Zobrazeno 1 - 10
of 50
pro vyhledávání: '"Kim Hazelwood"'
Publikováno v:
ACM Transactions on Architecture and Code Optimization. 19:1-25
Traditional offline optimization frameworks rely on representative hardware, software, and inputs to compare different optimizations on. With application-specific optimization for mobile systems though, the idea of a representative testbench is unrea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dd631d06443e1c87c752c4fe0b74cda1
https://doi.org/10.1145/3517338
https://doi.org/10.1145/3517338
Autor:
Denis Sheahan, Janet Yang, Lei Tian, Valentin Andrei, Bilge Acun, Cyril Meurillon, Gisle Dankel, Peifeng Yu, Adnan Aziz, Christopher Gregg, Lukasz Wesolowski, Kim Hazelwood, Xiaoqiao Meng
Publikováno v:
IEEE Micro. 41:101-112
In this article, we present a system to collectively optimize efficiency in a very large scale deployment of GPU servers for machine learning workloads at Facebook. Our system 1) measures and stores system-wide efficiency metrics for every executed w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::28d38d31c236b057ae2b76014b945313
https://doi.org/10.1109/mm.2021.3097287
https://doi.org/10.1109/mm.2021.3097287
Autor:
Cheng Fu, Hanxian Huang, Bram Wasti, Chris Cummins, Riyadh Baghdadi, Kim Hazelwood, Yuandong Tian, Jishen Zhao, Hugh Leather
Publikováno v:
Proceedings of the International Conference on Parallel Architectures and Compilation Techniques.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::46508b13ec625b55fd3fb3b8e69aa6d7
https://doi.org/10.1145/3559009.3569673
https://doi.org/10.1145/3559009.3569673
Publikováno v:
ACM Transactions on Architecture and Code Optimization. 18:1-23
State-of-the-art machine learning frameworks support a wide variety of design features to enable a flexible machine learning programming interface and to ease the programmability burden on machine learning developers. Identifying and using a performa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ae4506269a3b78150e9b0fb3ac544b9e
https://doi.org/10.1145/3431388
https://doi.org/10.1145/3431388
Autor:
Smail Kourta, Adel Abderahmane Namani, Fatima Benbouzid-Si Tayeb, Kim Hazelwood, Chris Cummins, Hugh Leather, Riyadh Baghdadi
Term Rewriting Systems (TRSs) are used in compilers to simplify and prove expressions. State-of-the-art TRSs in compilers use a greedy algorithm that applies a set of rewriting rules in a predefined order (where some of the rules are not axiomatic).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e152ac0f6be5b018663697ab10ea7412
http://arxiv.org/abs/2111.12116
http://arxiv.org/abs/2111.12116
Publikováno v:
Mpeis, P, Petoumenos, P, Hazelwood, K & Leather, H 2021, Developer and User-Transparent Compiler Optimization for Interactive Applications . in Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation (PLDI '21) . Association for Computing Machinery (ACM), pp. 268-281, 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, 20/06/21 . https://doi.org/10.1145/3453483.3454043
PLDI
PLDI
Traditional offline optimization frameworks rely on representative hardware, software, and inputs to compare different optimization decisions on. With application-specific optimization for mobile systems though, the idea of a representative testbench
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5721ca478c063a7d7c07fef4f0c60aef
https://www.pure.ed.ac.uk/ws/files/214205579/Developer_and_User_Transparent_MPEIS_DOA06042021_AFV.pdf
https://www.pure.ed.ac.uk/ws/files/214205579/Developer_and_User_Transparent_MPEIS_DOA06042021_AFV.pdf
Publikováno v:
HPCA
The use of GPUs has proliferated for machine learning workflows and is now considered mainstream for many deep learning models. Meanwhile, when training state-of-the-art personal recommendation models, which consume the highest number of compute cycl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40d23b0b9c4e4e9196102c961e74b6a1
http://arxiv.org/abs/2011.05497
http://arxiv.org/abs/2011.05497
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
Autor:
Kim Hazelwood
Dynamic binary modification tools form a software layer between a running application and the underlying operating system, providing the powerful opportunity to inspect and potentially modify every user-level guest application instruction that execut
Autor:
David Brooks, Kevin Chen, Tommer Leyvand, Andrew Tulloch, Bill Jia, Yiming Wu, Sy Choudhury, Hao Lu, Kim Hazelwood, Yanghan Wang, Peizhao Zhang, Lin Qiao, Bram Wasti, Ran Xian, Peter Vajda, Brandon Reagen, Yangqing Jia, Fei Sun, Carole-Jean Wu, Yang Lu, Xiaodong Wang, Marat Dukhan, Eldad Isaac, Joe Spisak, Douglas Chen, Sungjoo Yoo
Publikováno v:
HPCA
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5cca28b23ff7aff7afad048e5c2368cd
https://doi.org/10.1109/hpca.2019.00048
https://doi.org/10.1109/hpca.2019.00048