cfaed Publications

@InProceedings{dasilva_samos25,
author = {Anderson Faustino da Silva and Hamid Farzaned and Joao Paulo Cardoso De Lima and Asif Ali Khan and Jeronimo Castrillon},
booktitle = {Proceedings of the 25st IEEE International Conference on Embedded Computer Systems: Architectures Modeling and Simulation (SAMOS)},
date = {2025-07},
title = {{LearnCNM2Predict}: Transfer Learning-based Performance Model for CNM Systems},
location = {Samos, Greece},
organization = {IEEE},
publisher = {Springer-Verlag},
address = {Berlin, Heidelberg},
month = jul,
numpages = {17},
year = {2025},
abstract = {Compute-near-memory (CNM) architectures have emerged as a promising solution to address the von Neumann bottleneck by relocating computation closer to memory and utilizing dedicated logic near memory arrays or banks. Despite their early stage of development, these architectures have demonstrated significant performance improvements over traditional CPU and GPU systems in various application domains. CNM architectures tend to excel in memory-bound workloads that exhibit high levels of data-level parallelism. However, identifying which kernels can take advantage of CNM execution poses a considerable challenge for software developers. This paper introduces a transfer learning approach for predicting performance on CNM systems. Our method harnesses knowledge from previously analyzed applications to enhance prediction accuracy for new, unseen applications, thereby reducing the necessity for extensive training data for each application. We have developed a feature extraction framework that captures CNM-specific computation and memory access patterns, which are crucial for determining performance. Experimental results demonstrate that our transfer learning model achieves high prediction accuracy across diverse application domains, showcasing robust generalization even in scenarios with limited training data.},
}