New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Look into TVM+sparsity #41

Closed

vvolhejn opened this issue Jun 21, 2022 · 2 comments

Owner

vvolhejn commented Jun 21, 2022

https://tvm.apache.org/docs/how_to/tune_with_autoscheduler/tune_network_arm.html

https://tvm.apache.org/docs/how_to/deploy_models/deploy_sparse.html

Owner Author

vvolhejn commented Jun 24, 2022 •

edited

Loading

https://discuss.tvm.apache.org/t/running-a-cnn-using-sparsity-convertor/7267/7 says there is no performance improvement for CNNs, https://gist.github.com/Wheest/f608b7ce16b0b7c7a3414e950e934033 is the associated self-contained example

https://discuss.tvm.apache.org/t/sparse-conv2d-runs-slower-than-normal-conv2d/11430

Implementation of the optimizations: https://github.com/apache/tvm/tree/main/python/tvm/relay/data_dep_optimization

This is probably the right function to call, as used by the tune_network_arm tutorial: https://github.com/apache/tvm/blob/720e7b1ebd9b789a1100dee7536d0633c7941dd1/python/tvm/topi/sparse/utils.py#L143

relevant PR? apache/tvm#8065

Rewriter
https://github.com/apache/tvm/blob/248ad45c6ab197fbec11512b596c7449db2febe6/src/relay/transforms/convert_sparse_conv2d.cc#L184

Owner Author

vvolhejn commented Jun 24, 2022

Got it to work for dense and inverted_bottleneck models, but for dilated_conv it does nothing (probably only works on 1x1 convs) and is broken for dilated_conv_ib: https://discuss.tvm.apache.org/t/invalid-blocksize-when-trying-to-convert-cnn-to-sparse/13016

vvolhejn closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment