iree-full-benchmark-results-18177.md

Full Benchmark Summary

• @ commit 5afa967c199bea031b68509da2dd7591b49b497b (vs. base ab12a4effa1c59c41a8422daac198b8e34eed65e)
• Pull request
• Build

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%)