Dataflow-driven GPU performance projection for multi-kernel transformations
Published in IEEE International Conference on High Performance Computing, Data, and Analytics • Nov 10, 2012
NobleIDNI5P14W63R64S83
Authors:,,
Jiayuan Meng
Vitali Morozov
Venkatram Vishwanath
Abstract
Applications often have a sequence of parallel operations to be offloaded to graphics processors; each operation can become an individual GPU kernel. Developers typically explore a variety of transformations for each kernel. Furthermore, it is well known that efficient data management is critical in...
Finding related papers...
Discussions
(0)No comments yet
Be the first to share your thoughts!