Title :
Mixed-Signal Approximate Computation: A Neural Predictor Case Study
Author :
Amant, Renée St ; Jimenez, D.A. ; Burger, Doug
Author_Institution :
Univ. of Texas at Austin, Austin, TX
Abstract :
As transistors shrink and processors trend toward low power, maintaining precise digital behavior grows more expensive. Replacing digital units with analog equivalents sometimes allows similar computation to be performed at higher speed using less power. As a case study in mixed-signal approximate computation, the authors describe an enhanced neural prediction algorithm and its efficient analog implementation.
Keywords :
approximation theory; mixed analogue-digital integrated circuits; analog equivalents; digital units; enhanced neural prediction algorithm; mixed-signal approximate computation; Accuracy; Algorithm design and analysis; Analog circuits; Analog computers; Circuit noise; Computer aided software engineering; High performance computing; History; Prediction algorithms; Wire; analog circuits; approximate computation; computer architecture; imprecise; low power; mixed signal; neural predictor; programmable;
Journal_Title :
Micro, IEEE
