Skip to content

Instantly share code, notes, and snippets.

Show Gist options
  • Save iree-github-actions-bot/681c18c63a01a53071bd40a179e1cf84 to your computer and use it in GitHub Desktop.
Save iree-github-actions-bot/681c18c63a01a53071bd40a179e1cf84 to your computer and use it in GitHub Desktop.

Full Benchmark Summary

Regressed Latencies 🚩

Benchmark Name Average Latency (ms) Median Latency (ms) Latency Standard Deviation (ms)
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 25.574 (vs. 22.033, 16.07%↑) 25.598 0.277
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 152.524 (vs. 138.154, 10.40%↑) 152.373 0.665

Improved Latencies 🎉

Benchmark Name Average Latency (ms) Median Latency (ms) Latency Standard Deviation (ms)
MobileNetV3Small\_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags] local\_task(vmvx\_module)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 957.449 (vs. 1209.381, 20.83%↓) 957.428 16.119
MobileNetV2\_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags] local\_task(vmvx\_module)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 4752.208 (vs. 5843.818, 18.68%↓) 4805.548 115.906
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 20.715 (vs. 22.722, 8.83%↓) 20.874 0.306
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 7.747 (vs. 8.422, 8.01%↓) 7.778 0.083
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 62.255 (vs. 67.472, 7.73%↓) 62.062 2.026
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d,dotprod] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 122.234 (vs. 132.068, 7.45%↓) 123.337 3.788
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 15.295 (vs. 16.477, 7.17%↓) 15.396 0.384
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 181.009 (vs. 194.342, 6.86%↓) 183.552 9.324
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 46.512 (vs. 49.836, 6.67%↓) 46.548 0.283
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 32.205 (vs. 34.326, 6.18%↓) 32.276 0.224
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 55.664 (vs. 59.319, 6.16%↓) 54.446 2.254
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 11.983 (vs. 12.725, 5.83%↓) 12.024 0.342
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 376.317 (vs. 399.284, 5.75%↓) 377.087 2.926
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 20.624 (vs. 21.877, 5.73%↓) 20.817 0.624
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 18.739 (vs. 19.830, 5.50%↓) 18.780 0.333
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d,dotprod] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 260.407 (vs. 275.401, 5.44%↓) 260.852 1.916
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 6.139 (vs. 6.464, 5.03%↓) 6.193 0.206

Similar Latencies

Benchmark Name Average Latency (ms) Median Latency (ms) Latency Standard Deviation (ms)
BertForMaskedLMTF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 454.484 (vs. 413.718, 9.85%↑) 454.231 1.283
MiniLML12H384Uncased(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 23.692 (vs. 21.812, 8.62%↑) 23.890 2.256
MobileNetV2\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 3.690 (vs. 3.443, 7.17%↑) 3.766 0.140
DeepLabV3\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 8.393 (vs. 7.833, 7.15%↑) 8.385 0.037
DeepLabV3\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 7.219 (vs. 6.743, 7.07%↑) 7.313 0.438
MobileSSD\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 7.343 (vs. 6.878, 6.76%↑) 7.474 0.216
MobileNetV1\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 8.793 (vs. 8.353, 5.27%↑) 8.783 0.036
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 272.468 (vs. 285.253, 4.48%↓) 272.343 1.844
MobileBertSquad\_fp16(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 189.822 (vs. 198.384, 4.32%↓) 189.748 0.463
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 24.334 (vs. 25.398, 4.19%↓) 24.374 0.439
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 6.955 (vs. 7.253, 4.11%↓) 6.972 0.111
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 39.587 (vs. 41.266, 4.07%↓) 39.648 0.468
MobileBertSquad\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 190.157 (vs. 198.177, 4.05%↓) 190.116 0.283
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 6.309 (vs. 6.570, 3.97%↓) 6.325 0.044
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 214.631 (vs. 223.403, 3.93%↓) 215.640 9.315
MiniLML12H384Uncased(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 21.865 (vs. 22.740, 3.85%↓) 21.605 0.610
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 187.762 (vs. 195.117, 3.77%↓) 189.275 9.035
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 43.694 (vs. 45.396, 3.75%↓) 43.837 0.765
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 244.007 (vs. 253.393, 3.70%↓) 242.983 3.709
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d,dotprod] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 1596.204 (vs. 1656.089, 3.62%↓) 1595.652 2.924
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 619.273 (vs. 641.787, 3.51%↓) 619.893 1.455
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 28.756 (vs. 29.752, 3.35%↓) 28.913 0.557
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 6.380 (vs. 6.599, 3.32%↓) 6.385 0.057
EfficientNetV2SPT(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 390.713 (vs. 404.080, 3.31%↓) 390.602 0.611
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 20.983 (vs. 21.683, 3.23%↓) 20.989 0.278
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 10.329 (vs. 10.672, 3.21%↓) 10.310 0.263
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 2795.438 (vs. 2888.135, 3.21%↓) 2795.588 3.408
MobileSSD\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 34.029 (vs. 35.158, 3.21%↓) 33.994 0.086
MobileBertSquad\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 49.804 (vs. 51.429, 3.16%↓) 49.497 1.016
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 75.341 (vs. 77.520, 2.81%↓) 74.662 1.907
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 4.507 (vs. 4.631, 2.68%↓) 4.510 0.094
MiniLML12H384Uncased(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 89.859 (vs. 92.322, 2.67%↓) 89.770 0.359
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 833.565 (vs. 811.942, 2.66%↑) 831.696 8.396
MobileBertSquad\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 97.576 (vs. 100.221, 2.64%↓) 97.154 1.355
MobileNetV3Small\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 4.232 (vs. 4.337, 2.42%↓) 4.228 0.013
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 2804.628 (vs. 2873.300, 2.39%↓) 2804.905 4.485
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 342.731 (vs. 334.880, 2.34%↑) 322.696 69.896
EfficientNetV2SPT(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 87.143 (vs. 85.161, 2.33%↑) 86.526 2.698
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 488.676 (vs. 500.152, 2.29%↓) 491.204 8.164
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 115.506 (vs. 112.921, 2.29%↑) 113.995 4.612
MobileBertSquad\_fp16(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 51.890 (vs. 50.741, 2.27%↑) 52.229 4.126
MobileNetV2\_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags] local\_task(vmvx\_module)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 5478.575 (vs. 5603.692, 2.23%↓) 5517.770 132.173
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 27.079 (vs. 27.688, 2.20%↓) 27.309 0.854
Resnet50TFBatch1(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 31.651 (vs. 30.974, 2.19%↑) 30.900 1.698
MobileBertSquad\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 504.835 (vs. 515.886, 2.14%↓) 504.462 1.262
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 197.774 (vs. 201.959, 2.07%↓) 197.808 0.302
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 30.994 (vs. 31.649, 2.07%↓) 31.006 0.059
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 18.876 (vs. 19.275, 2.07%↓) 18.923 0.463
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 814.118 (vs. 831.216, 2.06%↓) 812.604 5.537
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 13.372 (vs. 13.652, 2.05%↓) 13.360 0.056
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 49.698 (vs. 48.731, 1.98%↑) 48.939 1.802
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 1288.659 (vs. 1314.600, 1.97%↓) 1287.421 2.743
MobileNetV2\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 24.025 (vs. 24.480, 1.86%↓) 24.028 0.064
MobileNetV2\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 12.831 (vs. 13.074, 1.86%↓) 12.728 0.410
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 2726.926 (vs. 2778.063, 1.84%↓) 2726.241 2.513
MobileNetV3Small\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ c2-standard-16[cpu] 3.762 (vs. 3.694, 1.83%↑) 3.757 0.017
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 648.376 (vs. 660.266, 1.80%↓) 647.781 1.537
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 88.563 (vs. 90.172, 1.79%↓) 90.523 4.552
PoseNet\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 6.169 (vs. 6.063, 1.75%↑) 6.119 0.116
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 3253.121 (vs. 3308.788, 1.68%↓) 3251.468 4.008
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 60.637 (vs. 59.635, 1.68%↑) 59.081 3.176
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 77.575 (vs. 76.302, 1.67%↑) 76.225 2.157
EfficientNetV2STF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 267.009 (vs. 271.485, 1.65%↓) 266.945 0.359
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 552.637 (vs. 561.786, 1.63%↓) 558.107 12.577
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d,dotprod] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 236.154 (vs. 239.998, 1.60%↓) 235.023 2.076
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 38.932 (vs. 39.557, 1.58%↓) 39.139 0.612
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 857.722 (vs. 871.433, 1.57%↓) 857.633 0.624
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 57.017 (vs. 57.919, 1.56%↓) 57.387 0.926
MobileNetV1\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 27.838 (vs. 28.268, 1.52%↓) 27.868 0.146
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 216.349 (vs. 219.682, 1.52%↓) 216.393 2.099
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 57.872 (vs. 58.755, 1.50%↓) 58.152 0.900
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 275.701 (vs. 279.841, 1.48%↓) 272.188 6.365
MobileNetV2\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 7.431 (vs. 7.541, 1.45%↓) 7.395 0.111
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 62.213 (vs. 63.126, 1.45%↓) 62.216 0.069
MobileSSD\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 9.359 (vs. 9.496, 1.44%↓) 9.341 0.397
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 66.250 (vs. 67.211, 1.43%↓) 66.273 0.190
EfficientNet\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 8.546 (vs. 8.668, 1.42%↓) 8.794 0.453
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 5.410 (vs. 5.487, 1.41%↓) 5.407 0.015
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 1519.666 (vs. 1539.968, 1.32%↓) 1518.923 2.328
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 27.038 (vs. 27.397, 1.31%↓) 27.142 0.775
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 1533.860 (vs. 1553.866, 1.29%↓) 1533.461 8.125
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 68.238 (vs. 69.123, 1.28%↓) 68.228 0.092
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 400.316 (vs. 405.399, 1.25%↓) 400.636 0.949
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 494.055 (vs. 500.284, 1.25%↓) 476.353 53.074
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 1066.521 (vs. 1079.899, 1.24%↓) 1066.449 0.580
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 105.348 (vs. 104.070, 1.23%↑) 105.420 0.734
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 10.828 (vs. 10.956, 1.17%↓) 10.822 0.019
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 21.727 (vs. 21.977, 1.14%↓) 21.807 0.309
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 573.922 (vs. 580.296, 1.10%↓) 573.821 0.660
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 4070.442 (vs. 4115.127, 1.09%↓) 4068.856 8.933
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 36.677 (vs. 37.072, 1.06%↓) 36.673 0.069
DeepLabV3\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 27.780 (vs. 27.489, 1.06%↑) 27.743 0.114
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 253.344 (vs. 255.917, 1.01%↓) 255.618 7.865
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 37.251 (vs. 36.887, 0.99%↑) 37.060 0.360
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 1254.142 (vs. 1266.522, 0.98%↓) 1254.047 0.615
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 195.671 (vs. 193.827, 0.95%↑) 195.857 1.346
EfficientNet\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 7.478 (vs. 7.549, 0.95%↓) 7.420 0.160
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 22.447 (vs. 22.659, 0.94%↓) 22.458 0.082
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 15.034 (vs. 15.175, 0.93%↓) 15.103 0.395
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 73.718 (vs. 73.061, 0.90%↑) 74.647 1.905
EfficientNetV2STF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 55.512 (vs. 55.022, 0.89%↑) 55.021 0.927
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 157.520 (vs. 156.211, 0.84%↑) 157.193 0.923
EfficientNetV2STF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 57.362 (vs. 56.905, 0.80%↑) 57.345 0.113
MobileBertSquad\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 50.777 (vs. 50.377, 0.79%↑) 49.675 1.924
Resnet50TFBatch1(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 182.653 (vs. 184.106, 0.79%↓) 182.707 0.713
MobileNetV3Small\_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags] local\_task(vmvx\_module)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 1062.783 (vs. 1071.187, 0.78%↓) 1062.580 16.731
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 20.356 (vs. 20.508, 0.74%↓) 20.542 0.722
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d,dotprod] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 393.247 (vs. 396.042, 0.71%↓) 393.261 0.180
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 549.714 (vs. 553.600, 0.70%↓) 549.024 6.321
BertLargeTF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 1527.812 (vs. 1538.555, 0.70%↓) 1521.659 20.429
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 11.980 (vs. 11.897, 0.70%↑) 11.976 0.010
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 66.967 (vs. 66.514, 0.68%↑) 66.964 0.047
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d,dotprod] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 460.827 (vs. 463.950, 0.67%↓) 460.898 0.277
MobileNetV2\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 7.468 (vs. 7.418, 0.67%↑) 7.430 0.090
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 355.565 (vs. 357.967, 0.67%↓) 355.552 0.104
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 397.070 (vs. 394.445, 0.67%↑) 397.148 1.743
PoseNet\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 22.867 (vs. 23.011, 0.63%↓) 22.803 0.204
PoseNet\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 5.549 (vs. 5.583, 0.60%↓) 5.544 0.019
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 455.436 (vs. 458.189, 0.60%↓) 455.189 1.089
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 74.975 (vs. 74.532, 0.59%↑) 74.929 0.343
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 192.824 (vs. 191.695, 0.59%↑) 192.824 0.141
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 667.636 (vs. 671.404, 0.56%↓) 667.477 0.771
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 101.121 (vs. 101.687, 0.56%↓) 101.206 0.249
MobileNetV3Small\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 3.786 (vs. 3.806, 0.52%↓) 3.780 0.015
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 7.197 (vs. 7.233, 0.50%↓) 7.185 0.046
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 3915.379 (vs. 3897.393, 0.46%↑) 3918.959 7.326
EfficientNetB7PT(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 629.531 (vs. 626.728, 0.45%↑) 628.179 4.382
EfficientNet\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 33.781 (vs. 33.931, 0.44%↓) 33.766 0.051
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 399.817 (vs. 398.089, 0.43%↑) 399.773 1.234
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 34.366 (vs. 34.508, 0.41%↓) 34.329 0.631
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 350.984 (vs. 352.256, 0.36%↓) 351.536 1.675
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 38.795 (vs. 38.662, 0.34%↑) 39.067 0.567
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 36.452 (vs. 36.329, 0.34%↑) 36.455 0.020
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 596.688 (vs. 594.728, 0.33%↑) 596.131 4.039
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 414.356 (vs. 415.709, 0.33%↓) 413.954 1.313
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 85.927 (vs. 86.202, 0.32%↓) 85.988 0.142
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 79.264 (vs. 79.017, 0.31%↑) 79.281 0.091
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 56.365 (vs. 56.539, 0.31%↓) 56.355 0.114
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 4114.163 (vs. 4126.700, 0.30%↓) 4110.208 17.325
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 592.501 (vs. 594.248, 0.29%↓) 592.162 3.912
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 25.481 (vs. 25.407, 0.29%↑) 25.434 0.206
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 72.617 (vs. 72.417, 0.28%↑) 72.621 0.031
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 3923.409 (vs. 3934.199, 0.27%↓) 3923.975 10.427
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 350.370 (vs. 351.321, 0.27%↓) 350.529 2.538
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 1322.273 (vs. 1318.754, 0.27%↑) 1321.430 3.948
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d,dotprod] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 1605.212 (vs. 1609.275, 0.25%↓) 1608.104 10.139
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 201.039 (vs. 201.501, 0.23%↓) 201.404 0.928
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 2753.073 (vs. 2759.375, 0.23%↓) 2753.408 3.199
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 82.358 (vs. 82.178, 0.22%↑) 82.360 0.068
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 306.490 (vs. 305.820, 0.22%↑) 306.409 1.248
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 13.093 (vs. 13.065, 0.22%↑) 13.092 0.014
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d,dotprod] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 150.190 (vs. 150.513, 0.21%↓) 150.146 0.144
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[big-core] 76.801 (vs. 76.642, 0.21%↑) 76.805 0.102
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 31.812 (vs. 31.747, 0.21%↑) 31.809 0.013
MobileNetV2\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 4.757 (vs. 4.766, 0.20%↓) 4.669 0.135
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 31.580 (vs. 31.637, 0.18%↓) 31.497 1.217
MobileSSD\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 442.234 (vs. 441.473, 0.17%↑) 443.492 6.699
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 305.871 (vs. 306.384, 0.17%↓) 305.952 1.381
MobileNetV2\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 193.358 (vs. 193.082, 0.14%↑) 193.446 0.372
PersonDetect\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 0.790 (vs. 0.789, 0.13%↑) 0.790 0.001
MobileBertSquad\_int8(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 616.843 (vs. 617.562, 0.12%↓) 616.689 1.865
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[big-core] 181.479 (vs. 181.279, 0.11%↑) 181.541 0.321
BertLargeTF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,fuse-padding] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 1530.186 (vs. 1528.747, 0.09%↑) 1518.192 59.286
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 352.648 (vs. 352.393, 0.07%↑) 352.383 0.608
MobileNetV3Small\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-4[big-core] 11.562 (vs. 11.554, 0.07%↑) 11.553 0.029
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[little-core] 1310.659 (vs. 1309.801, 0.07%↑) 1312.763 9.450
PoseNet\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 182.050 (vs. 181.948, 0.06%↑) 182.025 0.314
PersonDetect\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 0.794 (vs. 0.795, 0.04%↓) 0.795 0.007
MobileBertSquad\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 99.923 (vs. 99.895, 0.03%↑) 97.891 4.400
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][experimental-flags,mmt4d] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-6-pro[little-core] 3392.529 (vs. 3393.415, 0.03%↓) 3392.943 7.447
PersonDetect\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ c2-standard-16[cpu] 0.717 (vs. 0.717, 0.02%↑) 0.717 0.000
MobileBertSquad\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_task(embedded\_elf)[4-thread,full-inference,system-scheduling] with zeros @ pixel-4[little-core] 1320.932 (vs. 1320.663, 0.02%↑) 1320.497 6.571
DeepLabV3\_fp32(tflite) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags] local\_sync(embedded\_elf)[full-inference,default-flags] with zeros @ pixel-4[little-core] 405.008 (vs. 404.972, 0.01%↑) 404.888 1.549

All Compilation Metrics

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