[PATCH] D11926: [NVPTX] Use 32-bit divides instead of 64-bit divides where possible

[Jingyue Wu via llvm-commits]

jingyue added a comment.

Does any Eigen3 kernel (https://bitbucket.org/eigen/eigen/src/890ac1744b090c8de30aba2a33f4393e049d1559/unsupported/Eigen/CXX11/src/Tensor/?at=default) benefit from this improvement? If so, we can report some numbers there, so that people can understand how important this is for real-world CUDA programs.

Also, can you come up with some llc tests?

Thanks!


http://reviews.llvm.org/D11926