Title :
VENICE: A compact vector processor for FPGA applications
Author :
Aaron Severance;Guy Lemieux
Author_Institution :
University of British Columbia, Vancouver, Canada
Abstract :
This article consists of a collection of slides from the author´s conference presentation on VENICE (Vector Extensions to NIOS Implemented Compactly and Elegantly), a SVP (soft vector processor) intended to accelerate computationally intensive applications implemented on an FPGA. SVPs are exclusively for FPGAs, targeted at the productivity gap between writing custom hardware in an HDL and writing software for a soft processor in FPGA-based applications. They provide the convenience of software programming and software compile times, and yet they can achieve over 200x speedup compared to a scalar soft processor.
Keywords :
"Field programmable gate arrays","Vector processors","Programming","Parallel processing","Throughput"
Conference_Titel :
Hot Chips 23 Symposium (HCS), 2011 IEEE
DOI :
10.1109/HOTCHIPS.2011.7477515