Hahnfeld created this revision.
This was previously done in some places, but for example not for
bundling so that single object compilation with -c failed. In
addition cubin was used for all file types during unbundling which
is incorrect for assembly files that are passed to ptxas.
Tighten up the tests so that we can't regress in that area.
https://reviews.llvm.org/D40250
Files:
include/clang/Driver/ToolChain.h
lib/Driver/ToolChain.cpp
lib/Driver/ToolChains/Clang.cpp
lib/Driver/ToolChains/Cuda.cpp
lib/Driver/ToolChains/Cuda.h
test/Driver/openmp-offload-gpu.c
Index: test/Driver/openmp-offload-gpu.c
===================================================================
--- test/Driver/openmp-offload-gpu.c
+++ test/Driver/openmp-offload-gpu.c
@@ -28,43 +28,61 @@
/// ###########################################################################
/// Check cubin file generation and usage by nvlink
-// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps %s 2>&1 \
-// RUN: | FileCheck -check-prefix=CHK-CUBIN %s
+// RUN: %clang -### -no-canonical-prefixes -target powerpc64le-unknown-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps %s 2>&1 \
+// RUN: | FileCheck -check-prefix=CHK-CUBIN-NVLINK %s
+/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
+// RUN: %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
+// RUN: | FileCheck -check-prefix=CHK-CUBIN-NVLINK %s
+
+// CHK-CUBIN-NVLINK: clang{{.*}}" "-o" "[[PTX:.*\.s]]"
+// CHK-CUBIN-NVLINK-NEXT: ptxas{{.*}}" "--output-file" "[[CUBIN:.*\.cubin]]" {{.*}}"[[PTX]]"
+// CHK-CUBIN-NVLINK-NEXT: nvlink{{.*}}" {{.*}}"[[CUBIN]]"
+
+/// ###########################################################################
-// CHK-CUBIN: clang{{.*}}" "-o" "{{.*}}.s"
-// CHK-CUBIN-NEXT: ptxas{{.*}}" "--output-file" {{.*}}.cubin" {{.*}}.s"
-// CHK-CUBIN-NEXT: nvlink" {{.*}}.cubin"
+/// Check unbundlink of assembly file, cubin file generation and usage by nvlink
+// RUN: touch %t.s
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps %t.s 2>&1 \
+// RUN: | FileCheck -check-prefix=CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK %s
+/// Use DAG to ensure that assembly file has been unbundled.
+// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK-DAG: ptxas{{.*}}" "--output-file" "[[CUBIN:.*\.cubin]]" {{.*}}"[[PTX:.*\.s]]"
+// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK-DAG: clang-offload-bundler{{.*}}" "-type=s" {{.*}}"-outputs={{.*}}[[PTX]]
+// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK: nvlink{{.*}}" {{.*}}"[[CUBIN]]"
/// ###########################################################################
-/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
-// RUN: %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
-// RUN: | FileCheck -check-prefix=CHK-CUBIN-DARWIN %s
+/// Check cubin file generation and bundling
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps %s -c 2>&1 \
+// RUN: | FileCheck -check-prefix=CHK-PTXAS-CUBIN-BUNDLING %s
-// CHK-CUBIN-DARWIN: clang{{.*}}" "-o" "{{.*}}.s"
-// CHK-CUBIN-DARWIN-NEXT: ptxas{{.*}}" "--output-file" {{.*}}.cubin" {{.*}}.s"
-// CHK-CUBIN-DARWIN-NEXT: nvlink" {{.*}}.cubin"
+// CHK-PTXAS-CUBIN-BUNDLING: clang{{.*}}" "-o" "[[PTX:.*\.s]]"
+// CHK-PTXAS-CUBIN-BUNDLING-NEXT: ptxas{{.*}}" "--output-file" "[[CUBIN:.*\.cubin]]" {{.*}}"[[PTX]]"
+// CHK-PTXAS-CUBIN-BUNDLING: clang-offload-bundler{{.*}}" "-type=o" {{.*}}"-inputs={{.*}}[[CUBIN]]
/// ###########################################################################
-/// Check cubin file generation and usage by nvlink
-// RUN: touch %t1.o
-// RUN: touch %t2.o
-// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %t1.o %t2.o 2>&1 \
-// RUN: | FileCheck -check-prefix=CHK-TWOCUBIN %s
+/// Check cubin file unbundling and usage by nvlink
+// RUN: touch %t.o
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps %t.o 2>&1 \
+// RUN: | FileCheck -check-prefix=CHK-CUBIN-UNBUNDLING-NVLINK %s
-// CHK-TWOCUBIN: nvlink{{.*}}openmp-offload-{{.*}}.cubin" "{{.*}}openmp-offload-{{.*}}.cubin"
+/// Use DAG to ensure that cubin file has been unbundled.
+// CHK-CUBIN-UNBUNDLING-NVLINK-DAG: nvlink{{.*}}" {{.*}}"[[CUBIN:.*\.cubin]]"
+// CHK-CUBIN-UNBUNDLING-NVLINK-DAG: clang-offload-bundler{{.*}}" "-type=o" {{.*}}"-outputs={{.*}}[[CUBIN]]
/// ###########################################################################
-/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
+/// Check cubin file generation and usage by nvlink
// RUN: touch %t1.o
// RUN: touch %t2.o
+// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %t1.o %t2.o 2>&1 \
+// RUN: | FileCheck -check-prefix=CHK-TWOCUBIN %s
+/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
// RUN: %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %t1.o %t2.o 2>&1 \
-// RUN: | FileCheck -check-prefix=CHK-TWOCUBIN-DARWIN %s
+// RUN: | FileCheck -check-prefix=CHK-TWOCUBIN %s
-// CHK-TWOCUBIN-DARWIN: nvlink{{.*}}openmp-offload-{{.*}}.cubin" "{{.*}}openmp-offload-{{.*}}.cubin"
+// CHK-TWOCUBIN: nvlink{{.*}}openmp-offload-{{.*}}.cubin" "{{.*}}openmp-offload-{{.*}}.cubin"
/// ###########################################################################
Index: lib/Driver/ToolChains/Cuda.h
===================================================================
--- lib/Driver/ToolChains/Cuda.h
+++ lib/Driver/ToolChains/Cuda.h
@@ -141,6 +141,8 @@
return &HostTC.getTriple();
}
+ virtual std::string getInputFilename(const InputInfo &Input) const override;
+
llvm::opt::DerivedArgList *
TranslateArgs(const llvm::opt::DerivedArgList &Args, StringRef BoundArch,
Action::OffloadKind DeviceOffloadKind) const override;
Index: lib/Driver/ToolChains/Cuda.cpp
===================================================================
--- lib/Driver/ToolChains/Cuda.cpp
+++ lib/Driver/ToolChains/Cuda.cpp
@@ -301,10 +301,7 @@
CmdArgs.push_back("--gpu-name");
CmdArgs.push_back(Args.MakeArgString(CudaArchToString(gpu_arch)));
CmdArgs.push_back("--output-file");
- SmallString<256> OutputFileName(Output.getFilename());
- if (JA.isOffloading(Action::OFK_OpenMP))
- llvm::sys::path::replace_extension(OutputFileName, "cubin");
- CmdArgs.push_back(Args.MakeArgString(OutputFileName));
+ CmdArgs.push_back(Args.MakeArgString(TC.getInputFilename(Output)));
for (const auto& II : Inputs)
CmdArgs.push_back(Args.MakeArgString(II.getFilename()));
@@ -431,11 +428,8 @@
if (!II.isFilename())
continue;
- SmallString<256> Name(II.getFilename());
- llvm::sys::path::replace_extension(Name, "cubin");
-
- const char *CubinF =
- C.addTempFile(C.getArgs().MakeArgString(Name));
+ const char *CubinF = C.addTempFile(
+ C.getArgs().MakeArgString(getToolChain().getInputFilename(II)));
CmdArgs.push_back(CubinF);
}
@@ -463,6 +457,17 @@
getProgramPaths().push_back(getDriver().Dir);
}
+std::string CudaToolChain::getInputFilename(const InputInfo &Input) const {
+ if (OK != Action::OFK_OpenMP || Input.getType() != types::TY_Object)
+ return ToolChain::getInputFilename(Input);
+
+ // Replace extension for object files with cubin because nvlink relies on
+ // these particular file names.
+ SmallString<256> Filename(ToolChain::getInputFilename(Input));
+ llvm::sys::path::replace_extension(Filename, "cubin");
+ return Filename.str();
+}
+
void CudaToolChain::addClangTargetOptions(
const llvm::opt::ArgList &DriverArgs,
llvm::opt::ArgStringList &CC1Args,
Index: lib/Driver/ToolChains/Clang.cpp
===================================================================
--- lib/Driver/ToolChains/Clang.cpp
+++ lib/Driver/ToolChains/Clang.cpp
@@ -5336,7 +5336,13 @@
for (unsigned I = 0; I < Inputs.size(); ++I) {
if (I)
UB += ',';
- UB += Inputs[I].getFilename();
+
+ const ToolChain *CurTC = &getToolChain();
+ if (const auto *OA = dyn_cast<OffloadAction>(JA.getInputs()[I])) {
+ OA->doOnEachDependence(
+ [&](Action *, const ToolChain *TC, const char *) { CurTC = TC; });
+ }
+ UB += CurTC->getInputFilename(Inputs[I]);
}
CmdArgs.push_back(TCArgs.MakeArgString(UB));
@@ -5396,13 +5402,7 @@
for (unsigned I = 0; I < Outputs.size(); ++I) {
if (I)
UB += ',';
- SmallString<256> OutputFileName(Outputs[I].getFilename());
- // Change extension of target files for OpenMP offloading
- // to NVIDIA GPUs.
- if (DepInfo[I].DependentToolChain->getTriple().isNVPTX() &&
- JA.isOffloading(Action::OFK_OpenMP))
- llvm::sys::path::replace_extension(OutputFileName, "cubin");
- UB += OutputFileName;
+ UB += DepInfo[I].DependentToolChain->getInputFilename(Outputs[I]);
}
CmdArgs.push_back(TCArgs.MakeArgString(UB));
CmdArgs.push_back("-unbundle");
Index: lib/Driver/ToolChain.cpp
===================================================================
--- lib/Driver/ToolChain.cpp
+++ lib/Driver/ToolChain.cpp
@@ -215,6 +215,10 @@
}
}
+std::string ToolChain::getInputFilename(const InputInfo &Input) const {
+ return Input.getFilename();
+}
+
bool ToolChain::IsUnwindTablesDefault(const ArgList &Args) const {
return false;
}
Index: include/clang/Driver/ToolChain.h
===================================================================
--- include/clang/Driver/ToolChain.h
+++ include/clang/Driver/ToolChain.h
@@ -40,6 +40,7 @@
class Compilation;
class CudaInstallationDetector;
class Driver;
+ class InputInfo;
class JobAction;
class RegisterEffectiveTriple;
class SanitizerArgs;
@@ -172,6 +173,11 @@
/// while the aux triple is the host (CPU) toolchain, e.g. x86-linux-gnu.
virtual const llvm::Triple *getAuxTriple() const { return nullptr; }
+ /// Some toolchains need to modify the file name, for example to replace the
+ /// extension for object files with .cubin for OpenMP offloading to Nvidia
+ /// GPUs.
+ virtual std::string getInputFilename(const InputInfo &Input) const;
+
llvm::Triple::ArchType getArch() const { return Triple.getArch(); }
StringRef getArchName() const { return Triple.getArchName(); }
StringRef getPlatform() const { return Triple.getVendorName(); }
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
