Skip to content

Commit

Permalink
[CUDA] Collapsed offload actions should not be top-level jobs.
Browse files Browse the repository at this point in the history 
If they are, we end up with the last intermediary output preserved
in the current directory after compilation.

Added a test case to verify that we're using appropriate filenames
for outputs of different phases.

Differential Revision: https://reviews.llvm.org/D23526

llvm-svn: 279455
@Artem-B
Artem-B committed Aug 22, 2016
1 parent 0fee97f commit bee2f41
Showing 2 changed files with 138 additions and 1 deletion.
2 changes: 1 addition & 1 deletion clang/lib/Driver/Driver.cpp
View file
Original file line number Diff line number Diff line change
@@ -2230,7 +2230,7 @@ InputInfo Driver::BuildJobsForActionNoCache(
/*IsHostDependence=*/BuildForOffloadDevice,
[&](Action *DepA, const ToolChain *DepTC, const char *DepBoundArch) {
OffloadDependencesInputInfo.push_back(BuildJobsForAction(
C, DepA, DepTC, DepBoundArch, AtTopLevel,
C, DepA, DepTC, DepBoundArch, /* AtTopLevel */ false,
/*MultipleArchs=*/!!DepBoundArch, LinkingOutput, CachedResults,
/*BuildForOffloadDevice=*/DepA->getOffloadingDeviceKind() !=
Action::OFK_None));
137 changes: 137 additions & 0 deletions clang/test/Driver/cuda-bindings.cu
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,137 @@
// Tests the bindings generated for a CUDA offloading target for different
// combinations of:
// - Number of gpu architectures;
// - Host/device-only compilation;
// - User-requested final phase - binary or assembly.
// It parallels cuda-phases.cu test, but verifies whether output file is temporary or not.

// It's hard to check whether file name is temporary in a portable
// way. Instead we check whether we've generated a permanent name on
// device side, which appends '-device-cuda-<triple>' suffix.

// REQUIRES: clang-driver
// REQUIRES: powerpc-registered-target
// REQUIRES: nvptx-registered-target

//
// Test single gpu architecture with complete compilation.
// No intermediary device files should have "-device-cuda..." in the name.
//
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings --cuda-gpu-arch=sm_30 %s 2>&1 \
// RUN: | FileCheck -check-prefix=BIN %s
// BIN: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output:
// BIN-NOT: cuda-bindings-device-cuda-nvptx64
// BIN: # "nvptx64-nvidia-cuda" - "NVPTX::Assembler",{{.*}} output:
// BIN-NOT: cuda-bindings-device-cuda-nvptx64
// BIN: # "nvptx64-nvidia-cuda" - "NVPTX::Linker",{{.*}} output:
// BIN-NOT: cuda-bindings-device-cuda-nvptx64
// BIN: # "powerpc64le-ibm-linux-gnu" - "clang",{{.*}} output:
// BIN-NOT: cuda-bindings-device-cuda-nvptx64
// BIN: # "powerpc64le-ibm-linux-gnu" - "GNU::Linker", inputs:{{.*}}, output: "a.out"

//
// Test single gpu architecture up to the assemble phase.
//
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings --cuda-gpu-arch=sm_30 %s -S 2>&1 \
// RUN: | FileCheck -check-prefix=ASM %s
// ASM: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output: "cuda-bindings-device-cuda-nvptx64-nvidia-cuda-sm_30.s"
// ASM: # "powerpc64le-ibm-linux-gnu" - "clang",{{.*}} output: "cuda-bindings.s"

//
// Test two gpu architectures with complete compilation.
//
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s 2>&1 \
// RUN: | FileCheck -check-prefix=BIN2 %s
// BIN2: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output:
// BIN2-NOT: cuda-bindings-device-cuda-nvptx64
// BIN2: # "nvptx64-nvidia-cuda" - "NVPTX::Assembler",{{.*}} output:
// BIN2-NOT: cuda-bindings-device-cuda-nvptx64
// BIN2: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output:
// BIN2-NOT: cuda-bindings-device-cuda-nvptx64
// BIN2: # "nvptx64-nvidia-cuda" - "NVPTX::Assembler",{{.*}} output:
// BIN2-NOT: cuda-bindings-device-cuda-nvptx64
// BIN2: # "nvptx64-nvidia-cuda" - "NVPTX::Linker",{{.*}} output:
// BIN2-NOT: cuda-bindings-device-cuda-nvptx64
// BIN2: # "powerpc64le-ibm-linux-gnu" - "clang",{{.*}} output:
// BIN2-NOT: cuda-bindings-device-cuda-nvptx64
// BIN2: # "powerpc64le-ibm-linux-gnu" - "GNU::Linker", inputs:{{.*}}, output: "a.out"

//
// Test two gpu architectures up to the assemble phase.
//
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s -S 2>&1 \
// RUN: | FileCheck -check-prefix=ASM2 %s
// ASM2: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output: "cuda-bindings-device-cuda-nvptx64-nvidia-cuda-sm_30.s"
// ASM2: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output: "cuda-bindings-device-cuda-nvptx64-nvidia-cuda-sm_35.s"
// ASM2: # "powerpc64le-ibm-linux-gnu" - "clang",{{.*}} output: "cuda-bindings.s"

//
// Test one or more gpu architecture with complete compilation in host-only
// compilation mode.
//
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --cuda-gpu-arch=sm_30 %s --cuda-host-only 2>&1 \
// RUN: | FileCheck -check-prefix=HBIN %s
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s --cuda-host-only 2>&1 \
// RUN: | FileCheck -check-prefix=HBIN %s
// HBIN: # "powerpc64le-ibm-linux-gnu" - "clang",{{.*}} output:
// HBIN-NOT: cuda-bindings-device-cuda-nvptx64
// HBIN: # "powerpc64le-ibm-linux-gnu" - "GNU::Linker", inputs:{{.*}}, output: "a.out"

//
// Test one or more gpu architecture up to the assemble phase in host-only
// compilation mode.
//
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --cuda-gpu-arch=sm_30 %s --cuda-host-only -S 2>&1 \
// RUN: | FileCheck -check-prefix=HASM %s
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s --cuda-host-only -S 2>&1 \
// RUN: | FileCheck -check-prefix=HASM %s
// HASM: # "powerpc64le-ibm-linux-gnu" - "clang",{{.*}} output: "cuda-bindings.s"

//
// Test single gpu architecture with complete compilation in device-only
// compilation mode.
//
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --cuda-gpu-arch=sm_30 %s --cuda-device-only 2>&1 \
// RUN: | FileCheck -check-prefix=DBIN %s
// DBIN: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output:
// DBIN-NOT: cuda-bindings-device-cuda-nvptx64
// DBIN: # "nvptx64-nvidia-cuda" - "NVPTX::Assembler",{{.*}} output: "cuda-bindings-device-cuda-nvptx64-nvidia-cuda-sm_30.o"

//
// Test single gpu architecture up to the assemble phase in device-only
// compilation mode.
//
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --cuda-gpu-arch=sm_30 %s --cuda-device-only -S 2>&1 \
// RUN: | FileCheck -check-prefix=DASM %s
// DASM: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output: "cuda-bindings-device-cuda-nvptx64-nvidia-cuda-sm_30.s"

//
// Test two gpu architectures with complete compilation in device-only
// compilation mode.
//
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s --cuda-device-only 2>&1 \
// RUN: | FileCheck -check-prefix=DBIN2 %s
// DBIN2: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output:
// DBIN2-NOT: cuda-bindings-device-cuda-nvptx64
// DBIN2: # "nvptx64-nvidia-cuda" - "NVPTX::Assembler",{{.*}} output: "cuda-bindings-device-cuda-nvptx64-nvidia-cuda-sm_30.o"
// DBIN2: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output:
// DBIN2-NOT: cuda-bindings-device-cuda-nvptx64
// DBIN2: # "nvptx64-nvidia-cuda" - "NVPTX::Assembler",{{.*}} output: "cuda-bindings-device-cuda-nvptx64-nvidia-cuda-sm_35.o"

//
// Test two gpu architectures up to the assemble phase in device-only
// compilation mode.
//
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s --cuda-device-only -S 2>&1 \
// RUN: | FileCheck -check-prefix=DASM2 %s
// DASM2: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output: "cuda-bindings-device-cuda-nvptx64-nvidia-cuda-sm_30.s"
// DASM2: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output: "cuda-bindings-device-cuda-nvptx64-nvidia-cuda-sm_35.s"

0 comments on commit bee2f41

Please sign in to comment.