Výsledky vyhledávání - "Rezaei, Siavash"

Report

In-storage Processing of I/O Intensive Applications on Computational Storage Drives

Autor: HeydariGorji, Ali, Torabzadehkashi, Mahdi, Rezaei, Siavash, Bobarshad, Hossein, Alves, Vladimir, Chou, Pai H.

Computational storage drives (CSD) are solid-state drives (SSD) empowered by general-purpose processors that can perform in-storage processing. They have the potential to improve both performance and energy significantly for big-data analytics by bri

Externí odkaz: http://arxiv.org/abs/2112.12415

Zobrazit plný text záznamu

Report

Unobtrusive Pain Monitoring in Older Adults with Dementia using Pairwise and Contrastive Training

Autor: Rezaei, Siavash, Moturu, Abhishek, Zhao, Shun, Prkachin, Kenneth M., Hadjistavropoulos, Thomas, Taati, Babak

Although pain is frequent in old age, older adults are often undertreated for pain. This is especially the case for long-term care residents with moderate to severe dementia who cannot report their pain because of cognitive impairments that accompany

Externí odkaz: http://arxiv.org/abs/2101.03251

Zobrazit plný text záznamu

Report

HyperTune: Dynamic Hyperparameter Tuning For Efficient Distribution of DNN Training Over Heterogeneous Systems

Autor: HeydariGorji, Ali, Rezaei, Siavash, Torabzadehkashi, Mahdi, Bobarshad, Hossein, Alves, Vladimir, Chou, Pai H.

Distributed training is a novel approach to accelerate Deep Neural Networks (DNN) training, but common training libraries fall short of addressing the distributed cases with heterogeneous processors or the cases where the processing nodes get interru

Externí odkaz: http://arxiv.org/abs/2007.08077

Zobrazit plný text záznamu

Report

STANNIS: Low-Power Acceleration of Deep Neural Network Training Using Computational Storage

Autor: HeydariGorji, Ali, Torabzadehkashi, Mahdi, Rezaei, Siavash, Bobarshad, Hossein, Alves, Vladimir, Chou, Pai H.

This paper proposes a framework for distributed, in-storage training of neural networks on clusters of computational storage devices. Such devices not only contain hardware accelerators but also eliminate data movement between the host and storage, r

Externí odkaz: http://arxiv.org/abs/2002.07215

Zobrazit plný text záznamu

Report

UltraShare: FPGA-based Dynamic Accelerator Sharing and Allocation

Autor: Rezaei, Siavash, Bozorgzadeh, Eli, Kim, Kanghee

Despite all the available commercial and open-source frameworks to ease deploying FPGAs in accelerating applications, the current schemes fail to support sharing multiple accelerators among various applications. There are three main features that an

Externí odkaz: http://arxiv.org/abs/1910.00197

Zobrazit plný text záznamu