Transformation synthesis for data intensive applications to FPGAs

Authors:
Renqiu Huang;Ranga Vemuri
Affiliations:
University of Cincinnati, Cincinnati, OH;University of Cincinnati, Cincinnati, OH
Venue:
GLSVLSI '06 Proceedings of the 16th ACM Great Lakes symposium on VLSI
Year:
2006

Citing 7
Cited 0

Synthesis of application-specific memory designs

IEEE Transactions on Very Large Scale Integration (VLSI) Systems
High-level address optimization and synthesis techniques for data-transfer-intensive applications

IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Hierarchical memory mapping during synthesis in FPGA-based reconfigurable computers

Proceedings of the conference on Design, automation and test in Europe
Synthesis of pipelined memory access controllers for streamed data applications on FPGA-based computing engines

Proceedings of the 14th international symposium on Systems synthesis
Automatic Partitioning of Parallel Loops and Data Arrays for Distributed Shared-Memory Multiprocessors

IEEE Transactions on Parallel and Distributed Systems
High-level synthesis of distributed logic-memory architectures

Proceedings of the 2002 IEEE/ACM international conference on Computer-aided design
Using estimates from behavioral synthesis tools in compiler-directed design space exploration

Proceedings of the 40th annual Design Automation Conference

Quantified Score

Hi-index	0.01

Visualization

Abstract

Without the adequate awareness of trade-off between different resources, it is extremely difficult for system synthesis tools to achieve high performance solutions when mapping the applications to FPGA-based computing engines. In this paper, we present an automatic synthesis methodology which attacks both memory and logic assignments by interacting with behavioral synthesis. The problem is formulated as part of the heuristic algorithm by exploiting application specific information and organizing possible data structures and computations for data-intensive applications. We have evaluated the proposed framework on a set of DSP benchmarks and a real multimedia application by generating register-transfer level (RTL) implementations. The results show that, by using our proposed techniques, it is possible the synthesized designs obtain significant (avg. of 34.8%) performance improvements over the conventional synthesis approaches.