Home
last modified time | relevance | path

Searched hist:"39532 cebecbb2d92b9731aa00f651c10d4db5920" (Results 1 – 1 of 1) sorted by relevance

/libCEED/backends/cuda-gen/
H A Dceed-cuda-gen-operator.cdiff 39532cebecbb2d92b9731aa00f651c10d4db5920 Tue Sep 07 21:59:08 UTC 2021 Jed Brown <jed@jedbrown.org> backends/cuda-gen: use occupancy to calculate launch sizes

Choose sizes that actually fit while being big enough to amortize thread
block overhead and choosing sizes that permit high occupancy.

https://developer.nvidia.com/blog/cuda-pro-tip-occupancy-api-simplifies-launch-configuration/