[PATCH] D29659: [OpenMP] Add flag for disabling the default generation of relocatable OpenMP target code for NVIDIA GPUs.

Fri, 21 Apr 2017 08:05:26 -0700 

gtbercea updated this revision to Diff 96144.
gtbercea added a comment.

Refactor if condition.


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
@@ -608,6 +608,23 @@
 
 /// ###########################################################################
 
+/// 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-NORELO %s
+
+// CHK-PTXAS-NORELO-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-RELO %s
+
+// CHK-PTXAS-RELO: ptxas{{.*}}" "-c"
+
+/// ###########################################################################
+
 /// Check -fopenmp-is-device is also passed when generating the *.i and *.s 
intermediate files.
 // RUN:   %clang -### -fopenmp=libomp 
-fopenmp-targets=powerpc64le-ibm-linux-gnu -save-temps -no-canonical-prefixes 
%s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-FOPENMP-IS-DEVICE %s
Index: lib/Driver/ToolChains/Cuda.cpp
===================================================================
--- lib/Driver/ToolChains/Cuda.cpp
+++ lib/Driver/ToolChains/Cuda.cpp
@@ -295,7 +295,10 @@
     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_fopenmp_relocatable_target,
+                   options::OPT_fnoopenmp_relocatable_target,
+                   /*Default=*/ true))
     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
@@ -608,6 +608,23 @@
 
 /// ###########################################################################
 
+/// 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-NORELO %s
+
+// CHK-PTXAS-NORELO-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-RELO %s
+
+// CHK-PTXAS-RELO: ptxas{{.*}}" "-c"
+
+/// ###########################################################################
+
 /// Check -fopenmp-is-device is also passed when generating the *.i and *.s intermediate files.
 // RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu -save-temps -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-FOPENMP-IS-DEVICE %s
Index: lib/Driver/ToolChains/Cuda.cpp
===================================================================
--- lib/Driver/ToolChains/Cuda.cpp
+++ lib/Driver/ToolChains/Cuda.cpp
@@ -295,7 +295,10 @@
     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_fopenmp_relocatable_target,
+                   options::OPT_fnoopenmp_relocatable_target,
+                   /*Default=*/ true))
     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
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
  • [PATCH] D29659: [Op... Gheorghe-Teodor Bercea via Phabricator via cfe-commits
    • [PATCH] D29659... Alexey Bataev via Phabricator via cfe-commits
    • [PATCH] D29659... Gheorghe-Teodor Bercea via Phabricator via cfe-commits
    • [PATCH] D29659... Alexey Bataev via Phabricator via cfe-commits

Reply via email to