masahi · HackerTrans

TVM, similar to IREE, also has a good support for Vulkan. It compiles a tensor DSL written in Python into SPIR-V. AMD is using it in production for running deep learning models on their APU.

https://github.com/apache/tvm

masahi

8 lat temudiscuss

for plaid, I used

plaidbench keras mobilenet

plaidbench keras resnet50

time_evaluator is what tvm/nnvm folks use for benchmark. See their benchmark script here https://github.com/dmlc/nnvm/blob/master/examples/benchmark/...

masahi

8 lat temudiscuss

The TVM results on resnet50 and mobilenet seem a bit off. On GTX 1070 Ti, with an input of size (1, 3, 224, 224)

TVM result

Resnet50 : 100 inference/sec (0.009983 sec per each run)

Mobilenet: 450 inference/sec (0.002220 sec per each run)

PlaidML result

Resnet50 : 107 inference/sec (0.009302 sec per each run)

Mobilenet: 473 inference/sec (0.002112 sec per each run)

My benchmark script for tvm is here https://gist.github.com/masahi/a386c2ce5b5f8c2d9f7af5e09a8d8...

comments