resnet50_v2 cross compilation for Mali GPU shows the following Warning
target = tvm.target.mali()
target_host = 'llvm -target=armv7l-linux-gnueabihf'
Warning:
root@d5a405f6b887:~/workplace/resnet50/tmp# ./compile.py
model: resnet50_v2 , target: opencl -device=mali -model=unknown , target_host: llvm -target=armv7l-linux-gnueabihf , opt_level: 3 , data_shape: (1, 3, 224, 224)
Compiling...
Cannot find config for target=opencl -device=mali -model=unknown, workload=('conv2d', (1, 128, 56, 56, 'float32'), (128, 128, 3, 3, 'float32'), (2, 2), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=mali -model=unknown, workload=('conv2d', (1, 256, 28, 28, 'float32'), (256, 256, 3, 3, 'float32'), (2, 2), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=mali -model=unknown, workload=('conv2d', (1, 512, 14, 14, 'float32'), (512, 512, 3, 3, 'float32'), (2, 2), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Compilation done
Saving files
Files saved
resnet50_v2
Inference performance is 22% slower in comparison to resnet50_v1
Inference Performance on Tinker Board S (ctx = tvm.cl()
):
resnet50_v1 - 490ms
resnet50_v2 - 598ms