Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Maxim Naumov"'
Autor:
Ping Tak Peter Tang, Raghuraman Krishnamoorthi, Daya Shanker Khudia, Satish Nadathur, Jongsoo Park, Hector Yuen, Jianyu Huang, Maxim Naumov, Ellie Wen, Mikhail Smelyanskiy, Xiaohan Wei, Sam Naghshineh, Dhruv Choudhary, Jie Yang, Changkyu San Jose Kim, Haixin Liu, Deng Zhaoxia, Carole-Jean Wu
Publikováno v:
IEEE Micro. 41:93-100
Tremendous success of machine learning (ML) and the unabated growth in model complexity motivated many ML-specific designs in hardware architectures to speed up the model inference. While these architectures are diverse, highly optimized low-precisio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fcd9d56841f7bd8d51b6f6565668bb69
https://doi.org/10.1109/mm.2021.3081981
https://doi.org/10.1109/mm.2021.3081981
Autor:
Ehsan K. Ardestani, Changkyu Kim, Seung Jae Lee, Luoshang Pan, Jens Axboe, Valmiki Rampersad, Banit Agrawal, Fuxun Yu, Ansha Yu, Trung Le, Hector Yuen, Dheevatsa Mudigere, Shishir Juluri, Akshat Nanda, Manoj Wodekar, Krishnakumar Nair, Maxim Naumov, Chris Petersen, Mikhail Smelyanskiy, Vijay Rao
Deep Learning Recommendation Models (DLRM) are widespread, account for a considerable data center footprint, and grow by more than 1.5x per year. With model size soon to be in terabytes range, leveraging Storage ClassMemory (SCM) for inference enable
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7cb51982306cd2856dab236b3da9009d
http://arxiv.org/abs/2110.11489
http://arxiv.org/abs/2110.11489
Autor:
Dheevatsa Mudigere, Yuchen Hao, Jianyu Huang, Zhihao Jia, Andrew Tulloch, Srinivas Sridharan, Xing Liu, Mustafa Ozdal, Jade Nie, Jongsoo Park, Liang Luo, Jie (Amy) Yang, Leon Gao, Dmytro Ivchenko, Aarti Basant, Yuxi Hu, Jiyan Yang, Ehsan K. Ardestani, Xiaodong Wang, Rakesh Komuravelli, Ching-Hsiang Chu, Serhat Yilmaz, Huayu Li, Jiyuan Qian, Zhuobo Feng, Yinbin Ma, Junjie Yang, Ellie Wen, Hong Li, Lin Yang, Chonglin Sun, Whitney Zhao, Dimitry Melts, Krishna Dhulipala, KR Kishore, Tyler Graf, Assaf Eisenman, Kiran Kumar Matam, Adi Gangidi, Guoqiang Jerry Chen, Manoj Krishnan, Avinash Nayak, Krishnakumar Nair, Bharath Muthiah, Mahmoud khorashadi, Pallab Bhattacharya, Petr Lapukhov, Maxim Naumov, Ajit Mathews, Lin Qiao, Mikhail Smelyanskiy, Bill Jia, Vijay Rao
Deep learning recommendation models (DLRMs) are used across many business-critical services at Facebook and are the single largest AI application in terms of infrastructure demand in its data-centers. In this paper we discuss the SW/HW co-designed so
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3b1a6d07c5739fe931da1f91ac4f756a
http://arxiv.org/abs/2104.05158
http://arxiv.org/abs/2104.05158
Autor:
Dheevatsa Mudigere, Geeta Chauhan, Narine Kokhlikyan, Joe Spisak, Amanpreet Singh, Maxim Naumov, Vedanuj Goswami
Publikováno v:
KDD
In this tutorial we show how to build deep learning recommendation systems and resolve the associated interpretability, integrity and privacy challenges. We start with an overview of the PyTorch framework, features that it offers and a brief review o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::289196bfb3c1703e05b96c87e06a14d8
https://doi.org/10.1145/3394486.3406714
https://doi.org/10.1145/3394486.3406714
Autor:
Mikhail Smelyanskiy, Dheevatsa Mudigere, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Bradford Cottel, David Brooks, Xuan Zhang, Bill Jia, Brandon Reagen, Mark Hempstead, Maxim Naumov, Kim Hazelwood, Hsien-Hsin S. Lee, Liang Xiong, Andrey Malevich
Publikováno v:
HPCA
The widespread application of deep learning has changed the landscape of computation in data centers. In particular, personalized recommendation for content ranking is now largely accomplished using deep neural networks. However, despite their import
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::04af085a5721ef42f9a4798a26b03bcb
https://doi.org/10.1109/hpca47549.2020.00047
https://doi.org/10.1109/hpca47549.2020.00047
Publikováno v:
ISIT
Embedding representations power machine intelligence in many applications, including recommendation systems, but they are space intensive - potentially occupying hundreds of gigabytes in large-scale settings. To help manage this outsized memory consu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a27d4e51529e8ff4007bf50b6cf81ae
Autor:
Kim Hazelwood, Hsien-Hsin S. Lee, Bill Jia, Liu Ke, David Brooks, Martin Schatz, Maxim Naumov, Xuan Zhang, Benjamin Youngjae Cho, Carole-Jean Wu, Bert Maher, Amin Firoozshahian, Meng Li, Mark Hempstead, Utku Diril, Brandon Reagen, Mikhail Smelyanskiy, Vikas Chandra, Xiaodong Wang, Udit Gupta, Dheevatsa Mudigere
Publikováno v:
ISCA
Personalized recommendation systems leverage deep learning models and account for the majority of data center AI cycles. Their performance is dominated by memory-bound sparse embedding operations with unique irregular memory access patterns that pose
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::421f7b2188846753693aa1f8fa12cf0f
Publikováno v:
KDD
Modern deep learning-based recommendation systems exploit hundreds to thousands of different categorical features, each with millions of different categories ranging from clicks to posts. To respect the natural diversity within the categorical data,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f5f653a5c6b3e8363a7d85adf26ba8c1
Publikováno v:
IA3@SC
Large sparse symmetric indefinite matrices are notoriously hard to precondition. They often lack diagonal dominance and exhibit Schur-complements that render zero fill-in preconditioning ineffective. Pivoting, a necessity for stable LDLt factorizatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4027de64a7f29f0067c9dc5ba8b53933
https://doi.org/10.1109/ia3.2018.00008
https://doi.org/10.1109/ia3.2018.00008
Autor:
M. Arsaev, Joe Eaton, Jonathan Cohen, N. Markovskiy, Julien Demouth, Simon K. Layton, V. Sellappan, Maxim Naumov, Robert Strzodka, Patrice Castonguay, Istvan Z. Reguly, Nikolai Sakharnykh
Publikováno v:
SIAM Journal on Scientific Computing. 37:S602-S626
The solution of large sparse linear systems arises in many applications, such as computational fluid dynamics and oil reservoir simulation. In realistic cases the matrices are often so large that they require large scale distributed parallel computin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::20630c323c9f1af190e427ab80f80060
https://doi.org/10.1137/140980260
https://doi.org/10.1137/140980260