[PATCH] D29642: [OpenMP] Make OpenMP generated code for the NVIDIA device relocatable by default

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea updated this revision to Diff 93172.
gtbercea added a comment.
Herald added a subscriber: rengolin.

Update patch to reflect latest source code changes.


Repository:
  rL LLVM

https://reviews.llvm.org/D29642

Files:
  lib/Driver/ToolChains/Cuda.cpp
  test/Driver/openmp-offload.c


Index: test/Driver/openmp-offload.c
===================================================================
--- test/Driver/openmp-offload.c
+++ test/Driver/openmp-offload.c
@@ -587,3 +587,12 @@
 // CHK-UBUJOBS-ST-SAME: [[HOSTOBJ:[^\\/]+\.o]]" "{{.*}}[[HOSTASM]]"
 // CHK-UBUJOBS-ST: clang-offload-bundler{{.*}}" "-type=o" 
"-targets=openmp-powerpc64le-ibm-linux-gnu,openmp-x86_64-pc-linux-gnu,host-powerpc64le--linux"
 "-outputs=
 // CHK-UBUJOBS-ST-SAME: [[RES:[^\\/]+\.o]]" 
"-inputs={{.*}}[[T1OBJ]],{{.*}}[[T2OBJ]],{{.*}}[[HOSTOBJ]]"
+
+/// ###########################################################################
+
+/// Check PTXAS is passed -c flag when offloading to an NVIDIA device using 
OpenMP.
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda 
-save-temps -no-canonical-prefixes %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-PTXAS %s
+
+// CHK-PTXAS: ptxas{{.*}}" "-c"
+// CHK-PTXAS-NEXT: /bin/cp
Index: lib/Driver/ToolChains/Cuda.cpp
===================================================================
--- lib/Driver/ToolChains/Cuda.cpp
+++ lib/Driver/ToolChains/Cuda.cpp
@@ -272,6 +272,10 @@
   for (const auto& A : Args.getAllArgValues(options::OPT_Xcuda_ptxas))
     CmdArgs.push_back(Args.MakeArgString(A));
 
+  // In OpenMP we need to generate relocatable code.
+  if (JA.isOffloading(Action::OFK_OpenMP))
+    CmdArgs.push_back("-c");
+
   const char *Exec;
   if (Arg *A = Args.getLastArg(options::OPT_ptxas_path_EQ))
     Exec = A->getValue();



Index: test/Driver/openmp-offload.c
===================================================================
--- test/Driver/openmp-offload.c
+++ test/Driver/openmp-offload.c
@@ -587,3 +587,12 @@
 // CHK-UBUJOBS-ST-SAME: [[HOSTOBJ:[^\\/]+\.o]]" "{{.*}}[[HOSTASM]]"
 // CHK-UBUJOBS-ST: clang-offload-bundler{{.*}}" "-type=o" "-targets=openmp-powerpc64le-ibm-linux-gnu,openmp-x86_64-pc-linux-gnu,host-powerpc64le--linux" "-outputs=
 // CHK-UBUJOBS-ST-SAME: [[RES:[^\\/]+\.o]]" "-inputs={{.*}}[[T1OBJ]],{{.*}}[[T2OBJ]],{{.*}}[[HOSTOBJ]]"
+
+/// ###########################################################################
+
+/// Check PTXAS is passed -c flag when offloading to an NVIDIA device using OpenMP.
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps -no-canonical-prefixes %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-PTXAS %s
+
+// CHK-PTXAS: ptxas{{.*}}" "-c"
+// CHK-PTXAS-NEXT: /bin/cp
Index: lib/Driver/ToolChains/Cuda.cpp
===================================================================
--- lib/Driver/ToolChains/Cuda.cpp
+++ lib/Driver/ToolChains/Cuda.cpp
@@ -272,6 +272,10 @@
   for (const auto& A : Args.getAllArgValues(options::OPT_Xcuda_ptxas))
     CmdArgs.push_back(Args.MakeArgString(A));
 
+  // In OpenMP we need to generate relocatable code.
+  if (JA.isOffloading(Action::OFK_OpenMP))
+    CmdArgs.push_back("-c");
+
   const char *Exec;
   if (Arg *A = Args.getLastArg(options::OPT_ptxas_path_EQ))
     Exec = A->getValue();

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits