Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Zhang, Pengmiao"'
Convolutional Neural Networks (CNNs) have demonstrated remarkable ability throughout the field of computer vision. However, CNN inference requires a large number of arithmetic operations, making them expensive to deploy in hardware. Current approache
Externí odkaz:
http://arxiv.org/abs/2404.05872
Publikováno v:
2023 IEEE High Performance Extreme Computing Conference (HPEC), 2023, pp. 1-7
Deep neural networks (DNNs) have proven to be effective models for accurate Memory Access Prediction (MAP), a critical task in mitigating memory latency through data prefetching. However, existing DNN-based MAP models suffer from the challenges such
Externí odkaz:
http://arxiv.org/abs/2402.13441
Vision Transformers (ViTs) have emerged as a state-of-the-art solution for object classification tasks. However, their computational demands and high parameter count make them unsuitable for real-time inference, prompting the need for efficient hardw
Externí odkaz:
http://arxiv.org/abs/2402.09709
Attention-based Neural Networks (NN) have demonstrated their effectiveness in accurate memory access prediction, an essential step in data prefetching. However, the substantial computational overheads associated with these models result in high infer
Externí odkaz:
http://arxiv.org/abs/2401.06362
Memory performance is a bottleneck in graph analytics acceleration. Existing Machine Learning (ML) prefetchers struggle with phase transitions and irregular memory accesses in graph processing. We propose MPGraph, an ML-based Prefetcher for Graph ana
Externí odkaz:
http://arxiv.org/abs/2212.05250
Data Prefetching is a technique that can hide memory latency by fetching data before it is needed by a program. Prefetching relies on accurate memory access prediction, to which task machine learning based methods are increasingly applied. Unlike pre
Externí odkaz:
http://arxiv.org/abs/2205.14778
Machine learning algorithms have shown potential to improve prefetching performance by accurately predicting future memory accesses. Existing approaches are based on the modeling of text prediction, considering prefetching as a classification problem
Externí odkaz:
http://arxiv.org/abs/2205.02269
Publikováno v:
In Materials Today Energy January 2023 31
Autor:
Zhang, Pengmiao, Srivastava, Ajitesh, Wang, Ta-Yang, De Rose, Cesar A. F., Kannan, Rajgopal, Prasanna, Viktor K.
Publikováno v:
International Journal of Data Science & Analytics; Jan2022, Vol. 13 Issue 1, p3-16, 14p
Publikováno v:
2015 9th International Conference on Power Electronics & ECCE Asia (ICPE-ECCE Asia); 2015, p2427-2431, 5p