Open Xinyu302 opened 2 years ago
Can you give the following command line a try:
--canonicalize --stencil-inlining --cse --canonicalize --stencil-shape-inference --stencil-storage-materialization --stencil-shape-inference --stencil-combine-to-ifelse --cse --canonicalize --convert-stencil-to-std --cse --parallel-loop-tiling='parallel-loop-tile-sizes=128,1,1' --canonicalize --test-gpu-greedy-parallel-loop-mapping --convert-parallel-loops-to-gpu --lower-affine --convert-scf-to-std --gpu-kernel-outlining --cse --canonicalize --stencil-kernel-to-cubin --cse --canonicalize --mlir-disable-threading
Note that the full fastwaves kernel is rather complex. AFAIK it should still work though.
It works, thank you!
I use the latest version of open-earth to run some tests. When I compile 'Laplace.mlir' according to readme in this repo, the result is correct. However, when I use the following command to comile fastwaves.mlir:
It seems that open-earth can't do convert-stencil-to-std to fastwaves.mlir. The output is as follows:
Could you help me analyze where I may make mistakes and give a feasible solution? Thanks very much!