Cold-Air-Networks/mirror-llvm-project
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 7

[CUDA] Allow using -o with -fsyntax-only

Browse source 
-fsyntax-only breaks down CUDA compilation pipeline and make it look like
multiple independent subcompilations and that trips the multiple arguments check
when -o is specified.

We do want to allow -fsyntax-only to be used with otherwise unmodified clang
options as it's commonly used by various tooling.

Differential Revision: https://reviews.llvm.org/D133133
This commit is contained in:
Artem Belevich 2022-09-01 11:24:35 -07:00
parent ca01c996b2
commit 54c47ff939
2 changed files with 61 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
clang/lib/Driver/Driver.cpp
View file

@ -4536,7 +4536,8 @@ void Driver::BuildJobs(Compilation &C) const {
//
// OffloadClass of type TY_Nothing: device-only output will place many outputs
// into a single offloading action. We should count all inputs to the action
// as outputs.
// as outputs. Also ignore device-only outputs if we're compiling with
// -fsyntax-only.
if (FinalOutput) {
unsigned NumOutputs = 0;
unsigned NumIfsOutputs = 0;
@ -4550,7 +4551,8 @@ void Driver::BuildJobs(Compilation &C) const {
A->getInputs().front()->getKind() == Action::IfsMergeJobClass)))
++NumOutputs;
else if (A->getKind() == Action::OffloadClass &&
A->getType() == types::TY_Nothing)
A->getType() == types::TY_Nothing &&
!C.getArgs().hasArg(options::OPT_fsyntax_only))
NumOutputs += A->size();
}

61
clang/test/Driver/cuda-bindings.cu
View file

@ -39,9 +39,19 @@
//
// 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: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings --offload-arch=sm_30,sm_35 %s 2>&1 \
// RUN: | FileCheck -check-prefix=BIN2 %s
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=BIN2,AOUT %s
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --offload-arch=sm_30,sm_35 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=BIN2,AOUT %s
// .. same, but with explicitly specified output.
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s -o %t/out 2>&1 \
// RUN: | FileCheck -check-prefixes=BIN2,TOUT %s
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
// RUN: --offload-arch=sm_30,sm_35 %s -o %t/out 2>&1 \
// RUN: | FileCheck -check-prefixes=BIN2,TOUT %s
// BIN2: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output:
// BIN2-NOT: cuda-bindings-device-cuda-nvptx64
// BIN2: # "nvptx64-nvidia-cuda" - "NVPTX::Assembler",{{.*}} output:
@ -54,7 +64,50 @@
// 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"
// AOUT: # "powerpc64le-ibm-linux-gnu" - "GNU::Linker", inputs:{{.*}}, output: "a.out"
// TOUT: # "powerpc64le-ibm-linux-gnu" - "GNU::Linker", inputs:{{.*}}, output: "{{.*}}/out"
// .. same, but with -fsyntax-only
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings -fsyntax-only \
// RUN: --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s 2>&1 \
// RUN: | FileCheck -check-prefix=SYN %s
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings -fsyntax-only \
// RUN: --offload-arch=sm_30,sm_35 %s -o %t/out 2>&1 \
// RUN: | FileCheck -check-prefix=SYN %s
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings -fsyntax-only \
// RUN: --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s 2>&1 \
// RUN: | FileCheck -check-prefix=SYN %s
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings -fsyntax-only \
// RUN: --offload-arch=sm_30,sm_35 %s -o %t/out 2>&1 \
// RUN: | FileCheck -check-prefix=SYN %s
// SYN-NOT: inputs:
// SYN: # "powerpc64le-ibm-linux-gnu" - "clang", inputs: [{{.*}}], output: (nothing)
// SYN-NEXT: # "nvptx64-nvidia-cuda" - "clang", inputs: [{{.*}}], output: (nothing)
// SYN-NEXT: # "nvptx64-nvidia-cuda" - "clang", inputs: [{{.*}}], output: (nothing)
// SYN-NOT: inputs
// .. and with --offload-new-driver
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings -fsyntax-only \
// RUN: --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 --offload-new-driver %s 2>&1 \
// RUN: | FileCheck -check-prefix=NDSYN %s
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings -fsyntax-only \
// RUN: --offload-arch=sm_30,sm_35 %s --offload-new-driver -o %t/out 2>&1 \
// RUN: | FileCheck -check-prefix=NDSYN %s
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings -fsyntax-only \
// RUN: --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s --offload-new-driver 2>&1 \
// RUN: | FileCheck -check-prefix=NDSYN %s
// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings -fsyntax-only \
// RUN: --offload-arch=sm_30,sm_35 %s --offload-new-driver -o %t/out 2>&1 \
// RUN: | FileCheck -check-prefix=NDSYN %s
// NDSYN-NOT: inputs:
// NDSYN: # "nvptx64-nvidia-cuda" - "clang", inputs: [{{.*}}], output: (nothing)
// NDSYN-NEXT: # "nvptx64-nvidia-cuda" - "clang", inputs: [{{.*}}], output: (nothing)
// ! FIXME: new driver erroneously attempts to run linker phase w/ no inputs.
// Remove these checks once the issue is solved.
// NDSYN-NEXT: "nvptx64-nvidia-cuda" - "NVPTX::Linker", inputs: [(nothing), (nothing)], output: "{{.*}}"
// NDSYN-NEXT: # "powerpc64le-ibm-linux-gnu" - "clang", inputs: [{{.*}}], output: (nothing)
// NDSYN-NOT: inputs:
//
// Test two gpu architectures up to the assemble phase.