matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
1449 (vs. 1561, 7.17%↓) |
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] |
26897 (vs. 27192, 1.08%↓) |
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] |
40711 (vs. 43718, 6.88%↓) |
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] |
34843 (vs. 35588, 2.09%↓) |
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] |
63435 (vs. 61574, 3.02%↑) |
680016 (vs. 680000, 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] |
22114 (vs. 23752, 6.90%↓) |
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] |
32682 (vs. 36169, 9.64%↓) |
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] |
66269 (vs. 66489, 0.33%↓) |
569008 (vs. 568928, 0.01%↑) |
4219717 (vs. 4219653, 0.00%↑) |
144 (vs. 144, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
47866 (vs. 47672, 0.41%↑) |
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] |
26101 (vs. 23739, 9.95%↑) |
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] |
71681 (vs. 78748, 8.97%↓) |
84496 (vs. 84496, 0.00%) |
99926661 (vs. 99926661, 0.00%) |
728 (vs. 728, 0.00%) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
69758 (vs. 74783, 6.72%↓) |
93056 (vs. 93056, 0.00%) |
98443077 (vs. 98443077, 0.00%) |
704 (vs. 704, 0.00%) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
279173 (vs. 291042, 4.08%↓) |
5843296 (vs. 5843296, 0.00%) |
32142341 (vs. 32142341, 0.00%) |
1102 (vs. 1102, 0.00%) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
99900 (vs. 105924, 5.69%↓) |
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] |
31655 (vs. 29632, 6.83%↑) |
59344 (vs. 59344, 0.00%) |
133996207 (vs. 133996207, 0.00%) |
209 (vs. 209, 0.00%) |
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
37110 (vs. 37211, 0.27%↓) |
27920 (vs. 27920, 0.00%) |
652755092 (vs. 652755092, 0.00%) |
233 (vs. 233, 0.00%) |
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
31946 (vs. 38043, 16.03%↓) |
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] |
37063 (vs. 39137, 5.30%↓) |
68608 (vs. 68608, 0.00%) |
533841087 (vs. 533841087, 0.00%) |
212 (vs. 212, 0.00%) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
34036 (vs. 38818, 12.32%↓) |
50128 (vs. 50128, 0.00%) |
1336025023 (vs. 1336025023, 0.00%) |
413 (vs. 413, 0.00%) |
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
1408 (vs. 1544, 8.81%↓) |
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] |
26035 (vs. 27518, 5.39%↓) |
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] |
33833 (vs. 36467, 7.22%↓) |
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] |
33379 (vs. 32050, 4.15%↑) |
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] |
51651 (vs. 52442, 1.51%↓) |
269120 (vs. 269104, 0.01%↑) |
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] |
16700 (vs. 17890, 6.65%↓) |
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] |
30624 (vs. 29397, 4.17%↑) |
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] |
51656 (vs. 60959, 15.26%↓) |
330176 (vs. 330048, 0.04%↑) |
4003781 (vs. 4003653, 0.00%↑) |
213 (vs. 213, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
43037 (vs. 42969, 0.16%↑) |
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] |
14438 (vs. 15540, 7.09%↓) |
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] |
84926 (vs. 95318, 10.90%↓) |
53488 (vs. 52400, 2.08%↑) |
100084229 (vs. 100083141, 0.00%↑) |
1786 (vs. 1786, 0.00%) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
82843 (vs. 88475, 6.37%↓) |
53920 (vs. 52832, 2.06%↑) |
98589445 (vs. 98588357, 0.00%↑) |
1762 (vs. 1762, 0.00%) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
241427 (vs. 250678, 3.69%↓) |
2610608 (vs. 2610240, 0.01%↑) |
29088709 (vs. 29088325, 0.00%↑) |
2160 (vs. 2160, 0.00%) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
111058 (vs. 119734, 7.25%↓) |
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] |
37947 (vs. 39628, 4.24%↓) |
36480 (vs. 37936, 3.84%↓) |
219477487 (vs. 219509935, 0.01%↓) |
342 (vs. 330, 3.64%↑) |
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
44415 (vs. 48792, 8.97%↓) |
18224 (vs. 19328, 5.71%↓) |
992542996 (vs. 992542612, 0.00%↑) |
330 (vs. 318, 3.77%↑) |
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
43193 (vs. 47512, 9.09%↓) |
11392 (vs. 12864, 11.44%↓) |
992539860 (vs. 992543572, 0.00%↓) |
355 (vs. 367, 3.27%↓) |
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
48298 (vs. 48524, 0.47%↓) |
38336 (vs. 40144, 4.50%↓) |
875869119 (vs. 875939327, 0.01%↓) |
346 (vs. 334, 3.59%↑) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
55762 (vs. 56537, 1.37%↓) |
41632 (vs. 43840, 5.04%↓) |
1336061759 (vs. 1336053183, 0.00%↑) |
678 (vs. 654, 3.67%↑) |
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
1635 (vs. 1749, 6.52%↓) |
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] |
23669 (vs. 28201, 16.07%↓) |
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] |
35456 (vs. 36530, 2.94%↓) |
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] |
31964 (vs. 33663, 5.05%↓) |
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] |
47940 (vs. 49414, 2.98%↓) |
257968 (vs. 257952, 0.01%↑) |
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] |
19993 (vs. 21917, 8.78%↓) |
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] |
33054 (vs. 29101, 13.58%↑) |
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] |
55043 (vs. 63250, 12.98%↓) |
323920 (vs. 323792, 0.04%↑) |
3997509 (vs. 3997381, 0.00%↑) |
213 (vs. 213, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
44596 (vs. 42838, 4.10%↑) |
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] |
16397 (vs. 17002, 3.56%↓) |
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] |
85783 (vs. 95022, 9.72%↓) |
39040 (vs. 38880, 0.41%↑) |
100069765 (vs. 100069637, 0.00%↑) |
1786 (vs. 1786, 0.00%) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
85423 (vs. 90886, 6.01%↓) |
39456 (vs. 39296, 0.41%↑) |
98574981 (vs. 98574789, 0.00%↑) |
1762 (vs. 1762, 0.00%) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
237565 (vs. 247634, 4.07%↓) |
2600320 (vs. 2599872, 0.02%↑) |
29078405 (vs. 29077957, 0.00%↑) |
2160 (vs. 2160, 0.00%) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
109551 (vs. 120077, 8.77%↓) |
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] |
37245 (vs. 40076, 7.06%↓) |
32480 (vs. 33904, 4.20%↓) |
219473455 (vs. 219505903, 0.01%↓) |
342 (vs. 330, 3.64%↑) |
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
44265 (vs. 49313, 10.24%↓) |
18784 (vs. 18640, 0.77%↑) |
992543572 (vs. 992541972, 0.00%↑) |
330 (vs. 318, 3.77%↑) |
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
43145 (vs. 49997, 13.70%↓) |
11280 (vs. 12336, 8.56%↓) |
992539796 (vs. 992543060, 0.00%↓) |
355 (vs. 367, 3.27%↓) |
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
48064 (vs. 50697, 5.19%↓) |
33072 (vs. 34928, 5.31%↓) |
875863871 (vs. 875934143, 0.01%↓) |
346 (vs. 334, 3.59%↑) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
56721 (vs. 62792, 9.67%↓) |
37328 (vs. 39360, 5.16%↓) |
1336057407 (vs. 1336048703, 0.00%↑) |
678 (vs. 654, 3.67%↑) |
EfficientNetV2STF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
96430 (vs. 99522, 3.11%↓) |
843796 (vs. 844192, 0.05%↓) |
165158548 (vs. 165158932, 0.00%↓) |
276 (vs. 276, 0.00%) |
MiniLML12H384Uncased(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
27735 (vs. 26875, 3.20%↑) |
145080 (vs. 145212, 0.09%↓) |
134088303 (vs. 134088431, 0.00%↓) |
209 (vs. 209, 0.00%) |
BertForMaskedLMTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
35938 (vs. 33340, 7.79%↑) |
227480 (vs. 227968, 0.21%↓) |
534005410 (vs. 534005858, 0.00%↓) |
212 (vs. 212, 0.00%) |
BertLargeTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
33518 (vs. 35504, 5.59%↓) |
130704 (vs. 130852, 0.11%↓) |
1336110827 (vs. 1336110955, 0.00%↓) |
413 (vs. 413, 0.00%) |
matmul_3456x1024x2048_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1570 (vs. 1852, 15.23%↓) |
30556 (vs. 30540, 0.05%↑) |
41279 (vs. 41263, 0.04%↑) |
1 (vs. 1, 0.00%) |
matmul_3456x1024x2048_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1945 (vs. 1974, 1.47%↓) |
45028 (vs. 43516, 3.47%↑) |
55751 (vs. 54239, 2.79%↑) |
1 (vs. 1, 0.00%) |
matmul_2560x2560x2560_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1560 (vs. 1585, 1.58%↓) |
28524 (vs. 28492, 0.11%↑) |
39183 (vs. 39151, 0.08%↑) |
1 (vs. 1, 0.00%) |
matmul_2560x2560x2560_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1775 (vs. 2005, 11.47%↓) |
41404 (vs. 39892, 3.79%↑) |
52063 (vs. 50551, 2.99%↑) |
1 (vs. 1, 0.00%) |
matmul_2564x2564x2564_f32t_f32t_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
2116 (vs. 2364, 10.49%↓) |
86844 (vs. 85344, 1.76%↑) |
97503 (vs. 96003, 1.56%↑) |
1 (vs. 1, 0.00%) |
matmul_2562x2564x2562_f32t_f32t_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
2128 (vs. 2318, 8.20%↓) |
89724 (vs. 88224, 1.70%↑) |
100447 (vs. 98947, 1.52%↑) |
1 (vs. 1, 0.00%) |
matmul_2562x2561x2561_f32t_f32t_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
2847 (vs. 2729, 4.32%↑) |
84288 (vs. 82792, 1.81%↑) |
95011 (vs. 93515, 1.60%↑) |
1 (vs. 1, 0.00%) |
matmul_123x2561x2561_f32t_f32t_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
2141 (vs. 2152, 0.51%↓) |
51328 (vs. 49772, 3.13%↑) |
62050 (vs. 60494, 2.57%↑) |
1 (vs. 1, 0.00%) |
matmul_128x256x8192_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,splitk,compile-stats] |
792 (vs. 1006, 21.27%↓) |
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] |
890 (vs. 1172, 24.06%↓) |
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] |
32879 (vs. 32228, 2.02%↑) |
50648 (vs. 50552, 0.19%↑) |
133987505 (vs. 133987441, 0.00%↑) |
209 (vs. 209, 0.00%) |
DeepLabV3_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
21897 (vs. 21235, 3.12%↑) |
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] |
42260 (vs. 41855, 0.97%↑) |
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] |
67193 (vs. 76211, 11.83%↓) |
49416 (vs. 49416, 0.00%) |
98399431 (vs. 98399431, 0.00%) |
704 (vs. 704, 0.00%) |
MobileBertSquad_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
237306 (vs. 248980, 4.69%↓) |
2108280 (vs. 2108296, 0.00%↓) |
28407303 (vs. 28407303, 0.00%) |
1102 (vs. 1102, 0.00%) |
MobileNetV1_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
18495 (vs. 20993, 11.90%↓) |
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] |
50996 (vs. 54032, 5.62%↓) |
217016 (vs. 217032, 0.01%↓) |
3867719 (vs. 3867719, 0.00%) |
144 (vs. 144, 0.00%) |
PersonDetect_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
16865 (vs. 21725, 22.37%↓) |
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] |
50426 (vs. 52423, 3.81%↓) |
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] |
273470 (vs. 286675, 4.61%↓) |
2116860 (vs. 2116860, 0.00%) |
28415879 (vs. 28415879, 0.00%) |
1102 (vs. 1102, 0.00%) |
PersonDetect_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
26578 (vs. 22125, 20.13%↑) |
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] |
55589 (vs. 59765, 6.99%↓) |
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] |
23181 (vs. 21032, 10.22%↑) |
56176 (vs. 56272, 0.17%↓) |
2837573 (vs. 2837637, 0.00%↓) |
79 (vs. 79, 0.00%) |
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
47761 (vs. 51227, 6.77%↓) |
32912 (vs. 32912, 0.00%) |
98382917 (vs. 98382917, 0.00%) |
704 (vs. 704, 0.00%) |
GPT2_117M_TF_1X4XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
34412 (vs. 40240, 14.48%↓) |
20320 (vs. 20320, 0.00%) |
652747476 (vs. 652747476, 0.00%) |
233 (vs. 233, 0.00%) |
GPT2_117M_TF_1X1XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
32062 (vs. 38384, 16.47%↓) |
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] |
275310 (vs. 285544, 3.58%↓) |
4387664 (vs. 4387712, 0.00%↓) |
30686661 (vs. 30686725, 0.00%↓) |
1102 (vs. 1102, 0.00%) |
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
104213 (vs. 112045, 6.99%↓) |
694752 (vs. 694624, 0.02%↑) |
88728773 (vs. 88728645, 0.00%↑) |
268 (vs. 268, 0.00%) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
28493 (vs. 30729, 7.28%↓) |
50080 (vs. 49984, 0.19%↑) |
2849093 (vs. 2848965, 0.00%↑) |
144 (vs. 144, 0.00%) |
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
84104 (vs. 92234, 8.81%↓) |
21520 (vs. 21600, 0.37%↓) |
98556933 (vs. 98557061, 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] |
41060 (vs. 50116, 18.07%↓) |
11552 (vs. 11040, 4.64%↑) |
992511764 (vs. 992509844, 0.00%↑) |
330 (vs. 318, 3.77%↑) |
GPT2_117M_TF_1X1XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
45348 (vs. 48804, 7.08%↓) |
9120 (vs. 9232, 1.21%↓) |
992513044 (vs. 992515476, 0.00%↓) |
355 (vs. 367, 3.27%↓) |
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
216850 (vs. 227164, 4.54%↓) |
1373344 (vs. 1372976, 0.03%↑) |
27851461 (vs. 27851077, 0.00%↑) |
2160 (vs. 2160, 0.00%) |
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
83397 (vs. 87099, 4.25%↓) |
121904 (vs. 125600, 2.94%↓) |
88145797 (vs. 88155333, 0.01%↓) |
375 (vs. 386, 2.85%↓) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
23936 (vs. 25999, 7.93%↓) |
40992 (vs. 41008, 0.04%↓) |
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] |
76667 (vs. 84696, 9.48%↓) |
22064 (vs. 22096, 0.14%↓) |
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] |
44095 (vs. 48817, 9.67%↓) |
10720 (vs. 10640, 0.75%↑) |
992510932 (vs. 992509460, 0.00%↑) |
330 (vs. 318, 3.77%↑) |
GPT2_117M_TF_1X1XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
43667 (vs. 46597, 6.29%↓) |
8688 (vs. 8928, 2.69%↓) |
992512596 (vs. 992515156, 0.00%↓) |
355 (vs. 367, 3.27%↓) |
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
205290 (vs. 220740, 7.00%↓) |
1236624 (vs. 1235968, 0.05%↑) |
27714693 (vs. 27714053, 0.00%↑) |
2160 (vs. 2160, 0.00%) |
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
70275 (vs. 73607, 4.53%↓) |
113216 (vs. 116368, 2.71%↓) |
88137093 (vs. 88146053, 0.01%↓) |
375 (vs. 386, 2.85%↓) |
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
1158 (vs. 1200, 3.50%↓) |
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] |
1905 (vs. 1994, 4.46%↓) |
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] |
1259 (vs. 1249, 0.80%↑) |
3856 (vs. 3856, 0.00%) |
272965 (vs. 272965, 0.00%) |
4 (vs. 4, 0.00%) |
MobileBertSquad_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
63728 (vs. 67703, 5.87%↓) |
246320 (vs. 246320, 0.00%) |
98597530 (vs. 98597530, 0.00%) |
704 (vs. 704, 0.00%) |
MobileBertSquad_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
68693 (vs. 75092, 8.52%↓) |
246320 (vs. 246320, 0.00%) |
98597530 (vs. 98597530, 0.00%) |
704 (vs. 704, 0.00%) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
65338 (vs. 74914, 12.78%↓) |
143012 (vs. 143012, 0.00%) |
98493753 (vs. 98493753, 0.00%) |
704 (vs. 704, 0.00%) |
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,demote-f32-to-f16,compile-stats] |
95138 (vs. 109158, 12.84%↓) |
3004452 (vs. 3004452, 0.00%) |
52898580 (vs. 52898580, 0.00%) |
728 (vs. 728, 0.00%) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
188148 (vs. 200143, 5.99%↓) |
6756400 (vs. 6756400, 0.00%) |
33056470 (vs. 33056470, 0.00%) |
1102 (vs. 1102, 0.00%) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,compile-stats] |
66594 (vs. 71231, 6.51%↓) |
143012 (vs. 143012, 0.00%) |
98493881 (vs. 98493881, 0.00%) |
704 (vs. 704, 0.00%) |
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,demote-f32-to-f16,compile-stats] |
85914 (vs. 93196, 7.81%↓) |
3008480 (vs. 3008480, 0.00%) |
52905492 (vs. 52905492, 0.00%) |
728 (vs. 728, 0.00%) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,compile-stats] |
191035 (vs. 200845, 4.88%↓) |
6736144 (vs. 6736144, 0.00%) |
33024150 (vs. 33024150, 0.00%) |
1102 (vs. 1102, 0.00%) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,repeated-kernel,compile-stats] |
104408 (vs. 110561, 5.57%↓) |
143012 (vs. 143012, 0.00%) |
99716025 (vs. 99716025, 0.00%) |
704 (vs. 704, 0.00%) |
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,repeated-kernel,demote-f32-to-f16,compile-stats] |
124634 (vs. 133622, 6.73%↓) |
3008480 (vs. 3008480, 0.00%) |
54169300 (vs. 54169300, 0.00%) |
728 (vs. 728, 0.00%) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,repeated-kernel,compile-stats] |
289845 (vs. 309764, 6.43%↓) |
6736144 (vs. 6736144, 0.00%) |
34937238 (vs. 34937238, 0.00%) |
1102 (vs. 1102, 0.00%) |
MobileNetV2_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] |
23089 (vs. 24710, 6.56%↓) |
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] |
32279 (vs. 34864, 7.41%↓) |
311349 (vs. 311349, 0.00%) |
10551678 (vs. 10551678, 0.00%) |
210 (vs. 210, 0.00%) |