This matches the way nvcc encapsulates GPU binaries into host object file.
Now cuobjdump can deal with clang-compiled object files.
Details
Details
Diff Detail
Diff Detail
- Repository
- rL LLVM
Paths
| Differential D23429
[CUDA] Place GPU binary into .nv_fatbin section and align it by 8.
ClosedPublic Authored by tra on Aug 11 2016, 3:29 PM.
Details Summary This matches the way nvcc encapsulates GPU binaries into host object file.
Diff Detail
Event Timeline
This revision is now accepted and ready to land.Aug 12 2016, 10:22 AM Closed by commit rL278549: [CUDA] Place GPU binary into .nv_fatbin section and align it by 8. (authored by tra). · Explain WhyAug 12 2016, 11:51 AM This revision was automatically updated to reflect the committed changes. tra marked an inline comment as done.
Revision Contents
Diff 67878 cfe/trunk/lib/CodeGen/CGCUDANV.cpp
cfe/trunk/test/CodeGenCUDA/device-stub.cu
|