Issue No. 10 - October (1991 vol. 17)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/32.99191
<p>An experimental approach is chosen to investigate the performance of a fine-grained dataflow architecture for numerically intensive digital signal processing (DSP) applications. The focus is on the behavior of pipelined data-parallel algorithms. However, the granularity of the high-level language programming blocks is not explicitly optimized to balance computation and communication; a natural and logical fine-grained decomposition of problems is used instead. The authors interpret their empirical data by means of parameters such as a number of instructions per generic unit of computation, a density of precedence relations, and a serial fraction. The performance and limitations of fine-grained general-purpose dataflow computing are discussed.</p>
DSP applications; fine-grained dataflow architecture; numerically intensive digital signal processing; pipelined data-parallel algorithms; high-level language programming blocks; logical fine-grained decomposition; precedence relations; serial fraction; fine-grained general-purpose dataflow computing; computerised signal processing; parallel algorithms; parallel architectures; pipeline processing
I. Radivojevic and J. Herath, "Executing DSP Applications in a Fine-Grained Dataflow Environment," in IEEE Transactions on Software Engineering, vol. 17, no. , pp. 1028-1041, 1991.