This is an archive of the discontinued LLVM Phabricator instance.

[mlir][sparse][python] add an "exhaustive" sparse test using python
ClosedPublic

Authored by aartbik on Aug 11 2021, 7:00 PM.

Details

Summary

Using the python API to easily set up sparse kernels, this test
exhaustively builds, compilers, and runs SpMM for all annotations
on a sparse tensor, making sure every version generates the correct
result. This test also illustrates using the python API to set up
a sparse kernel and sparse compilation.

Diff Detail

Event Timeline

aartbik created this revision.Aug 11 2021, 7:00 PM
aartbik requested review of this revision.Aug 11 2021, 7:00 PM
bixia accepted this revision.Aug 12 2021, 9:29 AM
bixia added inline comments.
mlir/test/python/dialects/sparse_tensor/test_SpMM.py
18–21

I don't see any use of this routine?

This revision is now accepted and ready to land.Aug 12 2021, 9:29 AM
aartbik marked an inline comment as done.Aug 12 2021, 9:44 AM
aartbik added inline comments.
mlir/test/python/dialects/sparse_tensor/test_SpMM.py
18–21

It is an idiom that is mandatory for the MLIR python tests (see other files).
The use is very hidden at L130 ;-)

This revision was automatically updated to reflect the committed changes.
aartbik marked an inline comment as done.