Initial results on fuzzy floating point computation for multimedia processors

Abstract

During the recent years, the market of mid/low-end portable systems such as PDAs or mobile digital phones have experimented a revolution in both selling volume and features as handheld devices incorporate Multimedia applications. This fact brings to an increase in the computational demands of the devices, while still having the limitation of power (and energy) consumption. Instruction memoization is a promising technique to help alleviate the problem of power consumption of expensive functional units such as the floating-point one. Unfortunately, this technique could be energy-inefficient for low-end systems due to the additional power consumption of the relatively big tables required. In this paper we present a novel way of understanding multimedia floating point operations based on the fuzzy computation paradigm: losses in the computation precision may exchange performance for negligible errors in the output. Exploiting the implicit characteristics of media FP computation, we propose a new technique called fuzzy memoization. Fuzzy memoization expands the capabilities of classic memoization by attaching entries with similar inputs to the same output. We present a case of study for a SH4 like processor and report good performance and power-delay improvements with feasible hardware requirements.