Supporting systolic and memory communication in iWarp
- 4 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
The iWarp communication system supports two widely used interprocessor communication styles: memory communication and systolic communication. A description is given of the rationale, architecture, and implementation for the iWarp communication system. Memory communication is flexible and well suited for general computing, whereas systolic communication is efficient and well suited for speed-critical applications. The iWarp design is made possible by two important innovations in communication: (1) program access to communication and (2) logical channels. The former allows programs to access data as they are transmitted and to redirect portions of messages to different destinations efficiently. The latter increases the connectivity between the processors and guarantees communication bandwidth for classes of messages. These innovations have provided a focus for the iWarp architecture. The result is a communication system that provides a total bandwidth of 320 MBytes/sec and that is integrated on a single VLSI component with a 20 MFLOPS plus 20 MIPS long instruction work computation engine.<>Keywords
This publication has 12 references indexed in Scilit:
- Comprehensive evaluation of a two-dimensional configurable arrayPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Systolic communicationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- iWarp: an integrated solution to high-speed parallel computingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- An architecture independent programming language for low-level visionComputer Vision, Graphics, and Image Processing, 1989
- Architecture and compiler tradeoffs for a long instruction wordprocessorPublished by Association for Computing Machinery (ACM) ,1989
- Multicomputers: message-passing concurrent computersComputer, 1988
- The architecture and programming of the Ametek series 2010 multicomputerPublished by Association for Computing Machinery (ACM) ,1988
- The Warp Computer: Architecture, Implementation, and PerformanceIEEE Transactions on Computers, 1987
- A VLSI Architecture for Concurrent Data StructuresPublished by Springer Nature ,1987
- The torus routing chipDistributed Computing, 1986