matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
1580 (vs. 1549, 2.00%↑) |
9664 (vs. 9664, 0.00%) |
277497 (vs. 277497, 0.00%) |
1 (vs. 1, 0.00%) |
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
22586 (vs. 23220, 2.73%↓) |
144032 (vs. 144032, 0.00%) |
399877 (vs. 399877, 0.00%) |
60 (vs. 60, 0.00%) |
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
36977 (vs. 39575, 6.56%↓) |
238720 (vs. 238720, 0.00%) |
10458245 (vs. 10458245, 0.00%) |
97 (vs. 97, 0.00%) |
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
38422 (vs. 35396, 8.55%↑) |
177680 (vs. 177680, 0.00%) |
2959045 (vs. 2959045, 0.00%) |
79 (vs. 79, 0.00%) |
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
66537 (vs. 64481, 3.19%↑) |
680016 (vs. 680016, 0.00%) |
5603397 (vs. 5603397, 0.00%) |
89 (vs. 89, 0.00%) |
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
22144 (vs. 23526, 5.87%↓) |
174400 (vs. 174400, 0.00%) |
17094405 (vs. 17094405, 0.00%) |
51 (vs. 51, 0.00%) |
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
35249 (vs. 34182, 3.12%↑) |
190096 (vs. 190096, 0.00%) |
14173189 (vs. 14173189, 0.00%) |
74 (vs. 74, 0.00%) |
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
67222 (vs. 67204, 0.03%↑) |
569008 (vs. 569008, 0.00%) |
4219717 (vs. 4219717, 0.00%) |
144 (vs. 144, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
50441 (vs. 50931, 0.96%↓) |
287600 (vs. 287600, 0.00%) |
18229253 (vs. 18229253, 0.00%) |
124 (vs. 124, 0.00%) |
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
23617 (vs. 23219, 1.71%↑) |
142288 (vs. 142288, 0.00%) |
5195653 (vs. 5195653, 0.00%) |
48 (vs. 48, 0.00%) |
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
74101 (vs. 75095, 1.32%↓) |
91184 (vs. 84496, 7.92%↑) |
99930437 (vs. 99926661, 0.00%↑) |
703 (vs. 728, 3.43%↓) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
68599 (vs. 72283, 5.10%↓) |
99760 (vs. 93056, 7.20%↑) |
98445637 (vs. 98443077, 0.00%↑) |
679 (vs. 704, 3.55%↓) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
303437 (vs. 283475, 7.04%↑) |
6001648 (vs. 5843296, 2.71%↑) |
32296069 (vs. 32142341, 0.48%↑) |
1077 (vs. 1102, 2.27%↓) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
102143 (vs. 96962, 5.34%↑) |
216304 (vs. 216304, 0.00%) |
164497708 (vs. 164497708, 0.00%) |
276 (vs. 276, 0.00%) |
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
31882 (vs. 32204, 1.00%↓) |
66176 (vs. 59344, 11.51%↑) |
133998767 (vs. 133996207, 0.00%↑) |
185 (vs. 209, 11.48%↓) |
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
37583 (vs. 37728, 0.38%↓) |
27680 (vs. 27920, 0.86%↓) |
652752660 (vs. 652755092, 0.00%↓) |
221 (vs. 233, 5.15%↓) |
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
33509 (vs. 35404, 5.35%↓) |
14736 (vs. 14736, 0.00%) |
652736084 (vs. 652736084, 0.00%) |
246 (vs. 246, 0.00%) |
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
38744 (vs. 36199, 7.03%↑) |
75968 (vs. 68608, 10.73%↑) |
533843199 (vs. 533841087, 0.00%↑) |
188 (vs. 212, 11.32%↓) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
34580 (vs. 36987, 6.51%↓) |
57536 (vs. 50128, 14.78%↑) |
1336022015 (vs. 1336025023, 0.00%↓) |
365 (vs. 413, 11.62%↓) |
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
1518 (vs. 1512, 0.40%↑) |
9664 (vs. 9664, 0.00%) |
277497 (vs. 277497, 0.00%) |
1 (vs. 1, 0.00%) |
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
24523 (vs. 24836, 1.26%↓) |
107248 (vs. 107248, 0.00%) |
371397 (vs. 371397, 0.00%) |
87 (vs. 87, 0.00%) |
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
33688 (vs. 37293, 9.67%↓) |
96944 (vs. 96944, 0.00%) |
10398725 (vs. 10398725, 0.00%) |
147 (vs. 147, 0.00%) |
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
32827 (vs. 30371, 8.09%↑) |
113392 (vs. 113392, 0.00%) |
2921349 (vs. 2921349, 0.00%) |
144 (vs. 144, 0.00%) |
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
50992 (vs. 49158, 3.73%↑) |
269120 (vs. 269120, 0.00%) |
5219205 (vs. 5219205, 0.00%) |
148 (vs. 148, 0.00%) |
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
18537 (vs. 18659, 0.65%↓) |
60288 (vs. 60288, 0.00%) |
17017925 (vs. 17017925, 0.00%) |
79 (vs. 79, 0.00%) |
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
30950 (vs. 28341, 9.21%↑) |
95248 (vs. 95248, 0.00%) |
14133765 (vs. 14133765, 0.00%) |
136 (vs. 136, 0.00%) |
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
59522 (vs. 59719, 0.33%↓) |
330176 (vs. 330176, 0.00%) |
4003781 (vs. 4003781, 0.00%) |
213 (vs. 213, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
45246 (vs. 42295, 6.98%↑) |
136080 (vs. 136080, 0.00%) |
18361413 (vs. 18361413, 0.00%) |
223 (vs. 223, 0.00%) |
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
17847 (vs. 15629, 14.19%↑) |
44208 (vs. 44208, 0.00%) |
5147973 (vs. 5147973, 0.00%) |
79 (vs. 79, 0.00%) |
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
93368 (vs. 89504, 4.32%↑) |
53488 (vs. 53488, 0.00%) |
100084229 (vs. 100084229, 0.00%) |
1786 (vs. 1786, 0.00%) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
87689 (vs. 85638, 2.39%↑) |
53920 (vs. 53920, 0.00%) |
98589445 (vs. 98589445, 0.00%) |
1762 (vs. 1762, 0.00%) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
255609 (vs. 246977, 3.50%↑) |
2610608 (vs. 2610608, 0.00%) |
29088709 (vs. 29088709, 0.00%) |
2160 (vs. 2160, 0.00%) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
114093 (vs. 111520, 2.31%↑) |
154864 (vs. 154864, 0.00%) |
169910060 (vs. 169910060, 0.00%) |
439 (vs. 439, 0.00%) |
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
37364 (vs. 36873, 1.33%↑) |
36480 (vs. 36480, 0.00%) |
219477487 (vs. 219477487, 0.00%) |
342 (vs. 342, 0.00%) |
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
46978 (vs. 47239, 0.55%↓) |
18224 (vs. 18224, 0.00%) |
992542996 (vs. 992542996, 0.00%) |
330 (vs. 330, 0.00%) |
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
42259 (vs. 44905, 5.89%↓) |
11392 (vs. 11392, 0.00%) |
992539860 (vs. 992539860, 0.00%) |
355 (vs. 355, 0.00%) |
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
50697 (vs. 43959, 15.33%↑) |
38336 (vs. 38336, 0.00%) |
875869119 (vs. 875869119, 0.00%) |
346 (vs. 346, 0.00%) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
54175 (vs. 52444, 3.30%↑) |
41632 (vs. 41632, 0.00%) |
1336061759 (vs. 1336061759, 0.00%) |
678 (vs. 678, 0.00%) |
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
1569 (vs. 1713, 8.41%↓) |
9664 (vs. 9664, 0.00%) |
277497 (vs. 277497, 0.00%) |
1 (vs. 1, 0.00%) |
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
23607 (vs. 27859, 15.26%↓) |
99488 (vs. 99488, 0.00%) |
363653 (vs. 363653, 0.00%) |
87 (vs. 87, 0.00%) |
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
36562 (vs. 33651, 8.65%↑) |
98656 (vs. 98656, 0.00%) |
10400453 (vs. 10400453, 0.00%) |
147 (vs. 147, 0.00%) |
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
35615 (vs. 32025, 11.21%↑) |
117504 (vs. 117504, 0.00%) |
2925445 (vs. 2925445, 0.00%) |
144 (vs. 144, 0.00%) |
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
51436 (vs. 48363, 6.35%↑) |
257968 (vs. 257968, 0.00%) |
5208069 (vs. 5208069, 0.00%) |
148 (vs. 148, 0.00%) |
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
20664 (vs. 19437, 6.31%↑) |
65376 (vs. 65376, 0.00%) |
17023045 (vs. 17023045, 0.00%) |
79 (vs. 79, 0.00%) |
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
31112 (vs. 31408, 0.94%↓) |
99104 (vs. 99104, 0.00%) |
14137669 (vs. 14137669, 0.00%) |
136 (vs. 136, 0.00%) |
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
57421 (vs. 59636, 3.71%↓) |
323920 (vs. 323920, 0.00%) |
3997509 (vs. 3997509, 0.00%) |
213 (vs. 213, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
46966 (vs. 44430, 5.71%↑) |
122656 (vs. 122656, 0.00%) |
18348037 (vs. 18348037, 0.00%) |
223 (vs. 223, 0.00%) |
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
17669 (vs. 18833, 6.18%↓) |
47200 (vs. 47200, 0.00%) |
5150981 (vs. 5150981, 0.00%) |
79 (vs. 79, 0.00%) |
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
92180 (vs. 83834, 9.96%↑) |
39040 (vs. 39040, 0.00%) |
100069765 (vs. 100069765, 0.00%) |
1786 (vs. 1786, 0.00%) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
85451 (vs. 84122, 1.58%↑) |
39456 (vs. 39456, 0.00%) |
98574981 (vs. 98574981, 0.00%) |
1762 (vs. 1762, 0.00%) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
243515 (vs. 239954, 1.48%↑) |
2600320 (vs. 2600320, 0.00%) |
29078405 (vs. 29078405, 0.00%) |
2160 (vs. 2160, 0.00%) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
112153 (vs. 114572, 2.11%↓) |
140240 (vs. 140240, 0.00%) |
169895468 (vs. 169895468, 0.00%) |
439 (vs. 439, 0.00%) |
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
37522 (vs. 36722, 2.18%↑) |
32480 (vs. 32480, 0.00%) |
219473455 (vs. 219473455, 0.00%) |
342 (vs. 342, 0.00%) |
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
47614 (vs. 51452, 7.46%↓) |
18784 (vs. 18784, 0.00%) |
992543572 (vs. 992543572, 0.00%) |
330 (vs. 330, 0.00%) |
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
47698 (vs. 47872, 0.36%↓) |
11280 (vs. 11280, 0.00%) |
992539796 (vs. 992539796, 0.00%) |
355 (vs. 355, 0.00%) |
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
48368 (vs. 46808, 3.33%↑) |
33072 (vs. 33072, 0.00%) |
875863871 (vs. 875863871, 0.00%) |
346 (vs. 346, 0.00%) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
60921 (vs. 56350, 8.11%↑) |
37328 (vs. 37328, 0.00%) |
1336057407 (vs. 1336057407, 0.00%) |
678 (vs. 678, 0.00%) |
EfficientNetV2STF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
91809 (vs. 91950, 0.15%↓) |
843788 (vs. 843788, 0.00%) |
165158548 (vs. 165158548, 0.00%) |
276 (vs. 276, 0.00%) |
MiniLML12H384Uncased(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
24852 (vs. 24996, 0.58%↓) |
184872 (vs. 145080, 27.43%↑) |
134123521 (vs. 134088303, 0.03%↑) |
185 (vs. 209, 11.48%↓) |
BertForMaskedLMTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
34805 (vs. 32540, 6.96%↑) |
264976 (vs. 227472, 16.49%↑) |
534037300 (vs. 534005346, 0.01%↑) |
188 (vs. 212, 11.32%↓) |
BertLargeTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
36274 (vs. 32247, 12.49%↑) |
168240 (vs. 130696, 28.73%↑) |
1336137589 (vs. 1336110763, 0.00%↑) |
365 (vs. 413, 11.62%↓) |
matmul_3456x1024x2048_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1727 (vs. 1789, 3.47%↓) |
30556 (vs. 30556, 0.00%) |
41279 (vs. 41279, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_3456x1024x2048_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1836 (vs. 1835, 0.05%↑) |
45028 (vs. 45028, 0.00%) |
55751 (vs. 55751, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_2560x2560x2560_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1593 (vs. 1618, 1.55%↓) |
28524 (vs. 28524, 0.00%) |
39183 (vs. 39183, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_2560x2560x2560_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1942 (vs. 1888, 2.86%↑) |
41404 (vs. 41404, 0.00%) |
52063 (vs. 52063, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_2564x2564x2564_f32t_f32t_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
2090 (vs. 2143, 2.47%↓) |
86844 (vs. 86844, 0.00%) |
97503 (vs. 97503, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_2562x2564x2562_f32t_f32t_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
2253 (vs. 2225, 1.26%↑) |
89724 (vs. 89724, 0.00%) |
100447 (vs. 100447, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_2562x2561x2561_f32t_f32t_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
2681 (vs. 2656, 0.94%↑) |
84196 (vs. 84196, 0.00%) |
94919 (vs. 94919, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_123x2561x2561_f32t_f32t_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1986 (vs. 2064, 3.78%↓) |
51232 (vs. 51232, 0.00%) |
61954 (vs. 61954, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_128x256x8192_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,splitk,compile-stats] |
1112 (vs. 788, 41.12%↑) |
8828 (vs. 8828, 0.00%) |
26181 (vs. 26181, 0.00%) |
2 (vs. 2, 0.00%) |
matmul_128x256x8192_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,splitk,compile-stats] |
939 (vs. 1002, 6.29%↓) |
9784 (vs. 9784, 0.00%) |
27137 (vs. 27137, 0.00%) |
2 (vs. 2, 0.00%) |
MiniLML12H384Uncased(stablehlo) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
33054 (vs. 32657, 1.22%↑) |
52680 (vs. 50648, 4.01%↑) |
133985329 (vs. 133987505, 0.00%↓) |
185 (vs. 209, 11.48%↓) |
DeepLabV3_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
19871 (vs. 21729, 8.55%↓) |
42840 (vs. 42840, 0.00%) |
2824263 (vs. 2824263, 0.00%) |
79 (vs. 79, 0.00%) |
EfficientNet_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
41459 (vs. 39539, 4.86%↑) |
185480 (vs. 185480, 0.00%) |
5108871 (vs. 5108871, 0.00%) |
89 (vs. 89, 0.00%) |
MobileBertSquad_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
71518 (vs. 66503, 7.54%↑) |
48760 (vs. 49416, 1.33%↓) |
98394631 (vs. 98399431, 0.00%↓) |
679 (vs. 704, 3.55%↓) |
MobileBertSquad_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
252127 (vs. 239662, 5.20%↑) |
2079512 (vs. 2108280, 1.36%↓) |
28373959 (vs. 28407303, 0.12%↓) |
1077 (vs. 1102, 2.27%↓) |
MobileNetV1_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
15275 (vs. 18346, 16.74%↓) |
50984 (vs. 50984, 0.00%) |
16976263 (vs. 16976263, 0.00%) |
65 (vs. 65, 0.00%) |
MobileNetV2_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
54047 (vs. 54075, 0.05%↓) |
217016 (vs. 217016, 0.00%) |
3867719 (vs. 3867719, 0.00%) |
144 (vs. 144, 0.00%) |
PersonDetect_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
18494 (vs. 17782, 4.00%↑) |
58936 (vs. 58936, 0.00%) |
314759 (vs. 314759, 0.00%) |
60 (vs. 60, 0.00%) |
EfficientNet_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
53006 (vs. 50592, 4.77%↑) |
390748 (vs. 390748, 0.00%) |
5314183 (vs. 5314183, 0.00%) |
89 (vs. 89, 0.00%) |
MobileBertSquad_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
285056 (vs. 273804, 4.11%↑) |
2043340 (vs. 2116860, 3.47%↓) |
28337735 (vs. 28415879, 0.28%↓) |
1077 (vs. 1102, 2.27%↓) |
PersonDetect_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
23593 (vs. 20758, 13.66%↑) |
124428 (vs. 124428, 0.00%) |
380231 (vs. 380231, 0.00%) |
60 (vs. 60, 0.00%) |
MobileNetV2_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
61586 (vs. 62561, 1.56%↓) |
328664 (vs. 328664, 0.00%) |
3979399 (vs. 3979399, 0.00%) |
144 (vs. 144, 0.00%) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
21510 (vs. 19612, 9.68%↑) |
56176 (vs. 56176, 0.00%) |
2837573 (vs. 2837573, 0.00%) |
79 (vs. 79, 0.00%) |
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
51906 (vs. 48489, 7.05%↑) |
33872 (vs. 32912, 2.92%↑) |
98379717 (vs. 98382917, 0.00%↓) |
679 (vs. 704, 3.55%↓) |
GPT2_117M_TF_1X4XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
36481 (vs. 38769, 5.90%↓) |
20192 (vs. 20320, 0.63%↓) |
652745172 (vs. 652747476, 0.00%↓) |
221 (vs. 233, 5.15%↓) |
GPT2_117M_TF_1X1XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
36395 (vs. 40149, 9.35%↓) |
9024 (vs. 9024, 0.00%) |
652730324 (vs. 652730324, 0.00%) |
246 (vs. 246, 0.00%) |
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
287207 (vs. 278851, 3.00%↑) |
4510784 (vs. 4388208, 2.79%↑) |
30805189 (vs. 30687237, 0.38%↑) |
1077 (vs. 1102, 2.27%↓) |
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
117539 (vs. 108411, 8.42%↑) |
839376 (vs. 694752, 20.82%↑) |
88869253 (vs. 88728773, 0.16%↑) |
243 (vs. 268, 9.33%↓) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
31666 (vs. 25442, 24.46%↑) |
50080 (vs. 50080, 0.00%) |
2849093 (vs. 2849093, 0.00%) |
144 (vs. 144, 0.00%) |
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
88606 (vs. 83710, 5.85%↑) |
21520 (vs. 21520, 0.00%) |
98556933 (vs. 98556933, 0.00%) |
1762 (vs. 1762, 0.00%) |
GPT2_117M_TF_1X4XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
42535 (vs. 49953, 14.85%↓) |
11552 (vs. 11552, 0.00%) |
992511764 (vs. 992511764, 0.00%) |
330 (vs. 330, 0.00%) |
GPT2_117M_TF_1X1XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
45560 (vs. 49103, 7.22%↓) |
9120 (vs. 9120, 0.00%) |
992513044 (vs. 992513044, 0.00%) |
355 (vs. 355, 0.00%) |
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
230718 (vs. 219441, 5.14%↑) |
1373856 (vs. 1373856, 0.00%) |
27851973 (vs. 27851973, 0.00%) |
2160 (vs. 2160, 0.00%) |
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
81163 (vs. 81518, 0.44%↓) |
121904 (vs. 121904, 0.00%) |
88145797 (vs. 88145797, 0.00%) |
375 (vs. 375, 0.00%) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
26411 (vs. 22768, 16.00%↑) |
40992 (vs. 40992, 0.00%) |
2840005 (vs. 2840005, 0.00%) |
144 (vs. 144, 0.00%) |
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
80806 (vs. 82532, 2.09%↓) |
22064 (vs. 22064, 0.00%) |
98557509 (vs. 98557509, 0.00%) |
1762 (vs. 1762, 0.00%) |
GPT2_117M_TF_1X4XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
42218 (vs. 42794, 1.35%↓) |
10720 (vs. 10720, 0.00%) |
992510932 (vs. 992510932, 0.00%) |
330 (vs. 330, 0.00%) |
GPT2_117M_TF_1X1XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
41717 (vs. 44950, 7.19%↓) |
8688 (vs. 8688, 0.00%) |
992512596 (vs. 992512596, 0.00%) |
355 (vs. 355, 0.00%) |
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
228530 (vs. 219618, 4.06%↑) |
1380992 (vs. 1380992, 0.00%) |
27859077 (vs. 27859077, 0.00%) |
2160 (vs. 2160, 0.00%) |
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
73505 (vs. 72444, 1.46%↑) |
124400 (vs. 124400, 0.00%) |
88148293 (vs. 88148293, 0.00%) |
375 (vs. 375, 0.00%) |
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
1114 (vs. 1241, 10.23%↓) |
3872 (vs. 3872, 0.00%) |
271673 (vs. 271673, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
2149 (vs. 1901, 13.05%↑) |
4480 (vs. 4480, 0.00%) |
273605 (vs. 273605, 0.00%) |
4 (vs. 4, 0.00%) |
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
1835 (vs. 1498, 22.50%↑) |
6496 (vs. 6496, 0.00%) |
275653 (vs. 275653, 0.00%) |
4 (vs. 4, 0.00%) |
MobileBertSquad_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
69586 (vs. 63750, 9.15%↑) |
255780 (vs. 246320, 3.84%↑) |
98602842 (vs. 98597530, 0.01%↑) |
679 (vs. 704, 3.55%↓) |
MobileBertSquad_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
73263 (vs. 76906, 4.74%↓) |
255780 (vs. 246320, 3.84%↑) |
98602842 (vs. 98597530, 0.01%↑) |
679 (vs. 704, 3.55%↓) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
69667 (vs. 70105, 0.62%↓) |
146608 (vs. 143012, 2.51%↑) |
98493241 (vs. 98493753, 0.00%↓) |
679 (vs. 704, 3.55%↓) |
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,demote-f32-to-f16,compile-stats] |
109003 (vs. 106055, 2.78%↑) |
3161912 (vs. 3004452, 5.24%↑) |
53052820 (vs. 52898580, 0.29%↑) |
703 (vs. 728, 3.43%↓) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
198511 (vs. 192549, 3.10%↑) |
6930868 (vs. 6756400, 2.58%↑) |
33226646 (vs. 33056470, 0.51%↑) |
1077 (vs. 1102, 2.27%↓) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,compile-stats] |
72334 (vs. 65713, 10.08%↑) |
146592 (vs. 143012, 2.50%↑) |
98493369 (vs. 98493881, 0.00%↓) |
679 (vs. 704, 3.55%↓) |
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,demote-f32-to-f16,compile-stats] |
89951 (vs. 88539, 1.59%↑) |
3163928 (vs. 3008480, 5.17%↑) |
53056596 (vs. 52905492, 0.29%↑) |
703 (vs. 728, 3.43%↓) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,compile-stats] |
198775 (vs. 190467, 4.36%↑) |
6928536 (vs. 6736144, 2.86%↑) |
33212630 (vs. 33024150, 0.57%↑) |
1077 (vs. 1102, 2.27%↓) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,repeated-kernel,compile-stats] |
109357 (vs. 105615, 3.54%↑) |
146592 (vs. 143012, 2.50%↑) |
99672121 (vs. 99716025, 0.04%↓) |
679 (vs. 704, 3.55%↓) |
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,repeated-kernel,demote-f32-to-f16,compile-stats] |
129871 (vs. 128126, 1.36%↑) |
3163928 (vs. 3008480, 5.17%↑) |
54277012 (vs. 54169300, 0.20%↑) |
703 (vs. 728, 3.43%↓) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,repeated-kernel,compile-stats] |
307876 (vs. 297955, 3.33%↑) |
6928536 (vs. 6736144, 2.86%↑) |
35082326 (vs. 34937238, 0.42%↑) |
1077 (vs. 1102, 2.27%↓) |
MobileNetV2_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] |
23219 (vs. 21218, 9.43%↑) |
208629 (vs. 208629, 0.00%) |
14213630 (vs. 14213630, 0.00%) |
172 (vs. 172, 0.00%) |
MobileNetV3Small_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] |
31045 (vs. 33798, 8.15%↓) |
311349 (vs. 311349, 0.00%) |
10551678 (vs. 10551678, 0.00%) |
210 (vs. 210, 0.00%) |