Zobrazeno 1 - 10
of 216
pro vyhledávání: '"Partha Pratim Pande"'
Autor:
Dwaipayan Choudhury, Lizhi Xiang, Aravind Rajam, Anantharaman Kalyanaraman, Partha Pratim Pande
Publikováno v:
ACM Transactions on Design Automation of Electronic Systems. 28:1-16
Graph application workloads are dominated by random memory accesses with the poor locality. To tackle the irregular and sparse nature of computation, ReRAM-based Processing-in-Memory (PIM) architectures have been proposed recently. Most of these ReRA
Autor:
Zhiyuan Zhou, Nghia Tang, Bai Nguyen, Wookpyo Hong, Partha Pratim Pande, Ram K. Krishnamurthy, Deukhyoun Heo
Publikováno v:
IEEE Transactions on Circuits and Systems I: Regular Papers. 69:4823-4836
Publikováno v:
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 41:4145-4156
Autor:
Chukwufumnanya Ogbogu, Aqeeb Iqbal Arka, Biresh Kumar Joardar, Janardhan Rao Doppa, Hai Li, Krishnendu Chakrabarty, Partha Pratim Pande
Publikováno v:
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 41:3626-3637
Autor:
Dwaipayan Choudhury, Reet Barik, Aravind Sukumaran Rajam, Ananth Kalyanaraman, Partha Pratim Pande
Publikováno v:
ACM Transactions on Design Automation of Electronic Systems. 27:1-22
Manycore GPU architectures have become the mainstay for accelerating graph computations. One of the primary bottlenecks to performance of graph computations on manycore architectures is the data movement. Since most of the accesses in graph processin
Autor:
Janardhan Rao Doppa, Partha Pratim Pande, Krishnendu Chakrabarty, Biresh Kumar Joardar, Aryan Deshwal
Publikováno v:
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 41:1537-1549
Resistive random-access memory (ReRAM)-based architectures can be used to accelerate Convolutional Neural Network (CNN) training. However, existing architectures either do not support normalization at all or they support only a limited version of it.
Autor:
Biresh Kumar Joardar, Janardhan Rao Doppa, Hai Li, Krishnendu Chakrabarty, Partha Pratim Pande
Publikováno v:
IEEE Transactions on Emerging Topics in Computing. :1-14
Autor:
Partha Pratim Pande, Janardhan Rao Doppa, Krishnendu Chakrabarty, Biresh Kumar Joardar, Aqeeb Iqbal Arka
Publikováno v:
IEEE Transactions on Very Large Scale Integration (VLSI) Systems. 29:1743-1756
Graph neural network (GNN) is a variant of deep neural networks (DNNs) operating on graphs. However, GNNs are more complex compared with DNNs as they simultaneously exhibit attributes of both DNN and graph computations. In this work, we propose a ReR
Autor:
Hai Li, Janardhan Rao Doppa, Biresh Kumar Joardar, Partha Pratim Pande, Krishnendu Chakrabarty
Publikováno v:
ACM Transactions on Embedded Computing Systems. 20:1-23
The growing popularity of convolutional neural networks (CNNs) has led to the search for efficient computational platforms to accelerate CNN training. Resistive random-access memory (ReRAM)-based manycore architectures offer a promising alternative t
Publikováno v:
Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design.