[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

3 files changed, 96 insertions, 1 deletions

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"
+