DocumentCode :
598617
Title :
Dataflow-driven GPU performance projection for multi-kernel transformations
Author :
Jiayuan Meng ; Morozov, V.A. ; Vishwanath, Venkatram ; Kumaran, Kalyan
fYear :
2012
fDate :
10-16 Nov. 2012
Firstpage :
1
Lastpage :
11
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 achieving high GPU performance and that "fusing" multiple kernels into one may greatly improve data locality. Doing so, however, requires transformations across multiple, potentially nested, parallel loops; at the same time, the original code semantics and data dependency must be preserved. Since each kernel may have distinct data access patterns, their combined dataflow can be nontrivial. As a result, the complexity of multi-kernel transformations often leads to significant effort with no guarantee of performance benefits. This paper proposes a dataflow-driven analytical framework to project GPU performance for a sequence of parallel operations. Users need only provide CPU code skeletons for a sequence of parallel loops. The framework can then automatically identify opportunities for multi-kernel transformations and data management. It is also able to project the overall performance without implementing GPU code or using physical hardware.
Keywords :
graphics processing units; CPU code skeletons; code semantics; data access patterns; data dependency; data locality improvement; data management; dataflow-driven GPU performance projection; graphics processors; multikernel transformations; parallel loops; parallel operations; physical hardware; Arrays; Fuses; Graphics processing units; Instruction sets; Kernel; Optimization; Skeleton;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
High Performance Computing, Networking, Storage and Analysis (SC), 2012 International Conference for
Conference_Location :
Salt Lake City, UT
ISSN :
2167-4329
Print_ISBN :
978-1-4673-0805-2
Type :
conf
DOI :
10.1109/SC.2012.42
Filename :
6468531
Link To Document :
بازگشت