forked from OSchip/llvm-project
b071092756
Summary: Add types for device memory and add the code that knows how to pack these device memory types if they are passed as arguments to kernel launches. Reviewers: jlebar, tra Subscribers: parallel_libs-commits Differential Revision: https://reviews.llvm.org/D23211 llvm-svn: 278021 |
||
---|---|---|
.. | ||
include/streamexecutor | ||
lib | ||
CMakeLists.txt | ||
README.txt |
README.txt
StreamExecutor ============== StreamExecutor is a wrapper around CUDA and OpenCL (host-side) programming models (runtimes). This abstraction cleanly permits host code to target either CUDA or OpenCL devices with identically-functioning data parallel kernels. It manages the execution of concurrent work targeting the accelerator, similar to a host-side Executor. This version of StreamExecutor can be built either as a sub-project of the LLVM project or as a standalone project depending on LLVM as an external package.