[OpenMP] Fix bug regarding cubin integration into host binary

when a BindArchAction is used.

This is not a functional change.

Original Diff: D29654

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@310433 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Driver/Driver.cpp b/lib/Driver/Driver.cpp
index 9c39a5547d7953c9421552bb0e1c05789485fed2..e1c632569df43601989525c4bc8b4cc4e4e383e0 100644 (file)
--- a/lib/Driver/Driver.cpp
+++ b/lib/Driver/Driver.cpp
@@ -579,7 +579,7 @@ void Driver::CreateOffloadingDeviceToolChains(Compilation &C,
                   C.getSingleOffloadToolChain<Action::OFK_Host>();
               assert(HostTC && "Host toolchain should be always defined.");
               auto &CudaTC =
-                  ToolChains[TT.str() + "/" + HostTC->getTriple().str()];
+                  ToolChains[TT.str() + "/" + HostTC->getTriple().normalize()];
               if (!CudaTC)
                 CudaTC = llvm::make_unique<toolchains::CudaToolChain>(
                     *this, TT, *HostTC, C.getInputArgs(), Action::OFK_OpenMP);
@@ -3407,7 +3407,7 @@ InputInfo Driver::BuildJobsForActionNoCache(
       // Get the unique string identifier for this dependence and cache the
       // result.
       CachedResults[{A, GetTriplePlusArchString(
-                            UI.DependentToolChain, UI.DependentBoundArch,
+                            UI.DependentToolChain, BoundArch,
                             UI.DependentOffloadKind)}] = CurI;
     }
 

diff --git a/lib/Driver/ToolChain.cpp b/lib/Driver/ToolChain.cpp
index 94d5e4fc0f24872a4035a3b850146e64940a6bcc..10fad752cfe0268f624e4144f54c5a97b2ed903c 100644 (file)
--- a/lib/Driver/ToolChain.cpp
+++ b/lib/Driver/ToolChain.cpp
@@ -802,6 +802,7 @@ ToolChain::TranslateOpenMPTargetArgs(const llvm::opt::DerivedArgList &Args,
   if (DeviceOffloadKind == Action::OFK_OpenMP) {
     DerivedArgList *DAL = new DerivedArgList(Args.getBaseArgs());
     const OptTable &Opts = getDriver().getOpts();
+    bool NewArgAdded = false;
 
     // Handle -Xopenmp-target flags
     for (Arg *A : Args) {
@@ -850,9 +851,10 @@ ToolChain::TranslateOpenMPTargetArgs(const llvm::opt::DerivedArgList &Args,
       XOpenMPTargetArg->setBaseArg(A);
       A = XOpenMPTargetArg.release();
       DAL->append(A);
+      NewArgAdded = true;
     }
 
-    return DAL;
+    return NewArgAdded ? DAL : nullptr;
   }
 
   return nullptr;

diff --git a/test/Driver/openmp-offload.c b/test/Driver/openmp-offload.c
index f174f6e50696821320d8ceaee4049c736e734b71..e9ad2dc0f5628d78f9fb7f147bfc634c64d7eb1e 100644 (file)
--- a/test/Driver/openmp-offload.c
+++ b/test/Driver/openmp-offload.c
@@ -660,6 +660,16 @@
 
 /// ###########################################################################
 
+/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
+// RUN:   %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps -no-canonical-prefixes %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-CUBIN-DARWIN %s
+
+// CHK-CUBIN-DARWIN: clang{{.*}}" "-o" "{{.*}}-openmp-nvptx64-nvidia-cuda.s"
+// CHK-CUBIN-DARWIN-NEXT: ptxas{{.*}}" "--output-file" "{{.*}}-openmp-nvptx64-nvidia-cuda.cubin" "{{.*}}-openmp-nvptx64-nvidia-cuda.s"
+// CHK-CUBIN-DARWIN-NEXT: nvlink" "-o" "{{.*}}-openmp-nvptx64-nvidia-cuda" {{.*}} "openmp-offload-openmp-nvptx64-nvidia-cuda.cubin"
+
+/// ###########################################################################
+
 /// Check cubin file generation and usage by nvlink
 // RUN:   touch %t1.o
 // RUN:   touch %t2.o
@@ -667,3 +677,13 @@
 // RUN:   | FileCheck -check-prefix=CHK-TWOCUBIN %s
 
 // CHK-TWOCUBIN: nvlink"{{.*}}"openmp-offload-{{.*}}.cubin" "openmp-offload-{{.*}}.cubin"
+
+/// ###########################################################################
+
+/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
+// RUN:   touch %t1.o
+// RUN:   touch %t2.o
+// RUN:   %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %t1.o %t2.o 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-TWOCUBIN-DARWIN %s
+
+// CHK-TWOCUBIN-DARWIN: nvlink"{{.*}}"openmp-offload-{{.*}}.cubin" "openmp-offload-{{.*}}.cubin"