jhuber6 updated this revision to Diff 361667.
jhuber6 added a comment.
Adding test
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D106793/new/
https://reviews.llvm.org/D106793
Files:
clang/include/clang/Basic/LangOptions.def
clang/include/clang/Driver/Options.td
clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
clang/lib/Driver/ToolChains/Cuda.cpp
clang/test/Driver/Inputs/libomptarget/libomptarget-new-nvptx-sm_35.bc
clang/test/Driver/openmp-offload-gpu.c
Index: clang/test/Driver/openmp-offload-gpu.c
===================================================================
--- clang/test/Driver/openmp-offload-gpu.c
+++ clang/test/Driver/openmp-offload-gpu.c
@@ -154,6 +154,11 @@
// RUN: -Xopenmp-target -march=sm_35
--cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
// RUN: -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s
2>&1 \
// RUN: | FileCheck -check-prefix=CHK-BCLIB %s
+/// Check with the new runtime enabled
+// RUN: env LIBRARY_PATH=%S/Inputs/libomptarget %clang -### -fopenmp=libomp
-fopenmp-targets=nvptx64-nvidia-cuda \
+// RUN: -Xopenmp-target -march=sm_35
--cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
+// RUN: -fopenmp-relocatable-target -fopenmp-target-new-runtime -save-temps
-no-canonical-prefixes %s 2>&1 \
+// RUN: | FileCheck -check-prefix=CHK-BCLIB-NEW %s
/// The user can override default detection using
--libomptarget-nvptx-bc-path=.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN:
--libomptarget-nvptx-bc-path=%S/Inputs/libomptarget/libomptarget-nvptx-test.bc \
@@ -162,6 +167,7 @@
// RUN: | FileCheck -check-prefix=CHK-BCLIB-USER %s
// CHK-BCLIB:
clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget-nvptx-sm_35.bc
+// CHK-BCLIB-NEW:
clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget-new-nvptx-sm_35.bc
// CHK-BCLIB-USER:
clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget-nvptx-test.bc
// CHK-BCLIB-NOT: {{error:|warning:}}
Index: clang/test/Driver/Inputs/libomptarget/libomptarget-new-nvptx-sm_35.bc
===================================================================
--- /dev/null
+++ clang/test/Driver/Inputs/libomptarget/libomptarget-new-nvptx-sm_35.bc
@@ -0,0 +1 @@
+
Index: clang/lib/Driver/ToolChains/Cuda.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Cuda.cpp
+++ clang/lib/Driver/ToolChains/Cuda.cpp
@@ -751,7 +751,13 @@
return;
}
- std::string BitcodeSuffix = "nvptx-" + GpuArch.str();
+ std::string BitcodeSuffix;
+ if (DriverArgs.hasFlag(options::OPT_fopenmp_target_new_runtime,
+ options::OPT_fno_openmp_target_new_runtime, false))
+ BitcodeSuffix = "new-nvptx-" + GpuArch.str();
+ else
+ BitcodeSuffix = "nvptx-" + GpuArch.str();
+
addOpenMPDeviceRTL(getDriver(), DriverArgs, CC1Args, BitcodeSuffix,
getTriple());
}
Index: clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
===================================================================
--- clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
+++ clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
@@ -222,7 +222,14 @@
if (DriverArgs.hasArg(options::OPT_nogpulib))
return;
- std::string BitcodeSuffix = "amdgcn-" + GPUArch;
+
+ std::string BitcodeSuffix;
+ if (DriverArgs.hasFlag(options::OPT_fopenmp_target_new_runtime,
+ options::OPT_fno_openmp_target_new_runtime, false))
+ BitcodeSuffix = "new-amdgcn-" + GPUArch;
+ else
+ BitcodeSuffix = "amdgcn-" + GPUArch;
+
addOpenMPDeviceRTL(getDriver(), DriverArgs, CC1Args, BitcodeSuffix,
getTriple());
}
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -2373,6 +2373,10 @@
Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
def fopenmp_cuda_teams_reduction_recs_num_EQ : Joined<["-"],
"fopenmp-cuda-teams-reduction-recs-num=">, Group<f_Group>,
Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
+defm openmp_target_new_runtime: BoolFOption<"openmp-target-new-runtime",
+ LangOpts<"OpenMPTargetNewRuntime">, DefaultFalse,
+ PosFlag<SetTrue, [CC1Option], "Use the new bitcode library for OpenMP
offloading">,
+ NegFlag<SetFalse>>;
defm openmp_optimistic_collapse : BoolFOption<"openmp-optimistic-collapse",
LangOpts<"OpenMPOptimisticCollapse">, DefaultFalse,
PosFlag<SetTrue, [CC1Option]>, NegFlag<SetFalse>,
BothFlags<[NoArgumentUnused, HelpHidden]>>;
Index: clang/include/clang/Basic/LangOptions.def
===================================================================
--- clang/include/clang/Basic/LangOptions.def
+++ clang/include/clang/Basic/LangOptions.def
@@ -240,6 +240,7 @@
LANGOPT(OpenMPCUDANumSMs , 32, 0, "Number of SMs for CUDA devices.")
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(OpenMPTargetNewRuntime , 1, 0, "Use the new bitcode library for OpenMP
offloading")
LANGOPT(OpenMPOptimisticCollapse , 1, 0, "Use at most 32 bits to represent
the collapsed loop nest counter.")
LANGOPT(RenderScript , 1, 0, "RenderScript")
Index: clang/test/Driver/openmp-offload-gpu.c
===================================================================
--- clang/test/Driver/openmp-offload-gpu.c
+++ clang/test/Driver/openmp-offload-gpu.c
@@ -154,6 +154,11 @@
// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
// RUN: -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-BCLIB %s
+/// Check with the new runtime enabled
+// RUN: env LIBRARY_PATH=%S/Inputs/libomptarget %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
+// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
+// RUN: -fopenmp-relocatable-target -fopenmp-target-new-runtime -save-temps -no-canonical-prefixes %s 2>&1 \
+// RUN: | FileCheck -check-prefix=CHK-BCLIB-NEW %s
/// The user can override default detection using --libomptarget-nvptx-bc-path=.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget/libomptarget-nvptx-test.bc \
@@ -162,6 +167,7 @@
// RUN: | FileCheck -check-prefix=CHK-BCLIB-USER %s
// CHK-BCLIB: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget-nvptx-sm_35.bc
+// CHK-BCLIB-NEW: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget-new-nvptx-sm_35.bc
// CHK-BCLIB-USER: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget-nvptx-test.bc
// CHK-BCLIB-NOT: {{error:|warning:}}
Index: clang/test/Driver/Inputs/libomptarget/libomptarget-new-nvptx-sm_35.bc
===================================================================
--- /dev/null
+++ clang/test/Driver/Inputs/libomptarget/libomptarget-new-nvptx-sm_35.bc
@@ -0,0 +1 @@
+
Index: clang/lib/Driver/ToolChains/Cuda.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Cuda.cpp
+++ clang/lib/Driver/ToolChains/Cuda.cpp
@@ -751,7 +751,13 @@
return;
}
- std::string BitcodeSuffix = "nvptx-" + GpuArch.str();
+ std::string BitcodeSuffix;
+ if (DriverArgs.hasFlag(options::OPT_fopenmp_target_new_runtime,
+ options::OPT_fno_openmp_target_new_runtime, false))
+ BitcodeSuffix = "new-nvptx-" + GpuArch.str();
+ else
+ BitcodeSuffix = "nvptx-" + GpuArch.str();
+
addOpenMPDeviceRTL(getDriver(), DriverArgs, CC1Args, BitcodeSuffix,
getTriple());
}
Index: clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
===================================================================
--- clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
+++ clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
@@ -222,7 +222,14 @@
if (DriverArgs.hasArg(options::OPT_nogpulib))
return;
- std::string BitcodeSuffix = "amdgcn-" + GPUArch;
+
+ std::string BitcodeSuffix;
+ if (DriverArgs.hasFlag(options::OPT_fopenmp_target_new_runtime,
+ options::OPT_fno_openmp_target_new_runtime, false))
+ BitcodeSuffix = "new-amdgcn-" + GPUArch;
+ else
+ BitcodeSuffix = "amdgcn-" + GPUArch;
+
addOpenMPDeviceRTL(getDriver(), DriverArgs, CC1Args, BitcodeSuffix,
getTriple());
}
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -2373,6 +2373,10 @@
Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
def fopenmp_cuda_teams_reduction_recs_num_EQ : Joined<["-"], "fopenmp-cuda-teams-reduction-recs-num=">, Group<f_Group>,
Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
+defm openmp_target_new_runtime: BoolFOption<"openmp-target-new-runtime",
+ LangOpts<"OpenMPTargetNewRuntime">, DefaultFalse,
+ PosFlag<SetTrue, [CC1Option], "Use the new bitcode library for OpenMP offloading">,
+ NegFlag<SetFalse>>;
defm openmp_optimistic_collapse : BoolFOption<"openmp-optimistic-collapse",
LangOpts<"OpenMPOptimisticCollapse">, DefaultFalse,
PosFlag<SetTrue, [CC1Option]>, NegFlag<SetFalse>, BothFlags<[NoArgumentUnused, HelpHidden]>>;
Index: clang/include/clang/Basic/LangOptions.def
===================================================================
--- clang/include/clang/Basic/LangOptions.def
+++ clang/include/clang/Basic/LangOptions.def
@@ -240,6 +240,7 @@
LANGOPT(OpenMPCUDANumSMs , 32, 0, "Number of SMs for CUDA devices.")
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(OpenMPTargetNewRuntime , 1, 0, "Use the new bitcode library for OpenMP offloading")
LANGOPT(OpenMPOptimisticCollapse , 1, 0, "Use at most 32 bits to represent the collapsed loop nest counter.")
LANGOPT(RenderScript , 1, 0, "RenderScript")
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
