[PATCH] D102940: [OpenMP] Remove OpenMP CUDA Target Parallel compiler flag

[Joseph Huber via Phabricator via cfe-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rGbc768aac2e4e: [OpenMP] Remove OpenMP CUDA Target Parallel 
compiler flag (authored by jhuber6).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D102940/new/

https://reviews.llvm.org/D102940

Files:
  clang/include/clang/Basic/LangOptions.def
  clang/include/clang/Driver/Options.td
  clang/lib/Driver/ToolChains/Clang.cpp
  clang/lib/Frontend/CompilerInvocation.cpp


Index: clang/lib/Frontend/CompilerInvocation.cpp
===
--- clang/lib/Frontend/CompilerInvocation.cpp
+++ clang/lib/Frontend/CompilerInvocation.cpp
@@ -3475,9 +3475,6 @@
   if (Opts.OpenMPCUDAMode)
 GenerateArg(Args, OPT_fopenmp_cuda_mode, SA);
 
-  if (Opts.OpenMPCUDATargetParallel)
-GenerateArg(Args, OPT_fopenmp_cuda_parallel_target_regions, SA);
-
   if (Opts.OpenMPCUDAForceFullRuntime)
 GenerateArg(Args, OPT_fopenmp_cuda_force_full_runtime, SA);
 
@@ -3910,12 +3907,6 @@
   Opts.OpenMPCUDAMode = Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
 Args.hasArg(options::OPT_fopenmp_cuda_mode);
 
-  // Set CUDA support for parallel execution of target regions for OpenMP 
target
-  // NVPTX/AMDGCN if specified in options.
-  Opts.OpenMPCUDATargetParallel =
-  Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
-  Args.hasArg(options::OPT_fopenmp_cuda_parallel_target_regions);
-
   // Set CUDA mode for OpenMP target NVPTX/AMDGCN if specified in options
   Opts.OpenMPCUDAForceFullRuntime =
   Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
Index: clang/lib/Driver/ToolChains/Clang.cpp
===
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -5714,13 +5714,6 @@
options::OPT_fno_openmp_cuda_mode, /*Default=*/false))
 CmdArgs.push_back("-fopenmp-cuda-mode");
 
-  // When in OpenMP offloading mode with NVPTX target, forward
-  // cuda-parallel-target-regions flag
-  if (Args.hasFlag(options::OPT_fopenmp_cuda_parallel_target_regions,
-   options::OPT_fno_openmp_cuda_parallel_target_regions,
-   /*Default=*/true))
-CmdArgs.push_back("-fopenmp-cuda-parallel-target-regions");
-
   // When in OpenMP offloading mode with NVPTX target, check if full 
runtime
   // is required.
   if (Args.hasFlag(options::OPT_fopenmp_cuda_force_full_runtime,
Index: clang/include/clang/Driver/Options.td
===
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -2363,12 +2363,6 @@
 defm openmp_optimistic_collapse : BoolFOption<"openmp-optimistic-collapse",
   LangOpts<"OpenMPOptimisticCollapse">, DefaultFalse,
   PosFlag, NegFlag, 
BothFlags<[NoArgumentUnused, HelpHidden]>>;
-def fopenmp_cuda_parallel_target_regions : Flag<["-"], 
"fopenmp-cuda-parallel-target-regions">, Group,
-  Flags<[CC1Option, NoArgumentUnused, HelpHidden]>,
-  HelpText<"Support parallel execution of target regions on Cuda-based 
devices.">;
-def fno_openmp_cuda_parallel_target_regions : Flag<["-"], 
"fno-openmp-cuda-parallel-target-regions">, Group,
-  Flags<[NoArgumentUnused, HelpHidden]>,
-  HelpText<"Support only serial execution of target regions on Cuda-based 
devices.">;
 def static_openmp: Flag<["-"], "static-openmp">,
   HelpText<"Use the static host OpenMP runtime while linking.">;
 def fno_optimize_sibling_calls : Flag<["-"], "fno-optimize-sibling-calls">, 
Group;
Index: clang/include/clang/Basic/LangOptions.def
===
--- clang/include/clang/Basic/LangOptions.def
+++ clang/include/clang/Basic/LangOptions.def
@@ -237,7 +237,6 @@
 LANGOPT(OpenMPCUDABlocksPerSM  , 32, 0, "Number of blocks per SM for CUDA 
devices.")
 LANGOPT(OpenMPCUDAReductionBufNum , 32, 1024, "Number of the reduction records 
in the intermediate reduction buffer used for the teams reductions.")
 LANGOPT(OpenMPOptimisticCollapse  , 1, 0, "Use at most 32 bits to represent 
the collapsed loop nest counter.")
-LANGOPT(OpenMPCUDATargetParallel, 1, 0, "Support parallel execution of target 
region on Cuda-based devices.")
 LANGOPT(RenderScript  , 1, 0, "RenderScript")
 
 LANGOPT(CUDAIsDevice  , 1, 0, "compiling for CUDA device")


Index: clang/lib/Frontend/CompilerInvocation.cpp
===
--- clang/lib/Frontend/CompilerInvocation.cpp
+++ clang/lib/Frontend/CompilerInvocation.cpp
@@ -3475,9 +3475,6 @@
   if (Opts.OpenMPCUDAMode)
 GenerateArg(Args, OPT_fopenmp_cuda_mode, SA);
 
-  if (Opts.OpenMPCUDATargetParallel)
-GenerateArg(Args, OPT_fopenmp_cuda_parallel_target_regions, SA);
-
   if (Opts.OpenMPCUDAForceFullRuntime)
 GenerateArg(Args, OPT_fopen

[PATCH] D102940: [OpenMP] Remove OpenMP CUDA Target Parallel compiler flag

[Shilei Tian via Phabricator via cfe-commits]

tianshilei1992 accepted this revision.
tianshilei1992 added a comment.
This revision is now accepted and ready to land.

LGTM


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D102940/new/

https://reviews.llvm.org/D102940

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D102940: [OpenMP] Remove OpenMP CUDA Target Parallel compiler flag

[Joseph Huber via Phabricator via cfe-commits]

jhuber6 created this revision.
jhuber6 added reviewers: jdoerfert, tianshilei1992.
jhuber6 added a project: clang.
Herald added subscribers: dexonsmith, dang, guansong, yaxunl.
jhuber6 requested review of this revision.
Herald added subscribers: cfe-commits, sstefan1.

The changes introduced in D97680  turns this 
command line option into a no-op so
it can be removed entirely.

Depends on D97680 


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D102940

Files:
  clang/include/clang/Basic/LangOptions.def
  clang/include/clang/Driver/Options.td
  clang/lib/Driver/ToolChains/Clang.cpp
  clang/lib/Frontend/CompilerInvocation.cpp


Index: clang/lib/Frontend/CompilerInvocation.cpp
===
--- clang/lib/Frontend/CompilerInvocation.cpp
+++ clang/lib/Frontend/CompilerInvocation.cpp
@@ -3475,9 +3475,6 @@
   if (Opts.OpenMPCUDAMode)
 GenerateArg(Args, OPT_fopenmp_cuda_mode, SA);
 
-  if (Opts.OpenMPCUDATargetParallel)
-GenerateArg(Args, OPT_fopenmp_cuda_parallel_target_regions, SA);
-
   if (Opts.OpenMPCUDAForceFullRuntime)
 GenerateArg(Args, OPT_fopenmp_cuda_force_full_runtime, SA);
 
@@ -3905,12 +3902,6 @@
   Opts.OpenMPCUDAMode = Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
 Args.hasArg(options::OPT_fopenmp_cuda_mode);
 
-  // Set CUDA support for parallel execution of target regions for OpenMP 
target
-  // NVPTX/AMDGCN if specified in options.
-  Opts.OpenMPCUDATargetParallel =
-  Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
-  Args.hasArg(options::OPT_fopenmp_cuda_parallel_target_regions);
-
   // Set CUDA mode for OpenMP target NVPTX/AMDGCN if specified in options
   Opts.OpenMPCUDAForceFullRuntime =
   Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
Index: clang/lib/Driver/ToolChains/Clang.cpp
===
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -5673,13 +5673,6 @@
options::OPT_fno_openmp_cuda_mode, /*Default=*/false))
 CmdArgs.push_back("-fopenmp-cuda-mode");
 
-  // When in OpenMP offloading mode with NVPTX target, forward
-  // cuda-parallel-target-regions flag
-  if (Args.hasFlag(options::OPT_fopenmp_cuda_parallel_target_regions,
-   options::OPT_fno_openmp_cuda_parallel_target_regions,
-   /*Default=*/true))
-CmdArgs.push_back("-fopenmp-cuda-parallel-target-regions");
-
   // When in OpenMP offloading mode with NVPTX target, check if full 
runtime
   // is required.
   if (Args.hasFlag(options::OPT_fopenmp_cuda_force_full_runtime,
Index: clang/include/clang/Driver/Options.td
===
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -2340,12 +2340,6 @@
 defm openmp_optimistic_collapse : BoolFOption<"openmp-optimistic-collapse",
   LangOpts<"OpenMPOptimisticCollapse">, DefaultFalse,
   PosFlag, NegFlag, 
BothFlags<[NoArgumentUnused, HelpHidden]>>;
-def fopenmp_cuda_parallel_target_regions : Flag<["-"], 
"fopenmp-cuda-parallel-target-regions">, Group,
-  Flags<[CC1Option, NoArgumentUnused, HelpHidden]>,
-  HelpText<"Support parallel execution of target regions on Cuda-based 
devices.">;
-def fno_openmp_cuda_parallel_target_regions : Flag<["-"], 
"fno-openmp-cuda-parallel-target-regions">, Group,
-  Flags<[NoArgumentUnused, HelpHidden]>,
-  HelpText<"Support only serial execution of target regions on Cuda-based 
devices.">;
 def static_openmp: Flag<["-"], "static-openmp">,
   HelpText<"Use the static host OpenMP runtime while linking.">;
 def fno_optimize_sibling_calls : Flag<["-"], "fno-optimize-sibling-calls">, 
Group;
Index: clang/include/clang/Basic/LangOptions.def
===
--- clang/include/clang/Basic/LangOptions.def
+++ clang/include/clang/Basic/LangOptions.def
@@ -237,7 +237,6 @@
 LANGOPT(OpenMPCUDABlocksPerSM  , 32, 0, "Number of blocks per SM for CUDA 
devices.")
 LANGOPT(OpenMPCUDAReductionBufNum , 32, 1024, "Number of the reduction records 
in the intermediate reduction buffer used for the teams reductions.")
 LANGOPT(OpenMPOptimisticCollapse  , 1, 0, "Use at most 32 bits to represent 
the collapsed loop nest counter.")
-LANGOPT(OpenMPCUDATargetParallel, 1, 0, "Support parallel execution of target 
region on Cuda-based devices.")
 LANGOPT(RenderScript  , 1, 0, "RenderScript")
 
 LANGOPT(CUDAIsDevice  , 1, 0, "compiling for CUDA device")


Index: clang/lib/Frontend/CompilerInvocation.cpp
===
--- clang/lib/Frontend/CompilerInvocation.cpp
+++ clang/lib/Frontend/CompilerInvocation.cpp
@@ -3475,9 +3475,6 @@
   if (Opts.OpenMPCUDAMode)
 GenerateArg(Args, O