Dear all,
Is anybody working on CUDA launch bounds support?
On PTX level, attribute((launch_bounds(MAX_THREADS_PER_BLOCK, MIN_BLOCKS_PER_MP))) should be emitted into .maxntid / .minnctapersm specification.
Thanks,
- D.
Dear all,
Is anybody working on CUDA launch bounds support?
On PTX level, attribute((launch_bounds(MAX_THREADS_PER_BLOCK, MIN_BLOCKS_PER_MP))) should be emitted into .maxntid / .minnctapersm specification.
Thanks,
Yes, this is supported through metadata. An example usage of these annotations is given in the test/CodeGen/NVPTX/annotations.ll unit test. I’ll try to remember to add this to the NVPTX documentation I’m putting together at http://llvm.org/docs/NVPTXUsage.html.
Wow, great, thanks! I will try to try it.
2013/4/2 Justin Holewinski <justin.holewinski@gmail.com>