diff options
| author | Artem Belevich <tra@google.com> | 2016-08-12 18:44:01 +0000 |
|---|---|---|
| committer | Artem Belevich <tra@google.com> | 2016-08-12 18:44:01 +0000 |
| commit | 4c09318be2dd449812345a8277565589cebd25e5 (patch) | |
| tree | 6e8d32a64e44c49df691977bcbc5e7be205ef914 /clang/test/CodeGenCUDA | |
| parent | dc698c3e91997836a7ae3f2d5a0766469edf0d20 (diff) | |
| download | bcm5719-llvm-4c09318be2dd449812345a8277565589cebd25e5.tar.gz bcm5719-llvm-4c09318be2dd449812345a8277565589cebd25e5.zip | |
[CUDA] Place GPU binary into .nv_fatbin section and align it by 8.
This matches the way nvcc encapsulates GPU binaries into host object file.
Now cuobjdump can deal with clang-compiled object files.
Differential Revision: https://reviews.llvm.org/D23429
llvm-svn: 278549
Diffstat (limited to 'clang/test/CodeGenCUDA')
| -rw-r--r-- | clang/test/CodeGenCUDA/device-stub.cu | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/clang/test/CodeGenCUDA/device-stub.cu b/clang/test/CodeGenCUDA/device-stub.cu index 5979ba3fce6..3376803c502 100644 --- a/clang/test/CodeGenCUDA/device-stub.cu +++ b/clang/test/CodeGenCUDA/device-stub.cu @@ -45,10 +45,12 @@ void use_pointers() { // * constant unnamed string with the kernel name // CHECK: private unnamed_addr constant{{.*}}kernelfunc{{.*}}\00" // * constant unnamed string with GPU binary -// CHECK: private unnamed_addr constant{{.*}}\00" +// CHECK: private unnamed_addr constant{{.*GPU binary would be here.*}}\00" +// CHECK-SAME: section ".nv_fatbin", align 8 // * constant struct that wraps GPU binary // CHECK: @__cuda_fatbin_wrapper = internal constant { i32, i32, i8*, i8* } -// CHECK: { i32 1180844977, i32 1, {{.*}}, i8* null } +// CHECK-SAME: { i32 1180844977, i32 1, {{.*}}, i8* null } +// CHECK-SAME: section ".nvFatBinSegment" // * variable to save GPU binary handle after initialization // CHECK: @__cuda_gpubin_handle = internal global i8** null // * Make sure our constructor/destructor was added to global ctor/dtor list. |
