[PATCH] D101595: [Clang][OpenMP] Allow unified_shared_memory for Pascal-generation GPUs.

[Michael Kruse via Phabricator via cfe-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rG83ff0ff46337: [Clang][OpenMP] Allow unified_shared_memory for Pascal-generation GPUs. (authored by Meinersbur).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D101595/new/

https://reviews.llvm.org/D101595

Files:
  clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
  clang/test/OpenMP/requires_codegen.cpp


Index: clang/test/OpenMP/requires_codegen.cpp
===================================================================
--- clang/test/OpenMP/requires_codegen.cpp
+++ clang/test/OpenMP/requires_codegen.cpp
@@ -8,9 +8,9 @@
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-nvidia-cuda -fopenmp-targets=nvptx64-nvidia-cuda -target-cpu sm_50 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t-out.ll -DREGION_DEVICE
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-nvidia-cuda -fopenmp-targets=nvptx64-nvidia-cuda -target-cpu sm_52 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t-out.ll -DREGION_DEVICE
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-nvidia-cuda -fopenmp-targets=nvptx64-nvidia-cuda -target-cpu sm_53 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t-out.ll -DREGION_DEVICE
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-nvidia-cuda -fopenmp-targets=nvptx64-nvidia-cuda -target-cpu sm_60 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t-out.ll -DREGION_DEVICE
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-nvidia-cuda -fopenmp-targets=nvptx64-nvidia-cuda -target-cpu sm_61 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t-out.ll -DREGION_DEVICE
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-nvidia-cuda -fopenmp-targets=nvptx64-nvidia-cuda -target-cpu sm_62 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t-out.ll -DREGION_DEVICE
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-nvidia-cuda -fopenmp-targets=nvptx64-nvidia-cuda -target-cpu sm_60 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t-out.ll -DREGION_DEVICE_NO_ERR
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-nvidia-cuda -fopenmp-targets=nvptx64-nvidia-cuda -target-cpu sm_61 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t-out.ll -DREGION_DEVICE_NO_ERR
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-nvidia-cuda -fopenmp-targets=nvptx64-nvidia-cuda -target-cpu sm_62 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t-out.ll -DREGION_DEVICE_NO_ERR
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-nvidia-cuda -fopenmp-targets=nvptx64-nvidia-cuda -target-cpu sm_70 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t-out.ll -DREGION_DEVICE_NO_ERR
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-nvidia-cuda -fopenmp-targets=nvptx64-nvidia-cuda -target-cpu sm_72 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t-out.ll -DREGION_DEVICE_NO_ERR
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-nvidia-cuda -fopenmp-targets=nvptx64-nvidia-cuda -target-cpu sm_75 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t-out.ll -DREGION_DEVICE_NO_ERR
Index: clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
===================================================================
--- clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -4441,10 +4441,7 @@
       case CudaArch::SM_37:
       case CudaArch::SM_50:
       case CudaArch::SM_52:
-      case CudaArch::SM_53:
-      case CudaArch::SM_60:
-      case CudaArch::SM_61:
-      case CudaArch::SM_62: {
+      case CudaArch::SM_53: {
         SmallString<256> Buffer;
         llvm::raw_svector_ostream Out(Buffer);
         Out << "Target architecture " << CudaArchToString(Arch)
@@ -4452,6 +4449,9 @@
         CGM.Error(Clause->getBeginLoc(), Out.str());
         return;
       }
+      case CudaArch::SM_60:
+      case CudaArch::SM_61:
+      case CudaArch::SM_62:
       case CudaArch::SM_70:
       case CudaArch::SM_72:
       case CudaArch::SM_75:


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D101595.345299.patch
Type: text/x-patch
Size: 3918 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20210513/de5ac690/attachment-0001.bin>