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

[gtbercea]

Summary

Previously we have added the "-c" flag which gets passed to PTXAS by default to generate relocatable OpenMP target code by default. This set of flags exposes control over this behaviour.

[gtbercea]

Additional test added to check "-c" is passed in appropriately.

[gtbercea]

Update patch to reflect latest source code changes.

[Hahnfeld]

Having something with dashes behind other used prefixes (CHK-PTXAS, CHK-PTXAS-C, CHK-PTXAS-C-RELO) might not be optimal and break when other suffixes like -NOT or -SAME are added to lit. Please see inline about my suggestions but feel free to use others...

test/Driver/openmp-offload.c

606–607

CHK-PTXAS-DEFAULT (to be changed in D29642)

606–607

CHK-PTXAS-VERBOSE (to be changed in D29644)

611

CHK-PTXAS-NORELO

620

CHK-PTXAS-RELO

[gtbercea]

Update test.

[ABataev]

lib/Driver/ToolChains/Cuda.cpp

300

1. Add a comment with the name of the parameter for false argument
2. Why not to use this logic:

Args.hasFlag(options::OPT_fopenmp_relocatable_target,
                    options::OPT_fnoopenmp_relocatable_target, true)

?

[gtbercea]

Refactor if condition.

[ABataev]

LG

include/clang/Driver/Options.td

 def fopenmp_version_EQ : Joined<["-"], "fopenmp-version=">, Group<f_Group>, Flags<[CC1Option, NoArgumentUnused]>;
 def fopenmp_EQ : Joined<["-"], "fopenmp=">, Group<f_Group>;
 def fopenmp_use_tls : Flag<["-"], "fopenmp-use-tls">, Group<f_Group>, Flags<[NoArgumentUnused]>;
 def fnoopenmp_use_tls : Flag<["-"], "fnoopenmp-use-tls">, Group<f_Group>, Flags<[CC1Option, NoArgumentUnused]>;
 def fopenmp_targets_EQ : CommaJoined<["-"], "fopenmp-targets=">, Flags<[DriverOption, CC1Option]>,
   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">;
 def force__flat__namespace : Flag<["-"], "force_flat_namespace">;
 def force__load : Separate<["-"], "force_load">;
 def force_addr : Joined<["-"], "fforce-addr">, Group<clang_ignored_f_Group>;
 def foutput_class_dir_EQ : Joined<["-"], "foutput-class-dir=">, Group<f_Group>;
 def fpack_struct : Flag<["-"], "fpack-struct">, Group<f_Group>;

lib/Driver/ToolChains/Cuda.cpp

void NVPTX::Assembler::ConstructJob(Compilation &C, const JobAction &JA,
   CmdArgs.push_back(Args.MakeArgString(OutputFileName));
   for (const auto& II : Inputs)
     CmdArgs.push_back(Args.MakeArgString(II.getFilename()));
 
   for (const auto& A : Args.getAllArgValues(options::OPT_Xcuda_ptxas))
     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;
   if (Arg *A = Args.getLastArg(options::OPT_ptxas_path_EQ))
     Exec = A->getValue();
   else
     Exec = Args.MakeArgString(TC.GetProgramPath("ptxas"));
   C.addCommand(llvm::make_unique<Command>(JA, *this, Exec, CmdArgs, Inputs));

test/Driver/openmp-offload.c

 // CHK-CUBIN-NEXT: ptxas{{.*}}" "--output-file" "{{.*}}-openmp-nvptx64-nvidia-cuda.cubin" "{{.*}}-openmp-nvptx64-nvidia-cuda.s"
 // CHK-CUBIN-NEXT: nvlink" "-o" "{{.*}}-openmp-nvptx64-nvidia-cuda" {{.*}} "openmp-offload-openmp-nvptx64-nvidia-cuda.cubin"
 
 /// ###########################################################################
 
 /// Check PTXAS is passed -c flag when offloading to an NVIDIA device using OpenMP.
 // RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-PTXAS-DEFAULT %s
 
 // CHK-PTXAS-DEFAULT: ptxas{{.*}}" "-c"
 
 /// ###########################################################################
 
+/// 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
 
 // CHK-FOPENMP-IS-DEVICE: clang{{.*}}.i" {{.*}}" "-fopenmp-is-device"
 // CHK-FOPENMP-IS-DEVICE-NEXT: clang{{.*}}.bc" {{.*}}.i" "-fopenmp-is-device" "-fopenmp-host-ir-file-path"
 // CHK-FOPENMP-IS-DEVICE-NEXT: clang{{.*}}.s" {{.*}}.bc" "-fopenmp-is-device"
 
 /// ###########################################################################
 
 /// Check that the lib folder pointed to by the LIBRARY_PATH is correctly passsed to the loader script.
 // RUN:   LIBRARY_PATH=/a/b/c/lib %clang -### -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu -save-temps -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-LIB-PATH %s
 
 // CHK-LIB-PATH: ld{{.*}}.o" "-L/a/b/c/lib"
 // CHK-LIB-PATH: ld{{.*}}.o" "-L/a/b/c/lib"