[Openmp-commits] [PATCH] D119313: [OpenMP][CUDA] Set the hard team limit to 2^31-1

[Shilei Tian via Phabricator via Openmp-commits]

tianshilei1992 updated this revision to Diff 407622.
tianshilei1992 added a comment.

remove the hard limit


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D119313/new/

https://reviews.llvm.org/D119313

Files:
  openmp/libomptarget/plugins/cuda/src/rtl.cpp


Index: openmp/libomptarget/plugins/cuda/src/rtl.cpp
===================================================================
--- openmp/libomptarget/plugins/cuda/src/rtl.cpp
+++ openmp/libomptarget/plugins/cuda/src/rtl.cpp
@@ -327,10 +327,9 @@
   // Number of initial streams for each device.
   int NumInitialStreams = 32;
 
-  static constexpr const int HardTeamLimit = 1U << 16U; // 64k
-  static constexpr const int HardThreadLimit = 1024;
-  static constexpr const int DefaultNumTeams = 128;
-  static constexpr const int DefaultNumThreads = 128;
+  static constexpr const int32_t HardThreadLimit = 1024;
+  static constexpr const int32_t DefaultNumTeams = 128;
+  static constexpr const int32_t DefaultNumThreads = 128;
 
   using StreamPoolTy = ResourcePoolTy<CUstream>;
   std::vector<std::unique_ptr<StreamPoolTy>> StreamPool;
@@ -651,14 +650,9 @@
       DP("Error getting max grid dimension, use default value %d\n",
          DeviceRTLTy::DefaultNumTeams);
       DeviceData[DeviceId].BlocksPerGrid = DeviceRTLTy::DefaultNumTeams;
-    } else if (MaxGridDimX <= DeviceRTLTy::HardTeamLimit) {
+    } else {
       DP("Using %d CUDA blocks per grid\n", MaxGridDimX);
       DeviceData[DeviceId].BlocksPerGrid = MaxGridDimX;
-    } else {
-      DP("Max CUDA blocks per grid %d exceeds the hard team limit %d, capping "
-         "at the hard limit\n",
-         MaxGridDimX, DeviceRTLTy::HardTeamLimit);
-      DeviceData[DeviceId].BlocksPerGrid = DeviceRTLTy::HardTeamLimit;
     }
 
     // We are only exploiting threads along the x axis.


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D119313.407622.patch
Type: text/x-patch
Size: 1546 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/openmp-commits/attachments/20220210/dc8dec2d/attachment.bin>