TY - GEN
T1 - A versatile performance and energy simulation tool for composite GPU global memory
AU - Wang, Bin
AU - Jiao, Yizheng
AU - Yu, Weikuan
AU - Shen, Xipeng
AU - Li, Dong
AU - Vetter, Jeffrey S.
PY - 2013
Y1 - 2013
N2 - As a cost-effective compute device, Graphic Processing Unit (GPU) has been widely embraced in the field of high performance computing. GPU is characterized by its massive thread-level parallelism and high memory bandwidth. Although GPU has exhibited tremendous potential, recent GPU architecture researches mainly focus on GPU compute units and full system exploration is rare due to the lack of accurate simulators that can reveal hardware organization of both GPU compute units and its memory system. In order to fill this void, we build a GPU simulator called VxGPUSim that can support the simulation with detailed performance, timing and power consumption statistics. Our experimental evaluation demonstrates that VxGPUSim can faithfully reveal the internal execution details of GPU global memory of various memory configurations. It can enable further research on the design of GPU global memory for performance and energy tradeoffs.
AB - As a cost-effective compute device, Graphic Processing Unit (GPU) has been widely embraced in the field of high performance computing. GPU is characterized by its massive thread-level parallelism and high memory bandwidth. Although GPU has exhibited tremendous potential, recent GPU architecture researches mainly focus on GPU compute units and full system exploration is rare due to the lack of accurate simulators that can reveal hardware organization of both GPU compute units and its memory system. In order to fill this void, we build a GPU simulator called VxGPUSim that can support the simulation with detailed performance, timing and power consumption statistics. Our experimental evaluation demonstrates that VxGPUSim can faithfully reveal the internal execution details of GPU global memory of various memory configurations. It can enable further research on the design of GPU global memory for performance and energy tradeoffs.
UR - http://www.scopus.com/inward/record.url?scp=84894559876&partnerID=8YFLogxK
U2 - 10.1109/MASCOTS.2013.39
DO - 10.1109/MASCOTS.2013.39
M3 - Conference contribution
AN - SCOPUS:84894559876
SN - 9780769551029
T3 - Proceedings - IEEE Computer Society's Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, MASCOTS
SP - 298
EP - 302
BT - Proceedings - 2013 IEEE 21st International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication, MASCOTS 2013
T2 - 2013 IEEE 21st International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication, MASCOTS 2013
Y2 - 14 August 2013 through 16 August 2013
ER -