[Openmp-commits] [PATCH] D86038: [OpenMP][CUDA] Cache the maximal number of threads per block (per kernel)
Shilei Tian via Phabricator via Openmp-commits
openmp-commits at lists.llvm.org
Sun Aug 16 10:15:53 PDT 2020
tianshilei1992 added inline comments.
================
Comment at: openmp/libomptarget/plugins/cuda/src/rtl.cpp:79
+ /// Maximal number of threads per block for this kernel.
+ int MaxThreadsPerBlock = 0;
+
----------------
tianshilei1992 wrote:
> Do we need to change the front end? This data structure should be generated by the FE, right?
Oh, my bad. It is not. The pointer is replaced during the initialization.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D86038/new/
https://reviews.llvm.org/D86038
More information about the Openmp-commits
mailing list