Closed Max191 closed 2 months ago
@ commit 345e194eecf1bbb895deac31f6240d8335354754 (vs. base 52b21f8274f7e62d7c44e4c8b7b2147a00016bc0)
Benchmark Name | Average Latency (ms) | Median Latency (ms) | Latency Standard Deviation (ms) |
---|---|---|---|
MobileBertSquad\_int8(tflite) [arm-valhall-vulkan\_android31-vulkan\_spirv][default-flags] vulkan(none)[full-inference,default-flags] with default @ pixel-6-pro[gpu] | 80.115 (vs. 92.710, 13.59%↓) | 80.196 | 0.479 |
MobileBertSquad\_int8(tflite) [arm-valhall-vulkan\_android31-vulkan\_spirv][experimental-flags,fuse-padding,max-concurrency] vulkan(none)[full-inference,default-flags] with default @ pixel-6-pro[gpu] | 69.120 (vs. 75.448, 8.39%↓) | 69.041 | 0.465 |
GPT2\_117M\_TF\_1X4XI32(stablehlo) [armv8.2-a-generic-linux\_android29-llvm\_cpu][default-flags,dt-uk] local\_sync(embedded\_elf)[full-inference,default-flags] with default @ pixel-6-pro[big-cores] | 27.012 (vs. 28.789, 6.17%↓) | 27.211 | 0.942 |
[Top 3 out of 5 results showed]
No improved or regressed compilation metrics 🏖️
For more information:
Checking out a branch with https://github.com/llvm/llvm-project/pull/95020 to test here in IREE before landing upstream.