replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[OpenMP] Enable previously successful offloading tests. 

Create a separate test file to contain all tests for OpenMP
offloading to GPUs.

Make libdevice checking more robust by accounting for
the case in which no libdevice is found.

This changes are in connrection with diff: D29660

llvm-svn: 310718
This commit is contained in:
Gheorghe-Teodor Bercea 2017-08-11 15:46:22 +00:00
parent 169dae70a6
commit 9c52574886
4 changed files with 109 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
clang/lib/Driver/ToolChains/Cuda.cpp
View File

@ -153,6 +153,19 @@ CudaInstallationDetector::CudaInstallationDetector(
}
}
// This code prevents IsValid from being set when
// no libdevice has been found.
bool allEmpty = true;
std::string LibDeviceFile;
for (auto key : LibDeviceMap.keys()) {
LibDeviceFile = LibDeviceMap.lookup(key);
if (!LibDeviceFile.empty())
allEmpty = false;
}
if (allEmpty)
continue;
IsValid = true;
break;
}

2
clang/lib/Driver/ToolChains/Cuda.h
View File

@ -85,7 +85,7 @@ public:
if (!LibDeviceFile.empty())
return key;
}
return "sm_35";
return "sm_20";
}
};

95
clang/test/Driver/openmp-offload-gpu.c Normal file
View File

@ -0,0 +1,95 @@
///
/// Perform several driver tests for OpenMP offloading
///
// Until this test is stabilized on all local configurations.
// UNSUPPORTED: linux
// REQUIRES: clang-driver
// REQUIRES: x86-registered-target
// REQUIRES: powerpc-registered-target
// REQUIRES: nvptx-registered-target
/// ###########################################################################
/// Check -Xopenmp-target uses one of the archs provided when several archs are used.
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_35 -Xopenmp-target -march=sm_60 %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-FOPENMP-TARGET-ARCHS %s
// CHK-FOPENMP-TARGET-ARCHS: ptxas{{.*}}" "--gpu-name" "sm_60"
// CHK-FOPENMP-TARGET-ARCHS: nvlink{{.*}}" "-arch" "sm_60"
/// ###########################################################################
/// Check -Xopenmp-target -march=sm_35 works as expected when two triples are present.
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu,nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_35 %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-FOPENMP-TARGET-COMPILATION %s
// CHK-FOPENMP-TARGET-COMPILATION: ptxas{{.*}}" "--gpu-name" "sm_35"
// CHK-FOPENMP-TARGET-COMPILATION: nvlink{{.*}}" "-arch" "sm_35"
/// ###########################################################################
/// 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
// CHK-CUBIN: clang{{.*}}" "-o" "{{.*}}.s"
// CHK-CUBIN-NEXT: ptxas{{.*}}" "--output-file" {{.*}}.cubin" {{.*}}.s"
// CHK-CUBIN-NEXT: 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
// CHK-CUBIN-DARWIN: clang{{.*}}" "-o" "{{.*}}.s"
// CHK-CUBIN-DARWIN-NEXT: ptxas{{.*}}" "--output-file" {{.*}}.cubin" {{.*}}.s"
// CHK-CUBIN-DARWIN-NEXT: nvlink" {{.*}}.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
// CHK-TWOCUBIN: nvlink"{{.*}}"openmp-offload-{{.*}}.cubin" "openmp-offload-{{.*}}.cubin"
/// ###########################################################################
/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
// RUN: touch %t1.o
// RUN: touch %t2.o
// 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
// CHK-TWOCUBIN-DARWIN: nvlink"{{.*}}"openmp-offload-{{.*}}.cubin" "openmp-offload-{{.*}}.cubin"
/// ###########################################################################
/// Check PTXAS is passed -c flag when offloading to an NVIDIA device using OpenMP.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -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"

21
clang/test/Driver/openmp-offload.c
View File

@ -2,9 +2,6 @@
/// Perform several driver tests for OpenMP offloading
///
// Until this test is stabilized on all local configurations.
// UNSUPPORTED: linux
// REQUIRES: clang-driver
// REQUIRES: x86-registered-target
// REQUIRES: powerpc-registered-target
@ -632,21 +629,3 @@
// RUN: | FileCheck -check-prefix=CHK-FOPENMP-TARGET-NESTED-ERROR %s
// CHK-FOPENMP-TARGET-NESTED-ERROR: clang{{.*}} error: invalid -Xopenmp-target argument: '-Xopenmp-target -Xopenmp-target', options requiring arguments are unsupported
/// ###########################################################################
/// Check -Xopenmp-target uses one of the archs provided when several archs are used.
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_35 -Xopenmp-target -march=sm_60 %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-FOPENMP-TARGET-ARCHS %s
// CHK-FOPENMP-TARGET-ARCHS: ptxas{{.*}}" "--gpu-name" "sm_60"
// CHK-FOPENMP-TARGET-ARCHS: nvlink{{.*}}" "-arch" "sm_60"
/// ###########################################################################
/// Check -Xopenmp-target -march=sm_35 works as expected when two triples are present.
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu,nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_35 %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-FOPENMP-TARGET-COMPILATION %s
// CHK-FOPENMP-TARGET-COMPILATION: ptxas{{.*}}" "--gpu-name" "sm_35"
// CHK-FOPENMP-TARGET-COMPILATION: nvlink{{.*}}" "-arch" "sm_35"