Express Cube Topologies for on-Chip Interconnects
Authors:
- 1 February 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15300897,p. 163-174
Abstract
Driven by continuing scaling of Moore's law, chip multi-processors and systems-on-a-chip are expected to grow the core count from dozens today to hundreds in the near future. Scalability of on-chip interconnect topologies is critical to meeting these demands. In this work, we seek to develop a better understanding of how network topologies scale with regard to cost, performance, and energy considering the advantages and limitations afforded on a die. Our contributions are three-fold. First, we propose a new topology, called Multidrop Express Channels (MECS), that uses a one-to-many communication model enabling a high degree of connectivity in a bandwidth-efficient manner. In a 64-terminal network, MECS enjoys a 9% latency advantage over other topologies at low network loads, which extends to over 20% in a 256-terminal network. Second, we demonstrate that partitioning the available wires among multiple networks and channels enables new opportunities for trading-off performance, area, and energy-efficiency that depend on the partitioning scheme. Third, we introduce Generalized Express Cubes - a framework for expressing the space of on-chip interconnects - and demonstrate how existing and proposed topologies can be mapped to it.Keywords
This publication has 21 references indexed in Scilit:
- Implementation and Evaluation of a Dynamically Routed Processor Operand Network2007
- An 80-Tile 1.28TFLOPS Network-on-Chip in 65nm CMOSIEEE International Solid-State Circuits Conference, 2007
- Overview of the Architecture, Circuit Design, and Physical Implementation of a First-Generation Cell ProcessorIEEE Journal of Solid-State Circuits, 2005
- Near-Optimal Worst-Case Throughput Routing for Two-Dimensional Mesh NetworksACM SIGARCH Computer Architecture News, 2005
- Globally Adaptive Load-Balanced Routing on ToriIEEE Computer Architecture Letters, 2004
- The SPLASH-2 programs: characterization and methodological considerations2002
- A delay model and speculative architecture for pipelined routers2002
- Baring it all to software: Raw machinesComputer, 1997
- Synchronization and communication in the T3E multiprocessorACM SIGPLAN Notices, 1996
- Express cubes: improving the performance of k-ary n-cube interconnection networksIEEE Transactions on Computers, 1991