Design of approximate overclocked datapath

Abstract

Embedded applications can often demand stringent latency requirements. While high degrees of parallelism within custom FPGA-based accelerators may help to some extent, it may also be necessary to limit the precision used in the datapath to boost the operating frequency of the implementation. However, by reducing the precision, the engineer introduces quantisation error into the design. In this thesis, we describe an alternative circuit design methodology when considering trade-offs between accuracy, performance and silicon area. We compare two different approaches that could trade accuracy for performance. One is the traditional approach where the precision used in the datapath is limited to meet a target latency. The other is a proposed new approach which simply allows the datapath to operate without timing closure. We demonstrate analytically and experimentally that for many applications it would be preferable to simply overclock the design and accept that timing violations may arise. Since the errors introduced by timing violations occur rarely, they will cause less noise than quantisation errors. Furthermore, we show that conventional forms of computer arithmetic do not fail gracefully when pushed beyond the deterministic clocking region. In this thesis we take a fresh look at Online Arithmetic, originally proposed for digit serial operation, and synthesize unrolled digit parallel online arithmetic operators to allow for graceful degradation. We quantify the impact of timing violations on key arithmetic primitives, and show that substantial performance benefits can be obtained in comparison to binary arithmetic. Since timing errors are caused by long carry chains, these result in errors in least significant digits with online arithmetic, causing less impact than conventional implementations.