Title :
Power-aware Programming with GPU Accelerators
Author :
Zhang, Changyou ; Huang, Kun ; Cui, Xiang ; Chen, Yifeng
Author_Institution :
Key Lab. of High Confidence Software Technol., Peking Univ., Beijing, China
Abstract :
On-chip parallelism with GPU accelerators is now ubiquitous and has received significant attention in the past few years. GPU is becoming an integral part of mainstream computing systems with highly parallel, multithreaded, many-core processors of great computational power and high memory bandwidth. Finding the best tradeoff between performance and power efficiency is more challenging than mere performance tuning. To find the principles of power-aware programming with GPU accelerators, we abstract a set of primitives from program statements. These power consumption values of primitives are helpful for power estimation during high-level program development.
Keywords :
graphics processing units; multi-threading; multiprocessing systems; power aware computing; ubiquitous computing; GPU accelerators; high-level program development; manycore processor; multithreaded processor; on-chip parallelism; parallel processor; power consumption values; power efficiency; power estimation; power-aware programming; processor computational power; processor memory bandwidth; program statements; ubiquitous computing; Bandwidth; Graphics processing unit; Hardware; Memory management; Message systems; Power demand; Power measurement; GPU; Power-aware; Primitive; Programming;
Conference_Titel :
Parallel and Distributed Processing Symposium Workshops & PhD Forum (IPDPSW), 2012 IEEE 26th International
Conference_Location :
Shanghai
Print_ISBN :
978-1-4673-0974-5
DOI :
10.1109/IPDPSW.2012.301
