mboehm7 commented on pull request #1127: URL: https://github.com/apache/systemds/pull/1127#issuecomment-748197271
Just as a side note: these operations are best profiled with more operations, and printing the execution time per operation (simply decomment that in `LibMatrixReorg`) then you'll see that often the variance comes from individual operations (e.g., first 2-3 times due to JIT, or arbitrary ones due to GC). Generally, we try to optimize for the steady state after JIT and without one-time GC influences. Anyway, thanks for inspiring the sparse-sparse improvements. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected]
