[Parallel_libs-commits] [PATCH] D24528: [SE] Pack global dev handle addresses

[Jason Henline via Parallel_libs-commits]

jhen created this revision.
jhen added a reviewer: jlebar.
jhen added subscribers: parallel_libs-commits, jprice.
Herald added a subscriber: jlebar.

We were packing global device memory handles in
`PackedKernelArgumentArray`, but as I was implementing the CUDA
platform, I realized that CUDA wants the address of the handle, not the
handle itself. So this patch switches to packing the address of the
handle.

https://reviews.llvm.org/D24528

Files:
  streamexecutor/examples/HostSaxpy.cpp
  streamexecutor/include/streamexecutor/DeviceMemory.h
  streamexecutor/include/streamexecutor/PackedKernelArgumentArray.h
  streamexecutor/unittests/CoreTests/PackedKernelArgumentArrayTest.cpp

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D24528.71256.patch
Type: text/x-patch
Size: 6182 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/parallel_libs-commits/attachments/20160913/dc247ef0/attachment-0001.bin>