diff options
| author | Shilei Tian <i@tianshilei.me> | 2022-02-10 22:13:18 +0300 |
|---|---|---|
| committer | Shilei Tian <i@tianshilei.me> | 2022-02-10 22:13:32 +0300 |
| commit | f6685f774697c85d6a352dcea013f46a99f9fe31 (patch) | |
| tree | 3ab9e7cfb3c65b3fc65e9d4e4608af84a0d2bf29 /openmp | |
| parent | 547a667ceeb60dca5447e5bc09165a52b22925eb (diff) | |
[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
Diffstat (limited to 'openmp')
| -rw-r--r-- | openmp/libomptarget/plugins/cuda/src/rtl.cpp | 10 |
1 files changed, 6 insertions, 4 deletions
diff --git a/openmp/libomptarget/plugins/cuda/src/rtl.cpp b/openmp/libomptarget/plugins/cuda/src/rtl.cpp index e17593878b7c..0ca05f0ec3a0 100644 --- a/openmp/libomptarget/plugins/cuda/src/rtl.cpp +++ b/openmp/libomptarget/plugins/cuda/src/rtl.cpp @@ -1170,15 +1170,17 @@ public: 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)) |