matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
1361 (vs. 1325, 2.72%↑) |
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] |
33184 (vs. 29827, 11.25%↑) |
186928 (vs. 186928, 0.00%) |
442757 (vs. 442757, 0.00%) |
60 (vs. 60, 0.00%) |
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
40976 (vs. 39409, 3.98%↑) |
238768 (vs. 238768, 0.00%) |
10458309 (vs. 10458309, 0.00%) |
97 (vs. 97, 0.00%) |
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
38010 (vs. 38126, 0.30%↓) |
178288 (vs. 178288, 0.00%) |
2959685 (vs. 2959685, 0.00%) |
79 (vs. 79, 0.00%) |
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
61222 (vs. 57880, 5.77%↑) |
598960 (vs. 598960, 0.00%) |
5522373 (vs. 5522373, 0.00%) |
89 (vs. 89, 0.00%) |
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
30359 (vs. 22493, 34.97%↑) |
179392 (vs. 179392, 0.00%) |
17099397 (vs. 17099397, 0.00%) |
51 (vs. 51, 0.00%) |
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
35501 (vs. 33471, 6.06%↑) |
177648 (vs. 177648, 0.00%) |
14160773 (vs. 14160773, 0.00%) |
74 (vs. 74, 0.00%) |
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
69598 (vs. 65209, 6.73%↑) |
545824 (vs. 545824, 0.00%) |
4196549 (vs. 4196549, 0.00%) |
144 (vs. 144, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
49313 (vs. 47011, 4.90%↑) |
296320 (vs. 296320, 0.00%) |
18237957 (vs. 18237957, 0.00%) |
124 (vs. 124, 0.00%) |
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
22618 (vs. 24201, 6.54%↓) |
168064 (vs. 168064, 0.00%) |
5221445 (vs. 5221445, 0.00%) |
48 (vs. 48, 0.00%) |
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
76312 (vs. 68599, 11.24%↑) |
87536 (vs. 87536, 0.00%) |
99929733 (vs. 99929733, 0.00%) |
728 (vs. 728, 0.00%) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
72650 (vs. 68739, 5.69%↑) |
96800 (vs. 96800, 0.00%) |
98446853 (vs. 98446853, 0.00%) |
704 (vs. 704, 0.00%) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
299285 (vs. 295607, 1.24%↑) |
5908560 (vs. 5908560, 0.00%) |
32207557 (vs. 32207557, 0.00%) |
1102 (vs. 1102, 0.00%) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
107247 (vs. 99589, 7.69%↑) |
215712 (vs. 215712, 0.00%) |
164497132 (vs. 164497132, 0.00%) |
276 (vs. 276, 0.00%) |
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
33783 (vs. 33897, 0.34%↓) |
64976 (vs. 64976, 0.00%) |
134001839 (vs. 134001839, 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] |
36684 (vs. 35004, 4.80%↑) |
30272 (vs. 30272, 0.00%) |
652757396 (vs. 652757396, 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] |
36171 (vs. 33227, 8.86%↑) |
16656 (vs. 16656, 0.00%) |
652738004 (vs. 652738004, 0.00%) |
246 (vs. 246, 0.00%) |
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
38097 (vs. 35555, 7.15%↑) |
74464 (vs. 74464, 0.00%) |
533846975 (vs. 533846975, 0.00%) |
212 (vs. 212, 0.00%) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] |
38538 (vs. 36391, 5.90%↑) |
56768 (vs. 56768, 0.00%) |
1336031679 (vs. 1336031679, 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] |
1456 (vs. 1474, 1.22%↓) |
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] |
23807 (vs. 23782, 0.11%↑) |
106864 (vs. 106864, 0.00%) |
371013 (vs. 371013, 0.00%) |
87 (vs. 87, 0.00%) |
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
34758 (vs. 34127, 1.85%↑) |
114608 (vs. 114608, 0.00%) |
11446533 (vs. 11446533, 0.00%) |
147 (vs. 147, 0.00%) |
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
37404 (vs. 32666, 14.50%↑) |
127376 (vs. 127376, 0.00%) |
2935237 (vs. 2935237, 0.00%) |
144 (vs. 144, 0.00%) |
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
54710 (vs. 50900, 7.49%↑) |
269840 (vs. 269840, 0.00%) |
5219909 (vs. 5219909, 0.00%) |
148 (vs. 148, 0.00%) |
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
19770 (vs. 16840, 17.40%↑) |
62160 (vs. 62160, 0.00%) |
17019781 (vs. 17019781, 0.00%) |
79 (vs. 79, 0.00%) |
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
32038 (vs. 29446, 8.80%↑) |
99152 (vs. 99152, 0.00%) |
14219589 (vs. 14219589, 0.00%) |
136 (vs. 136, 0.00%) |
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
59168 (vs. 57732, 2.49%↑) |
322624 (vs. 322624, 0.00%) |
3996229 (vs. 3996229, 0.00%) |
213 (vs. 213, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
45974 (vs. 41584, 10.56%↑) |
139168 (vs. 139168, 0.00%) |
18503941 (vs. 18503941, 0.00%) |
223 (vs. 223, 0.00%) |
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
35840 (vs. 36209, 1.02%↓) |
84080 (vs. 84080, 0.00%) |
5188101 (vs. 5188101, 0.00%) |
81 (vs. 81, 0.00%) |
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
98185 (vs. 90536, 8.45%↑) |
74048 (vs. 74048, 0.00%) |
100104773 (vs. 100104773, 0.00%) |
1786 (vs. 1786, 0.00%) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
93640 (vs. 84052, 11.41%↑) |
73184 (vs. 73184, 0.00%) |
98608709 (vs. 98608709, 0.00%) |
1762 (vs. 1762, 0.00%) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
260179 (vs. 247074, 5.30%↑) |
2642416 (vs. 2642416, 0.00%) |
29120517 (vs. 29120517, 0.00%) |
2160 (vs. 2160, 0.00%) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
114287 (vs. 108326, 5.50%↑) |
179696 (vs. 179696, 0.00%) |
179806124 (vs. 179806124, 0.00%) |
439 (vs. 439, 0.00%) |
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
42661 (vs. 40461, 5.44%↑) |
42224 (vs. 42224, 0.00%) |
219514223 (vs. 219514223, 0.00%) |
330 (vs. 330, 0.00%) |
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
51841 (vs. 44690, 16.00%↑) |
23808 (vs. 23808, 0.00%) |
992645460 (vs. 992645460, 0.00%) |
318 (vs. 318, 0.00%) |
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
41834 (vs. 39451, 6.04%↑) |
14688 (vs. 14688, 0.00%) |
992644244 (vs. 992644244, 0.00%) |
367 (vs. 367, 0.00%) |
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
50882 (vs. 45836, 11.01%↑) |
42368 (vs. 42368, 0.00%) |
875941567 (vs. 875941567, 0.00%) |
334 (vs. 334, 0.00%) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] |
64994 (vs. 52809, 23.07%↑) |
76336 (vs. 76336, 0.00%) |
1336085695 (vs. 1336085695, 0.00%) |
654 (vs. 654, 0.00%) |
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
1595 (vs. 1475, 8.14%↑) |
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] |
23020 (vs. 22240, 3.51%↑) |
91520 (vs. 91520, 0.00%) |
355653 (vs. 355653, 0.00%) |
87 (vs. 87, 0.00%) |
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
32992 (vs. 34184, 3.49%↓) |
93472 (vs. 93472, 0.00%) |
10395269 (vs. 10395269, 0.00%) |
147 (vs. 147, 0.00%) |
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
31573 (vs. 31273, 0.96%↑) |
106960 (vs. 106960, 0.00%) |
2915333 (vs. 2915333, 0.00%) |
144 (vs. 144, 0.00%) |
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
49760 (vs. 47313, 5.17%↑) |
239056 (vs. 239056, 0.00%) |
5189125 (vs. 5189125, 0.00%) |
148 (vs. 148, 0.00%) |
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
20032 (vs. 16376, 22.33%↑) |
57120 (vs. 57120, 0.00%) |
17014789 (vs. 17014789, 0.00%) |
79 (vs. 79, 0.00%) |
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
34313 (vs. 29653, 15.72%↑) |
88784 (vs. 88784, 0.00%) |
14127301 (vs. 14127301, 0.00%) |
136 (vs. 136, 0.00%) |
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
53554 (vs. 58959, 9.17%↓) |
291328 (vs. 291328, 0.00%) |
3964933 (vs. 3964933, 0.00%) |
213 (vs. 213, 0.00%) |
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
43152 (vs. 41543, 3.87%↑) |
122128 (vs. 122128, 0.00%) |
18347461 (vs. 18347461, 0.00%) |
223 (vs. 223, 0.00%) |
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
19757 (vs. 20265, 2.51%↓) |
55840 (vs. 55840, 0.00%) |
5182597 (vs. 5182597, 0.00%) |
79 (vs. 79, 0.00%) |
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
95271 (vs. 82392, 15.63%↑) |
48928 (vs. 48928, 0.00%) |
100108421 (vs. 100108421, 0.00%) |
1786 (vs. 1786, 0.00%) |
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
94061 (vs. 85802, 9.63%↑) |
50112 (vs. 50112, 0.00%) |
98614277 (vs. 98614277, 0.00%) |
1762 (vs. 1762, 0.00%) |
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
246103 (vs. 241467, 1.92%↑) |
2631824 (vs. 2631824, 0.00%) |
29117061 (vs. 29117061, 0.00%) |
2160 (vs. 2160, 0.00%) |
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
116879 (vs. 108786, 7.44%↑) |
150448 (vs. 150448, 0.00%) |
169905644 (vs. 169905644, 0.00%) |
439 (vs. 439, 0.00%) |
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
39460 (vs. 39549, 0.23%↓) |
39792 (vs. 39792, 0.00%) |
219511791 (vs. 219511791, 0.00%) |
330 (vs. 330, 0.00%) |
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
50075 (vs. 42777, 17.06%↑) |
19328 (vs. 19328, 0.00%) |
992542612 (vs. 992542612, 0.00%) |
318 (vs. 318, 0.00%) |
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
49054 (vs. 43765, 12.08%↑) |
14112 (vs. 14112, 0.00%) |
992544916 (vs. 992544916, 0.00%) |
367 (vs. 367, 0.00%) |
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
45987 (vs. 42617, 7.91%↑) |
39072 (vs. 39072, 0.00%) |
875938303 (vs. 875938303, 0.00%) |
334 (vs. 334, 0.00%) |
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] |
59676 (vs. 51890, 15.00%↑) |
45760 (vs. 45760, 0.00%) |
1336112447 (vs. 1336112447, 0.00%) |
654 (vs. 654, 0.00%) |
EfficientNetV2STF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
97790 (vs. 90235, 8.37%↑) |
847160 (vs. 847160, 0.00%) |
165161940 (vs. 165161940, 0.00%) |
276 (vs. 276, 0.00%) |
MiniLML12H384Uncased(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
27200 (vs. 30247, 10.07%↓) |
145116 (vs. 145116, 0.00%) |
134088367 (vs. 134088367, 0.00%) |
209 (vs. 209, 0.00%) |
BertForMaskedLMTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
34010 (vs. 36140, 5.89%↓) |
227820 (vs. 227820, 0.00%) |
534005730 (vs. 534005730, 0.00%) |
212 (vs. 212, 0.00%) |
BertLargeTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] |
37828 (vs. 32540, 16.25%↑) |
130808 (vs. 130808, 0.00%) |
1336110891 (vs. 1336110891, 0.00%) |
413 (vs. 413, 0.00%) |
matmul_3456x1024x2048_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1476 (vs. 1500, 1.60%↓) |
30540 (vs. 30540, 0.00%) |
41263 (vs. 41263, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_3456x1024x2048_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1756 (vs. 1739, 0.98%↑) |
43516 (vs. 43516, 0.00%) |
54239 (vs. 54239, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_2560x2560x2560_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1526 (vs. 1510, 1.06%↑) |
28492 (vs. 28492, 0.00%) |
39151 (vs. 39151, 0.00%) |
1 (vs. 1, 0.00%) |
matmul_2560x2560x2560_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] |
1707 (vs. 1788, 4.53%↓) |
39892 (vs. 39892, 0.00%) |
50551 (vs. 50551, 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] |
1882 (vs. 1908, 1.36%↓) |
86300 (vs. 86300, 0.00%) |
96959 (vs. 96959, 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] |
2044 (vs. 2065, 1.02%↓) |
89040 (vs. 89040, 0.00%) |
99763 (vs. 99763, 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] |
2501 (vs. 2367, 5.66%↑) |
85768 (vs. 85768, 0.00%) |
96491 (vs. 96491, 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] |
1801 (vs. 1972, 8.67%↓) |
51280 (vs. 51280, 0.00%) |
62002 (vs. 62002, 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] |
863 (vs. 797, 8.28%↑) |
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] |
888 (vs. 826, 7.51%↑) |
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] |
36133 (vs. 33497, 7.87%↑) |
51640 (vs. 51640, 0.00%) |
133988529 (vs. 133988529, 0.00%) |
209 (vs. 209, 0.00%) |
DeepLabV3_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
22297 (vs. 21456, 3.92%↑) |
43080 (vs. 43080, 0.00%) |
2824455 (vs. 2824455, 0.00%) |
79 (vs. 79, 0.00%) |
EfficientNet_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
43404 (vs. 39195, 10.74%↑) |
175288 (vs. 175288, 0.00%) |
5098695 (vs. 5098695, 0.00%) |
89 (vs. 89, 0.00%) |
MobileBertSquad_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
75264 (vs. 68860, 9.30%↑) |
51112 (vs. 51112, 0.00%) |
98401159 (vs. 98401159, 0.00%) |
704 (vs. 704, 0.00%) |
MobileBertSquad_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
250374 (vs. 238218, 5.10%↑) |
2291592 (vs. 2291592, 0.00%) |
28590599 (vs. 28590599, 0.00%) |
1102 (vs. 1102, 0.00%) |
MobileNetV1_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
20782 (vs. 16549, 25.58%↑) |
51560 (vs. 51560, 0.00%) |
16976839 (vs. 16976839, 0.00%) |
65 (vs. 65, 0.00%) |
MobileNetV2_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
57054 (vs. 55929, 2.01%↑) |
227592 (vs. 227592, 0.00%) |
3878279 (vs. 3878279, 0.00%) |
144 (vs. 144, 0.00%) |
PersonDetect_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
19241 (vs. 21919, 12.22%↓) |
73272 (vs. 73272, 0.00%) |
329095 (vs. 329095, 0.00%) |
60 (vs. 60, 0.00%) |
EfficientNet_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
55519 (vs. 45885, 21.00%↑) |
327308 (vs. 327308, 0.00%) |
5250695 (vs. 5250695, 0.00%) |
89 (vs. 89, 0.00%) |
MobileBertSquad_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
301184 (vs. 281399, 7.03%↑) |
2523180 (vs. 2523180, 0.00%) |
28822215 (vs. 28822215, 0.00%) |
1102 (vs. 1102, 0.00%) |
PersonDetect_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
23642 (vs. 23829, 0.78%↓) |
175772 (vs. 175772, 0.00%) |
431623 (vs. 431623, 0.00%) |
60 (vs. 60, 0.00%) |
MobileNetV2_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] |
61845 (vs. 56173, 10.10%↑) |
315096 (vs. 315096, 0.00%) |
3965831 (vs. 3965831, 0.00%) |
144 (vs. 144, 0.00%) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
23113 (vs. 20431, 13.13%↑) |
56656 (vs. 56656, 0.00%) |
2838021 (vs. 2838021, 0.00%) |
79 (vs. 79, 0.00%) |
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
52245 (vs. 51172, 2.10%↑) |
33120 (vs. 33120, 0.00%) |
98383173 (vs. 98383173, 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] |
38244 (vs. 34134, 12.04%↑) |
20784 (vs. 20784, 0.00%) |
652747924 (vs. 652747924, 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] |
38093 (vs. 34390, 10.77%↑) |
9584 (vs. 9584, 0.00%) |
652730900 (vs. 652730900, 0.00%) |
246 (vs. 246, 0.00%) |
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
285052 (vs. 278554, 2.33%↑) |
4407168 (vs. 4407168, 0.00%) |
30706181 (vs. 30706181, 0.00%) |
1102 (vs. 1102, 0.00%) |
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] |
113326 (vs. 104125, 8.84%↑) |
711552 (vs. 711552, 0.00%) |
88745541 (vs. 88745541, 0.00%) |
268 (vs. 268, 0.00%) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
22199 (vs. 21131, 5.05%↑) |
41216 (vs. 41216, 0.00%) |
2840133 (vs. 2840133, 0.00%) |
144 (vs. 144, 0.00%) |
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
88591 (vs. 81947, 8.11%↑) |
22384 (vs. 22384, 0.00%) |
98570181 (vs. 98570181, 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] |
42476 (vs. 40355, 5.26%↑) |
11040 (vs. 11040, 0.00%) |
992509780 (vs. 992509780, 0.00%) |
318 (vs. 318, 0.00%) |
GPT2_117M_TF_1X1XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
48274 (vs. 43082, 12.05%↑) |
10048 (vs. 10048, 0.00%) |
992516180 (vs. 992516180, 0.00%) |
367 (vs. 367, 0.00%) |
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
230669 (vs. 217252, 6.18%↑) |
1356736 (vs. 1356736, 0.00%) |
27837893 (vs. 27837893, 0.00%) |
2160 (vs. 2160, 0.00%) |
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] |
85248 (vs. 77083, 10.59%↑) |
129888 (vs. 129888, 0.00%) |
88159621 (vs. 88159621, 0.00%) |
386 (vs. 386, 0.00%) |
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
22252 (vs. 21662, 2.72%↑) |
41568 (vs. 41568, 0.00%) |
2840517 (vs. 2840517, 0.00%) |
144 (vs. 144, 0.00%) |
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
84833 (vs. 78374, 8.24%↑) |
22496 (vs. 22496, 0.00%) |
98558021 (vs. 98558021, 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] |
46677 (vs. 39579, 17.93%↑) |
11152 (vs. 11152, 0.00%) |
992509908 (vs. 992509908, 0.00%) |
318 (vs. 318, 0.00%) |
GPT2_117M_TF_1X1XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
43073 (vs. 38695, 11.31%↑) |
10096 (vs. 10096, 0.00%) |
992516244 (vs. 992516244, 0.00%) |
367 (vs. 367, 0.00%) |
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
220331 (vs. 205299, 7.32%↑) |
1219136 (vs. 1219136, 0.00%) |
27697221 (vs. 27697221, 0.00%) |
2160 (vs. 2160, 0.00%) |
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] |
74149 (vs. 69831, 6.18%↑) |
122416 (vs. 122416, 0.00%) |
88152133 (vs. 88152133, 0.00%) |
386 (vs. 386, 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] |
1120 (vs. 909, 23.21%↑) |
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] |
1693 (vs. 1744, 2.92%↓) |
4432 (vs. 4432, 0.00%) |
273541 (vs. 273541, 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] |
1295 (vs. 1158, 11.83%↑) |
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] |
65500 (vs. 64020, 2.31%↑) |
246212 (vs. 246212, 0.00%) |
98597402 (vs. 98597402, 0.00%) |
704 (vs. 704, 0.00%) |
MobileBertSquad_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] |
73899 (vs. 68309, 8.18%↑) |
246212 (vs. 246212, 0.00%) |
98597402 (vs. 98597402, 0.00%) |
704 (vs. 704, 0.00%) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
74243 (vs. 70944, 4.65%↑) |
142904 (vs. 142904, 0.00%) |
98493689 (vs. 98493689, 0.00%) |
704 (vs. 704, 0.00%) |
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,demote-f32-to-f16,compile-stats] |
100523 (vs. 101873, 1.33%↓) |
3003516 (vs. 3003516, 0.00%) |
52897620 (vs. 52897620, 0.00%) |
728 (vs. 728, 0.00%) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] |
203050 (vs. 192191, 5.65%↑) |
6755236 (vs. 6755236, 0.00%) |
33055318 (vs. 33055318, 0.00%) |
1102 (vs. 1102, 0.00%) |
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,compile-stats] |
69507 (vs. 65058, 6.84%↑) |
142904 (vs. 142904, 0.00%) |
98493817 (vs. 98493817, 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] |
88852 (vs. 85235, 4.24%↑) |
3007544 (vs. 3007544, 0.00%) |
52904532 (vs. 52904532, 0.00%) |
728 (vs. 728, 0.00%) |
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,compile-stats] |
199544 (vs. 190363, 4.82%↑) |
6734980 (vs. 6734980, 0.00%) |
33022998 (vs. 33022998, 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] |
118021 (vs. 103119, 14.45%↑) |
142904 (vs. 142904, 0.00%) |
99715961 (vs. 99715961, 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] |
132395 (vs. 120266, 10.09%↑) |
3007544 (vs. 3007544, 0.00%) |
54168340 (vs. 54168340, 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] |
309745 (vs. 301444, 2.75%↑) |
6734980 (vs. 6734980, 0.00%) |
34936086 (vs. 34936086, 0.00%) |
1102 (vs. 1102, 0.00%) |
MobileNetV2_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] |
23571 (vs. 22439, 5.04%↑) |
208053 (vs. 208053, 0.00%) |
14213054 (vs. 14213054, 0.00%) |
172 (vs. 172, 0.00%) |
MobileNetV3Small_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] |
33373 (vs. 31657, 5.42%↑) |
311157 (vs. 311157, 0.00%) |
10551486 (vs. 10551486, 0.00%) |
210 (vs. 210, 0.00%) |