Výsledky vyhledávání - "Demirkiran, Cansu"

Dissertation/ Thesis

Building next-generation deep learning hardware using photonic computing

Autor: Demirkiran, Cansu

In recent years, the demand for computational power has skyrocketed due to the rapid advancement of artificial intelligence (AI). As we move past Moore’s Law, the limitations of traditional digital computing are pushing the exploration of alternati

Externí odkaz: https://hdl.handle.net/2144/49259

Zobrazit plný text záznamu

Report

Towards Efficient Hyperdimensional Computing Using Photonics

Autor: Fayza, Farbin, Demirkiran, Cansu, Chen, Hanning, Liu, Che-Kai, Mohan, Avi, Errahmouni, Hamza, Yun, Sanggeon, Imani, Mohsen, Zhang, David, Bunandar, Darius, Joshi, Ajay

Over the past few years, silicon photonics-based computing has emerged as a promising alternative to CMOS-based computing for Deep Neural Networks (DNN). Unfortunately, the non-linear operations and the high-precision requirements of DNNs make it ext

Externí odkaz: http://arxiv.org/abs/2311.17801

Zobrazit plný text záznamu

Report

Mirage: An RNS-Based Photonic Accelerator for DNN Training

Autor: Demirkiran, Cansu, Yang, Guowei, Bunandar, Darius, Joshi, Ajay

Publikováno v: ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA) 2024

Photonic computing is a compelling avenue for performing highly efficient matrix multiplication, a crucial operation in Deep Neural Networks (DNNs). While this method has shown great success in DNN inference, meeting the high precision demands of DNN

Externí odkaz: http://arxiv.org/abs/2311.17323

Zobrazit plný text záznamu

Report

A Blueprint for Precise and Fault-Tolerant Analog Neural Networks

Autor: Demirkiran, Cansu, Nair, Lakshmi, Bunandar, Darius, Joshi, Ajay

Analog computing has reemerged as a promising avenue for accelerating deep neural networks (DNNs) due to its potential to overcome the energy efficiency and scalability challenges posed by traditional digital architectures. However, achieving high pr

Externí odkaz: http://arxiv.org/abs/2309.10759

Zobrazit plný text záznamu

Report

Leveraging Residue Number System for Designing High-Precision Analog Deep Neural Network Accelerators

Autor: Demirkiran, Cansu, Agrawal, Rashmi, Reddi, Vijay Janapa, Bunandar, Darius, Joshi, Ajay

Achieving high accuracy, while maintaining good energy efficiency, in analog DNN accelerators is challenging as high-precision data converters are expensive. In this paper, we overcome this challenge by using the residue number system (RNS) to compos

Externí odkaz: http://arxiv.org/abs/2306.09481

Zobrazit plný text záznamu

Report

An Electro-Photonic System for Accelerating Deep Neural Networks

Autor: Demirkiran, Cansu, Eris, Furkan, Wang, Gongyu, Elmhurst, Jonathan, Moore, Nick, Harris, Nicholas C., Basumallik, Ayon, Reddi, Vijay Janapa, Joshi, Ajay, Bunandar, Darius

Publikováno v: J. Emerg. Technol. Comput. Syst. 19, 4, Article 30 (October 2023)

The number of parameters in deep neural networks (DNNs) is scaling at about 5$\times$ the rate of Moore's Law. To sustain this growth, photonic computing is a promising avenue, as it enables higher throughput in dominant general matrix-matrix multipl

Externí odkaz: http://arxiv.org/abs/2109.01126

Zobrazit plný text záznamu

Report

Custom Tailored Suite of Random Forests for Prefetcher Adaptation

Autor: Eris, Furkan, Canakci, Sadullah, Demirkiran, Cansu, Joshi, Ajay

To close the gap between memory and processors, and in turn improve performance, there has been an abundance of work in the area of data/instruction prefetcher designs. Prefetchers are deployed in each level of the memory hierarchy, but typically, ea

Externí odkaz: http://arxiv.org/abs/2008.00176

Zobrazit plný text záznamu