48152, 0.00%) |
2829191 (vs. 2829191, 0.00%) |
MobileBertSquad_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
51882 (vs. 47563, 9.08%↑) |
38408 (vs. 38456, 0.12%↓) |
98436935 (vs. 98436999, 0.00%↓) |
MobileNetV1_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
14039 (vs. 15589, 9.94%↓) |
52760 (vs. 53064, 0.57%↓) |
16969031 (vs. 16969287, 0.00%↓) |
MobileBertSquad_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
245782 (vs. 227517, 8.03%↑) |
2170032 (vs. 2170080, 0.00%↓) |
27379143 (vs. 27379207, 0.00%↓) |
PersonDetect_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
21793 (vs. 22515, 3.21%↓) |
72232 (vs. 72232, 0.00%) |
332103 (vs. 332103, 0.00%) |
EfficientNet_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
41096 (vs. 41516, 1.01%↓) |
170088 (vs. 170088, 0.00%) |
5204871 (vs. 5204871, 0.00%) |
MobileNetV2_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
51564 (vs. 59982, 14.03%↓) |
184976 (vs. 184976, 0.00%) |
3837703 (vs. 3837703, 0.00%) |
EfficientNet_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
37805 (vs. 38539, 1.90%↓) |
300652 (vs. 300652, 0.00%) |
5335431 (vs. 5335431, 0.00%) |
MobileBertSquad_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
304019 (vs. 290106, 4.80%↑) |
2297764 (vs. 2297668, 0.00%↑) |
27506887 (vs. 27506759, 0.00%↑) |
PersonDetect_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
23578 (vs. 26511, 11.06%↓) |
174140 (vs. 174140, 0.00%) |
433991 (vs. 433991, 0.00%) |
MobileNetV2_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
56331 (vs. 64234, 12.30%↓) |
254340 (vs. 254340, 0.00%) |
3907079 (vs. 3907079, 0.00%) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,compile-stats] |
35010 (vs. 31827, 10.00%↑) |
96440 (vs. 96440, 0.00%) |
2877445 (vs. 2877445, 0.00%) |
MobileSSD_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,compile-stats] |
94230 (vs. 79710, 18.22%↑) |
284360 (vs. 284360, 0.00%) |
18224325 (vs. 18224325, 0.00%) |
PoseNet_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,compile-stats] |
17906 (vs. 19762, 9.39%↓) |
33816 (vs. 33816, 0.00%) |
5086853 (vs. 5086853, 0.00%) |
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,compile-stats] |
62788 (vs. 65702, 4.44%↓) |
113752 (vs. 113576, 0.15%↑) |
98512325 (vs. 98512133, 0.00%↑) |
MobileNetV2_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,compile-stats] |
36941 (vs. 34712, 6.42%↑) |
104216 (vs. 104216, 0.00%) |
14087493 (vs. 14087493, 0.00%) |
MobileNetV3Small_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,compile-stats] |
47976 (vs. 47113, 1.83%↑) |
94808 (vs. 94808, 0.00%) |
10316165 (vs. 10316165, 0.00%) |
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,compile-stats] |
279413 (vs. 267084, 4.62%↑) |
2065048 (vs. 2064888, 0.01%↑) |
27274181 (vs. 27273989, 0.00%↑) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,mmt4d,compile-stats] |
46537 (vs. 36166, 28.68%↑) |
95504 (vs. 95504, 0.00%) |
2892229 (vs. 2892229, 0.00%) |
MobileSSD_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,mmt4d,compile-stats] |
62317 (vs. 55778, 11.72%↑) |
133568 (vs. 133568, 0.00%) |
18092805 (vs. 18092805, 0.00%) |
PoseNet_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,mmt4d,compile-stats] |
20795 (vs. 23743, 12.42%↓) |
43920 (vs. 43920, 0.00%) |
5102789 (vs. 5102789, 0.00%) |
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,mmt4d,compile-stats] |
69493 (vs. 62028, 12.03%↑) |
29424 (vs. 29248, 0.60%↑) |
98591813 (vs. 98591621, 0.00%↑) |
MobileNetV2_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,mmt4d,compile-stats] |
40057 (vs. 38225, 4.79%↑) |
92528 (vs. 92528, 0.00%) |
14089221 (vs. 14089221, 0.00%) |
MobileNetV3Small_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,mmt4d,compile-stats] |
55217 (vs. 50002, 10.43%↑) |
127296 (vs. 127296, 0.00%) |
10365893 (vs. 10365893, 0.00%) |
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,mmt4d,dotprod,compile-stats] |
258278 (vs. 252985, 2.09%↑) |
1615600 (vs. 1615424, 0.01%↑) |
27009989 (vs. 27009797, 0.00%↑) |
DeepLabV3_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
12805 (vs. 14820, 13.60%↓) |
389704 (vs. 389704, 0.00%) |
3189487 (vs. 3189487, 0.00%) |
MobileSSD_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
28992 (vs. 31264, 7.27%↓) |
543662 (vs. 543662, 0.00%) |
18517723 (vs. 18517723, 0.00%) |
PoseNet_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
8814 (vs. 8815, 0.01%↓) |
137332 (vs. 137332, 0.00%) |
5201323 (vs. 5201323, 0.00%) |
MobileBertSquad_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
52294 (vs. 41812, 25.07%↑) |
224190 (vs. 224190, 0.00%) |
98633946 (vs. 98633946, 0.00%) |
MobileNetV2_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
12155 (vs. 10929, 11.22%↑) |
330534 (vs. 330534, 0.00%) |
14332098 (vs. 14332098, 0.00%) |
MobileNetV3Small_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
21052 (vs. 22974, 8.37%↓) |
395100 (vs. 395100, 0.00%) |
10648489 (vs. 10648489, 0.00%) |
DeepLabV3_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
12598 (vs. 18559, 32.12%↓) |
411244 (vs. 411244, 0.00%) |
3202952 (vs. 3202952, 0.00%) |
MobileSSD_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
24330 (vs. 23697, 2.67%↑) |
603028 (vs. 603028, 0.00%) |
18566530 (vs. 18566530, 0.00%) |
PoseNet_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
10003 (vs. 6882, 45.35%↑) |
158108 (vs. 158108, 0.00%) |
5215325 (vs. 5215325, 0.00%) |
MobileBertSquad_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
47291 (vs. 48663, 2.82%↓) |
224190 (vs. 224190, 0.00%) |
98633946 (vs. 98633946, 0.00%) |
MobileNetV2_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
17109 (vs. 16316, 4.86%↑) |
373464 (vs. 373464, 0.00%) |
14366036 (vs. 14366036, 0.00%) |
MobileNetV3Small_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
22615 (vs. 22556, 0.26%↑) |
410130 (vs. 410130, 0.00%) |
10659246 (vs. 10659246, 0.00%) |
MobileSSD_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
28023 (vs. 35507, 21.08%↓) |
603028 (vs. 603028, 0.00%) |
18649730 (vs. 18649730, 0.00%) |
PoseNet_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
6949 (vs. 9461, 26.55%↓) |
158108 (vs. 158108, 0.00%) |
5243933 (vs. 5243933, 0.00%) |
MobileNetV2_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
18329 (vs. 18366, 0.20%↓) |
373464 (vs. 373464, 0.00%) |
14412308 (vs. 14412308, 0.00%) |
MobileNetV3Small_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
27089 (vs. 27682, 2.14%↓) |
410130 (vs. 410130, 0.00%) |
10738222 (vs. 10738222, 0.00%) |
DeepLabV3_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
16260 (vs. 13979, 16.32%↑) |
178828 (vs. 178828, 0.00%) |
2978735 (vs. 2978735, 0.00%) |
MobileSSD_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
20777 (vs. 21693, 4.22%↓) |
356186 (vs. 356186, 0.00%) |
18330395 (vs. 18330395, 0.00%) |
PoseNet_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
7737 (vs. 8192, 5.55%↓) |
95836 (vs. 95836, 0.00%) |
5159851 (vs. 5159851, 0.00%) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
48795 (vs. 42985, 13.52%↑) |
127750 (vs. 127750, 0.00%) |
98537498 (vs. 98537498, 0.00%) |
MobileNetV2_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
15750 (vs. 14857, 6.01%↑) |
196098 (vs. 196098, 0.00%) |
14197826 (vs. 14197826, 0.00%) |
MobileNetV3Small_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
26384 (vs. 22127, 19.24%↑) |
259492 (vs. 259492, 0.00%) |
10513001 (vs. 10513001, 0.00%) |
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,demote-f32-to-f16,compile-stats] |
78839 (vs. 76765, 2.70%↑) |
2977872 (vs. 2977872, 0.00%) |
52959520 (vs. 52959520, 0.00%) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
189308 (vs. 168792, 12.15%↑) |
7470618 (vs. 7470618, 0.00%) |
32920384 (vs. 32920384, 0.00%) |
EfficientNet_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
26694 (vs. 31330, 14.80%↓) |
523406 (vs. 523406, 0.00%) |
5600293 (vs. 5600293, 0.00%) |
PersonDetect_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
13725 (vs. 18429, 25.52%↓) |
326524 (vs. 326524, 0.00%) |
612979 (vs. 612979, 0.00%) |
DeepLabV3_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
16433 (vs. 15621, 5.20%↑) |
201944 (vs. 201944, 0.00%) |
2993736 (vs. 2993736, 0.00%) |
MobileSSD_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
19974 (vs. 22767, 12.27%↓) |
377916 (vs. 377916, 0.00%) |
18341634 (vs. 18341634, 0.00%) |
PoseNet_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
7996 (vs. 10596, 24.54%↓) |
117288 (vs. 117288, 0.00%) |
5174557 (vs. 5174557, 0.00%) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
37146 (vs. 44481, 16.49%↓) |
127750 (vs. 127750, 0.00%) |
98537498 (vs. 98537498, 0.00%) |
MobileNetV2_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
9039 (vs. 9106, 0.74%↓) |
213196 (vs. 213196, 0.00%) |
14205972 (vs. 14205972, 0.00%) |
MobileNetV3Small_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
18530 (vs. 22985, 19.38%↓) |
282506 (vs. 282506, 0.00%) |
10531758 (vs. 10531758, 0.00%) |
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,demote-f32-to-f16,compile-stats] |
88318 (vs. 90535, 2.45%↓) |
2977872 (vs. 2977872, 0.00%) |
52959520 (vs. 52959520, 0.00%) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
214747 (vs. 197440, 8.77%↑) |
7470618 (vs. 7470618, 0.00%) |
32920384 (vs. 32920384, 0.00%) |
EfficientNet_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
29778 (vs. 29203, 1.97%↑) |
548328 (vs. 548328, 0.00%) |
5616147 (vs. 5616147, 0.00%) |
PersonDetect_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
16066 (vs. 16789, 4.31%↓) |
340138 (vs. 340138, 0.00%) |
620254 (vs. 620254, 0.00%) |
DeepLabV3_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
15083 (vs. 18661, 19.17%↓) |
201944 (vs. 201944, 0.00%) |
3097864 (vs. 3097864, 0.00%) |
MobileSSD_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
32120 (vs. 34472, 6.82%↓) |
377916 (vs. 377916, 0.00%) |
18513474 (vs. 18513474, 0.00%) |
PoseNet_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
10425 (vs. 6476, 60.98%↑) |
117288 (vs. 117288, 0.00%) |
5233629 (vs. 5233629, 0.00%) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
69443 (vs. 59518, 16.68%↑) |
127750 (vs. 127750, 0.00%) |
99801306 (vs. 99801306, 0.00%) |
MobileNetV2_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
10921 (vs. 13266, 17.68%↓) |
213196 (vs. 213196, 0.00%) |
14301460 (vs. 14301460, 0.00%) |
MobileNetV3Small_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
22473 (vs. 25845, 13.05%↓) |
282506 (vs. 282506, 0.00%) |
10694958 (vs. 10694958, 0.00%) |
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,demote-f32-to-f16,compile-stats] |
174863 (vs. 159906, 9.35%↑) |
2977872 (vs. 2977872, 0.00%) |
54223328 (vs. 54223328, 0.00%) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
281164 (vs. 276283, 1.77%↑) |
7470618 (vs. 7470618, 0.00%) |
35441088 (vs. 35441088, 0.00%) |
EfficientNet_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
41477 (vs. 41110, 0.89%↑) |
548328 (vs. 548328, 0.00%) |
5824467 (vs. 5824467, 0.00%) |
PersonDetect_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,repeated-kernel,compile-stats] |
22359 (vs. 25637, 12.79%↓) |
340138 (vs. 340138, 0.00%) |
748766 (vs. 748766, 0.00%) |
ClipTextSeqLen64PT(linalg) [nvidia-ampere-vulkan_linux-vulkan_spirv][experimental-flags,tensorcore,compile-stats] |
79810 (vs. 76739, 4.00%↑) |
202696 (vs. 202696, 0.00%) |
492522977 (vs. 492522977, 0.00%) |
Unet2dPT(linalg) [nvidia-ampere-vulkan_linux-vulkan_spirv][experimental-flags,tensorcore,compile-stats] |
242602 (vs. 243892, 0.53%↓) |
3787496 (vs. 3787496, 0.00%) |
3442195216 (vs. 3442195216, 0.00%) |
ClipTextSeqLen64PT(linalg) [nvidia-pascal-vulkan_linux-vulkan_spirv][experimental-flags,simt,compile-stats] |
69234 (vs. 66308, 4.41%↑) |
202696 (vs. 202696, 0.00%) |
492522977 (vs. 492522977, 0.00%) |
Unet2dPT(linalg) [nvidia-pascal-vulkan_linux-vulkan_spirv][experimental-flags,simt,compile-stats] |
240324 (vs. 237343, 1.26%↑) |
3778208 (vs. 3778208, 0.00%) |
3442185936 (vs. 3442185936, 0.00%) |
MobileNetV2_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] |
19461 (vs. 14986, 29.86%↑) |
95861 (vs. 95861, 0.00%) |
14079102 (vs. 14079102, 0.00%) |
MobileNetV3Small_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] |
24443 (vs. 26280, 6.99%↓) |
164533 (vs. 164533, 0.00%) |
10385854 (vs. 10385854, 0.00%) |