as4230 commented on PR #19497: URL: https://github.com/apache/tvm/pull/19497#issuecomment-4366309914
@tlopex Thanks for the feedback and telling me your preferences. I reworked the PR. The generic topi.scatter_elements and topi.scatter_nd are untouched, GPU lowering lives in topi/gpu/scatter_elements.py and topi/gpu/scatter_nd.py with explicit blockIdx/threadIdx bindings, and dispatch happens in legalize_ops/manipulate.py. I also added a CUDA compile/build regression tests for both ops next to the existing scatter tests in test_transform_legalize_ops_manipulate.py. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
