[CUDA] Disable PGO and coverage instrumentation in NVPTX.

Artem-B · Artem-B · commit c30bcad19c74 · 2018-01-24T17:41:02.000Z
NVPTX does not have runtime support necessary for profiling to work and even call arc collection is prohibitively expensive. Furthermore, there's no easy way to collect the samples. NVPTX also does not support global constructors that clang generates if sample/arc collection is enabled. Differential Revision: https://reviews.llvm.org/D42452 llvm-svn: 323345
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -3625,7 +3625,11 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
       options::OPT_finstrument_function_entry_bare))
     A->render(Args, CmdArgs);
 
-  addPGOAndCoverageFlags(C, D, Output, Args, CmdArgs);
+  // NVPTX doesn't support PGO or coverage. There's no runtime support for
+  // sampling, overhead of call arc collection is way too high and there's no
+  // way to collect the output.
+  if (!Triple.isNVPTX())
+    addPGOAndCoverageFlags(C, D, Output, Args, CmdArgs);
 
   if (auto *ABICompatArg = Args.getLastArg(options::OPT_fclang_abi_compat_EQ))
     ABICompatArg->render(Args, CmdArgs);
diff --git a/clang/test/Driver/cuda-no-pgo-or-coverage.cu b/clang/test/Driver/cuda-no-pgo-or-coverage.cu
@@ -0,0 +1,34 @@
+// Check that profiling/coverage arguments doen't get passed down to device-side
+// compilation.
+//
+// REQUIRES: clang-driver
+//
+// XRUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// XRUN:   -fprofile-generate %s 2>&1 | \
+// XRUN: FileCheck --check-prefixes=CHECK,PROF %s
+//
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// RUN:   -fprofile-instr-generate %s 2>&1 | \
+// RUN: FileCheck --check-prefixes=CHECK,PROF %s
+//
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// RUN:   -coverage %s 2>&1 | \
+// RUN: FileCheck --check-prefixes=CHECK,GCOV %s
+//
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// RUN:   -ftest-coverage %s 2>&1 | \
+// RUN: FileCheck --check-prefixes=CHECK,GCOV %s
+//
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20   \
+// RUN:   -fprofile-instr-generate -fcoverage-mapping %s 2>&1 | \
+// RUN: FileCheck --check-prefixes=CHECK,PROF,GCOV %s
+//
+//
+// CHECK-NOT: error: unsupported option '-fprofile
+// CHECK-NOT: error: invalid argument
+// CHECK-DAG: "-fcuda-is-device"
+// CHECK-NOT: "-f{{[^"]*coverage.*}}"
+// CHECK-NOT: "-fprofile{{[^"]*}}"
+// CHECK: "-triple" "x86_64--linux-gnu"
+// PROF-DAG: "-fprofile{{.*}}"
+// GCOV-DAG: "-f{{(coverage|emit-coverage).*}}"
