Skip to content

Instantly share code, notes, and snippets.

Show Gist options
  • Save iree-github-actions-bot/31fa819a022e5f819bf2eb1174b16ba2 to your computer and use it in GitHub Desktop.
Save iree-github-actions-bot/31fa819a022e5f819bf2eb1174b16ba2 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] 740.539 (1.0X) 273.180 (2.7X) 222.451 (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] 7.018 (1.0X) 9.262 (0.8X) 8.534 (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] 36.063 (1.0X) 36.106 (1.0X) 34.395 (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] 5.853 (1.0X) 10.989 (0.5X) 5.029 (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] 9.273 (1.0X) 8.439 (1.1X) 8.461 (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] 11.074 (1.0X) 9.018 (1.2X) 8.884 (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] 12.026 (1.0X) 15.330 (0.8X) 13.743 (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] 33.528 (1.0X) 65.189 (0.5X) 61.186 (0.5X)
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] 33.842 (1.0X) 65.304 (0.5X) 61.402 (0.6X)
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] 69.133 (1.0X) 133.864 (0.5X) 64.118 (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] 4.949 (1.0X) 5.316 (0.9X) 4.578 (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] 3.789 (1.0X) 5.338 (0.7X) 4.885 (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] 5.930 (1.0X) 9.572 (0.6X) 5.414 (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] 2.889 (1.0X) 3.364 (0.9X) 2.830 (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] 8.502 (1.0X) 10.990 (0.8X) 9.888 (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] 0.787 (1.0X) 1.381 (0.6X) 0.657 (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] 4.230 (1.0X) 5.870 (0.7X) 5.288 (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] 7.559 (1.0X) 7.546 (1.0X) 7.553 (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] 6.674 (1.0X) 13.288 (0.5X) 1.810 (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] 218.617 (1.0X) 138.033 (1.6X) 108.506 (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] 32.202 (1.0X) 36.179 (0.9X) 30.201 (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] 273.440 (1.0X) 258.471 (1.1X) 229.938 (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] 26.898 (1.0X) 51.473 (0.5X) 13.094 (2.1X)
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] 70.271 (1.0X) 38.963 (1.8X) 39.685 (1.8X)
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] 89.146 (1.0X) 42.257 (2.1X) 42.014 (2.1X)
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] 79.517 (1.0X) 78.185 (1.0X) 59.160 (1.3X)
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] 180.696 (1.0X) 248.075 (0.7X) 186.244 (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] 182.660 (1.0X) 252.987 (0.7X) 192.808 (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] 519.849 (1.0X) 1087.256 (0.5X) 244.514 (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] 25.575 (1.0X) 22.637 (1.1X) 18.060 (1.4X)
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] 11.811 (1.0X) 14.965 (0.8X) 11.394 (1.0X)
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] 21.631 (1.0X) 42.320 (0.5X) 11.907 (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] 2.815 (1.0X) 3.277 (0.9X) 2.719 (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] 34.510 (1.0X) 39.413 (0.9X) 31.751 (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] 0.716 (1.0X) 1.302 (0.6X) 0.579 (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] 17.882 (1.0X) 23.787 (0.8X) 19.620 (0.9X)
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] 0.055 (1.0X) 0.055 (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] 0.049 (1.0X) 0.226 (0.2X) 0.022 (2.3X)

Regressed Latencies 🚩

Benchmark Name Average Latency (ms) Median Latency (ms) Latency Standard Deviation (ms)
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] 0.049 (vs. 0.040, 21.19%↑) 0.049 0.000

Similar Latencies

Benchmark Name Average Latency (ms) Median Latency (ms) Latency Standard Deviation (ms)
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] 740.539 (vs. 716.955, 3.29%↑) 716.455 44.740
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] 11.394 (vs. 11.748, 3.02%↓) 11.388 0.078
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] 4.885 (vs. 5.034, 2.96%↓) 4.877 0.017
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] 13.743 (vs. 14.157, 2.92%↓) 13.674 0.163
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] 25.575 (vs. 24.942, 2.54%↑) 25.562 0.221
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] 4.949 (vs. 4.836, 2.34%↑) 4.946 0.040
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] 6.674 (vs. 6.833, 2.32%↓) 6.672 0.011
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] 222.451 (vs. 227.344, 2.15%↓) 222.076 2.192
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] 15.330 (vs. 15.661, 2.12%↓) 15.267 0.119
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] 273.180 (vs. 278.607, 1.95%↓) 273.532 2.205
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] 8.439 (vs. 8.591, 1.77%↓) 8.389 0.096
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] 38.963 (vs. 39.653, 1.74%↓) 38.447 1.265
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] 5.288 (vs. 5.377, 1.66%↓) 5.286 0.019
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] 5.338 (vs. 5.425, 1.60%↓) 5.337 0.019
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] 9.888 (vs. 10.043, 1.55%↓) 9.875 0.036
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] 2.815 (vs. 2.773, 1.53%↑) 2.821 0.021
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] 8.461 (vs. 8.584, 1.43%↓) 8.419 0.092
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] 3.364 (vs. 3.412, 1.40%↓) 3.358 0.025
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] 17.882 (vs. 17.636, 1.39%↑) 17.905 0.091
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] 1.381 (vs. 1.399, 1.33%↓) 1.383 0.009
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] 108.506 (vs. 107.114, 1.30%↑) 108.219 1.437
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] 4.578 (vs. 4.637, 1.28%↓) 4.572 0.023
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] 33.528 (vs. 33.962, 1.28%↓) 33.153 0.824
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] 14.965 (vs. 15.152, 1.23%↓) 14.983 0.130
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] 33.842 (vs. 34.253, 1.20%↓) 33.431 0.856
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] 8.884 (vs. 8.987, 1.15%↓) 8.848 0.090
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] 5.414 (vs. 5.474, 1.08%↓) 5.412 0.018
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] 273.440 (vs. 276.306, 1.04%↓) 274.851 8.050
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] 5.316 (vs. 5.371, 1.03%↓) 5.311 0.022
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] 39.413 (vs. 39.814, 1.01%↓) 39.195 0.487
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] 5.870 (vs. 5.928, 0.98%↓) 5.868 0.022
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] 9.018 (vs. 9.095, 0.85%↓) 8.963 0.113
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] 0.579 (vs. 0.584, 0.83%↓) 0.579 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] 0.055 (vs. 0.055, 0.81%↑) 0.055 0.000
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] 61.402 (vs. 61.873, 0.76%↓) 61.141 0.593
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] 252.987 (vs. 254.830, 0.72%↓) 251.835 4.712
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] 4.230 (vs. 4.261, 0.71%↓) 4.230 0.013
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] 2.889 (vs. 2.909, 0.69%↓) 2.892 0.012
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] 19.620 (vs. 19.754, 0.68%↓) 19.606 0.101
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] 10.990 (vs. 11.064, 0.67%↓) 10.980 0.046
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] 42.014 (vs. 41.754, 0.62%↑) 41.183 1.768
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] 30.201 (vs. 30.015, 0.62%↑) 30.170 0.184
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] 192.808 (vs. 191.638, 0.61%↑) 191.188 3.448
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] 9.273 (vs. 9.217, 0.61%↑) 8.986 0.474
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] 1765.210 (vs. 1775.430, 0.58%↓) 1765.387 6.835
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] 70.271 (vs. 70.677, 0.57%↓) 70.046 2.692
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] 7870.014 (vs. 7825.248, 0.57%↑) 7861.206 39.037
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] 34.510 (vs. 34.316, 0.56%↑) 34.335 0.415
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] 9.262 (vs. 9.314, 0.55%↓) 9.285 0.042
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] 64.118 (vs. 64.464, 0.54%↓) 63.851 0.486
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] 36.106 (vs. 36.297, 0.53%↓) 35.953 0.424
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] 5.853 (vs. 5.884, 0.52%↓) 5.851 0.015
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] 5.029 (vs. 5.055, 0.51%↓) 5.030 0.009
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] 7.559 (vs. 7.522, 0.50%↑) 7.574 0.036
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] 11.074 (vs. 11.127, 0.48%↓) 10.690 0.637
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] 0.055 (vs. 0.055, 0.47%↓) 0.055 0.000
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] 78.185 (vs. 78.542, 0.45%↓) 77.626 1.164
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] 23.787 (vs. 23.895, 0.45%↓) 23.805 0.157
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] 31.751 (vs. 31.616, 0.43%↑) 31.577 0.378
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] 7.553 (vs. 7.584, 0.41%↓) 7.553 0.034
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] 61.186 (vs. 61.435, 0.40%↓) 61.049 0.499
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] 8.534 (vs. 8.568, 0.40%↓) 8.523 0.041
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] 65.304 (vs. 65.562, 0.39%↓) 64.994 0.583
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] 36.179 (vs. 36.318, 0.38%↓) 36.129 0.239
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, 0.38%↑) 0.055 0.000
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] 34.395 (vs. 34.526, 0.38%↓) 34.154 0.420
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] 180.696 (vs. 181.375, 0.37%↓) 179.357 2.704
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] 39.685 (vs. 39.834, 0.37%↓) 39.051 1.548
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] 22.637 (vs. 22.721, 0.37%↓) 22.551 0.245
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] 65.189 (vs. 65.429, 0.37%↓) 64.810 0.632
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] 79.517 (vs. 79.806, 0.36%↓) 79.302 1.134
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] 248.075 (vs. 248.939, 0.35%↓) 246.797 3.869
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] 26.898 (vs. 26.811, 0.32%↑) 26.880 0.070
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] 7.546 (vs. 7.569, 0.31%↓) 7.547 0.009
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] 218.617 (vs. 219.249, 0.29%↓) 211.060 15.256
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] 3.789 (vs. 3.800, 0.28%↓) 3.786 0.029
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] 2.719 (vs. 2.711, 0.28%↑) 2.719 0.028
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] 258.471 (vs. 259.191, 0.28%↓) 255.960 4.540
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] 2.830 (vs. 2.822, 0.27%↑) 2.827 0.008
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] 8.502 (vs. 8.522, 0.23%↓) 8.483 0.065
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] 11.811 (vs. 11.785, 0.22%↑) 11.778 0.072
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] 182.660 (vs. 182.256, 0.22%↑) 181.333 2.939
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] 10.989 (vs. 11.013, 0.22%↓) 10.990 0.027
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] 5.930 (vs. 5.942, 0.20%↓) 5.925 0.036
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] 59.160 (vs. 59.040, 0.20%↑) 58.708 0.949
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] 69.133 (vs. 69.258, 0.18%↓) 68.798 0.520
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] 3.277 (vs. 3.281, 0.14%↓) 3.281 0.019
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] 7.018 (vs. 7.025, 0.10%↓) 7.015 0.018
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] 89.146 (vs. 89.054, 0.10%↑) 89.447 3.603
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] 0.787 (vs. 0.788, 0.10%↓) 0.787 0.001
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] 138.033 (vs. 137.894, 0.10%↑) 137.564 1.732
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] 42.320 (vs. 42.361, 0.10%↓) 42.281 0.155
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] 0.657 (vs. 0.658, 0.09%↓) 0.657 0.002
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] 51.473 (vs. 51.433, 0.08%↑) 51.416 0.157
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] 244.514 (vs. 244.331, 0.07%↑) 244.123 1.359
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] 21.631 (vs. 21.615, 0.07%↑) 21.623 0.079
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, 0.07%↑) 0.226 0.000
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] 1.810 (vs. 1.809, 0.07%↑) 1.812 0.006
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] 13.094 (vs. 13.085, 0.07%↑) 13.092 0.057
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] 229.938 (vs. 229.796, 0.06%↑) 228.190 3.869
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] 42.257 (vs. 42.232, 0.06%↑) 41.599 1.489
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] 12.026 (vs. 12.033, 0.06%↓) 11.840 0.317
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] 32.202 (vs. 32.184, 0.06%↑) 32.147 0.238
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, 0.06%↑) 0.022 0.000
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] 18.060 (vs. 18.069, 0.05%↓) 17.997 0.159
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] 1087.256 (vs. 1087.822, 0.05%↓) 1086.384 3.625
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] 36.063 (vs. 36.081, 0.05%↓) 35.481 0.921
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] 519.849 (vs. 520.048, 0.04%↓) 518.505 2.510
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] 9.572 (vs. 9.568, 0.04%↑) 9.567 0.021
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] 1.302 (vs. 1.301, 0.04%↑) 1.301 0.001
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] 0.716 (vs. 0.716, 0.03%↑) 0.716 0.000
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] 133.864 (vs. 133.900, 0.03%↓) 133.860 0.959
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] 11.907 (vs. 11.905, 0.01%↑) 11.925 0.082
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] 186.244 (vs. 186.267, 0.01%↓) 185.033 2.880
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] 13.288 (vs. 13.289, 0.01%↓) 13.289 0.011

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] 1139 (vs. 1485, 23.30%↓) 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] 1857 (vs. 1801, 3.11%↑) 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] 949 (vs. 1065, 10.89%↓) 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] 1459 (vs. 1594, 8.47%↓) 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] 24344 (vs. 21988, 10.71%↑) 144544 (vs. 144544, 0.00%) 399493 (vs. 399493, 0.00%) 60 (vs. 60, 0.00%)
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 39825 (vs. 45426, 12.33%↓) 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] 31283 (vs. 32383, 3.40%↓) 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] 57409 (vs. 61935, 7.31%↓) 682752 (vs. 682752, 0.00%) 5603845 (vs. 5603845, 0.00%) 89 (vs. 89, 0.00%)
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 20054 (vs. 23395, 14.28%↓) 175008 (vs. 175008, 0.00%) 17092293 (vs. 17092293, 0.00%) 51 (vs. 51, 0.00%)
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 32430 (vs. 32740, 0.95%↓) 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] 60236 (vs. 70622, 14.71%↓) 568880 (vs. 568880, 0.00%) 4216837 (vs. 4216837, 0.00%) 144 (vs. 144, 0.00%)
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 46603 (vs. 52834, 11.79%↓) 287728 (vs. 287728, 0.00%) 18226245 (vs. 18226245, 0.00%) 124 (vs. 124, 0.00%)
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 20413 (vs. 20240, 0.85%↑) 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] 64709 (vs. 76906, 15.86%↓) 91888 (vs. 91888, 0.00%) 99892293 (vs. 99892293, 0.00%) 703 (vs. 703, 0.00%)
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 66403 (vs. 79053, 16.00%↓) 100448 (vs. 100448, 0.00%) 98413445 (vs. 98413445, 0.00%) 679 (vs. 679, 0.00%)
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 323275 (vs. 343721, 5.95%↓) 6817872 (vs. 6817872, 0.00%) 33068869 (vs. 33068869, 0.00%) 1053 (vs. 1053, 0.00%)
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 99109 (vs. 114140, 13.17%↓) 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] 31901 (vs. 29286, 8.93%↑) 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] 34971 (vs. 41321, 15.37%↓) 27504 (vs. 27504, 0.00%) 652742996 (vs. 652742996, 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] 36684 (vs. 41281, 11.14%↓) 15008 (vs. 15008, 0.00%) 652726804 (vs. 652726804, 0.00%) 246 (vs. 246, 0.00%)
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 35156 (vs. 39592, 11.20%↓) 76768 (vs. 76768, 0.00%) 533839615 (vs. 533839615, 0.00%) 188 (vs. 188, 0.00%)
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,no-dt,compile-stats] 32397 (vs. 40427, 19.86%↓) 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] 1024 (vs. 1293, 20.80%↓) 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] 1789 (vs. 1972, 9.28%↓) 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] 1825 (vs. 2425, 24.74%↓) 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] 2290 (vs. 2776, 17.51%↓) 6432 (vs. 6432, 0.00%) 538501 (vs. 538501, 0.00%) 3 (vs. 3, 0.00%)
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 24719 (vs. 23561, 4.91%↑) 106672 (vs. 106672, 0.00%) 368069 (vs. 368069, 0.00%) 87 (vs. 87, 0.00%)
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 32392 (vs. 37323, 13.21%↓) 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] 29033 (vs. 30640, 5.24%↓) 114416 (vs. 114416, 0.00%) 2917637 (vs. 2917637, 0.00%) 144 (vs. 144, 0.00%)
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 46889 (vs. 56306, 16.72%↓) 269312 (vs. 269312, 0.00%) 5215301 (vs. 5215301, 0.00%) 148 (vs. 148, 0.00%)
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 16755 (vs. 18476, 9.31%↓) 60352 (vs. 60352, 0.00%) 17014213 (vs. 17014213, 0.00%) 79 (vs. 79, 0.00%)
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 32762 (vs. 30667, 6.83%↑) 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] 56277 (vs. 64067, 12.16%↓) 329856 (vs. 329856, 0.00%) 3999301 (vs. 3999301, 0.00%) 213 (vs. 213, 0.00%)
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 42478 (vs. 47642, 10.84%↓) 135552 (vs. 135552, 0.00%) 18353669 (vs. 18353669, 0.00%) 223 (vs. 223, 0.00%)
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 16873 (vs. 15688, 7.55%↑) 44256 (vs. 44256, 0.00%) 5146821 (vs. 5146821, 0.00%) 79 (vs. 79, 0.00%)
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 78950 (vs. 90253, 12.52%↓) 48496 (vs. 48496, 0.00%) 99982021 (vs. 99982021, 0.00%) 1786 (vs. 1786, 0.00%)
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 73814 (vs. 84993, 13.15%↓) 48880 (vs. 48880, 0.00%) 98493893 (vs. 98493893, 0.00%) 1762 (vs. 1762, 0.00%)
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 265271 (vs. 289054, 8.23%↓) 3422160 (vs. 3422160, 0.00%) 29827141 (vs. 29827141, 0.00%) 2136 (vs. 2136, 0.00%)
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 107813 (vs. 124999, 13.75%↓) 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] 32962 (vs. 37105, 11.17%↓) 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] 44140 (vs. 50748, 13.02%↓) 17344 (vs. 17344, 0.00%) 992526804 (vs. 992526804, 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] 40775 (vs. 50401, 19.10%↓) 10272 (vs. 10272, 0.00%) 992522068 (vs. 992522068, 0.00%) 355 (vs. 355, 0.00%)
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 40719 (vs. 49398, 17.57%↓) 38224 (vs. 38224, 0.00%) 875850367 (vs. 875850367, 0.00%) 346 (vs. 346, 0.00%)
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][experimental-flags,dt-only,compile-stats] 48681 (vs. 57047, 14.67%↓) 41568 (vs. 41568, 0.00%) 1336020671 (vs. 1336020671, 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] 1219 (vs. 1499, 18.68%↓) 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] 1822 (vs. 1674, 8.84%↑) 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][default-flags,dt-uk,compile-stats] 2616 (vs. 3010, 13.09%↓) 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] 2690 (vs. 3044, 11.63%↓) 4800 (vs. 4800, 0.00%) 536837 (vs. 536837, 0.00%) 3 (vs. 3, 0.00%)
PersonDetect_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 22434 (vs. 25734, 12.82%↓) 100464 (vs. 100464, 0.00%) 361861 (vs. 361861, 0.00%) 87 (vs. 87, 0.00%)
MobileNetV3Small_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 36505 (vs. 35537, 2.72%↑) 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] 31015 (vs. 32903, 5.74%↓) 119792 (vs. 119792, 0.00%) 2923013 (vs. 2923013, 0.00%) 144 (vs. 144, 0.00%)
EfficientNet_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 45963 (vs. 54933, 16.33%↓) 260256 (vs. 260256, 0.00%) 5206277 (vs. 5206277, 0.00%) 148 (vs. 148, 0.00%)
MobileNetV1_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 18087 (vs. 21458, 15.71%↓) 66256 (vs. 66256, 0.00%) 17020101 (vs. 17020101, 0.00%) 79 (vs. 79, 0.00%)
MobileNetV2_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 30936 (vs. 32751, 5.54%↓) 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] 56622 (vs. 54986, 2.98%↑) 325280 (vs. 325280, 0.00%) 3994693 (vs. 3994693, 0.00%) 213 (vs. 213, 0.00%)
MobileSSD_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 41648 (vs. 47030, 11.44%↓) 123312 (vs. 123312, 0.00%) 18341381 (vs. 18341381, 0.00%) 223 (vs. 223, 0.00%)
PoseNet_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 19081 (vs. 18099, 5.43%↑) 47808 (vs. 47808, 0.00%) 5150341 (vs. 5150341, 0.00%) 79 (vs. 79, 0.00%)
MobileBertSquad_fp16(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 77081 (vs. 90961, 15.26%↓) 39616 (vs. 39616, 0.00%) 99973125 (vs. 99973125, 0.00%) 1786 (vs. 1786, 0.00%)
MobileBertSquad_fp32(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 73710 (vs. 90328, 18.40%↓) 40016 (vs. 40016, 0.00%) 98484933 (vs. 98484933, 0.00%) 1762 (vs. 1762, 0.00%)
MobileBertSquad_int8(tflite) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 257063 (vs. 273382, 5.97%↓) 3414288 (vs. 3414288, 0.00%) 29819269 (vs. 29819269, 0.00%) 2136 (vs. 2136, 0.00%)
EfficientNetV2STF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 104553 (vs. 123768, 15.53%↓) 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] 36028 (vs. 41292, 12.75%↓) 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] 42785 (vs. 53736, 20.38%↓) 18784 (vs. 18784, 0.00%) 992528276 (vs. 992528276, 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] 44304 (vs. 52935, 16.30%↓) 11312 (vs. 11312, 0.00%) 992523092 (vs. 992523092, 0.00%) 355 (vs. 355, 0.00%)
BertForMaskedLMTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 44889 (vs. 52401, 14.34%↓) 33968 (vs. 33968, 0.00%) 875846143 (vs. 875846143, 0.00%) 346 (vs. 346, 0.00%)
BertLargeTF(stablehlo) [x86_64-cascadelake-linux_gnu-llvm_cpu][default-flags,dt-uk,compile-stats] 48585 (vs. 54662, 11.12%↓) 38112 (vs. 38112, 0.00%) 1336017151 (vs. 1336017151, 0.00%) 678 (vs. 678, 0.00%)
EfficientNetV2STF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] 94074 (vs. 97819, 3.83%↓) 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] 25497 (vs. 24888, 2.45%↑) 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] 33564 (vs. 36428, 7.86%↓) 264548 (vs. 264548, 0.00%) 534033972 (vs. 534033972, 0.00%) 188 (vs. 188, 0.00%)
BertLargeTF(stablehlo) [cuda-sm_80-linux_gnu-cuda][default-flags,compile-stats] 28326 (vs. 31024, 8.70%↓) 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] 1654 (vs. 1691, 2.19%↓) 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] 1864 (vs. 2554, 27.02%↓) 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] 1632 (vs. 1654, 1.33%↓) 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] 1753 (vs. 1943, 9.78%↓) 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] 2198 (vs. 2786, 21.11%↓) 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] 2342 (vs. 2568, 8.80%↓) 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] 2694 (vs. 3002, 10.26%↓) 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] 2234 (vs. 2644, 15.51%↓) 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] 898 (vs. 1344, 33.18%↓) 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] 846 (vs. 1057, 19.96%↓) 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] 32110 (vs. 35138, 8.62%↓) 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] 20782 (vs. 18917, 9.86%↑) 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] 42054 (vs. 40785, 3.11%↑) 188816 (vs. 188816, 0.00%) 5109575 (vs. 5109575, 0.00%) 89 (vs. 89, 0.00%)
MobileBertSquad_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 64339 (vs. 72437, 11.18%↓) 50432 (vs. 50432, 0.00%) 98363079 (vs. 98363079, 0.00%) 679 (vs. 679, 0.00%)
MobileBertSquad_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 376347 (vs. 383106, 1.76%↓) 3537584 (vs. 3537584, 0.00%) 29788295 (vs. 29788295, 0.00%) 1053 (vs. 1053, 0.00%)
MobileNetV1_fp32(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 14631 (vs. 15535, 5.82%↓) 51488 (vs. 51488, 0.00%) 16971207 (vs. 16971207, 0.00%) 65 (vs. 65, 0.00%)
MobileNetV2_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 51735 (vs. 52304, 1.09%↓) 217328 (vs. 217328, 0.00%) 3864967 (vs. 3864967, 0.00%) 144 (vs. 144, 0.00%)
PersonDetect_int8(tflite) [riscv_64-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 18090 (vs. 18751, 3.53%↓) 59520 (vs. 59520, 0.00%) 314183 (vs. 314183, 0.00%) 60 (vs. 60, 0.00%)
EfficientNet_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 46176 (vs. 56129, 17.73%↓) 393668 (vs. 393668, 0.00%) 5314439 (vs. 5314439, 0.00%) 89 (vs. 89, 0.00%)
MobileBertSquad_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 438544 (vs. 439117, 0.13%↓) 3825444 (vs. 3825444, 0.00%) 30076167 (vs. 30076167, 0.00%) 1053 (vs. 1053, 0.00%)
PersonDetect_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 20912 (vs. 19827, 5.47%↑) 125236 (vs. 125236, 0.00%) 379847 (vs. 379847, 0.00%) 60 (vs. 60, 0.00%)
MobileNetV2_int8(tflite) [riscv_32-generic-linux_gnu-llvm_cpu][default-flags,compile-stats] 55513 (vs. 60647, 8.47%↓) 330176 (vs. 330176, 0.00%) 3977799 (vs. 3977799, 0.00%) 144 (vs. 144, 0.00%)
DeepLabV3_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 22359 (vs. 22502, 0.64%↓) 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] 57923 (vs. 67525, 14.22%↓) 33856 (vs. 33856, 0.00%) 98346437 (vs. 98346437, 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] 35593 (vs. 40593, 12.32%↓) 20208 (vs. 20208, 0.00%) 652735380 (vs. 652735380, 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] 32168 (vs. 37944, 15.22%↓) 8992 (vs. 8992, 0.00%) 652720468 (vs. 652720468, 0.00%) 246 (vs. 246, 0.00%)
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 299643 (vs. 314949, 4.86%↓) 4939360 (vs. 4939360, 0.00%) 31190085 (vs. 31190085, 0.00%) 1053 (vs. 1053, 0.00%)
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,no-dt,compile-stats] 100974 (vs. 110735, 8.81%↓) 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] 24552 (vs. 24988, 1.74%↓) 50848 (vs. 50848, 0.00%) 2844741 (vs. 2844741, 0.00%) 144 (vs. 144, 0.00%)
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] 72451 (vs. 81144, 10.71%↓) 21840 (vs. 21840, 0.00%) 98466437 (vs. 98466437, 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] 42586 (vs. 48304, 11.84%↓) 11536 (vs. 11536, 0.00%) 992496148 (vs. 992496148, 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] 47850 (vs. 51882, 7.77%↓) 9136 (vs. 9136, 0.00%) 992496020 (vs. 992496020, 0.00%) 355 (vs. 355, 0.00%)
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] 227690 (vs. 250403, 9.07%↓) 1800576 (vs. 1800576, 0.00%) 28205189 (vs. 28205189, 0.00%) 2136 (vs. 2136, 0.00%)
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][default-flags,dt-uk,compile-stats] 78551 (vs. 80351, 2.24%↓) 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] 20810 (vs. 22119, 5.92%↓) 41008 (vs. 41008, 0.00%) 2834885 (vs. 2834885, 0.00%) 144 (vs. 144, 0.00%)
MobileBertSquad_fp32(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] 68303 (vs. 81943, 16.65%↓) 22064 (vs. 22064, 0.00%) 98466693 (vs. 98466693, 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] 43338 (vs. 49772, 12.93%↓) 10736 (vs. 10736, 0.00%) 992495316 (vs. 992495316, 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] 41229 (vs. 50316, 18.06%↓) 8672 (vs. 8672, 0.00%) 992495572 (vs. 992495572, 0.00%) 355 (vs. 355, 0.00%)
MobileBertSquad_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] 228692 (vs. 248626, 8.02%↓) 1808112 (vs. 1808112, 0.00%) 28212741 (vs. 28212741, 0.00%) 2136 (vs. 2136, 0.00%)
Vit_int8(tflite) [armv8.2-a-generic-linux_android29-llvm_cpu][experimental-flags,dt-only,compile-stats] 66950 (vs. 79512, 15.80%↓) 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] 905 (vs. 1040, 12.98%↓) 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] 977 (vs. 1143, 14.52%↓) 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] 827 (vs. 1026, 19.40%↓) 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] 917 (vs. 1192, 23.07%↓) 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] 1982 (vs. 2179, 9.04%↓) 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] 2302 (vs. 2786, 17.37%↓) 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] 2274 (vs. 2732, 16.76%↓) 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] 2440 (vs. 2870, 14.98%↓) 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] 1334 (vs. 1833, 27.22%↓) 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] 1734 (vs. 2009, 13.69%↓) 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] 2081 (vs. 2380, 12.56%↓) 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] 2247 (vs. 2712, 17.15%↓) 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] 55976 (vs. 70507, 20.61%↓) 257480 (vs. 257480, 0.00%) 98583085 (vs. 98583085, 0.00%) 679 (vs. 679, 0.00%)
MobileBertSquad_fp32(tflite) [qualcomm-adreno-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,compile-stats] 65569 (vs. 71745, 8.61%↓) 257480 (vs. 257480, 0.00%) 98583085 (vs. 98583085, 0.00%) 679 (vs. 679, 0.00%)
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] 60345 (vs. 72084, 16.29%↓) 148236 (vs. 148236, 0.00%) 98473901 (vs. 98473901, 0.00%) 679 (vs. 679, 0.00%)
MobileBertSquad_fp16(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,demote-f32-to-f16,compile-stats] 97142 (vs. 106374, 8.68%↓) 3178840 (vs. 3178840, 0.00%) 53160559 (vs. 53160559, 0.00%) 703 (vs. 703, 0.00%)
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][default-flags,compile-stats] 189905 (vs. 211414, 10.17%↓) 7145960 (vs. 7145960, 0.00%) 33672074 (vs. 33672074, 0.00%) 1053 (vs. 1053, 0.00%)
MobileBertSquad_fp32(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,compile-stats] 57255 (vs. 68416, 16.31%↓) 148220 (vs. 148220, 0.00%) 98475629 (vs. 98475629, 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] 72847 (vs. 82803, 12.02%↓) 3180856 (vs. 3180856, 0.00%) 53169775 (vs. 53169775, 0.00%) 703 (vs. 703, 0.00%)
MobileBertSquad_int8(tflite) [arm-valhall-vulkan_android31-vulkan_spirv][experimental-flags,fuse-padding,max-concurrency,compile-stats] 184421 (vs. 213277, 13.53%↓) 7144540 (vs. 7144540, 0.00%) 33657802 (vs. 33657802, 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] 101579 (vs. 118304, 14.14%↓) 148220 (vs. 148220, 0.00%) 99696557 (vs. 99696557, 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] 123062 (vs. 134406, 8.44%↓) 3180856 (vs. 3180856, 0.00%) 54433775 (vs. 54433775, 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] 330425 (vs. 359306, 8.04%↓) 7144540 (vs. 7144540, 0.00%) 35551114 (vs. 35551114, 0.00%) 1053 (vs. 1053, 0.00%)
MobileNetV2_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] 21011 (vs. 19336, 8.66%↑) 189941 (vs. 189941, 0.00%) 14185150 (vs. 14185150, 0.00%) 171 (vs. 171, 0.00%)
MobileNetV3Small_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags,compile-stats] 25305 (vs. 26459, 4.36%↓) 277813 (vs. 277813, 0.00%) 10508286 (vs. 10508286, 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