Skip to content

Instantly share code, notes, and snippets.

Show Gist options
  • Save iree-github-actions-bot/8c43f2d9afa602abc2846c5205f213da to your computer and use it in GitHub Desktop.
Save iree-github-actions-bot/8c43f2d9afa602abc2846c5205f213da to your computer and use it in GitHub Desktop.

Full Benchmark Summary

Data-Tiling Comparison Table

Name No-DT (baseline) DT-Only DT-UK
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[30-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 741.449 (1.0X) 270.500 (2.7X) 221.635 (3.3X)
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 7.036 (1.0X) 9.280 (0.8X) 8.594 (0.8X)
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 35.977 (1.0X) 36.206 (1.0X) 34.363 (1.0X)
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 5.864 (1.0X) 10.990 (0.5X) 5.049 (1.2X)
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 9.165 (1.0X) 8.617 (1.1X) 8.575 (1.1X)
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 11.177 (1.0X) 9.038 (1.2X) 8.969 (1.2X)
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 12.016 (1.0X) 15.414 (0.8X) 13.764 (0.9X)
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 34.454 (1.0X) 65.444 (0.5X) 61.248 (0.6X)
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 33.831 (1.0X) 65.606 (0.5X) 61.569 (0.5X)
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 69.375 (1.0X) 133.918 (0.5X) 64.435 (1.1X)
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 4.876 (1.0X) 5.362 (0.9X) 4.598 (1.1X)
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 3.790 (1.0X) 5.358 (0.7X) 4.969 (0.8X)
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 5.916 (1.0X) 9.573 (0.6X) 5.441 (1.1X)
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 2.867 (1.0X) 3.444 (0.8X) 2.858 (1.0X)
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 8.474 (1.0X) 11.104 (0.8X) 9.939 (0.9X)
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 0.788 (1.0X) 1.397 (0.6X) 0.655 (1.2X)
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 4.189 (1.0X) 5.947 (0.7X) 5.240 (0.8X)
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_sync(embedded_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 7.545 (1.0X) 7.555 (1.0X) 7.573 (1.0X)
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_sync(embedded_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 6.673 (1.0X) 13.247 (0.5X) 1.807 (3.7X)
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[30-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 217.828 (1.0X) 136.413 (1.6X) 108.389 (2.0X)
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 32.373 (1.0X) 36.239 (0.9X) 30.185 (1.1X)
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 277.565 (1.0X) 258.583 (1.1X) 229.656 (1.2X)
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 26.868 (1.0X) 51.381 (0.5X) 13.158 (2.0X)
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 70.739 (1.0X) 37.892 (1.9X) 38.185 (1.9X)
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 89.257 (1.0X) 41.914 (2.1X) 40.665 (2.2X)
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 79.495 (1.0X) 78.007 (1.0X) 58.872 (1.4X)
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 179.223 (1.0X) 249.868 (0.7X) 188.005 (1.0X)
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 180.558 (1.0X) 255.916 (0.7X) 191.058 (0.9X)
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 519.813 (1.0X) 1087.155 (0.5X) 244.471 (2.1X)
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 26.077 (1.0X) 22.586 (1.2X) 17.936 (1.5X)
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 12.127 (1.0X) 15.027 (0.8X) 11.474 (1.1X)
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 21.698 (1.0X) 42.297 (0.5X) 11.808 (1.8X)
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_sync(embedded_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 2.789 (1.0X) 3.282 (0.8X) 2.718 (1.0X)
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 34.662 (1.0X) 39.092 (0.9X) 31.588 (1.1X)
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_sync(embedded_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 0.718 (1.0X) 1.299 (0.6X) 0.581 (1.2X)
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_task(embedded_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 17.961 (1.0X) 23.785 (0.8X) 18.866 (1.0X)
matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_sync(embedded_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 0.054 (1.0X) 0.054 (1.0X) 0.055 (1.0X)
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu] local_sync(embedded_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 0.043 (1.0X) 0.226 (0.2X) 0.022 (2.0X)

Similar Latencies

Benchmark Name Average Latency (ms) Median Latency (ms) Latency Standard Deviation (ms)
GPT2\_117M\_TF\_1X1XI32(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 37.892 (vs. 41.246, 8.13%↓) 37.385 1.344
GPT2\_117M\_TF\_1X1XI32(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 38.185 (vs. 41.408, 7.78%↓) 37.618 1.296
PoseNet\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 18.866 (vs. 19.683, 4.15%↓) 18.830 0.099
GPT2\_117M\_TF\_1X4XI32(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 40.665 (vs. 42.341, 3.96%↓) 40.122 1.619
MobileNetV1\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 4.876 (vs. 5.055, 3.53%↓) 4.879 0.040
BertLargeTF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[30-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 741.449 (vs. 765.382, 3.13%↓) 730.099 37.428
MiniLML12H384Uncased(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 13.764 (vs. 14.107, 2.43%↓) 13.726 0.108
GPT2\_117M\_TF\_1X4XI32(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 41.914 (vs. 42.775, 2.01%↓) 41.184 1.546
MobileNetV3Small\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 2.718 (vs. 2.666, 1.95%↑) 2.713 0.016
PoseNet\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 4.189 (vs. 4.267, 1.81%↓) 4.188 0.020
PersonDetect\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 0.581 (vs. 0.591, 1.77%↓) 0.581 0.001
MobileSSD\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 39.092 (vs. 39.740, 1.63%↓) 38.896 0.540
MobileBertSquad\_fp16(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 34.454 (vs. 33.904, 1.62%↑) 34.364 1.025
MiniLML12H384Uncased(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 12.016 (vs. 12.205, 1.55%↓) 11.791 0.317
MiniLML12H384Uncased(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 58.872 (vs. 59.764, 1.49%↓) 58.393 1.026
MobileNetV3Small\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 2.867 (vs. 2.909, 1.44%↓) 2.870 0.014
MobileSSD\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 31.588 (vs. 32.007, 1.31%↓) 31.432 0.347
GPT2\_117M\_TF\_1X1XI32(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 9.165 (vs. 9.282, 1.27%↓) 8.891 0.470
MiniLML12H384Uncased(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 78.007 (vs. 78.943, 1.18%↓) 77.488 1.192
MobileNetV3Small\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 2.858 (vs. 2.825, 1.17%↑) 2.856 0.015
BertForMaskedLMTF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[30-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 136.413 (vs. 137.963, 1.12%↓) 135.468 1.625
MobileSSD\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 9.939 (vs. 10.046, 1.06%↓) 9.927 0.051
PoseNet\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 17.961 (vs. 17.779, 1.02%↑) 17.957 0.106
MobileNetV3Small\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 3.282 (vs. 3.315, 1.00%↓) 3.278 0.012
PersonDetect\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 0.655 (vs. 0.662, 1.00%↓) 0.655 0.003
BertForMaskedLMTF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[30-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 217.828 (vs. 219.914, 0.95%↓) 212.186 15.455
PoseNet\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 5.240 (vs. 5.192, 0.93%↑) 5.246 0.023
EfficientNet\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 13.158 (vs. 13.037, 0.93%↑) 13.147 0.045
MobileBertSquad\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 191.058 (vs. 192.712, 0.86%↓) 189.669 2.980
MobileNetV2\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 4.969 (vs. 4.927, 0.86%↑) 4.965 0.017
BertLargeTF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[30-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 221.635 (vs. 223.400, 0.79%↓) 221.165 2.416
MobileNetV1\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 26.077 (vs. 25.873, 0.79%↑) 26.120 0.325
GPT2\_117M\_TF\_1X4XI32(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 89.257 (vs. 89.953, 0.77%↓) 89.437 3.522
matmul\_1x256x2048\_i8\_i4\_i32\_tile\_config\_default(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 0.054 (vs. 0.055, 0.75%↓) 0.054 0.000
GPT2\_117M\_TF\_1X1XI32(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 8.617 (vs. 8.554, 0.74%↑) 8.581 0.078
matmul\_256x256x2048\_i8\_i8\_i32\_tile\_config\_default(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 6.673 (vs. 6.624, 0.74%↑) 6.673 0.008
matmul\_1x256x2048\_i8\_i8\_i32\_tile\_config\_default(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 0.022 (vs. 0.022, 0.71%↑) 0.022 0.000
BertLargeTF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[30-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 270.500 (vs. 272.394, 0.70%↓) 270.713 2.577
MobileNetV2\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 12.127 (vs. 12.045, 0.68%↑) 12.104 0.160
MobileBertSquad\_fp16(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 65.444 (vs. 65.010, 0.67%↑) 65.012 0.752
MobileNetV1\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 22.586 (vs. 22.729, 0.63%↓) 22.487 0.216
DeepLabV3\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 30.185 (vs. 30.011, 0.58%↑) 30.154 0.095
MobileNetV3Small\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 3.444 (vs. 3.425, 0.57%↑) 3.443 0.023
matmul\_1x256x2048\_i8\_i4\_i32\_tile\_config\_default(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 0.055 (vs. 0.055, 0.53%↑) 0.055 0.000
matmul\_256x256x2048\_i8\_i8\_i32\_tile\_config\_default(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 13.247 (vs. 13.317, 0.53%↓) 13.261 0.033
MobileBertSquad\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 180.558 (vs. 179.628, 0.52%↑) 179.665 3.195
MobileBertSquad\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 65.606 (vs. 65.274, 0.51%↑) 65.218 0.595
MobileNetV1\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 5.362 (vs. 5.335, 0.50%↑) 5.355 0.021
EfficientNet\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 26.868 (vs. 27.002, 0.50%↓) 26.854 0.064
MobileNetV3Small\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 2.789 (vs. 2.803, 0.49%↓) 2.786 0.015
GPT2\_117M\_TF\_1X1XI32(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 8.575 (vs. 8.534, 0.49%↑) 8.546 0.073
MobileBertSquad\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 33.831 (vs. 33.671, 0.48%↑) 33.298 1.029
MobileBertSquad\_fp16(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 179.223 (vs. 180.006, 0.43%↓) 178.422 2.405
DeepLabV3\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 9.280 (vs. 9.243, 0.41%↑) 9.273 0.025
EfficientNet\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 5.049 (vs. 5.070, 0.40%↓) 5.048 0.013
GPT2\_117M\_TF\_1X4XI32(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 8.969 (vs. 9.005, 0.39%↓) 8.936 0.091
MobileNetV2\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 11.808 (vs. 11.854, 0.39%↓) 11.794 0.037
MobileBertSquad\_fp16(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 188.005 (vs. 187.281, 0.39%↑) 186.306 2.989
matmul\_256x256x2048\_i8\_i4\_i32\_tile\_config\_default(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 7.573 (vs. 7.544, 0.38%↑) 7.569 0.021
PersonDetect\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 0.718 (vs. 0.716, 0.38%↑) 0.718 0.001
matmul\_1x256x2048\_i8\_i4\_i32\_tile\_config\_default(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 0.054 (vs. 0.055, 0.38%↓) 0.054 0.000
EfficientNetV2STF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 277.565 (vs. 276.518, 0.38%↑) 274.880 5.927
DeepLabV3\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 36.239 (vs. 36.107, 0.36%↑) 36.199 0.238
EfficientNetV2STF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 258.583 (vs. 259.513, 0.36%↓) 255.680 4.489
MiniLML12H384Uncased(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 79.495 (vs. 79.769, 0.34%↓) 78.847 1.357
MobileNetV2\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 15.027 (vs. 14.976, 0.34%↑) 14.969 0.105
EfficientNetV2STF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 34.363 (vs. 34.249, 0.33%↑) 34.168 0.367
PersonDetect\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 1.397 (vs. 1.392, 0.31%↑) 1.396 0.002
MobileNetV2\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 5.441 (vs. 5.458, 0.30%↓) 5.439 0.009
MobileNetV2\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 11.474 (vs. 11.440, 0.30%↑) 11.454 0.063
MobileSSD\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 34.662 (vs. 34.563, 0.29%↑) 34.494 0.373
matmul\_1x256x2048\_i8\_i8\_i32\_tile\_config\_default(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 0.043 (vs. 0.043, 0.29%↓) 0.043 0.000
DeepLabV3\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 7.036 (vs. 7.016, 0.28%↑) 7.034 0.020
MobileBertSquad\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 69.375 (vs. 69.183, 0.28%↑) 69.005 0.712
PoseNet\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 5.947 (vs. 5.931, 0.26%↑) 5.949 0.017
BertForMaskedLMTF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[30-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 108.389 (vs. 108.665, 0.25%↓) 107.588 1.370
DeepLabV3\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 8.594 (vs. 8.573, 0.24%↑) 8.602 0.032
MiniLML12H384Uncased(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 15.414 (vs. 15.451, 0.24%↓) 15.356 0.121
matmul\_256x256x2048\_i8\_i8\_i32\_tile\_config\_default(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 1.807 (vs. 1.811, 0.23%↓) 1.805 0.005
EfficientNetV2STF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 35.977 (vs. 36.058, 0.22%↓) 35.389 0.956
matmul\_256x256x2048\_i8\_i4\_i32\_tile\_config\_default(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 7.545 (vs. 7.562, 0.22%↓) 7.547 0.017
MobileNetV3Small\_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags] local\_task(vmvx\_module)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 1646.809 (vs. 1650.203, 0.21%↓) 1646.597 0.597
GPT2\_117M\_TF\_1X4XI32(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 9.038 (vs. 9.056, 0.20%↓) 9.001 0.090
PoseNet\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 23.785 (vs. 23.829, 0.18%↓) 23.771 0.068
MobileBertSquad\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 61.569 (vs. 61.457, 0.18%↑) 61.252 0.652
matmul\_256x256x2048\_i8\_i4\_i32\_tile\_config\_default(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 7.555 (vs. 7.568, 0.18%↓) 7.553 0.015
MobileBertSquad\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 133.918 (vs. 134.151, 0.17%↓) 133.517 1.045
MobileNetV2\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 3.790 (vs. 3.796, 0.16%↓) 3.787 0.012
MobileBertSquad\_fp16(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 61.248 (vs. 61.344, 0.16%↓) 61.029 0.516
MobileNetV1\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 4.598 (vs. 4.591, 0.15%↑) 4.593 0.021
MobileBertSquad\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 244.471 (vs. 244.104, 0.15%↑) 244.100 1.401
MobileNetV1\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 17.936 (vs. 17.962, 0.15%↓) 17.861 0.164
EfficientNet\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 51.381 (vs. 51.307, 0.14%↑) 51.363 0.171
EfficientNet\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 5.864 (vs. 5.872, 0.14%↓) 5.860 0.028
MobileSSD\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 11.104 (vs. 11.089, 0.13%↑) 11.079 0.090
GPT2\_117M\_TF\_1X1XI32(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 70.739 (vs. 70.649, 0.13%↑) 71.006 2.795
MobileNetV2\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 5.916 (vs. 5.909, 0.12%↑) 5.910 0.022
DeepLabV3\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 32.373 (vs. 32.413, 0.12%↓) 32.373 0.086
EfficientNetV2STF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 36.206 (vs. 36.163, 0.12%↑) 36.051 0.391
MobileSSD\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 8.474 (vs. 8.465, 0.11%↑) 8.469 0.049
MobileNetV2\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 5.358 (vs. 5.353, 0.10%↑) 5.356 0.014
PersonDetect\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 1.299 (vs. 1.298, 0.10%↑) 1.299 0.001
EfficientNet\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 10.990 (vs. 10.981, 0.09%↑) 10.985 0.019
MobileNetV2\_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags] local\_task(vmvx\_module)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 7307.914 (vs. 7314.050, 0.08%↓) 7305.363 5.369
MobileNetV2\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[8-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 9.573 (vs. 9.565, 0.08%↑) 9.561 0.036
MobileBertSquad\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 1087.155 (vs. 1086.270, 0.08%↑) 1086.600 3.705
MobileBertSquad\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 64.435 (vs. 64.383, 0.08%↑) 64.270 0.402
EfficientNetV2STF(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags,dt-uk] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 229.656 (vs. 229.482, 0.08%↑) 227.822 3.634
PersonDetect\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 0.788 (vs. 0.789, 0.07%↓) 0.788 0.001
GPT2\_117M\_TF\_1X4XI32(stablehlo) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[15-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 11.177 (vs. 11.184, 0.06%↓) 11.001 0.556
MobileNetV2\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 21.698 (vs. 21.708, 0.05%↓) 21.683 0.047
MobileBertSquad\_fp16(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 249.868 (vs. 249.969, 0.04%↓) 248.021 3.836
MobileNetV2\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 42.297 (vs. 42.312, 0.04%↓) 42.300 0.126
MobileBertSquad\_int8(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,no-dt] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 519.813 (vs. 519.680, 0.03%↑) 518.305 2.690
matmul\_1x256x2048\_i8\_i8\_i32\_tile\_config\_default(linalg) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ c2-standard-60[cpu] 0.226 (vs. 0.226, 0.02%↑) 0.226 0.000
MobileBertSquad\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][experimental-flags,dt-only] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with default @ c2-standard-60[cpu] 255.916 (vs. 255.914, 0.00%↑) 253.498 4.334

All Compilation Metrics

Benchmark Name Compilation Time (ms) Total Dispatch Size (bytes) Total Artifact Size (bytes) Stream IR Dispatch Count (# of cmd.dispatch ops)
matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 982 (vs. 1301, 24.52%↓) 4400 (vs. 4400, 0.00%) 273657 (vs. 273657, 0.00%) 1 (vs. 1, 0.00%)
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 1713 (vs. 2023, 15.32%↓) 9680 (vs. 9680, 0.00%) 278905 (vs. 278905, 0.00%) 1 (vs. 1, 0.00%)
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 938 (vs. 1111, 15.57%↓) 3328 (vs. 3328, 0.00%) 534713 (vs. 534713, 0.00%) 1 (vs. 1, 0.00%)
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 1419 (vs. 1875, 24.32%↓) 8480 (vs. 8480, 0.00%) 539833 (vs. 539833, 0.00%) 1 (vs. 1, 0.00%)
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 21471 (vs. 24261, 11.50%↓) 144544 (vs. 144544, 0.00%) 399621 (vs. 399621, 0.00%) 60 (vs. 60, 0.00%)
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 36609 (vs. 37586, 2.60%↓) 238656 (vs. 238656, 0.00%) 10455045 (vs. 10455045, 0.00%) 97 (vs. 97, 0.00%)
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 33995 (vs. 38045, 10.65%↓) 177696 (vs. 177696, 0.00%) 2957509 (vs. 2957509, 0.00%) 79 (vs. 79, 0.00%)
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 59884 (vs. 61303, 2.31%↓) 682752 (vs. 682752, 0.00%) 5604037 (vs. 5604037, 0.00%) 89 (vs. 89, 0.00%)
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 20850 (vs. 25580, 18.49%↓) 175008 (vs. 175008, 0.00%) 17092357 (vs. 17092357, 0.00%) 51 (vs. 51, 0.00%)
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 32315 (vs. 36234, 10.82%↓) 190512 (vs. 190512, 0.00%) 14172293 (vs. 14172293, 0.00%) 74 (vs. 74, 0.00%)
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 63909 (vs. 70202, 8.96%↓) 568880 (vs. 568880, 0.00%) 4216965 (vs. 4216965, 0.00%) 144 (vs. 144, 0.00%)
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 44806 (vs. 49751, 9.94%↓) 287728 (vs. 287728, 0.00%) 18226373 (vs. 18226373, 0.00%) 124 (vs. 124, 0.00%)
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 22876 (vs. 22495, 1.69%↑) 142464 (vs. 142464, 0.00%) 5195333 (vs. 5195333, 0.00%) 48 (vs. 48, 0.00%)
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 64593 (vs. 71264, 9.36%↓) 91888 (vs. 91888, 0.00%) 99892421 (vs. 99892421, 0.00%) 703 (vs. 703, 0.00%)
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 63506 (vs. 73677, 13.80%↓) 100448 (vs. 100448, 0.00%) 98413509 (vs. 98413509, 0.00%) 679 (vs. 679, 0.00%)
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 330099 (vs. 335373, 1.57%↓) 6817872 (vs. 6817872, 0.00%) 33068933 (vs. 33068933, 0.00%) 1053 (vs. 1053, 0.00%)
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 102016 (vs. 115993, 12.05%↓) 216688 (vs. 216688, 0.00%) 164493804 (vs. 164493804, 0.00%) 276 (vs. 276, 0.00%)
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 28042 (vs. 35934, 21.96%↓) 67120 (vs. 67120, 0.00%) 133993839 (vs. 133993839, 0.00%) 185 (vs. 185, 0.00%)
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 34005 (vs. 38582, 11.86%↓) 27504 (vs. 27504, 0.00%) 652743124 (vs. 652743124, 0.00%) 221 (vs. 221, 0.00%)
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 30982 (vs. 35154, 11.87%↓) 15008 (vs. 15008, 0.00%) 652726868 (vs. 652726868, 0.00%) 246 (vs. 246, 0.00%)
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 36142 (vs. 41595, 13.11%↓) 76768 (vs. 76768, 0.00%) 533839679 (vs. 533839679, 0.00%) 188 (vs. 188, 0.00%)
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 32401 (vs. 32183, 0.68%↑) 58176 (vs. 58176, 0.00%) 1336009791 (vs. 1336009791, 0.00%) 365 (vs. 365, 0.00%)
matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 1045 (vs. 1232, 15.18%↓) 4400 (vs. 4400, 0.00%) 273657 (vs. 273657, 0.00%) 1 (vs. 1, 0.00%)
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 1585 (vs. 1902, 16.67%↓) 9680 (vs. 9680, 0.00%) 278969 (vs. 278969, 0.00%) 1 (vs. 1, 0.00%)
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 1952 (vs. 2372, 17.71%↓) 2976 (vs. 2976, 0.00%) 534329 (vs. 534329, 0.00%) 1 (vs. 1, 0.00%)
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 2236 (vs. 2758, 18.93%↓) 6432 (vs. 6432, 0.00%) 538565 (vs. 538565, 0.00%) 3 (vs. 3, 0.00%)
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 21484 (vs. 23060, 6.83%↓) 106672 (vs. 106672, 0.00%) 368197 (vs. 368197, 0.00%) 87 (vs. 87, 0.00%)
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 28473 (vs. 36543, 22.08%↓) 96992 (vs. 96992, 0.00%) 10394437 (vs. 10394437, 0.00%) 147 (vs. 147, 0.00%)
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 30934 (vs. 33217, 6.87%↓) 114416 (vs. 114416, 0.00%) 2917765 (vs. 2917765, 0.00%) 144 (vs. 144, 0.00%)
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 41992 (vs. 53716, 21.83%↓) 269312 (vs. 269312, 0.00%) 5215557 (vs. 5215557, 0.00%) 148 (vs. 148, 0.00%)
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 16981 (vs. 21207, 19.93%↓) 60352 (vs. 60352, 0.00%) 17014277 (vs. 17014277, 0.00%) 79 (vs. 79, 0.00%)
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 30810 (vs. 30139, 2.23%↑) 95328 (vs. 95328, 0.00%) 14129477 (vs. 14129477, 0.00%) 136 (vs. 136, 0.00%)
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 52959 (vs. 57198, 7.41%↓) 329856 (vs. 329856, 0.00%) 3999429 (vs. 3999429, 0.00%) 213 (vs. 213, 0.00%)
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 44367 (vs. 50951, 12.92%↓) 135552 (vs. 135552, 0.00%) 18353861 (vs. 18353861, 0.00%) 223 (vs. 223, 0.00%)
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 15771 (vs. 16691, 5.51%↓) 44256 (vs. 44256, 0.00%) 5146949 (vs. 5146949, 0.00%) 79 (vs. 79, 0.00%)
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 77095 (vs. 84093, 8.32%↓) 48496 (vs. 48496, 0.00%) 99982149 (vs. 99982149, 0.00%) 1786 (vs. 1786, 0.00%)
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 77960 (vs. 88668, 12.08%↓) 48880 (vs. 48880, 0.00%) 98494021 (vs. 98494021, 0.00%) 1762 (vs. 1762, 0.00%)
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 273474 (vs. 289132, 5.42%↓) 3422160 (vs. 3422160, 0.00%) 29827269 (vs. 29827269, 0.00%) 2136 (vs. 2136, 0.00%)
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 111736 (vs. 122067, 8.46%↓) 155328 (vs. 155328, 0.00%) 169900268 (vs. 169900268, 0.00%) 439 (vs. 439, 0.00%)
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 37783 (vs. 40160, 5.92%↓) 36576 (vs. 36576, 0.00%) 219461551 (vs. 219461551, 0.00%) 342 (vs. 342, 0.00%)
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 40900 (vs. 52427, 21.99%↓) 17344 (vs. 17344, 0.00%) 992526932 (vs. 992526932, 0.00%) 330 (vs. 330, 0.00%)
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 38203 (vs. 41785, 8.57%↓) 10272 (vs. 10272, 0.00%) 992522132 (vs. 992522132, 0.00%) 355 (vs. 355, 0.00%)
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 44984 (vs. 41166, 9.27%↑) 38224 (vs. 38224, 0.00%) 875850431 (vs. 875850431, 0.00%) 346 (vs. 346, 0.00%)
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 48277 (vs. 54541, 11.48%↓) 41568 (vs. 41568, 0.00%) 1336020735 (vs. 1336020735, 0.00%) 678 (vs. 678, 0.00%)
matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 1032 (vs. 1334, 22.64%↓) 4400 (vs. 4400, 0.00%) 273657 (vs. 273657, 0.00%) 1 (vs. 1, 0.00%)
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 1528 (vs. 1924, 20.58%↓) 9680 (vs. 9680, 0.00%) 278969 (vs. 278969, 0.00%) 1 (vs. 1, 0.00%)
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 2519 (vs. 2851, 11.65%↓) 2464 (vs. 2464, 0.00%) 533817 (vs. 533817, 0.00%) 1 (vs. 1, 0.00%)
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 2678 (vs. 3130, 14.44%↓) 4800 (vs. 4800, 0.00%) 536901 (vs. 536901, 0.00%) 3 (vs. 3, 0.00%)
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 22479 (vs. 24071, 6.61%↓) 100464 (vs. 100464, 0.00%) 361989 (vs. 361989, 0.00%) 87 (vs. 87, 0.00%)
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 32182 (vs. 33516, 3.98%↓) 99152 (vs. 99152, 0.00%) 10396549 (vs. 10396549, 0.00%) 147 (vs. 147, 0.00%)
DeepLabV3_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 30433 (vs. 34492, 11.77%↓) 119792 (vs. 119792, 0.00%) 2923141 (vs. 2923141, 0.00%) 144 (vs. 144, 0.00%)
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 47125 (vs. 51778, 8.99%↓) 260256 (vs. 260256, 0.00%) 5206533 (vs. 5206533, 0.00%) 148 (vs. 148, 0.00%)
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 18206 (vs. 22011, 17.29%↓) 66256 (vs. 66256, 0.00%) 17020165 (vs. 17020165, 0.00%) 79 (vs. 79, 0.00%)
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 29964 (vs. 34946, 14.26%↓) 100048 (vs. 100048, 0.00%) 14134149 (vs. 14134149, 0.00%) 136 (vs. 136, 0.00%)
MobileNetV2_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 55231 (vs. 55716, 0.87%↓) 325280 (vs. 325280, 0.00%) 3994885 (vs. 3994885, 0.00%) 213 (vs. 213, 0.00%)
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 39472 (vs. 47531, 16.96%↓) 123312 (vs. 123312, 0.00%) 18341637 (vs. 18341637, 0.00%) 223 (vs. 223, 0.00%)
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 16149 (vs. 19236, 16.05%↓) 47808 (vs. 47808, 0.00%) 5150469 (vs. 5150469, 0.00%) 79 (vs. 79, 0.00%)
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 80608 (vs. 88065, 8.47%↓) 39616 (vs. 39616, 0.00%) 99973253 (vs. 99973253, 0.00%) 1786 (vs. 1786, 0.00%)
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 74156 (vs. 88433, 16.14%↓) 40016 (vs. 40016, 0.00%) 98485125 (vs. 98485125, 0.00%) 1762 (vs. 1762, 0.00%)
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 253250 (vs. 265317, 4.55%↓) 3414288 (vs. 3414288, 0.00%) 29819397 (vs. 29819397, 0.00%) 2136 (vs. 2136, 0.00%)
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 106182 (vs. 123614, 14.10%↓) 141760 (vs. 141760, 0.00%) 169886636 (vs. 169886636, 0.00%) 439 (vs. 439, 0.00%)
MiniLML12H384Uncased(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 38371 (vs. 43415, 11.62%↓) 33600 (vs. 33600, 0.00%) 219458607 (vs. 219458607, 0.00%) 342 (vs. 342, 0.00%)
GPT2_117M_TF_1X4XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 42210 (vs. 58130, 27.39%↓) 18784 (vs. 18784, 0.00%) 992528404 (vs. 992528404, 0.00%) 330 (vs. 330, 0.00%)
GPT2_117M_TF_1X1XI32(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 43830 (vs. 48372, 9.39%↓) 11312 (vs. 11312, 0.00%) 992523156 (vs. 992523156, 0.00%) 355 (vs. 355, 0.00%)
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 42347 (vs. 47925, 11.64%↓) 33968 (vs. 33968, 0.00%) 875846207 (vs. 875846207, 0.00%) 346 (vs. 346, 0.00%)
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 56055 (vs. 51126, 9.64%↑) 38112 (vs. 38112, 0.00%) 1336017279 (vs. 1336017279, 0.00%) 678 (vs. 678, 0.00%)
EfficientNetV2STF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] 91127 (vs. 107161, 14.96%↓) 841528 (vs. 841528, 0.00%) 165164692 (vs. 165164692, 0.00%) 276 (vs. 276, 0.00%)
MiniLML12H384Uncased(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] 23624 (vs. 33224, 28.89%↓) 184528 (vs. 184528, 0.00%) 134119041 (vs. 134119041, 0.00%) 185 (vs. 185, 0.00%)
BertForMaskedLMTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] 33900 (vs. 36808, 7.90%↓) 264548 (vs. 264548, 0.00%) 534034036 (vs. 534034036, 0.00%) 188 (vs. 188, 0.00%)
BertLargeTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] 29703 (vs. 33381, 11.02%↓) 168052 (vs. 168052, 0.00%) 1336126133 (vs. 1336126133, 0.00%) 365 (vs. 365, 0.00%)
matmul_3456x1024x2048_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] 1650 (vs. 1772, 6.88%↓) 30384 (vs. 30384, 0.00%) 42579 (vs. 42579, 0.00%) 1 (vs. 1, 0.00%)
matmul_3456x1024x2048_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] 1759 (vs. 2207, 20.30%↓) 44912 (vs. 44912, 0.00%) 57107 (vs. 57107, 0.00%) 1 (vs. 1, 0.00%)
matmul_2560x2560x2560_f16t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] 1467 (vs. 1790, 18.04%↓) 28344 (vs. 28344, 0.00%) 40475 (vs. 40475, 0.00%) 1 (vs. 1, 0.00%)
matmul_2560x2560x2560_f32t_tile_config_default(linalg) [cuda-sm_80-linux_gnu-cuda][ukernel,matmul,compile-stats] 2136 (vs. 2344, 8.87%↓) 41284 (vs. 41284, 0.00%) 53415 (vs. 53415, 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] 2195 (vs. 2778, 20.99%↓) 85956 (vs. 85956, 0.00%) 98087 (vs. 98087, 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] 2057 (vs. 2700, 23.81%↓) 88832 (vs. 88832, 0.00%) 101027 (vs. 101027, 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] 2737 (vs. 3094, 11.54%↓) 84036 (vs. 84036, 0.00%) 96231 (vs. 96231, 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] 2074 (vs. 2569, 19.27%↓) 51016 (vs. 51016, 0.00%) 63210 (vs. 63210, 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] 851 (vs. 1034, 17.70%↓) 9004 (vs. 9004, 0.00%) 28085 (vs. 28085, 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] 873 (vs. 1201, 27.31%↓) 9748 (vs. 9748, 0.00%) 28833 (vs. 28833, 0.00%) 2 (vs. 2, 0.00%)
MiniLML12H384Uncased(stablehlo) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 32749 (vs. 34286, 4.48%↓) 55792 (vs. 55792, 0.00%) 133982193 (vs. 133982193, 0.00%) 185 (vs. 185, 0.00%)
DeepLabV3_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 18553 (vs. 20306, 8.63%↓) 42768 (vs. 42768, 0.00%) 2822215 (vs. 2822215, 0.00%) 79 (vs. 79, 0.00%)
EfficientNet_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 39276 (vs. 48416, 18.88%↓) 188816 (vs. 188816, 0.00%) 5109767 (vs. 5109767, 0.00%) 89 (vs. 89, 0.00%)
MobileBertSquad_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 62087 (vs. 67988, 8.68%↓) 50432 (vs. 50432, 0.00%) 98363143 (vs. 98363143, 0.00%) 679 (vs. 679, 0.00%)
MobileBertSquad_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 366650 (vs. 379221, 3.31%↓) 3537584 (vs. 3537584, 0.00%) 29788423 (vs. 29788423, 0.00%) 1053 (vs. 1053, 0.00%)
MobileNetV1_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 14687 (vs. 18584, 20.97%↓) 51488 (vs. 51488, 0.00%) 16971271 (vs. 16971271, 0.00%) 65 (vs. 65, 0.00%)
MobileNetV2_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 49368 (vs. 57374, 13.95%↓) 217328 (vs. 217328, 0.00%) 3865095 (vs. 3865095, 0.00%) 144 (vs. 144, 0.00%)
PersonDetect_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 17776 (vs. 19261, 7.71%↓) 59520 (vs. 59520, 0.00%) 314311 (vs. 314311, 0.00%) 60 (vs. 60, 0.00%)
EfficientNet_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 52514 (vs. 56048, 6.31%↓) 393668 (vs. 393668, 0.00%) 5314631 (vs. 5314631, 0.00%) 89 (vs. 89, 0.00%)
MobileBertSquad_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 428587 (vs. 427918, 0.16%↑) 3825444 (vs. 3825444, 0.00%) 30076295 (vs. 30076295, 0.00%) 1053 (vs. 1053, 0.00%)
PersonDetect_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 21904 (vs. 23518, 6.86%↓) 125236 (vs. 125236, 0.00%) 379975 (vs. 379975, 0.00%) 60 (vs. 60, 0.00%)
MobileNetV2_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 58903 (vs. 60609, 2.81%↓) 330176 (vs. 330176, 0.00%) 3977927 (vs. 3977927, 0.00%) 144 (vs. 144, 0.00%)
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 18970 (vs. 20582, 7.83%↓) 56384 (vs. 56384, 0.00%) 2835845 (vs. 2835845, 0.00%) 79 (vs. 79, 0.00%)
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 61251 (vs. 71131, 13.89%↓) 33856 (vs. 33856, 0.00%) 98346565 (vs. 98346565, 0.00%) 679 (vs. 679, 0.00%)
GPT2_117M_TF_1X4XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 32387 (vs. 41668, 22.27%↓) 20208 (vs. 20208, 0.00%) 652735444 (vs. 652735444, 0.00%) 221 (vs. 221, 0.00%)
GPT2_117M_TF_1X1XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 30239 (vs. 36510, 17.18%↓) 8992 (vs. 8992, 0.00%) 652720532 (vs. 652720532, 0.00%) 246 (vs. 246, 0.00%)
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 295409 (vs. 296452, 0.35%↓) 4939360 (vs. 4939360, 0.00%) 31190149 (vs. 31190149, 0.00%) 1053 (vs. 1053, 0.00%)
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 99678 (vs. 112175, 11.14%↓) 819952 (vs. 819952, 0.00%) 88844933 (vs. 88844933, 0.00%) 255 (vs. 255, 0.00%)
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] 26410 (vs. 28952, 8.78%↓) 50848 (vs. 50848, 0.00%) 2844869 (vs. 2844869, 0.00%) 144 (vs. 144, 0.00%)
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] 77103 (vs. 79953, 3.56%↓) 21840 (vs. 21840, 0.00%) 98466565 (vs. 98466565, 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] 40659 (vs. 48390, 15.98%↓) 11536 (vs. 11536, 0.00%) 992496276 (vs. 992496276, 0.00%) 330 (vs. 330, 0.00%)
GPT2_117M_TF_1X1XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] 44140 (vs. 48047, 8.13%↓) 9136 (vs. 9136, 0.00%) 992496084 (vs. 992496084, 0.00%) 355 (vs. 355, 0.00%)
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] 235622 (vs. 244042, 3.45%↓) 1800576 (vs. 1800576, 0.00%) 28205381 (vs. 28205381, 0.00%) 2136 (vs. 2136, 0.00%)
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] 73321 (vs. 79994, 8.34%↓) 121824 (vs. 121824, 0.00%) 88135429 (vs. 88135429, 0.00%) 375 (vs. 375, 0.00%)
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] 21306 (vs. 24789, 14.05%↓) 41008 (vs. 41008, 0.00%) 2835013 (vs. 2835013, 0.00%) 144 (vs. 144, 0.00%)
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] 71122 (vs. 77632, 8.39%↓) 22064 (vs. 22064, 0.00%) 98466821 (vs. 98466821, 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] 39146 (vs. 49260, 20.53%↓) 10736 (vs. 10736, 0.00%) 992495444 (vs. 992495444, 0.00%) 330 (vs. 330, 0.00%)
GPT2_117M_TF_1X1XI32(stablehlo) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] 37578 (vs. 44811, 16.14%↓) 8672 (vs. 8672, 0.00%) 992495636 (vs. 992495636, 0.00%) 355 (vs. 355, 0.00%)
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] 229747 (vs. 240727, 4.56%↓) 1808112 (vs. 1808112, 0.00%) 28212933 (vs. 28212933, 0.00%) 2136 (vs. 2136, 0.00%)
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] 68391 (vs. 71264, 4.03%↓) 124384 (vs. 124384, 0.00%) 88137989 (vs. 88137989, 0.00%) 375 (vs. 375, 0.00%)
matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 901 (vs. 1181, 23.71%↓) 2464 (vs. 2464, 0.00%) 271353 (vs. 271353, 0.00%) 1 (vs. 1, 0.00%)
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 978 (vs. 1196, 18.23%↓) 3872 (vs. 3872, 0.00%) 272761 (vs. 272761, 0.00%) 1 (vs. 1, 0.00%)
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 825 (vs. 1020, 19.12%↓) 2368 (vs. 2368, 0.00%) 533433 (vs. 533433, 0.00%) 1 (vs. 1, 0.00%)
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 931 (vs. 1073, 13.23%↓) 3088 (vs. 3088, 0.00%) 534137 (vs. 534137, 0.00%) 1 (vs. 1, 0.00%)
matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] 1879 (vs. 2387, 21.28%↓) 3504 (vs. 3504, 0.00%) 273093 (vs. 273093, 0.00%) 2 (vs. 2, 0.00%)
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] 2294 (vs. 2484, 7.65%↓) 4528 (vs. 4528, 0.00%) 274693 (vs. 274693, 0.00%) 4 (vs. 4, 0.00%)
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] 2319 (vs. 2611, 11.18%↓) 2368 (vs. 2368, 0.00%) 533433 (vs. 533433, 0.00%) 1 (vs. 1, 0.00%)
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] 2633 (vs. 2879, 8.54%↓) 3360 (vs. 3360, 0.00%) 535109 (vs. 535109, 0.00%) 3 (vs. 3, 0.00%)
matmul_1x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] 1393 (vs. 1524, 8.60%↓) 4144 (vs. 4144, 0.00%) 273733 (vs. 273733, 0.00%) 2 (vs. 2, 0.00%)
matmul_256x256x2048_i8_i4_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] 1695 (vs. 2157, 21.42%↓) 6496 (vs. 6496, 0.00%) 276677 (vs. 276677, 0.00%) 4 (vs. 4, 0.00%)
matmul_1x256x2048_i8_i8_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] 1897 (vs. 2217, 14.43%↓) 2640 (vs. 2640, 0.00%) 533689 (vs. 533689, 0.00%) 1 (vs. 1, 0.00%)
matmul_256x256x2048_i8_i8_i32_tile_config_default(linalg) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] 2113 (vs. 2654, 20.38%↓) 4352 (vs. 4352, 0.00%) 536069 (vs. 536069, 0.00%) 3 (vs. 3, 0.00%)
MobileBertSquad_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][default-flags,compile-stats] 56304 (vs. 66762, 15.66%↓) 257480 (vs. 257480, 0.00%) 98583213 (vs. 98583213, 0.00%) 679 (vs. 679, 0.00%)
MobileBertSquad_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] 59194 (vs. 72506, 18.36%↓) 257480 (vs. 257480, 0.00%) 98583213 (vs. 98583213, 0.00%) 679 (vs. 679, 0.00%)
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] 65144 (vs. 67564, 3.58%↓) 148236 (vs. 148236, 0.00%) 98473965 (vs. 98473965, 0.00%) 679 (vs. 679, 0.00%)
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,demote-f32-to-f16,compile-stats] 95815 (vs. 113752, 15.77%↓) 3178840 (vs. 3178840, 0.00%) 53160687 (vs. 53160687, 0.00%) 703 (vs. 703, 0.00%)
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] 190894 (vs. 203065, 5.99%↓) 7145960 (vs. 7145960, 0.00%) 33672202 (vs. 33672202, 0.00%) 1053 (vs. 1053, 0.00%)
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,compile-stats] 58692 (vs. 63481, 7.54%↓) 148220 (vs. 148220, 0.00%) 98475757 (vs. 98475757, 0.00%) 679 (vs. 679, 0.00%)
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,demote-f32-to-f16,compile-stats] 74022 (vs. 76643, 3.42%↓) 3180856 (vs. 3180856, 0.00%) 53169839 (vs. 53169839, 0.00%) 703 (vs. 703, 0.00%)
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,compile-stats] 192041 (vs. 200915, 4.42%↓) 7144540 (vs. 7144540, 0.00%) 33657930 (vs. 33657930, 0.00%) 1053 (vs. 1053, 0.00%)
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,repeated-kernel,compile-stats] 104095 (vs. 118419, 12.10%↓) 148220 (vs. 148220, 0.00%) 99696621 (vs. 99696621, 0.00%) 679 (vs. 679, 0.00%)
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,repeated-kernel,demote-f32-to-f16,compile-stats] 131354 (vs. 140545, 6.54%↓) 3180856 (vs. 3180856, 0.00%) 54433903 (vs. 54433903, 0.00%) 703 (vs. 703, 0.00%)
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,repeated-kernel,compile-stats] 334133 (vs. 353022, 5.35%↓) 7144540 (vs. 7144540, 0.00%) 35551242 (vs. 35551242, 0.00%) 1053 (vs. 1053, 0.00%)
MobileNetV2_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] 17313 (vs. 19518, 11.30%↓) 197045 (vs. 197045, 0.00%) 14192638 (vs. 14192638, 0.00%) 171 (vs. 171, 0.00%)
MobileNetV3Small_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] 26455 (vs. 31139, 15.04%↓) 288181 (vs. 288181, 0.00%) 10519166 (vs. 10519166, 0.00%) 208 (vs. 208, 0.00%)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment