An astute LVQ approach using neural network for the prediction of conditional branches in pipeline processor

An astute LVQ approach using neural network for the prediction of conditional branches in pipeline processor

Nowadays, microprocessors use the deep pipeline to execute multiple instructions per cycle. The frequency and behavior of conditional instructions mainly affect the performance of instruction-level parallelism. However, recent processors still have problems with the correct prediction of condition...

Full description

Bibliographic Details
Main Authors: Sweety Nain, Prachi Chaudhary
Format: Article
Language:English
Published: European Alliance for Innovation (EAI) 2021-06-01
Series:EAI Endorsed Transactions on Scalable Information Systems
Subjects:
branch prediction
perceptron branch predictor
pipeline
linear vector quantization
accuracy rate
Online Access:https://eudl.eu/pdf/10.4108/eai.4-3-2021.168865
id doaj-5ec9cbb2f45c4c9186b8c4f8b05c659c
record_format Article
spelling doaj-5ec9cbb2f45c4c9186b8c4f8b05c659c2021-06-30T09:10:04ZengEuropean Alliance for Innovation (EAI)EAI Endorsed Transactions on Scalable Information Systems2032-94072021-06-0183110.4108/eai.4-3-2021.168865An astute LVQ approach using neural network for the prediction of conditional branches in pipeline processorSweety Nain0Prachi Chaudhary1Research Scholar, Department of E.C.E, D.C.R.U.S.T, Murthal, Haryana, 131001Assistant Professor, Department of E.C.E, D.C.R.U.S.T, Murthal, Haryana, 131001Nowadays, microprocessors use the deep pipeline to execute multiple instructions per cycle. The frequency and behavior of conditional instructions mainly affect the performance of instruction-level parallelism. However, recent processors still have problems with the correct prediction of conditional branches. Firstly, the perceptron neural network and global-based perceptron prediction has been exploited and implemented. Further, a new approach, linear vector quantization (LVQ) neural network, is explored and implemented to see its possibility and potentiality as a branch predictor in terms of accuracy rate. Simulation is performed by varying the parameter of hardware budget and the length of history register using different trace files for identification of the best branch predictor technique. The proposed LVQ perceptron branch predictor achieves an 85.56% accuracy rate using a hardware budget and an 86.36% accuracy rate in terms of history length by comparing the simulation results.https://eudl.eu/pdf/10.4108/eai.4-3-2021.168865branch predictionperceptron branch predictor pipelinelinear vector quantizationaccuracy rate
collection DOAJ
language English
format Article
sources DOAJ
author Sweety Nain
Prachi Chaudhary
spellingShingle Sweety Nain
Prachi Chaudhary
An astute LVQ approach using neural network for the prediction of conditional branches in pipeline processor
EAI Endorsed Transactions on Scalable Information Systems
branch prediction
perceptron branch predictor
pipeline
linear vector quantization
accuracy rate
author_facet Sweety Nain
Prachi Chaudhary
author_sort Sweety Nain
title An astute LVQ approach using neural network for the prediction of conditional branches in pipeline processor
title_short An astute LVQ approach using neural network for the prediction of conditional branches in pipeline processor
title_full An astute LVQ approach using neural network for the prediction of conditional branches in pipeline processor
title_fullStr An astute LVQ approach using neural network for the prediction of conditional branches in pipeline processor
title_full_unstemmed An astute LVQ approach using neural network for the prediction of conditional branches in pipeline processor
title_sort astute lvq approach using neural network for the prediction of conditional branches in pipeline processor
publisher European Alliance for Innovation (EAI)
series EAI Endorsed Transactions on Scalable Information Systems
issn 2032-9407
publishDate 2021-06-01
description Nowadays, microprocessors use the deep pipeline to execute multiple instructions per cycle. The frequency and behavior of conditional instructions mainly affect the performance of instruction-level parallelism. However, recent processors still have problems with the correct prediction of conditional branches. Firstly, the perceptron neural network and global-based perceptron prediction has been exploited and implemented. Further, a new approach, linear vector quantization (LVQ) neural network, is explored and implemented to see its possibility and potentiality as a branch predictor in terms of accuracy rate. Simulation is performed by varying the parameter of hardware budget and the length of history register using different trace files for identification of the best branch predictor technique. The proposed LVQ perceptron branch predictor achieves an 85.56% accuracy rate using a hardware budget and an 86.36% accuracy rate in terms of history length by comparing the simulation results.
topic branch prediction
perceptron branch predictor
pipeline
linear vector quantization
accuracy rate
url https://eudl.eu/pdf/10.4108/eai.4-3-2021.168865
work_keys_str_mv AT sweetynain anastutelvqapproachusingneuralnetworkforthepredictionofconditionalbranchesinpipelineprocessor
AT prachichaudhary anastutelvqapproachusingneuralnetworkforthepredictionofconditionalbranchesinpipelineprocessor
AT sweetynain astutelvqapproachusingneuralnetworkforthepredictionofconditionalbranchesinpipelineprocessor
AT prachichaudhary astutelvqapproachusingneuralnetworkforthepredictionofconditionalbranchesinpipelineprocessor
_version_ 1721353013449195520

Similar Items