Author: Shilei Tian Date: 2022-02-16T10:51:45-08:00 New Revision: 9bc22aa5078020bd76d5e4150d39e929c63cc355
URL: https://github.com/llvm/llvm-project/commit/9bc22aa5078020bd76d5e4150d39e929c63cc355 DIFF: https://github.com/llvm/llvm-project/commit/9bc22aa5078020bd76d5e4150d39e929c63cc355.diff LOG: [OpenMP][CUDA] Refine the logic to determine grid size This patch refines the logic to determine grid size as previous method can escape the check of whether `CudaBlocksPerGrid` could be greater than the actual hardware limit. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D119311 (cherry picked from commit f6685f774697c85d6a352dcea013f46a99f9fe31) Added: Modified: openmp/libomptarget/plugins/cuda/src/rtl.cpp Removed: ################################################################################ diff --git a/openmp/libomptarget/plugins/cuda/src/rtl.cpp b/openmp/libomptarget/plugins/cuda/src/rtl.cpp index e17593878b7c7..0ca05f0ec3a0f 100644 --- a/openmp/libomptarget/plugins/cuda/src/rtl.cpp +++ b/openmp/libomptarget/plugins/cuda/src/rtl.cpp @@ -1170,15 +1170,17 @@ class DeviceRTLTy { DP("Using default number of teams %d\n", DeviceData[DeviceId].NumTeams); CudaBlocksPerGrid = DeviceData[DeviceId].NumTeams; } - } else if (TeamNum > DeviceData[DeviceId].BlocksPerGrid) { - DP("Capping number of teams to team limit %d\n", - DeviceData[DeviceId].BlocksPerGrid); - CudaBlocksPerGrid = DeviceData[DeviceId].BlocksPerGrid; } else { DP("Using requested number of teams %d\n", TeamNum); CudaBlocksPerGrid = TeamNum; } + if (CudaBlocksPerGrid > DeviceData[DeviceId].BlocksPerGrid) { + DP("Capping number of teams to team limit %d\n", + DeviceData[DeviceId].BlocksPerGrid); + CudaBlocksPerGrid = DeviceData[DeviceId].BlocksPerGrid; + } + INFO(OMP_INFOTYPE_PLUGIN_KERNEL, DeviceId, "Launching kernel %s with %d blocks and %d threads in %s mode\n", (getOffloadEntry(DeviceId, TgtEntryPtr)) _______________________________________________ llvm-branch-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
