Skip to content

Instantly share code, notes, and snippets.

@iree-github-actions-bot

iree-github-actions-bot/iree-full-benchmark-result-206.md

Created June 8, 2021 19:55
Show Gist options
  • Save iree-github-actions-bot/200e32c9f8e429124e28bc7d26669663 to your computer and use it in GitHub Desktop.
Save iree-github-actions-bot/200e32c9f8e429124e28bc7d26669663 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
iree-full-benchmark-result-206.md

Full Benchmark Summary

Similar Benchmarks

Benchmark Name Average Latency (ms) Median Latency (ms) Latency Standard Deviation (ms)
MobileNetV2 [fp32,imagenet] (TensorFlow) kernel-execution with IREE-Vulkan @ SM-G980F (GPU-Mali-G77) 17 17 0
MobileNetV2 [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) 869 868 7
MobileNetV2 [fp32,imagenet] (TensorFlow) 1-thread,little-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) 1246 1252 21
MobileNetV2 [fp32,imagenet] (TensorFlow) full-inference with IREE-Vulkan @ SM-G980F (GPU-Mali-G77) 86 87 4
MobileNetV2 [fp32,imagenet] (TensorFlow) 3-thread,big-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) 190 190 5
MobileNetV2 [fp32,imagenet] (TensorFlow) 1-thread,big-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) 140 140 2
MobileNetV2 [fp32,imagenet] (TensorFlow) little-core,full-inference with IREE-Dylib-Sync @ SM-G980F (CPU-ARMv8.2-A) 1252 1254 6
MobileNetV2 [fp32,imagenet] (TensorFlow) big-core,full-inference with IREE-Dylib-Sync @ SM-G980F (CPU-ARMv8.2-A) 140 141 2
MobileNetV2 [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-VMVX @ SM-G980F (CPU-ARMv8.2-A) 63484 63433 155
MobileNetV3Small [fp32,imagenet] (TensorFlow) kernel-execution with IREE-Vulkan @ SM-G980F (GPU-Mali-G77) 20 20 1
MobileNetV3Small [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) 314 313 3
MobileNetV3Small [fp32,imagenet] (TensorFlow) 1-thread,little-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) 373 373 1
MobileNetV3Small [fp32,imagenet] (TensorFlow) full-inference with IREE-Vulkan @ SM-G980F (GPU-Mali-G77) 80 80 2
MobileNetV3Small [fp32,imagenet] (TensorFlow) 3-thread,big-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) 77 77 1
MobileNetV3Small [fp32,imagenet] (TensorFlow) 1-thread,big-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) 46 46 0
MobileNetV3Small [fp32,imagenet] (TensorFlow) little-core,full-inference with IREE-Dylib-Sync @ SM-G980F (CPU-ARMv8.2-A) 372 373 4
MobileNetV3Small [fp32,imagenet] (TensorFlow) big-core,full-inference with IREE-Dylib-Sync @ SM-G980F (CPU-ARMv8.2-A) 46 46 1
MobileNetV3Small [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-VMVX @ SM-G980F (CPU-ARMv8.2-A) 16929 16941 59
MobileNetV2 [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) 1002 1011 55
MobileNetV2 [fp32,imagenet] (TensorFlow) 1-thread,little-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) 1328 1328 5
MobileNetV2 [fp32,imagenet] (TensorFlow) 3-thread,big-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) 241 243 16
MobileNetV2 [fp32,imagenet] (TensorFlow) 1-thread,big-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) 170 170 0
MobileNetV2 [fp32,imagenet] (TensorFlow) little-core,full-inference with IREE-Dylib-Sync @ Pixel-4 (CPU-ARMv8.2-A) 1330 1329 6
MobileNetV2 [fp32,imagenet] (TensorFlow) big-core,full-inference with IREE-Dylib-Sync @ Pixel-4 (CPU-ARMv8.2-A) 211 210 1
MobileNetV2 [fp32,imagenet] (TensorFlow) full-inference with IREE-Vulkan @ Pixel-4 (GPU-Adreno-640) 74 74 0
MobileNetV2 [fp32,imagenet] (TensorFlow) kernel-execution with IREE-Vulkan @ Pixel-4 (GPU-Adreno-640) 70 70 1
MobileNetV2 [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-VMVX @ Pixel-4 (CPU-ARMv8.2-A) 71520 71505 46
MobileNetV3Small [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) 431 434 31
MobileNetV3Small [fp32,imagenet] (TensorFlow) 1-thread,little-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) 386 385 3
MobileNetV3Small [fp32,imagenet] (TensorFlow) 3-thread,big-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) 118 116 10
MobileNetV3Small [fp32,imagenet] (TensorFlow) 1-thread,big-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) 51 51 0
MobileNetV3Small [fp32,imagenet] (TensorFlow) little-core,full-inference with IREE-Dylib-Sync @ Pixel-4 (CPU-ARMv8.2-A) 388 388 2
MobileNetV3Small [fp32,imagenet] (TensorFlow) big-core,full-inference with IREE-Dylib-Sync @ Pixel-4 (CPU-ARMv8.2-A) 61 61 0
MobileNetV3Small [fp32,imagenet] (TensorFlow) full-inference with IREE-Vulkan @ Pixel-4 (GPU-Adreno-640) 38 38 0
MobileNetV3Small [fp32,imagenet] (TensorFlow) kernel-execution with IREE-Vulkan @ Pixel-4 (GPU-Adreno-640) 35 34 1
MobileNetV3Small [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-VMVX @ Pixel-4 (CPU-ARMv8.2-A) 19098 19098 21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment