[Openmp-commits] [PATCH] D95013: [OpenMP][NVPTX] Replaced CUDA builtin vars with LLVM intrinsics

[Shilei Tian via Phabricator via Openmp-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rGfd70f70d1e02: [OpenMP][NVPTX] Replaced CUDA builtin vars with LLVM intrinsics (authored by tianshilei1992).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D95013/new/

https://reviews.llvm.org/D95013

Files:
  openmp/libomptarget/deviceRTLs/nvptx/src/target_impl.cu


Index: openmp/libomptarget/deviceRTLs/nvptx/src/target_impl.cu
===================================================================
--- openmp/libomptarget/deviceRTLs/nvptx/src/target_impl.cu
+++ openmp/libomptarget/deviceRTLs/nvptx/src/target_impl.cu
@@ -115,10 +115,12 @@
 DEVICE void __kmpc_impl_threadfence_system() { __threadfence_system(); }
 
 // Calls to the NVPTX layer (assuming 1D layout)
-DEVICE int GetThreadIdInBlock() { return threadIdx.x; }
-DEVICE int GetBlockIdInKernel() { return blockIdx.x; }
-DEVICE int GetNumberOfBlocksInKernel() { return gridDim.x; }
-DEVICE int GetNumberOfThreadsInBlock() { return blockDim.x; }
+DEVICE int GetThreadIdInBlock() { return __nvvm_read_ptx_sreg_tid_x(); }
+DEVICE int GetBlockIdInKernel() { return __nvvm_read_ptx_sreg_ctaid_x(); }
+DEVICE int GetNumberOfBlocksInKernel() {
+  return __nvvm_read_ptx_sreg_nctaid_x();
+}
+DEVICE int GetNumberOfThreadsInBlock() { return __nvvm_read_ptx_sreg_ntid_x(); }
 DEVICE unsigned GetWarpId() { return GetThreadIdInBlock() / WARPSIZE; }
 DEVICE unsigned GetLaneId() { return GetThreadIdInBlock() & (WARPSIZE - 1); }
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D95013.317895.patch
Type: text/x-patch
Size: 1111 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/openmp-commits/attachments/20210120/1ffe2f42/attachment.bin>