High-level synthesis

Robin C. Sarma, Mark D. Dooley, Nick Newman, G. Hetherington · 1990

High-level synthesis has been an active research area for ten years. However, the progress in research has yet to find its way into usage in industry. This paper describes the technology transfer of high-level synthesis at Texas Instruments. It explains how we have extended one research project, the System Architect's Workbench from Carnegie-Mellon University, into a tool that designers can use. Significant enhancements were made to the Workbench to enable it to make architectural tradeoffs and simulate the designs it produces. The resulting Architecture Design Tool was tested on a Texas Instruments' design. Based on this experience, the paper discusses how close high-level synthesis research is to being industrially useful.

Read the paper · More papers on PaperTik