Zobrazeno 1 - 10
of 76
pro vyhledávání: '"BUNANDAR, DARIUS"'
Photonic integrated circuits are finding use in a variety of applications including optical transceivers, LIDAR, bio-sensing, photonic quantum computing, and Machine Learning (ML). In particular, with the exponentially increasing sizes of ML models,
Externí odkaz:
http://arxiv.org/abs/2401.05121
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
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
Autor:
Nair, Lakshmi, Widemann, David, Turcott, Brad, Moore, Nick, Wleklinski, Alexandra, Bunandar, Darius, Papavasileiou, Ioannis, Wang, Shihu, Logan, Eric
Photonic computing promises faster and more energy-efficient deep neural network (DNN) inference than traditional digital hardware. Advances in photonic computing can have profound impacts on applications such as autonomous driving and defect detecti
Externí odkaz:
http://arxiv.org/abs/2309.16783
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
Autor:
Nair, Lakshmi, Bernadskiy, Mikhail, Madhavan, Arulselvan, Chan, Craig, Basumallik, Ayon, Bunandar, Darius
The recent rise of large language models (LLMs) has resulted in increased efforts towards running LLMs at reduced precision. Running LLMs at lower precision supports resource constraints and furthers their democratization, enabling users to run billi
Externí odkaz:
http://arxiv.org/abs/2307.03712
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
Autor:
Nair, Lakshmi, Bunandar, Darius
Existing methods to recover model accuracy on analog-digital hardware in the presence of quantization and analog noise include noise-injection training. However, it can be slow in practice, incurring high computational costs, even when starting from
Externí odkaz:
http://arxiv.org/abs/2306.03076
Autor:
Bandyopadhyay, Saumil, Sludds, Alexander, Krastanov, Stefan, Hamerly, Ryan, Harris, Nicholas, Bunandar, Darius, Streshinsky, Matthew, Hochberg, Michael, Englund, Dirk
As deep neural networks (DNNs) revolutionize machine learning, energy consumption and throughput are emerging as fundamental limitations of CMOS electronics. This has motivated a search for new hardware architectures optimized for artificial intellig
Externí odkaz:
http://arxiv.org/abs/2208.01623
Autor:
Basumallik, Ayon, Bunandar, Darius, Dronen, Nicholas, Harris, Nicholas, Levkova, Ludmila, McCarter, Calvin, Nair, Lakshmi, Walter, David, Widemann, David
Analog mixed-signal (AMS) devices promise faster, more energy-efficient deep neural network (DNN) inference than their digital counterparts. However, recent studies show that DNNs on AMS devices with fixed-point numbers can incur an accuracy penalty
Externí odkaz:
http://arxiv.org/abs/2205.06287