Open srkreddy1238 opened 1 week ago
Integrate implicit call of BYOC preprocessing module into collage tunning module and enable benchmark script for adreno targets.
Benchmark results:
Networks | OpenCL texture | OpenCLML | Collage resnet-18-float32 | 10.58 | 7.21 | 7.29 resnet-18-float16 | 7.05 | 4.56 | 4.86 resnet-34-float32 | 16.26 | 12.42 | 13.07 resnet-34-float16 | 11.35 | 7.35 | 7.97 resnet-50-float32 | 19.19 | 20.86 | 18.91 resnet-50-float16 | 13.39 | 12 | 11.09 (8%) densenet-121-float32 | 25.43 | 17.98 | 13.21 (36%) densenet-121-float16 | 12.38 | 11.01 | 8.72 (26%) inception_v3-float32 | 40.41 | 22.3 | 22.64 inception_v3-float16 | 29.91 | 13.69 | 14.52 mobilenet-float32 | 4.09 | 3.68 | 3.19 (15%) mobilenet-float16 | 2.8 | 2.44 | 2.1 (16%)
Integrate implicit call of BYOC preprocessing module into collage tunning module and enable benchmark script for adreno targets.
Benchmark results:
Networks | OpenCL texture | OpenCLML | Collage resnet-18-float32 | 10.58 | 7.21 | 7.29 resnet-18-float16 | 7.05 | 4.56 | 4.86 resnet-34-float32 | 16.26 | 12.42 | 13.07 resnet-34-float16 | 11.35 | 7.35 | 7.97 resnet-50-float32 | 19.19 | 20.86 | 18.91 resnet-50-float16 | 13.39 | 12 | 11.09 (8%) densenet-121-float32 | 25.43 | 17.98 | 13.21 (36%) densenet-121-float16 | 12.38 | 11.01 | 8.72 (26%) inception_v3-float32 | 40.41 | 22.3 | 22.64 inception_v3-float16 | 29.91 | 13.69 | 14.52 mobilenet-float32 | 4.09 | 3.68 | 3.19 (15%) mobilenet-float16 | 2.8 | 2.44 | 2.1 (16%)