Page MenuHomePhabricator
Differential D130020 Diff 455233 clang/test/Driver/openmp-offload-gpu.c

Changeset View

Standalone View

View Options

clang/test/Driver/openmp-offload-gpu.c

/// ///
/// Perform several driver tests for OpenMP offloading /// Perform several driver tests for OpenMP offloading
/// ///
// REQUIRES: x86-registered-target // REQUIRES: x86-registered-target
// REQUIRES: powerpc-registered-target // REQUIRES: powerpc-registered-target
// REQUIRES: nvptx-registered-target // REQUIRES: nvptx-registered-target
// REQUIRES: amdgpu-registered-target // REQUIRES: amdgpu-registered-target
// UNSUPPORTED: aix
/// ########################################################################### /// ###########################################################################
/// Check -Xopenmp-target uses one of the archs provided when several archs are used. /// Check -Xopenmp-target uses one of the archs provided when several archs are used.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -fno-openmp-new-driver -Xopenmp-target -march=sm_35 -Xopenmp-target -march=sm_60 %s 2>&1 \ // RUN: -Xopenmp-target -march=sm_35 -Xopenmp-target -march=sm_60 %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-FOPENMP-TARGET-ARCHS %s // RUN: | FileCheck -check-prefix=CHK-FOPENMP-TARGET-ARCHS %s
// CHK-FOPENMP-TARGET-ARCHS: ptxas{{.*}}" "--gpu-name" "sm_60" // 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. /// Check -Xopenmp-target -march=sm_35 works as expected when two triples are present.
// RUN: %clang -### -fopenmp=libomp -fno-openmp-new-driver \ // RUN: %clang -### -fopenmp=libomp \
// RUN: -fopenmp-targets=powerpc64le-ibm-linux-gnu,nvptx64-nvidia-cuda \ // RUN: -fopenmp-targets=powerpc64le-ibm-linux-gnu,nvptx64-nvidia-cuda \
// RUN: -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_35 %s 2>&1 \ // RUN: -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_35 %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-FOPENMP-TARGET-COMPILATION %s // RUN: | FileCheck -check-prefix=CHK-FOPENMP-TARGET-COMPILATION %s
// CHK-FOPENMP-TARGET-COMPILATION: ptxas{{.*}}" "--gpu-name" "sm_35" // 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 -### --target=powerpc64le-unknown-linux-gnu -fopenmp=libomp \
// RUN: -fno-openmp-new-driver -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 -### --target=x86_64-apple-darwin17.0.0 -fopenmp=libomp \
// RUN: -fno-openmp-new-driver -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-CUBIN-NVLINK %s
// CHK-CUBIN-NVLINK: clang{{.*}}" {{.*}}"-fopenmp-is-device" {{.*}}"-o" "[[PTX:.*\.s]]"
// CHK-CUBIN-NVLINK-NEXT: ptxas{{.*}}" "--output-file" "[[CUBIN:.*\.cubin]]" {{.*}}"[[PTX]]"
// CHK-CUBIN-NVLINK-NEXT: nvlink{{.*}}" {{.*}}"[[CUBIN]]"
/// ###########################################################################
/// Check unbundlink of assembly file, cubin file generation and usage by nvlink
// RUN: touch %t.s
// RUN: %clang -### --target=powerpc64le-unknown-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -fno-openmp-new-driver -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" {{.*}}"-output={{.*}}[[PTX]]
// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK-DAG-SAME: "-unbundle"
// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK: nvlink{{.*}}" {{.*}}"[[CUBIN]]"
/// ###########################################################################
/// Check cubin file generation and bundling
// RUN: %clang -### --target=powerpc64le-unknown-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -fno-openmp-new-driver -save-temps %s -c 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-PTXAS-CUBIN-BUNDLING %s
// 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" {{.*}}"-input={{.*}}[[CUBIN]]
/// ###########################################################################
/// Check cubin file unbundling and usage by nvlink
// RUN: touch %t.o
// RUN: %clang -### --target=powerpc64le-unknown-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -fno-openmp-new-driver -save-temps %t.o %S/Inputs/in.so 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-CUBIN-UNBUNDLING-NVLINK %s
/// Use DAG to ensure that cubin file has been unbundled.
// CHK-CUBIN-UNBUNDLING-NVLINK-NOT: clang-offload-bundler{{.*}}" "-type=o"{{.*}}in.so
// CHK-CUBIN-UNBUNDLING-NVLINK-DAG: nvlink{{.*}}" {{.*}}"[[CUBIN:.*\.cubin]]"
// CHK-CUBIN-UNBUNDLING-NVLINK-DAG: clang-offload-bundler{{.*}}" "-type=o" {{.*}}"-output={{.*}}[[CUBIN]]
// CHK-CUBIN-UNBUNDLING-NVLINK-DAG-SAME: "-unbundle"
// CHK-CUBIN-UNBUNDLING-NVLINK-NOT: clang-offload-bundler{{.*}}" "-type=o"{{.*}}in.so
/// ###########################################################################
/// Check cubin file generation and usage by nvlink
// RUN: touch %t1.o
// RUN: touch %t2.o
// RUN: %clang -### --target=powerpc64le-unknown-linux-gnu -fopenmp=libomp \
// RUN: -fno-openmp-new-driver -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 -### --target=x86_64-apple-darwin17.0.0 -fopenmp=libomp \
// RUN: -fno-openmp-new-driver -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 PTXAS is passed -c flag when offloading to an NVIDIA device using OpenMP. /// Check PTXAS is passed -c flag when offloading to an NVIDIA device using OpenMP.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-PTXAS-DEFAULT %s // RUN: | FileCheck -check-prefix=CHK-PTXAS-DEFAULT %s
// CHK-PTXAS-DEFAULT: ptxas{{.*}}" "-c" // CHK-PTXAS-DEFAULT: ptxas{{.*}}" "-c"
/// ########################################################################### /// ###########################################################################
▲ Show 20 Lines • Show All 91 Lines • ▼ Show 20 Lines
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_90/usr/local/cuda \ // RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_90/usr/local/cuda \
// RUN: -fopenmp-relocatable-target -save-temps %s 2>&1 \ // RUN: -fopenmp-relocatable-target -save-temps %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-CUDA-VERSION-ERROR %s // RUN: | FileCheck -check-prefix=CHK-CUDA-VERSION-ERROR %s
// CHK-CUDA-VERSION-ERROR: NVPTX target requires CUDA 9.2 or above; CUDA 9.0 detected // CHK-CUDA-VERSION-ERROR: NVPTX target requires CUDA 9.2 or above; CUDA 9.0 detected
/// Check that debug info is emitted in dwarf-2 /// Check that debug info is emitted in dwarf-2
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O1 --no-cuda-noopt-device-debug 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O1 --no-cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=DEBUG_DIRECTIVES %s // RUN: | FileCheck -check-prefix=DEBUG_DIRECTIVES %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O3 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O3 2>&1 \
// RUN: | FileCheck -check-prefix=DEBUG_DIRECTIVES %s // RUN: | FileCheck -check-prefix=DEBUG_DIRECTIVES %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O3 --no-cuda-noopt-device-debug 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O3 --no-cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=DEBUG_DIRECTIVES %s // RUN: | FileCheck -check-prefix=DEBUG_DIRECTIVES %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g0 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g0 2>&1 \
// RUN: | FileCheck -check-prefix=NO_DEBUG %s // RUN: | FileCheck -check-prefix=NO_DEBUG %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb0 -O3 --cuda-noopt-device-debug 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb0 -O3 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=NO_DEBUG %s // RUN: | FileCheck -check-prefix=NO_DEBUG %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -gline-directives-only 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -gline-directives-only 2>&1 \
// RUN: | FileCheck -check-prefix=DEBUG_DIRECTIVES %s // RUN: | FileCheck -check-prefix=DEBUG_DIRECTIVES %s
// DEBUG_DIRECTIVES-NOT: warning: debug // DEBUG_DIRECTIVES-NOT: warning: debug
// NO_DEBUG-NOT: warning: debug // NO_DEBUG-NOT: warning: debug
// NO_DEBUG: "-fopenmp-is-device" // NO_DEBUG: "-fopenmp-is-device"
// NO_DEBUG-NOT: "-debug-info-kind= // NO_DEBUG-NOT: "-debug-info-kind=
// NO_DEBUG: ptxas // NO_DEBUG: ptxas
// DEBUG_DIRECTIVES: "-triple" "nvptx64-nvidia-cuda" // DEBUG_DIRECTIVES: "-triple" "nvptx64-nvidia-cuda"
// DEBUG_DIRECTIVES-SAME: "-debug-info-kind=line-directives-only" // DEBUG_DIRECTIVES-SAME: "-debug-info-kind=line-directives-only"
// DEBUG_DIRECTIVES-SAME: "-fopenmp-is-device" // DEBUG_DIRECTIVES-SAME: "-fopenmp-is-device"
// DEBUG_DIRECTIVES: ptxas // DEBUG_DIRECTIVES: ptxas
// DEBUG_DIRECTIVES: "-lineinfo" // DEBUG_DIRECTIVES: "-lineinfo"
// NO_DEBUG-NOT: "-g"
// NO_DEBUG: nvlink
// NO_DEBUG-NOT: "-g"
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O0 --no-cuda-noopt-device-debug 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O0 --no-cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s // RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s // RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O0 --cuda-noopt-device-debug 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O0 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s // RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O3 --cuda-noopt-device-debug 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O3 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s // RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g2 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g2 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s // RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb2 -O0 --cuda-noopt-device-debug 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb2 -O0 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s // RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g3 -O3 --cuda-noopt-device-debug 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g3 -O3 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s // RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb3 -O2 --cuda-noopt-device-debug 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb3 -O2 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s // RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -gline-tables-only 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -gline-tables-only 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s // RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -fno-openmp-new-driver -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb1 -O2 --cuda-noopt-device-debug 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb1 -O2 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s // RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// HAS_DEBUG-NOT: warning: debug // HAS_DEBUG-NOT: warning: debug
// HAS_DEBUG: "-triple" "nvptx64-nvidia-cuda" // HAS_DEBUG: "-triple" "nvptx64-nvidia-cuda"
// HAS_DEBUG-SAME: "-debug-info-kind={{constructor|line-tables-only}}" // HAS_DEBUG-SAME: "-debug-info-kind={{constructor|line-tables-only}}"
// HAS_DEBUG-SAME: "-dwarf-version=2" // HAS_DEBUG-SAME: "-dwarf-version=2"
// HAS_DEBUG-SAME: "-fopenmp-is-device" // HAS_DEBUG-SAME: "-fopenmp-is-device"
// HAS_DEBUG: ptxas // HAS_DEBUG: ptxas
// HAS_DEBUG-SAME: "-g" // HAS_DEBUG-SAME: "-g"
// HAS_DEBUG-SAME: "--dont-merge-basicblocks" // HAS_DEBUG-SAME: "--dont-merge-basicblocks"
// HAS_DEBUG-SAME: "--return-at-end" // HAS_DEBUG-SAME: "--return-at-end"
// HAS_DEBUG: nvlink
// HAS_DEBUG-SAME: "-g"
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fopenmp-cuda-mode 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fopenmp-cuda-mode 2>&1 \
// RUN: | FileCheck -check-prefix=CUDA_MODE %s // RUN: | FileCheck -check-prefix=CUDA_MODE %s
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fno-openmp-cuda-mode -fopenmp-cuda-mode 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fno-openmp-cuda-mode -fopenmp-cuda-mode 2>&1 \
// RUN: | FileCheck -check-prefix=CUDA_MODE %s // RUN: | FileCheck -check-prefix=CUDA_MODE %s
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target -march=gfx906 %s -fopenmp-cuda-mode 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target -march=gfx906 %s -fopenmp-cuda-mode 2>&1 \
// RUN: | FileCheck -check-prefix=CUDA_MODE %s // RUN: | FileCheck -check-prefix=CUDA_MODE %s
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target -march=gfx906 %s -fno-openmp-cuda-mode -fopenmp-cuda-mode 2>&1 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target -march=gfx906 %s -fno-openmp-cuda-mode -fopenmp-cuda-mode 2>&1 \
▲ Show 20 Lines • Show All 47 Lines • ▼ Show 20 Lines
// SAVE_TEMPS_NAMES-NOT: "GNU::Linker"{{.*}}["[[SAVE_TEMPS_INPUT1:.*\.o]]", "[[SAVE_TEMPS_INPUT1]]"] // SAVE_TEMPS_NAMES-NOT: "GNU::Linker"{{.*}}["[[SAVE_TEMPS_INPUT1:.*\.o]]", "[[SAVE_TEMPS_INPUT1]]"]
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64 -Xopenmp-target=nvptx64 -march=sm_35 \ // RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64 -Xopenmp-target=nvptx64 -march=sm_35 \
// RUN: -save-temps %s -o openmp-offload-gpu 2>&1 \ // RUN: -save-temps %s -o openmp-offload-gpu 2>&1 \
// RUN: | FileCheck -check-prefix=TRIPLE %s // RUN: | FileCheck -check-prefix=TRIPLE %s
// TRIPLE: "-triple" "nvptx64-nvidia-cuda" // TRIPLE: "-triple" "nvptx64-nvidia-cuda"
// TRIPLE: "-target-cpu" "sm_35" // TRIPLE: "-target-cpu" "sm_35"
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 \
// RUN: --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget/libomptarget-nvptx-test.bc %s 2>&1 \
// RUN: | FileCheck %s
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: --offload-arch=sm_52 \
// RUN: --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget/libomptarget-nvptx-test.bc %s 2>&1 \
// RUN: | FileCheck %s
// verify the tools invocations
// CHECK: "-cc1" "-triple" "x86_64-unknown-linux-gnu"{{.*}}"-emit-llvm-bc"{{.*}}"-x" "c"
// CHECK: "-cc1" "-triple" "nvptx64-nvidia-cuda" "-aux-triple" "x86_64-unknown-linux-gnu"{{.*}}"-target-cpu" "sm_52"
// CHECK: "-cc1" "-triple" "x86_64-unknown-linux-gnu"{{.*}}"-emit-obj"
// CHECK: clang-linker-wrapper{{.*}}"--"{{.*}} "-o" "a.out"
// RUN: %clang -ccc-print-phases --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-PHASES %s
// CHECK-PHASES: 0: input, "[[INPUT:.+]]", c, (host-openmp)
// CHECK-PHASES: 1: preprocessor, {0}, cpp-output, (host-openmp)
// CHECK-PHASES: 2: compiler, {1}, ir, (host-openmp)
// CHECK-PHASES: 3: input, "[[INPUT]]", c, (device-openmp)
// CHECK-PHASES: 4: preprocessor, {3}, cpp-output, (device-openmp)
// CHECK-PHASES: 5: compiler, {4}, ir, (device-openmp)
// CHECK-PHASES: 6: offload, "host-openmp (x86_64-unknown-linux-gnu)" {2}, "device-openmp (nvptx64-nvidia-cuda)" {5}, ir
// CHECK-PHASES: 7: backend, {6}, assembler, (device-openmp)
// CHECK-PHASES: 8: assembler, {7}, object, (device-openmp)
// CHECK-PHASES: 9: offload, "device-openmp (nvptx64-nvidia-cuda)" {8}, object
// CHECK-PHASES: 10: clang-offload-packager, {9}, image
// CHECK-PHASES: 11: offload, "host-openmp (x86_64-unknown-linux-gnu)" {2}, " (x86_64-unknown-linux-gnu)" {10}, ir
// CHECK-PHASES: 12: backend, {11}, assembler, (host-openmp)
// CHECK-PHASES: 13: assembler, {12}, object, (host-openmp)
// CHECK-PHASES: 14: clang-linker-wrapper, {13}, image, (host-openmp)
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-BINDINGS
// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[HOST_BC:.+]]"
// CHECK-BINDINGS: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[DEVICE_BC:.+]]"
// CHECK-BINDINGS: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_BC]]"], output: "[[DEVICE_OBJ:.+]]"
// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[DEVICE_OBJ]]"], output: "[[BINARY:.+.out]]"
// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]", "[[BINARY]]"], output: "[[HOST_OBJ:.+]]"
// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs: ["[[HOST_OBJ]]"], output: "a.out"
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 -nogpulib -save-temps %s 2>&1 | FileCheck %s --check-prefix=CHECK-TEMP-BINDINGS
// CHECK-TEMP-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[DEVICE_OBJ:.+]]"], output: "[[BINARY:.+.out]]"
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda --offload-arch=sm_52 --offload-arch=sm_70 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-ARCH-BINDINGS
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda --offload-arch=sm_52,sm_70 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-ARCH-BINDINGS
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda --offload-arch=sm_52,sm_70,sm_35,sm_80 --no-offload-arch=sm_35,sm_80 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-ARCH-BINDINGS
// CHECK-ARCH-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.*]]"], output: "[[HOST_BC:.*]]"
// CHECK-ARCH-BINDINGS: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[DEVICE_BC_SM_52:.*]]"
// CHECK-ARCH-BINDINGS: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_BC_SM_52]]"], output: "[[DEVICE_OBJ_SM_52:.*]]"
// CHECK-ARCH-BINDINGS: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[DEVICE_BC_SM_70:.*]]"
// CHECK-ARCH-BINDINGS: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_BC_SM_70]]"], output: "[[DEVICE_OBJ_SM_70:.*]]"
// CHECK-ARCH-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[DEVICE_OBJ_SM_52]]", "[[DEVICE_OBJ_SM_70]]"], output: "[[BINARY:.*]]"
// CHECK-ARCH-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]", "[[BINARY]]"], output: "[[HOST_OBJ:.*]]"
// CHECK-ARCH-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs: ["[[HOST_OBJ]]"], output: "a.out"
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp \
// RUN: -fopenmp-targets=nvptx64-nvidia-cuda,amdgcn-amd-amdhsa -Xopenmp-target=nvptx64-nvidia-cuda --offload-arch=sm_70 \
// RUN: -fopenmp-targets=nvptx64-nvidia-cuda,amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa --offload-arch=gfx908 \
// RUN: -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-NVIDIA-AMDGPU
// CHECK-NVIDIA-AMDGPU: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[HOST_BC:.+]]"
// CHECK-NVIDIA-AMDGPU: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[NVIDIA_PTX:.+]]"
// CHECK-NVIDIA-AMDGPU: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[NVIDIA_PTX]]"], output: "[[NVIDIA_CUBIN:.+]]"
// CHECK-NVIDIA-AMDGPU: "amdgcn-amd-amdhsa" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[AMD_BC:.+]]"
// CHECK-NVIDIA-AMDGPU: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[NVIDIA_CUBIN]]", "[[AMD_BC]]"], output: "[[BINARY:.*]]"
// CHECK-NVIDIA-AMDGPU: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]", "[[BINARY]]"], output: "[[HOST_OBJ:.+]]"
// CHECK-NVIDIA-AMDGPU: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs: ["[[HOST_OBJ]]"], output: "a.out"
// RUN: %clang -x ir -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp --offload-arch=sm_52 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-IR
// CHECK-IR: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT_IR:.+]]"], output: "[[OBJECT:.+]]"
// CHECK-IR: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs: ["[[OBJECT]]"], output: "a.out"
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR
// CHECK-EMIT-LLVM-IR: "-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda"{{.*}}"-emit-llvm"
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvida-cuda -march=sm_70 \
// RUN: --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget/libomptarget-new-nvptx-test.bc \
// RUN: -nogpulib %s -o openmp-offload-gpu 2>&1 \
// RUN: | FileCheck -check-prefix=DRIVER_EMBEDDING %s
// DRIVER_EMBEDDING: -fembed-offload-object={{.*}}.out
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: --offload-host-only -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-HOST-ONLY
// CHECK-HOST-ONLY: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.*]]"], output: "[[OUTPUT:.*]]"
// CHECK-HOST-ONLY: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs: ["[[OUTPUT]]"], output: "a.out"
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: --offload-device-only -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-DEVICE-ONLY
// CHECK-DEVICE-ONLY: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.*]]"], output: "[[HOST_BC:.*]]"
// CHECK-DEVICE-ONLY: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[DEVICE_ASM:.*]]"
// CHECK-DEVICE-ONLY: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_ASM]]"], output: "{{.*}}-openmp-nvptx64-nvidia-cuda.o"
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: --offload-device-only -E -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-DEVICE-ONLY-PP
// CHECK-DEVICE-ONLY-PP: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT:.*]]"], output: "-"
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp --offload-arch=sm_52 \
// RUN: -foffload-lto %s 2>&1 | FileCheck --check-prefix=CHECK-LTO-LIBRARY %s
// CHECK-LTO-LIBRARY: {{.*}}-lomptarget{{.*}}-lomptarget.devicertl
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp --offload-arch=sm_52 -nogpulib \
// RUN: -foffload-lto %s 2>&1 | FileCheck --check-prefix=CHECK-NO-LIBRARY %s
// CHECK-NO-LIBRARY-NOT: {{.*}}-lomptarget{{.*}}-lomptarget.devicertl
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp --offload-arch=sm_52 -nogpulib \
// RUN: -Xoffload-linker a -Xoffload-linker-nvptx64-nvidia-cuda b -Xoffload-linker-nvptx64 c \
// RUN: %s 2>&1 | FileCheck --check-prefix=CHECK-XLINKER %s
// CHECK-XLINKER: -device-linker=a{{.*}}-device-linker=nvptx64-nvidia-cuda=b{{.*}}-device-linker=nvptx64-nvidia-cuda=c{{.*}}--
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp --offload-arch=sm_52 -nogpulib \
// RUN: -foffload-lto %s 2>&1 | FileCheck --check-prefix=CHECK-LTO-FEATURES %s
// CHECK-LTO-FEATURES: clang-offload-packager{{.*}}--image={{.*}}feature=+ptx{{[0-9]+}}
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp --offload-arch=sm_52 -nogpulib \
// RUN: -Xopenmp-target=nvptx64-nvidia-cuda --cuda-feature=+ptx64 -foffload-lto %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-SET-FEATURES %s
// CHECK-SET-FEATURES: clang-offload-packager{{.*}}--image={{.*}}feature=+ptx64