llvm-project

History

Jason Henline 6bfc863d74 [SE] Add CUDA platform Summary: Basic CUDA platform implementation and cmake infrastructure to control whether it's used. A few important TODOs will be handled in later patches: * Log some error messages that can't easily be returned as Errors. * Cache modules and kernels to prevent reloading them if someone tries to reload a kernel that's already loaded. * Tolerate shared memory arguments for kernel launches. Reviewers: jlebar Subscribers: beanz, mgorny, jprice, jlebar, parallel_libs-commits Differential Revision: https://reviews.llvm.org/D24538 llvm-svn: 281524		2016-09-14 19:58:34 +00:00
..
examples	[SE] Pack global dev handle addresses	2016-09-13 23:59:10 +00:00
include/streamexecutor	[SE] Add CUDA platform	2016-09-14 19:58:34 +00:00
lib	[SE] Add CUDA platform	2016-09-14 19:58:34 +00:00
tools/streamexecutor-config	Add streamexecutor-config	2016-09-08 16:12:33 +00:00
unittests	[SE] Pack global dev handle addresses	2016-09-13 23:59:10 +00:00
CMakeLists.txt	[SE] Add CUDA platform	2016-09-14 19:58:34 +00:00
Doxyfile.in	Add streamexecutor-config	2016-09-08 16:12:33 +00:00
README.txt	…
customdoxygen.css	[SE] Doc tweaks	2016-09-02 17:59:12 +00:00

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.