maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/Driver/cuda-march.cu

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

23 lines
772 B
Plaintext
Raw Normal View History

[CUDA] Don't pass top-level -march down to device cc1 or ptxas. Summary: Previously if you did e.g. $ clang -march=haswell -x cuda foo.cu we would pass "-march=haswell -march=sm_20" down to the ptxas tool. This causes it to assert, and rightly so! Reviewers: tra Subscribers: cfe-commits, echristo Differential Revision: http://reviews.llvm.org/D21419 llvm-svn: 272857
2016-06-16 07:46:11 +08:00
// Checks that cuda compilation does the right thing when passed -march.
// (Specifically, we want to pass it to host compilation, but not to device
// compilation or ptxas!)
//
// REQUIRES: clang-driver
// REQUIRES: x86-registered-target
// REQUIRES: nvptx-registered-target
A follow-up fixing on cuda-march.cu: Don't match clang to other place. llvm-svn: 272890
2016-06-16 21:27:02 +08:00
// RUN: %clang -no-canonical-prefixes -### -target x86_64-linux-gnu -c \
// RUN: -march=haswell %s 2>&1 | FileCheck %s
// RUN: %clang -no-canonical-prefixes -### -target x86_64-linux-gnu -c \
// RUN: -march=haswell --cuda-gpu-arch=sm_20 %s 2>&1 | FileCheck %s
[CUDA] Don't pass top-level -march down to device cc1 or ptxas. Summary: Previously if you did e.g. $ clang -march=haswell -x cuda foo.cu we would pass "-march=haswell -march=sm_20" down to the ptxas tool. This causes it to assert, and rightly so! Reviewers: tra Subscribers: cfe-commits, echristo Differential Revision: http://reviews.llvm.org/D21419 llvm-svn: 272857
2016-06-16 07:46:11 +08:00
A follow-up fixing on cuda-march.cu: Don't match clang to other place. llvm-svn: 272890
2016-06-16 21:27:02 +08:00
// CHECK: {{.*}}clang{{.*}}" "-cc1"
[CUDA] Don't pass top-level -march down to device cc1 or ptxas. Summary: Previously if you did e.g. $ clang -march=haswell -x cuda foo.cu we would pass "-march=haswell -march=sm_20" down to the ptxas tool. This causes it to assert, and rightly so! Reviewers: tra Subscribers: cfe-commits, echristo Differential Revision: http://reviews.llvm.org/D21419 llvm-svn: 272857
2016-06-16 07:46:11 +08:00
// CHECK-SAME: "-triple" "nvptx
// CHECK-SAME: "-target-cpu" "sm_20"
// CHECK: ptxas
// CHECK-SAME: "--gpu-name" "sm_20"
A follow-up fixing on cuda-march.cu: Don't match clang to other place. llvm-svn: 272890
2016-06-16 21:27:02 +08:00
// CHECK: {{.*}}clang{{.*}}" "-cc1"
[CUDA] Don't pass top-level -march down to device cc1 or ptxas. Summary: Previously if you did e.g. $ clang -march=haswell -x cuda foo.cu we would pass "-march=haswell -march=sm_20" down to the ptxas tool. This causes it to assert, and rightly so! Reviewers: tra Subscribers: cfe-commits, echristo Differential Revision: http://reviews.llvm.org/D21419 llvm-svn: 272857
2016-06-16 07:46:11 +08:00
// CHECK-SAME: "-target-cpu" "haswell"