HW/SW approaches to accelerate GRAPES in an FU array

Author

Wei Wang ; Jun Yao ; Youhui Zhang ; Wei Xue ; Nakashima, Yuta ; Weimin Zheng

Author_Institution

Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China

fYear

2013

fDate

17-19 April 2013

Firstpage

1

Lastpage

3

Abstract

In this research, a high performance computing weather forecasting application GRAPES has been tuned onto a functional unit (FU) array based architecture. Software and hardware approaches are specifically employed to increase the data locality and data reuse to accelerate the stencil computation in GRAPES. The simulation results indicate that we can achieve a per-core average IPC of 12.3 within a 20-stage FU array processor, which has a 5.8x power-efficiency boost than the many-core processor (MCP) of a same process technology. This can accordingly slow down the increase of communication by one order in the cluster system, resulting in a 12x power-efficiency boost in all PEs.

Keywords

hardware-software codesign; meteorological instruments; multiprocessing systems; weather forecasting; FU array; GRAPES; HW/SW approaches; functional unit array based architecture; high performance computing; many-core processor; software and hardware approaches; stencil computation; weather forecasting application; Acceleration; Arrays; Educational institutions; Hardware; High performance computing; Pipelines;

fLanguage

English

Publisher

ieee

Conference_Titel

Cool Chips XVI (COOL Chips), 2013 IEEE

Conference_Location

Yokohama

Print_ISBN

978-1-4673-5780-7

Electronic_ISBN

978-1-4673-5781-4

Type

conf

DOI

10.1109/CoolChips.2013.6547920

Filename

6547920