An energy-efficient dynamic branch predictor with a two-clock-cycle naive Bayes classifier for pipelined RISC microprocessors

Hida Itaru; Takamaeda-Yamazaki Shinya; Ikebe Masayuki; Motomura Masato; Asai Tetsuya

タイトル	en An energy-efficient dynamic branch predictor with a two-clock-cycle naive Bayes classifier for pipelined RISC microprocessors
作成者	en Hida, Itaru en Takamaeda-Yamazaki, Shinya en Ikebe, Masayuki NRID 1000020374613 en Motomura, Masato en Asai, Tetsuya NRID 1000000312380
アクセス権	open access
権利情報	en Copyright ©2017 The Institute of Electronics, Information and Communication Engineers
主題	Other en dynamic branch prediction Other en supervised machine learning Other en naive Bayes classifier Other en energy-efficient microprocessor Other en low-power architecture Other en CMOS digital circuit NDC 540
内容注記	Abstract en In this paper, we propose a Bayesian branch-prediction circuit, consisting of an instruction-feature extractor and a naive Bayes classifier (NBC), as a machine learning approach for branch prediction. A branch predictor predicts the outcome of a branch instruction by analyzing the pattern of the previous branch outcome. In other words, branch prediction can be viewed as a type of pattern recognition problem, and such problems are often solved using neural networks. A perceptron branch predictor has already been proposed as one example of a neural branch prediction architecture, which predicts the next branch outcome by using past branch history to form feature vectors. The proposed circuit is constructed by replacing the arithmetic unit (neurons) in conventional neural branch predictors with an NBC. By introducing an approximate Bayesian computation and its parallel architectures, the NBC circuit completes branch prediction within two clock cycles per instruction. This constitutes a suitable replacement for conventional branch predictors in modern pipelined reduced instruction set computing microprocessors.
出版者	ja 電子情報通信学会 en The Institute of Electronics, Information and Communication Engineers / IEICE
日付	Issued2017
言語	eng
資源タイプ	journal article
出版タイプ	VoR
資源識別子	HDL http://hdl.handle.net/2115/68659
関連	isIdenticalTo DOI https://doi.org/10.1587/nolta.8.235
収録誌情報	PISSN 2185-4106 en Nonlinear Theory and Its Applications, IEICE 巻8 号3 開始ページ235 終了ページ245
ファイル	fulltext 8_235.pdf 978.6 KB (application/pdf) Issued2017
コンテンツ更新日時	2023-07-26