summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorAlexey Bataev <a.bataev@hotmail.com>2018-04-18 16:31:09 +0000
committerAlexey Bataev <a.bataev@hotmail.com>2018-04-18 16:31:09 +0000
commite36c67b35c26d7c9a2974ffd2f8ba6a9f0260f15 (patch)
treeb2a4953d114bf03c8af176f93d4e2c5e19000514
parent242706b8d187ee70c9da3737dd8414b7a762a42b (diff)
downloadbcm5719-llvm-e36c67b35c26d7c9a2974ffd2f8ba6a9f0260f15.tar.gz
bcm5719-llvm-e36c67b35c26d7c9a2974ffd2f8ba6a9f0260f15.zip
[NVPTX] Emit debug info in DWARF-2 by default for Cuda devices.
Summary: NVPTX target supports debug info in DWARF-2 format. Patch adds emission of debug info in DWARF-2 by default. Reviewers: tra, jlebar Subscribers: aprantl, JDevlieghere, cfe-commits Differential Revision: https://reviews.llvm.org/D42581 llvm-svn: 330272
-rw-r--r--clang/lib/Driver/ToolChains/Cuda.cpp39
-rw-r--r--clang/lib/Driver/ToolChains/Cuda.h2
-rw-r--r--clang/test/Driver/cuda-dwarf-2.cu47
-rw-r--r--clang/test/Driver/cuda-external-tools.cu2
-rw-r--r--clang/test/Driver/openmp-offload-gpu.c48
5 files changed, 134 insertions, 4 deletions
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index c83d066fa26..fc74a8ebbf0 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -273,6 +273,35 @@ void CudaInstallationDetector::print(raw_ostream &OS) const {
<< CudaVersionToString(Version) << "\n";
}
+namespace {
+ /// Debug info kind.
+enum DebugInfoKind {
+ NoDebug, /// No debug info.
+ LineTableOnly, /// Line tables only.
+ FullDebug /// Full debug info.
+};
+} // anonymous namespace
+
+static DebugInfoKind mustEmitDebugInfo(const ArgList &Args) {
+ Arg *A = Args.getLastArg(options::OPT_O_Group);
+ if (Args.hasFlag(options::OPT_cuda_noopt_device_debug,
+ options::OPT_no_cuda_noopt_device_debug,
+ !A || A->getOption().matches(options::OPT_O0))) {
+ if (const Arg *A = Args.getLastArg(options::OPT_g_Group)) {
+ const Option &Opt = A->getOption();
+ if (Opt.matches(options::OPT_gN_Group)) {
+ if (Opt.matches(options::OPT_g0) || Opt.matches(options::OPT_ggdb0))
+ return NoDebug;
+ if (Opt.matches(options::OPT_gline_tables_only) ||
+ Opt.matches(options::OPT_ggdb1))
+ return LineTableOnly;
+ }
+ return FullDebug;
+ }
+ }
+ return NoDebug;
+}
+
void NVPTX::Assembler::ConstructJob(Compilation &C, const JobAction &JA,
const InputInfo &Output,
const InputInfoList &Inputs,
@@ -304,8 +333,8 @@ void NVPTX::Assembler::ConstructJob(Compilation &C, const JobAction &JA,
ArgStringList CmdArgs;
CmdArgs.push_back(TC.getTriple().isArch64Bit() ? "-m64" : "-m32");
- if (Args.hasFlag(options::OPT_cuda_noopt_device_debug,
- options::OPT_no_cuda_noopt_device_debug, false)) {
+ DebugInfoKind DIKind = mustEmitDebugInfo(Args);
+ if (DIKind == FullDebug) {
// ptxas does not accept -g option if optimization is enabled, so
// we ignore the compiler's -O* options if we want debug info.
CmdArgs.push_back("-g");
@@ -341,6 +370,8 @@ void NVPTX::Assembler::ConstructJob(Compilation &C, const JobAction &JA,
// to no optimizations, but ptxas's default is -O3.
CmdArgs.push_back("-O0");
}
+ if (DIKind == LineTableOnly)
+ CmdArgs.push_back("-lineinfo");
// Pass -v to ptxas if it was passed to the driver.
if (Args.hasArg(options::OPT_v))
@@ -410,6 +441,8 @@ void NVPTX::Linker::ConstructJob(Compilation &C, const JobAction &JA,
CmdArgs.push_back(TC.getTriple().isArch64Bit() ? "-64" : "-32");
CmdArgs.push_back(Args.MakeArgString("--create"));
CmdArgs.push_back(Args.MakeArgString(Output.getFilename()));
+ if (mustEmitDebugInfo(Args) == FullDebug)
+ CmdArgs.push_back("-g");
for (const auto& II : Inputs) {
auto *A = II.getAction();
@@ -461,7 +494,7 @@ void NVPTX::OpenMPLinker::ConstructJob(Compilation &C, const JobAction &JA,
CmdArgs.push_back(Output.getFilename());
} else
assert(Output.isNothing() && "Invalid output.");
- if (Args.hasArg(options::OPT_g_Flag))
+ if (mustEmitDebugInfo(Args) == FullDebug)
CmdArgs.push_back("-g");
if (Args.hasArg(options::OPT_v))
diff --git a/clang/lib/Driver/ToolChains/Cuda.h b/clang/lib/Driver/ToolChains/Cuda.h
index 3d08cec1643..9b34fa589e4 100644
--- a/clang/lib/Driver/ToolChains/Cuda.h
+++ b/clang/lib/Driver/ToolChains/Cuda.h
@@ -180,6 +180,8 @@ public:
computeMSVCVersion(const Driver *D,
const llvm::opt::ArgList &Args) const override;
+ unsigned GetDefaultDwarfVersion() const override { return 2; }
+
const ToolChain &HostTC;
CudaInstallationDetector CudaInstallation;
diff --git a/clang/test/Driver/cuda-dwarf-2.cu b/clang/test/Driver/cuda-dwarf-2.cu
new file mode 100644
index 00000000000..b6c7f500f5c
--- /dev/null
+++ b/clang/test/Driver/cuda-dwarf-2.cu
@@ -0,0 +1,47 @@
+// REQUIRES: clang-driver
+//
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -g -O0 --no-cuda-noopt-device-debug 2>&1 | \
+// RUN: FileCheck %s -check-prefix NO_DEBUG
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -g -O3 2>&1 | \
+// RUN: FileCheck %s -check-prefix NO_DEBUG
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -g -O3 --no-cuda-noopt-device-debug 2>&1 | \
+// RUN: FileCheck %s -check-prefix NO_DEBUG
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -g0 2>&1 | \
+// RUN: FileCheck %s -check-prefix NO_DEBUG
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -ggdb0 -O3 --cuda-noopt-device-debug 2>&1 | \
+// RUN: FileCheck %s -check-prefix NO_DEBUG
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -ggdb1 2>&1 | \
+// RUN: FileCheck %s -check-prefix NO_DEBUG -check-prefix LINE_TABLE
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -gline-tables-only -O2 --cuda-noopt-device-debug 2>&1 | \
+// RUN: FileCheck %s -check-prefix NO_DEBUG -check-prefix LINE_TABLE
+
+// NO_DEBUG: ptxas
+// NO_DEBUG-NOT: "-g"
+// LINE_TABLE: "-lineinfo"
+// NO_DEBUG: fatbinary
+// NO_DEBUG-NOT: "-g"
+
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -g 2>&1 | \
+// RUN: FileCheck %s -check-prefix HAS_DEBUG
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -g -O0 --cuda-noopt-device-debug 2>&1 | \
+// RUN: FileCheck %s -check-prefix HAS_DEBUG
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -g -O3 --cuda-noopt-device-debug 2>&1 | \
+// RUN: FileCheck %s -check-prefix HAS_DEBUG
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -g2 2>&1 | \
+// RUN: FileCheck %s -check-prefix HAS_DEBUG
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -ggdb2 -O0 2>&1 | \
+// RUN: FileCheck %s -check-prefix HAS_DEBUG
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -g3 -O2 --cuda-noopt-device-debug 2>&1 | \
+// RUN: FileCheck %s -check-prefix HAS_DEBUG
+// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s -ggdb3 -O3 --cuda-noopt-device-debug 2>&1 | \
+// RUN: FileCheck %s -check-prefix HAS_DEBUG
+
+// HAS_DEBUG: "-fcuda-is-device"
+// HAS_DEBUG-SAME: "-dwarf-version=2"
+// HAS_DEBUG: ptxas
+// HAS_DEBUG-SAME: "-g"
+// HAS_DEBUG-SAME: "--dont-merge-basicblocks"
+// HAS_DEBUG-SAME: "--return-at-end"
+// HAS_DEBUG: fatbinary
+// HAS_DEBUG-SAME: "-g"
+
diff --git a/clang/test/Driver/cuda-external-tools.cu b/clang/test/Driver/cuda-external-tools.cu
index c15cc05a7d0..367c6997ea8 100644
--- a/clang/test/Driver/cuda-external-tools.cu
+++ b/clang/test/Driver/cuda-external-tools.cu
@@ -23,7 +23,7 @@
// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,RDC %s
// With debugging enabled, ptxas should be run with with no ptxas optimizations.
-// RUN: %clang -### -target x86_64-linux-gnu --cuda-noopt-device-debug -O2 -c %s 2>&1 \
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-noopt-device-debug -O2 -g -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes=CHECK,ARCH64,SM20,DBG %s
// --no-cuda-noopt-device-debug overrides --cuda-noopt-device-debug.
diff --git a/clang/test/Driver/openmp-offload-gpu.c b/clang/test/Driver/openmp-offload-gpu.c
index 152e03a57c3..3d14041a13f 100644
--- a/clang/test/Driver/openmp-offload-gpu.c
+++ b/clang/test/Driver/openmp-offload-gpu.c
@@ -165,3 +165,51 @@
// RUN: | FileCheck -check-prefix=CHK-BCLIB-WARN %s
// CHK-BCLIB-WARN: No library 'libomptarget-nvptx-sm_20.bc' found in the default clang lib directory or in LIBRARY_PATH. Expect degraded performance due to no inlining of runtime functions on target devices.
+
+/// Check that debug info is emitted in dwarf-2
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O0 --no-cuda-noopt-device-debug 2>&1 \
+// RUN: | FileCheck -check-prefix=NO_DEBUG %s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O3 2>&1 \
+// RUN: | FileCheck -check-prefix=NO_DEBUG %s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O3 --no-cuda-noopt-device-debug 2>&1 \
+// RUN: | FileCheck -check-prefix=NO_DEBUG %s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g0 2>&1 \
+// RUN: | FileCheck -check-prefix=NO_DEBUG %s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb0 -O3 --cuda-noopt-device-debug 2>&1 \
+// RUN: | FileCheck -check-prefix=NO_DEBUG %s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -gline-tables-only 2>&1 \
+// RUN: | FileCheck -check-prefix=NO_DEBUG -check-prefix=LINE_TABLE %s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb1 -O2 --cuda-noopt-device-debug 2>&1 \
+// RUN: | FileCheck -check-prefix=NO_DEBUG -check-prefix=LINE_TABLE %s
+
+// NO_DEBUG: ptxas
+// LINE_TABLE: "-lineinfo"
+// NO_DEBUG-NOT: "-g"
+// NO_DEBUG: nvlink
+// NO_DEBUG-NOT: "-g"
+
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g 2>&1 \
+// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O0 --cuda-noopt-device-debug 2>&1 \
+// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O3 --cuda-noopt-device-debug 2>&1 \
+// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g2 2>&1 \
+// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb2 -O0 --cuda-noopt-device-debug 2>&1 \
+// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g3 -O3 --cuda-noopt-device-debug 2>&1 \
+// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb3 -O2 --cuda-noopt-device-debug 2>&1 \
+// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
+
+// HAS_DEBUG: "-triple" "nvptx64-nvidia-cuda"
+// HAS_DEBUG-SAME: "-dwarf-version=2"
+// HAS_DEBUG-SAME: "-fopenmp-is-device"
+// HAS_DEBUG: ptxas
+// HAS_DEBUG-SAME: "-g"
+// HAS_DEBUG-SAME: "--dont-merge-basicblocks"
+// HAS_DEBUG-SAME: "--return-at-end"
+// HAS_DEBUG: nvlink
+// HAS_DEBUG-SAME: "-g"
+
OpenPOWER on IntegriCloud