DocumentCode :
692981
Title :
A embedded real-time polymorphic computing platform architecture
Author :
Yi Wu ; Xingshe Zhou ; Xiao Wu ; Zhan Xu
Author_Institution :
Sch. of Comput. Sci. & Eng., Northwestern Polytech. Univ., Xi´an, China
fYear :
2013
fDate :
20-22 Dec. 2013
Firstpage :
2326
Lastpage :
2330
Abstract :
With rising requirements on computational capability, data throughput, reconfigure-ability, reliability, scalability and adaptability to poor working conditions of complex multi-task embedded systems, traditional embedded computing platforms obviously cannot meet these requirements. How to take advantage of all kinds of advanced embedded computing technologies to build a polymorphic computing platform architecture which can dynamically reconstruct its computing resources with tasks changing becomes a research hotspot. This paper presents a new high-performance VPX-based embedded polymorphic computing platforms architecture, and implements a polymorphic prototype system. The platform is comprised of three general and specific high-speed computing resources including GPU, FPGA, PowerPC, which are interconnected by high-speed serial RapidIO (SRIO) protocol and Gigabit Ethernet. It can be configured and widely used in varieties of complex embedded computing systems.
Keywords :
embedded systems; field programmable gate arrays; graphics processing units; parallel processing; FPGA; GPU; PowerPC; SRIO protocol; adaptability; advanced embedded computing technologies; complex embedded computing systems; complex multitask embedded systems; computational capability; data throughput; embedded computing platforms; embedded real-time polymorphic computing platform architecture; gigabit Ethernet; high-performance VPX-based embedded polymorphic computing platforms architecture; high-speed computing resources; high-speed serial RapidIO protocol; polymorphic prototype system; reconfigureability; reliability; scalability; Computer architecture; Computers; Field programmable gate arrays; Graphics processing units; Real-time systems; Standards; Switches; FPGA; Many-core; Polymorphic Computing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Mechatronic Sciences, Electric Engineering and Computer (MEC), Proceedings 2013 International Conference on
Conference_Location :
Shengyang
Print_ISBN :
978-1-4799-2564-3
Type :
conf
DOI :
10.1109/MEC.2013.6885429
Filename :
6885429
Link To Document :
بازگشت