gtbercea updated this revision to Diff 93240.
gtbercea added a comment.
Herald added a subscriber: rengolin.
Update patch to reflect latest source code changes.
Repository:
rL LLVM
https://reviews.llvm.org/D29659
Files:
include/clang/Driver/Options.td
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
@@ -610,6 +610,23 @@
/// ###########################################################################
+/// PTXAS is passed -c flag by default when offloading to an NVIDIA device
using OpenMP - disable it.
+// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda
-fnoopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
+// RUN: | FileCheck -check-prefix=CHK-PTXAS-C %s
+
+// CHK-PTXAS-C-NOT: ptxas{{.*}}" "-c"
+
+/// ###########################################################################
+
+/// PTXAS is passed -c flag by default when offloading to an NVIDIA device
using OpenMP
+/// Check that the flag is passed when -fopenmp-relocatable-target is used.
+// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda
-fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
+// RUN: | FileCheck -check-prefix=CHK-PTXAS-C-RELO %s
+
+// CHK-PTXAS-C-RELO: ptxas{{.*}}" "-c"
+
+/// ###########################################################################
+
/// Check that CLANG forwards the -v flag to PTXAS.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda
-save-temps -no-canonical-prefixes -v %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-VERBOSE %s
Index: lib/Driver/ToolChains/Cuda.cpp
===================================================================
--- lib/Driver/ToolChains/Cuda.cpp
+++ lib/Driver/ToolChains/Cuda.cpp
@@ -292,7 +292,9 @@
CmdArgs.push_back(Args.MakeArgString(A));
// In OpenMP we need to generate relocatable code.
- if (JA.isOffloading(Action::OFK_OpenMP))
+ if (JA.isOffloading(Action::OFK_OpenMP) &&
+ !Args.hasFlag(options::OPT_fnoopenmp_relocatable_target,
+ options::OPT_fopenmp_relocatable_target, false))
CmdArgs.push_back("-c");
const char *Exec;
Index: include/clang/Driver/Options.td
===================================================================
--- include/clang/Driver/Options.td
+++ include/clang/Driver/Options.td
@@ -1260,6 +1260,10 @@
HelpText<"Specify comma-separated list of triples OpenMP offloading targets
to be supported">;
def fopenmp_dump_offload_linker_script : Flag<["-"],
"fopenmp-dump-offload-linker-script">, Group<f_Group>,
Flags<[NoArgumentUnused]>;
+def fopenmp_relocatable_target : Flag<["-"], "fopenmp-relocatable-target">,
Group<f_Group>, Flags<[CC1Option, NoArgumentUnused]>,
+ HelpText<"OpenMP target code is compiled as relocatable using the -c flag.
For OpenMP targets the code is relocatable by default.">;
+def fnoopenmp_relocatable_target : Flag<["-"],
"fnoopenmp-relocatable-target">, Group<f_Group>, Flags<[CC1Option,
NoArgumentUnused]>,
+ HelpText<"Do not compile OpenMP target code as relocatable.">;
def fno_optimize_sibling_calls : Flag<["-"], "fno-optimize-sibling-calls">,
Group<f_Group>;
def foptimize_sibling_calls : Flag<["-"], "foptimize-sibling-calls">,
Group<f_Group>;
def force__cpusubtype__ALL : Flag<["-"], "force_cpusubtype_ALL">;
Index: test/Driver/openmp-offload.c
===================================================================
--- test/Driver/openmp-offload.c
+++ test/Driver/openmp-offload.c
@@ -610,6 +610,23 @@
/// ###########################################################################
+/// PTXAS is passed -c flag by default when offloading to an NVIDIA device using OpenMP - disable it.
+// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fnoopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
+// RUN: | FileCheck -check-prefix=CHK-PTXAS-C %s
+
+// CHK-PTXAS-C-NOT: ptxas{{.*}}" "-c"
+
+/// ###########################################################################
+
+/// PTXAS is passed -c flag by default when offloading to an NVIDIA device using OpenMP
+/// Check that the flag is passed when -fopenmp-relocatable-target is used.
+// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
+// RUN: | FileCheck -check-prefix=CHK-PTXAS-C-RELO %s
+
+// CHK-PTXAS-C-RELO: ptxas{{.*}}" "-c"
+
+/// ###########################################################################
+
/// Check that CLANG forwards the -v flag to PTXAS.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps -no-canonical-prefixes -v %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-VERBOSE %s
Index: lib/Driver/ToolChains/Cuda.cpp
===================================================================
--- lib/Driver/ToolChains/Cuda.cpp
+++ lib/Driver/ToolChains/Cuda.cpp
@@ -292,7 +292,9 @@
CmdArgs.push_back(Args.MakeArgString(A));
// In OpenMP we need to generate relocatable code.
- if (JA.isOffloading(Action::OFK_OpenMP))
+ if (JA.isOffloading(Action::OFK_OpenMP) &&
+ !Args.hasFlag(options::OPT_fnoopenmp_relocatable_target,
+ options::OPT_fopenmp_relocatable_target, false))
CmdArgs.push_back("-c");
const char *Exec;
Index: include/clang/Driver/Options.td
===================================================================
--- include/clang/Driver/Options.td
+++ include/clang/Driver/Options.td
@@ -1260,6 +1260,10 @@
HelpText<"Specify comma-separated list of triples OpenMP offloading targets to be supported">;
def fopenmp_dump_offload_linker_script : Flag<["-"], "fopenmp-dump-offload-linker-script">, Group<f_Group>,
Flags<[NoArgumentUnused]>;
+def fopenmp_relocatable_target : Flag<["-"], "fopenmp-relocatable-target">, Group<f_Group>, Flags<[CC1Option, NoArgumentUnused]>,
+ HelpText<"OpenMP target code is compiled as relocatable using the -c flag. For OpenMP targets the code is relocatable by default.">;
+def fnoopenmp_relocatable_target : Flag<["-"], "fnoopenmp-relocatable-target">, Group<f_Group>, Flags<[CC1Option, NoArgumentUnused]>,
+ HelpText<"Do not compile OpenMP target code as relocatable.">;
def fno_optimize_sibling_calls : Flag<["-"], "fno-optimize-sibling-calls">, Group<f_Group>;
def foptimize_sibling_calls : Flag<["-"], "foptimize-sibling-calls">, Group<f_Group>;
def force__cpusubtype__ALL : Flag<["-"], "force_cpusubtype_ALL">;
_______________________________________________
cfe-commits mailing list
[email protected]
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
