An Alternative Analytical Approach to Associative Processing (Best of CAL)

An Alternative Analytical Approach to Associative Processing (Best of CAL). KhoramS, S., ZhaS, Y., & Li, J. IEEE Computer Architecture Letters, 17(2):113-116, July, 2018.
doi abstract bibtex 1 download

Associative Processing (AP) is a promising alternative to the Von Neumann model as it addresses the memory wall problem through its inherent in-memory computations. However, because of the countless design parameter choices, comparisons between implementations of two so radically different models are challenging for simulation-based methods. To tackle these challenges, we develop an alternative analytical approach based on a new concept called architecturally-determined complexity. Using this method, we asymptotically evaluate the runtime/storage/energy bounds of the two models, i.e., AP and Von Neumann. We further apply the method to gain more insights into the performance bottlenecks of traditional AP and develop a new machine model named Two Dimensional AP to address these limitations. Finally, we experimentally validate our analytical method and confirm that the simulation results match our theoretical projections.

@ARTICLE{Khoram2018CAL, 
author={Khoram<sup>S</sup>, Soroosh and Zha<sup>S</sup>, Yue and Li, Jing}, 
journal={IEEE Computer Architecture Letters}, 
title={An Alternative Analytical Approach to Associative Processing (<strong>Best of CAL</strong>)}, 
year={2018}, 
month={July},
date={2018-01-03},
volume={17}, 
number={2}, 
pages={113-116}, 
abstract={Associative Processing (AP) is a promising alternative to the Von Neumann model as it addresses the memory wall problem through its inherent in-memory computations. However, because of the countless design parameter choices, comparisons between implementations of two so radically different models are challenging for simulation-based methods. To tackle these challenges, we develop an alternative analytical approach based on a new concept called architecturally-determined complexity. Using this method, we asymptotically evaluate the runtime/storage/energy bounds of the two models, i.e., AP and Von Neumann. We further apply the method to gain more insights into the performance bottlenecks of traditional AP and develop a new machine model named Two Dimensional AP to address these limitations. Finally, we experimentally validate our analytical method and confirm that the simulation results match our theoretical projections.},
keywords={journal, Analytical models,Complexity theory,Computational modeling,Computer architecture,Parallel processing,Runtime,Two dimensional displays,Analysis of Algorithms and Problem Complexity,Associative Processors,Modeling techniques,Models of Computation}, 
doi={10.1109/LCA.2018.2789424}, 
ISSN={1556-6056}, 
}

Downloads: 1