deposit_your_work

Register Organization for Media Processing

Files in this item

Files Size Format View
Rix2000Jan5RegisterOr.PDF 247.3Kb application/pdf Thumbnail

Show full item record

Item Metadata

Title: Register Organization for Media Processing
Author: Rixner, Scott; Dally, William J.; Khailany, Brucek; Mattson, Peter; Kapasi, Ujval J.; Owens, John D.
Type: Conference Paper
Keywords: media processing; register files; processor architecture
Citation: S. Rixner, W. J. Dally, B. Khailany, P. Mattson, U. J. Kapasi and J. D. Owens,"Register Organization for Media Processing," in International Symposium on High Performance Computer Architecture (HPCA),, pp. 375-386.
Abstract: Processor architectures with tens to hundreds of arithmetic units are emerging to handle media processing applications. These applications, such as image coding, image synthesis, and image understanding, require arithmetic rates of up to 10^11 operations per second. As the number of arithmetic units in a processor increases to meet these demands, register storage and communication between the arithmetic units dominate the area, delay, and power of the arithmetic units. In this paper we show that partitioning the register file along three axes reduces the cost of register storage and communication without significantly impacting performance. We develop a taxonomy of register architectures by partitioning across the data-parallel, instruction-level parallel, and memory hierarchy axes, and by optimizing the hierarchical register organization to operate on streams of data. Compared to a centralized global register file, the most compact of these organizations reduces the register file area, delay, and power dissipation of a media processor by factors of 195, 20, and 430, respectively. This reduction in cost is achieved with a performance degradation of only 8% on a representative set of media processing benchmarks.
Date Published: 2000-01-20

This item appears in the following Collection(s)

  • ECE Publications [1082 items]
    Publications by Rice University Electrical and Computer Engineering faculty and graduate students