projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: dc698c3) | patch
[CUDA] Place GPU binary into .nv_fatbin section and align it by 8.
authorArtem Belevich <tra@google.com>
Fri, 12 Aug 2016 18:44:01 +0000 (18:44 +0000)
committerArtem Belevich <tra@google.com>
Fri, 12 Aug 2016 18:44:01 +0000 (18:44 +0000)
commit4c09318be2dd449812345a8277565589cebd25e5
tree6e8d32a64e44c49df691977bcbc5e7be205ef914tree | snapshot
parentdc698c3e91997836a7ae3f2d5a0766469edf0d20commit | diff
[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
clang/lib/CodeGen/CGCUDANV.cpp diff | blob | history
clang/test/CodeGenCUDA/device-stub.cu diff | blob | history
Domain: System / Toolchain;