matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
1113 (vs. 1030, 8.06%↑) |
4400 (vs. 4400, 0.00%) |
272249 (vs. 272249, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
2094 (vs. 1923, 8.89%↑) |
9680 (vs. 9680, 0.00%) |
277497 (vs. 277497, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
1092 (vs. 1033, 5.71%↑) |
3328 (vs. 3328, 0.00%) |
533305 (vs. 533305, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
1600 (vs. 1645, 2.74%↓) |
8480 (vs. 8480, 0.00%) |
538425 (vs. 538425, 0.00%) |
1 (vs. 1, 0.00%) |
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
26283 (vs. 27060, 2.87%↓) |
144656 (vs. 144656, 0.00%) |
400453 (vs. 400453, 0.00%) |
60 (vs. 60, 0.00%) |
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
39810 (vs. 41165, 3.29%↓) |
238672 (vs. 238672, 0.00%) |
10458181 (vs. 10458181, 0.00%) |
97 (vs. 97, 0.00%) |
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
35418 (vs. 34954, 1.33%↑) |
177696 (vs. 177696, 0.00%) |
2959109 (vs. 2959109, 0.00%) |
79 (vs. 79, 0.00%) |
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
65444 (vs. 65278, 0.25%↑) |
681664 (vs. 681664, 0.00%) |
5605061 (vs. 5605061, 0.00%) |
89 (vs. 89, 0.00%) |
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
24169 (vs. 22710, 6.42%↑) |
174416 (vs. 174416, 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] |
33653 (vs. 32769, 2.70%↑) |
190192 (vs. 190192, 0.00%) |
14173317 (vs. 14173317, 0.00%) |
74 (vs. 74, 0.00%) |
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
67864 (vs. 69505, 2.36%↓) |
569168 (vs. 569168, 0.00%) |
4219845 (vs. 4219845, 0.00%) |
144 (vs. 144, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
52520 (vs. 47349, 10.92%↑) |
287728 (vs. 287728, 0.00%) |
18229381 (vs. 18229381, 0.00%) |
124 (vs. 124, 0.00%) |
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
24409 (vs. 20653, 18.19%↑) |
142464 (vs. 142464, 0.00%) |
5195845 (vs. 5195845, 0.00%) |
48 (vs. 48, 0.00%) |
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
74964 (vs. 68016, 10.22%↑) |
91184 (vs. 91184, 0.00%) |
99930437 (vs. 99930437, 0.00%) |
703 (vs. 703, 0.00%) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
77527 (vs. 76614, 1.19%↑) |
99760 (vs. 99760, 0.00%) |
98445637 (vs. 98445637, 0.00%) |
679 (vs. 679, 0.00%) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
335376 (vs. 316962, 5.81%↑) |
6806912 (vs. 6806912, 0.00%) |
33096773 (vs. 33096773, 0.00%) |
1053 (vs. 1053, 0.00%) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
104935 (vs. 97515, 7.61%↑) |
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] |
32030 (vs. 30764, 4.12%↑) |
66112 (vs. 66112, 0.00%) |
133998703 (vs. 133998703, 0.00%) |
185 (vs. 185, 0.00%) |
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
38715 (vs. 35742, 8.32%↑) |
27664 (vs. 27664, 0.00%) |
652752660 (vs. 652752660, 0.00%) |
221 (vs. 221, 0.00%) |
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
35319 (vs. 32317, 9.29%↑) |
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] |
38520 (vs. 34814, 10.65%↑) |
75968 (vs. 75968, 0.00%) |
533843199 (vs. 533843199, 0.00%) |
188 (vs. 188, 0.00%) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
35822 (vs. 37528, 4.55%↓) |
57520 (vs. 57520, 0.00%) |
1336022015 (vs. 1336022015, 0.00%) |
365 (vs. 365, 0.00%) |
matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
1102 (vs. 1221, 9.75%↓) |
4400 (vs. 4400, 0.00%) |
272249 (vs. 272249, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
1565 (vs. 2083, 24.87%↓) |
9680 (vs. 9680, 0.00%) |
277497 (vs. 277497, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
2262 (vs. 2060, 9.81%↑) |
2976 (vs. 2976, 0.00%) |
532857 (vs. 532857, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
2691 (vs. 2631, 2.28%↑) |
6432 (vs. 6432, 0.00%) |
537221 (vs. 537221, 0.00%) |
3 (vs. 3, 0.00%) |
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
26244 (vs. 25602, 2.51%↑) |
107232 (vs. 107232, 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] |
37186 (vs. 30525, 21.82%↑) |
97056 (vs. 97056, 0.00%) |
10398853 (vs. 10398853, 0.00%) |
147 (vs. 147, 0.00%) |
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
31291 (vs. 28202, 10.95%↑) |
113184 (vs. 113184, 0.00%) |
2921157 (vs. 2921157, 0.00%) |
144 (vs. 144, 0.00%) |
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
53255 (vs. 53532, 0.52%↓) |
269296 (vs. 269296, 0.00%) |
5219397 (vs. 5219397, 0.00%) |
148 (vs. 148, 0.00%) |
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
20918 (vs. 17164, 21.87%↑) |
60336 (vs. 60336, 0.00%) |
17017989 (vs. 17017989, 0.00%) |
79 (vs. 79, 0.00%) |
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
33479 (vs. 28336, 18.15%↑) |
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] |
60647 (vs. 53843, 12.64%↑) |
330080 (vs. 330080, 0.00%) |
4003717 (vs. 4003717, 0.00%) |
213 (vs. 213, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
43346 (vs. 44108, 1.73%↓) |
136016 (vs. 136016, 0.00%) |
18361349 (vs. 18361349, 0.00%) |
223 (vs. 223, 0.00%) |
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
19190 (vs. 15701, 22.22%↑) |
44256 (vs. 44256, 0.00%) |
5148037 (vs. 5148037, 0.00%) |
79 (vs. 79, 0.00%) |
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
96170 (vs. 85698, 12.22%↑) |
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] |
90591 (vs. 91802, 1.32%↓) |
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] |
288444 (vs. 275352, 4.75%↑) |
3415776 (vs. 3415776, 0.00%) |
29889285 (vs. 29889285, 0.00%) |
2136 (vs. 2136, 0.00%) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
116205 (vs. 116712, 0.43%↓) |
155344 (vs. 155344, 0.00%) |
169911212 (vs. 169911212, 0.00%) |
442 (vs. 442, 0.00%) |
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
40313 (vs. 40508, 0.48%↓) |
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] |
45979 (vs. 49856, 7.78%↓) |
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] |
43652 (vs. 45040, 3.08%↓) |
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] |
48847 (vs. 44933, 8.71%↑) |
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] |
61075 (vs. 50009, 22.13%↑) |
41680 (vs. 41680, 0.00%) |
1336061759 (vs. 1336061759, 0.00%) |
678 (vs. 678, 0.00%) |
matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
1091 (vs. 1336, 18.34%↓) |
4400 (vs. 4400, 0.00%) |
272249 (vs. 272249, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
2136 (vs. 1875, 13.92%↑) |
9680 (vs. 9680, 0.00%) |
277497 (vs. 277497, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
2736 (vs. 2516, 8.74%↑) |
2464 (vs. 2464, 0.00%) |
532345 (vs. 532345, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
3030 (vs. 2975, 1.85%↑) |
4800 (vs. 4800, 0.00%) |
535557 (vs. 535557, 0.00%) |
3 (vs. 3, 0.00%) |
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
27377 (vs. 24049, 13.84%↑) |
101024 (vs. 101024, 0.00%) |
365189 (vs. 365189, 0.00%) |
87 (vs. 87, 0.00%) |
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
34293 (vs. 35317, 2.90%↓) |
99216 (vs. 99216, 0.00%) |
10400965 (vs. 10400965, 0.00%) |
147 (vs. 147, 0.00%) |
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
33198 (vs. 31117, 6.69%↑) |
118560 (vs. 118560, 0.00%) |
2926533 (vs. 2926533, 0.00%) |
144 (vs. 144, 0.00%) |
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
48707 (vs. 52263, 6.80%↓) |
260240 (vs. 260240, 0.00%) |
5210309 (vs. 5210309, 0.00%) |
148 (vs. 148, 0.00%) |
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
25622 (vs. 18090, 41.64%↑) |
66256 (vs. 66256, 0.00%) |
17023877 (vs. 17023877, 0.00%) |
79 (vs. 79, 0.00%) |
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
27710 (vs. 27886, 0.63%↓) |
99968 (vs. 99968, 0.00%) |
14138501 (vs. 14138501, 0.00%) |
136 (vs. 136, 0.00%) |
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
56307 (vs. 54898, 2.57%↑) |
325504 (vs. 325504, 0.00%) |
3999109 (vs. 3999109, 0.00%) |
213 (vs. 213, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
48027 (vs. 40820, 17.66%↑) |
123808 (vs. 123808, 0.00%) |
18349189 (vs. 18349189, 0.00%) |
223 (vs. 223, 0.00%) |
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
20326 (vs. 18241, 11.43%↑) |
47696 (vs. 47696, 0.00%) |
5151429 (vs. 5151429, 0.00%) |
79 (vs. 79, 0.00%) |
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
91197 (vs. 91915, 0.78%↓) |
39360 (vs. 39360, 0.00%) |
100070085 (vs. 100070085, 0.00%) |
1786 (vs. 1786, 0.00%) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
91982 (vs. 83858, 9.69%↑) |
39776 (vs. 39776, 0.00%) |
98575301 (vs. 98575301, 0.00%) |
1762 (vs. 1762, 0.00%) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
284640 (vs. 266298, 6.89%↑) |
3405840 (vs. 3405840, 0.00%) |
29879301 (vs. 29879301, 0.00%) |
2136 (vs. 2136, 0.00%) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
116619 (vs. 118488, 1.58%↓) |
141248 (vs. 141248, 0.00%) |
169897132 (vs. 169897132, 0.00%) |
442 (vs. 442, 0.00%) |
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
36867 (vs. 38698, 4.73%↓) |
33024 (vs. 33024, 0.00%) |
219474031 (vs. 219474031, 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] |
49708 (vs. 48828, 1.80%↑) |
18928 (vs. 18928, 0.00%) |
992543700 (vs. 992543700, 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] |
49246 (vs. 50805, 3.07%↓) |
11424 (vs. 11424, 0.00%) |
992539924 (vs. 992539924, 0.00%) |
355 (vs. 355, 0.00%) |
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
52632 (vs. 46042, 14.31%↑) |
33376 (vs. 33376, 0.00%) |
875864191 (vs. 875864191, 0.00%) |
346 (vs. 346, 0.00%) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
59821 (vs. 66989, 10.70%↓) |
37520 (vs. 37520, 0.00%) |
1336057599 (vs. 1336057599, 0.00%) |
678 (vs. 678, 0.00%) |
EfficientNetV2STF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
103784 (vs. 88524, 17.24%↑) |
842380 (vs. 842380, 0.00%) |
165157140 (vs. 165157140, 0.00%) |
276 (vs. 276, 0.00%) |
MiniLML12H384Uncased(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
27540 (vs. 24693, 11.53%↑) |
184920 (vs. 184920, 0.00%) |
134123521 (vs. 134123521, 0.00%) |
185 (vs. 185, 0.00%) |
BertForMaskedLMTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
36793 (vs. 32993, 11.52%↑) |
264944 (vs. 264944, 0.00%) |
534037236 (vs. 534037236, 0.00%) |
188 (vs. 188, 0.00%) |
BertLargeTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
34854 (vs. 33770, 3.21%↑) |
168376 (vs. 168376, 0.00%) |
1336137653 (vs. 1336137653, 0.00%) |
365 (vs. 365, 0.00%) |
matmul_3456x1024x2048_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1699 (vs. 2204, 22.91%↓) |
30592 (vs. 30592, 0.00%) |
41315 (vs. 41315, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_3456x1024x2048_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
2253 (vs. 2003, 12.48%↑) |
45064 (vs. 45064, 0.00%) |
55787 (vs. 55787, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_2560x2560x2560_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1625 (vs. 1810, 10.22%↓) |
28556 (vs. 28556, 0.00%) |
39215 (vs. 39215, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_2560x2560x2560_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
2252 (vs. 1951, 15.43%↑) |
41440 (vs. 41440, 0.00%) |
52099 (vs. 52099, 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] |
2484 (vs. 2592, 4.17%↓) |
86104 (vs. 86104, 0.00%) |
96763 (vs. 96763, 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] |
2872 (vs. 2512, 14.33%↑) |
88988 (vs. 88988, 0.00%) |
99711 (vs. 99711, 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] |
3138 (vs. 3157, 0.60%↓) |
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] |
2380 (vs. 2367, 0.55%↑) |
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] |
1014 (vs. 981, 3.36%↑) |
8884 (vs. 8884, 0.00%) |
26245 (vs. 26245, 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] |
1035 (vs. 979, 5.72%↑) |
9624 (vs. 9624, 0.00%) |
26977 (vs. 26977, 0.00%) |
2 (vs. 2, 0.00%) |
MiniLML12H384Uncased(stablehlo) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
30516 (vs. 32260, 5.41%↓) |
52720 (vs. 52720, 0.00%) |
133985393 (vs. 133985393, 0.00%) |
185 (vs. 185, 0.00%) |
DeepLabV3_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
20777 (vs. 19608, 5.96%↑) |
42768 (vs. 42768, 0.00%) |
2824135 (vs. 2824135, 0.00%) |
79 (vs. 79, 0.00%) |
EfficientNet_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
40900 (vs. 39494, 3.56%↑) |
187488 (vs. 187488, 0.00%) |
5110919 (vs. 5110919, 0.00%) |
89 (vs. 89, 0.00%) |
MobileBertSquad_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
72992 (vs. 78802, 7.37%↓) |
48736 (vs. 48736, 0.00%) |
98394631 (vs. 98394631, 0.00%) |
679 (vs. 679, 0.00%) |
MobileBertSquad_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
376586 (vs. 361104, 4.29%↑) |
3574480 (vs. 3574480, 0.00%) |
29864327 (vs. 29864327, 0.00%) |
1053 (vs. 1053, 0.00%) |
MobileNetV1_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
17909 (vs. 15286, 17.16%↑) |
51184 (vs. 51184, 0.00%) |
16976455 (vs. 16976455, 0.00%) |
65 (vs. 65, 0.00%) |
MobileNetV2_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
56792 (vs. 50440, 12.59%↑) |
216336 (vs. 216336, 0.00%) |
3867015 (vs. 3867015, 0.00%) |
144 (vs. 144, 0.00%) |
PersonDetect_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
20810 (vs. 19716, 5.55%↑) |
59232 (vs. 59232, 0.00%) |
315079 (vs. 315079, 0.00%) |
60 (vs. 60, 0.00%) |
EfficientNet_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
51621 (vs. 55281, 6.62%↓) |
392180 (vs. 392180, 0.00%) |
5315591 (vs. 5315591, 0.00%) |
89 (vs. 89, 0.00%) |
MobileBertSquad_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
419169 (vs. 421696, 0.60%↓) |
3860516 (vs. 3860516, 0.00%) |
30150407 (vs. 30150407, 0.00%) |
1053 (vs. 1053, 0.00%) |
PersonDetect_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
24041 (vs. 23914, 0.53%↑) |
124948 (vs. 124948, 0.00%) |
380807 (vs. 380807, 0.00%) |
60 (vs. 60, 0.00%) |
MobileNetV2_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
65938 (vs. 62039, 6.28%↑) |
329472 (vs. 329472, 0.00%) |
3980167 (vs. 3980167, 0.00%) |
144 (vs. 144, 0.00%) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
23415 (vs. 20744, 12.88%↑) |
56208 (vs. 56208, 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] |
67765 (vs. 71466, 5.18%↓) |
33856 (vs. 33856, 0.00%) |
98379717 (vs. 98379717, 0.00%) |
679 (vs. 679, 0.00%) |
GPT2_117M_TF_1X4XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
36221 (vs. 37547, 3.53%↓) |
20192 (vs. 20192, 0.00%) |
652745172 (vs. 652745172, 0.00%) |
221 (vs. 221, 0.00%) |
GPT2_117M_TF_1X1XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
35969 (vs. 36024, 0.15%↓) |
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] |
311481 (vs. 292253, 6.58%↑) |
4935968 (vs. 4935968, 0.00%) |
31225861 (vs. 31225861, 0.00%) |
1053 (vs. 1053, 0.00%) |
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
111781 (vs. 108126, 3.38%↑) |
825456 (vs. 825456, 0.00%) |
88857925 (vs. 88857925, 0.00%) |
255 (vs. 255, 0.00%) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
28731 (vs. 28221, 1.81%↑) |
50848 (vs. 50848, 0.00%) |
2849861 (vs. 2849861, 0.00%) |
144 (vs. 144, 0.00%) |
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
87202 (vs. 93364, 6.60%↓) |
21856 (vs. 21856, 0.00%) |
98557317 (vs. 98557317, 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] |
47374 (vs. 45582, 3.93%↑) |
11520 (vs. 11520, 0.00%) |
992511700 (vs. 992511700, 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] |
48936 (vs. 47404, 3.23%↑) |
9136 (vs. 9136, 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] |
249252 (vs. 237021, 5.16%↑) |
1799840 (vs. 1799840, 0.00%) |
28273349 (vs. 28273349, 0.00%) |
2136 (vs. 2136, 0.00%) |
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
85210 (vs. 73729, 15.57%↑) |
122192 (vs. 122192, 0.00%) |
88145989 (vs. 88145989, 0.00%) |
375 (vs. 375, 0.00%) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
24596 (vs. 22663, 8.53%↑) |
41008 (vs. 41008, 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] |
83248 (vs. 82437, 0.98%↑) |
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] |
47275 (vs. 47537, 0.55%↓) |
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] |
42089 (vs. 43082, 2.30%↓) |
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] |
247844 (vs. 229926, 7.79%↑) |
1807392 (vs. 1807392, 0.00%) |
28280901 (vs. 28280901, 0.00%) |
2136 (vs. 2136, 0.00%) |
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
78382 (vs. 70667, 10.92%↑) |
124752 (vs. 124752, 0.00%) |
88148549 (vs. 88148549, 0.00%) |
375 (vs. 375, 0.00%) |
matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
1021 (vs. 1004, 1.69%↑) |
2464 (vs. 2464, 0.00%) |
270265 (vs. 270265, 0.00%) |
1 (vs. 1, 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] |
1193 (vs. 1188, 0.42%↑) |
3872 (vs. 3872, 0.00%) |
271673 (vs. 271673, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
1047 (vs. 913, 14.68%↑) |
2368 (vs. 2368, 0.00%) |
532345 (vs. 532345, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
1076 (vs. 1176, 8.50%↓) |
3088 (vs. 3088, 0.00%) |
533049 (vs. 533049, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
1855 (vs. 1919, 3.34%↓) |
3504 (vs. 3504, 0.00%) |
272069 (vs. 272069, 0.00%) |
2 (vs. 2, 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] |
2424 (vs. 2332, 3.95%↑) |
4528 (vs. 4528, 0.00%) |
273669 (vs. 273669, 0.00%) |
4 (vs. 4, 0.00%) |
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
2699 (vs. 2619, 3.05%↑) |
2368 (vs. 2368, 0.00%) |
532281 (vs. 532281, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
2775 (vs. 2734, 1.50%↑) |
3360 (vs. 3360, 0.00%) |
534149 (vs. 534149, 0.00%) |
3 (vs. 3, 0.00%) |
matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
1370 (vs. 1271, 7.79%↑) |
4144 (vs. 4144, 0.00%) |
272709 (vs. 272709, 0.00%) |
2 (vs. 2, 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] |
2258 (vs. 1982, 13.93%↑) |
6496 (vs. 6496, 0.00%) |
275653 (vs. 275653, 0.00%) |
4 (vs. 4, 0.00%) |
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
2222 (vs. 2086, 6.52%↑) |
2640 (vs. 2640, 0.00%) |
532537 (vs. 532537, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
2719 (vs. 2544, 6.88%↑) |
4352 (vs. 4352, 0.00%) |
535109 (vs. 535109, 0.00%) |
3 (vs. 3, 0.00%) |
MobileBertSquad_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
71068 (vs. 67867, 4.72%↑) |
255936 (vs. 255936, 0.00%) |
98602970 (vs. 98602970, 0.00%) |
679 (vs. 679, 0.00%) |
MobileBertSquad_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
75409 (vs. 68740, 9.70%↑) |
255936 (vs. 255936, 0.00%) |
98602970 (vs. 98602970, 0.00%) |
679 (vs. 679, 0.00%) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
68011 (vs. 64822, 4.92%↑) |
146764 (vs. 146764, 0.00%) |
98493369 (vs. 98493369, 0.00%) |
679 (vs. 679, 0.00%) |
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,demote-f32-to-f16,compile-stats] |
110669 (vs. 99305, 11.44%↑) |
3164204 (vs. 3164204, 0.00%) |
53055124 (vs. 53055124, 0.00%) |
703 (vs. 703, 0.00%) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
203379 (vs. 194348, 4.65%↑) |
7113320 (vs. 7113320, 0.00%) |
33404201 (vs. 33404201, 0.00%) |
1053 (vs. 1053, 0.00%) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,compile-stats] |
70724 (vs. 71377, 0.91%↓) |
146748 (vs. 146748, 0.00%) |
98493561 (vs. 98493561, 0.00%) |
679 (vs. 679, 0.00%) |
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,demote-f32-to-f16,compile-stats] |
86264 (vs. 80723, 6.86%↑) |
3166220 (vs. 3166220, 0.00%) |
53058900 (vs. 53058900, 0.00%) |
703 (vs. 703, 0.00%) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,compile-stats] |
203934 (vs. 197265, 3.38%↑) |
7111900 (vs. 7111900, 0.00%) |
33391081 (vs. 33391081, 0.00%) |
1053 (vs. 1053, 0.00%) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,repeated-kernel,compile-stats] |
114082 (vs. 106043, 7.58%↑) |
146748 (vs. 146748, 0.00%) |
99672313 (vs. 99672313, 0.00%) |
679 (vs. 679, 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] |
123780 (vs. 116453, 6.29%↑) |
3166220 (vs. 3166220, 0.00%) |
54279316 (vs. 54279316, 0.00%) |
703 (vs. 703, 0.00%) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,repeated-kernel,compile-stats] |
309542 (vs. 301750, 2.58%↑) |
7111900 (vs. 7111900, 0.00%) |
35219113 (vs. 35219113, 0.00%) |
1053 (vs. 1053, 0.00%) |
MobileNetV2_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] |
23344 (vs. 19948, 17.02%↑) |
208693 (vs. 208693, 0.00%) |
14213694 (vs. 14213694, 0.00%) |
172 (vs. 172, 0.00%) |
MobileNetV3Small_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] |
30831 (vs. 31254, 1.35%↓) |
311477 (vs. 311477, 0.00%) |
10551806 (vs. 10551806, 0.00%) |
210 (vs. 210, 0.00%) |