A floating-point accumulator for FPGA-based high performance computing applications
Authors:
- 1 December 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 493-499
Abstract
A floating-point accumulator for FPGA-based high performance computing applications is proposed and evaluated. Compared to previous work, our accumulator uses a fixed size circuit, and can reduce an arbitrary number of input sets of varying sizes without requiring prior knowledge of the bounds of summands. In this paper, we describe how the adder accumulator operator can be heavily pipelined to achieve a high clock speed when mapped to FPGA technology, while still maintaining the original input ordering. Our experimental results show that our accumulator design is very competitive with previous efforts in terms of FPGA resource usage and clock frequency, making it an ideal building block for large-scale sparse matrix computations as implemented in FPGA-based high performance computing systems.Keywords
This publication has 7 references indexed in Scilit:
- An FPGA-specific approach to floating-point accumulation and sum-of-products2008
- An FPGA architecture for the Pagerank eigenvector problem2008
- High-Performance Reduction Circuits Using Deeply Pipelined Operators on FPGAsIEEE Transactions on Parallel and Distributed Systems, 2007
- Architectures and APIs: Assessing Requirements for Delivering FPGA Performance to Applications2006
- High-Performance and Area-Efficient Reduction Circuits on FPGAs2006
- Designing Scalable FPGA-Based Reduction Circuits Using Pipelined Floating-Point Cores2005
- Vector-Reduction Techniques for Arithmetic PipelinesIEEE Transactions on Computers, 1985