Memory partitioning for multidimensional arrays in high-level synthesis
Authors:
Open Access
- 29 May 2013
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Abstract
Memory partitioning is widely adopted to efficiently increase the memory bandwidth by using multiple memory banks and reducing data access conflict. Previous methods for memory partitioning mainly focused on one-dimensional arrays. As a consequence, designers must flatten a multidimensional array to fit those methodologies. In this work we propose an automatic memory partitioning scheme for multidimensional arrays based on linear transformation to provide high data throughput of on-chip memories for the loop pipelining in high-level synthesis. An optimal solution based on Ehrhart points counting is presented, and a heuristic solution based on memory padding is proposed to achieve a near optimal solution with a small logic overhead. Compared to the previous one-dimensional partitioning work, the experimental results show that our approach saves up to 21% of block RAMs, 19% in slices, and 46% in DSPs.Keywords
This publication has 9 references indexed in Scilit:
- Memory partitioning and scheduling co-optimization in behavioral synthesis2012
- Optimizing memory hierarchy allocation with loop transformations for high-level synthesis2012
- Automatic memory partitioning and scheduling for throughput and power optimizationACM Transactions on Design Automation of Electronic Systems, 2011
- Automatic memory partitioning2010
- Computation of Storage Requirements for Multi-Dimensional Signal Processing ApplicationsIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2007
- pn: A Tool for Improved Derivation of Process NetworksEURASIP Journal on Embedded Systems, 2007
- Parametric Analysis of Polyhedral Iteration SpacesJournal of Signal Processing Systems, 1998
- Generating Local Addresses and Communication Sets for Data-Parallel ProgramsJournal of Parallel and Distributed Computing, 1995
- Some efficient solutions to the affine scheduling problem. I. One-dimensional timeInternational Journal of Parallel Programming, 1992