masahi
Re:Prefix sum on portable compute shaders
on Wednesday December 01, 2021 @07:38AM (#29403108)
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.
Re:Tensor Compilers: Comparing PlaidML, Tensor Comprehensions, and TVM
on Tuesday May 22, 2018 @12:44AM (#17123779)
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/...
Re:Tensor Compilers: Comparing PlaidML, Tensor Comprehensions, and TVM
on Monday May 21, 2018 @08:38PM (#17122962)
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...