Confused: TVM vs TF, performance compare


#1

My cuda info:

cuda: 9.0
cublas: 9.0
cudnn: 7.0

I run resnet50(2242243) using TVM and TF at the same computer, time result is as follows:

  1. TVM: 3.5ms
  2. TF(1.9.0): 2ms

I wonder to know why TF is faster than TVM so much?


#2

Can you share more details about your TVM setup (e.g., are you using a cuda target or cuda -libs=cudnn, the model of the GPU, etc…)? You may be able to improve the performance by tuning for your specific GPU.


#3

lspci的结果:

VGA compatible controller: NVIDIA Corporation GM200 [GeForce GTX TITAN X] (rev a1)

when compiling TVM, I open USE_CUDA and USE_CUDNN switch.

can you help me to analyze the performance reason?


#4

Does print the cuDNN profiling results the first time you run inference (just to verify that the JIT compilation to cuDNN is happening)?