Synergistic Processing in Cell's Multicore Architecture
Authors:
- Michael GschwindMGMichael Gschwind
- H. Peter HofsteeHHH. Peter Hofstee
- Brian FlachsBFBrian Flachs
- Martin HopkinsMHMartin Hopkins
Top Cited Papers
- 24 April 2006
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 26 (2) , 10-24
Abstract
Eight synergistic processor units enable the Cell Broadband Engine's breakthrough performance. The SPU architecture implements a novel, pervasively data-parallel architecture combining scalar and SIMD processing on a wide data path. A large number of SPUs per chip provide high thread-level parallelism. The streamlined architecture provides an efficient multithreaded execution environment for both scalar and SIMD threads and represents a reaffirmation of the RISC principles of combining leading edge architecture and compiler optimizations. These design decisions have enabled the Cell BE to deliver unprecedented supercomputer-class compute power for consumer applicationsKeywords
This publication has 8 references indexed in Scilit:
- The design and implementation of a first-generation CELL processor2005
- Characterizing the impact of predicated execution on branch prediction2005
- Introduction to the Cell multiprocessorIBM Journal of Research and Development, 2005
- Power Efficient Processor Architecture and The Cell Processor2005
- Optimizing Compiler for the CELL Processor2005
- Optimizing pipelines for power and performance2003
- Exploiting superword level parallelism with multimedia instruction setsACM SIGPLAN Notices, 2000
- AltiVec extension to PowerPC accelerates media processingIEEE Micro, 2000