Follow
Daya S Khudia
Title
Cited by
Cited by
Year
Deep learning inference in facebook data centers: Characterization, performance optimizations and hardware implications
J Park, M Naumov, P Basu, S Deng, A Kalaiah, D Khudia, J Law, P Malani, ...
arXiv preprint arXiv:1811.09886, 2018
2182018
Rumba: An online quality management system for approximate computing
DS Khudia, B Zamirai, M Samadi, S Mahlke
Proceedings of the 42nd Annual International Symposium on Computer …, 2015
1882015
Harnessing soft computations for low-budget fault tolerance
DS Khudia, S Mahlke
2014 47th Annual IEEE/ACM International Symposium on Microarchitecture, 319-330, 2014
762014
Efficient soft error protection for commodity embedded microprocessors using profile information
DS Khudia, G Wright, S Mahlke
Proceedings of the 13th ACM SIGPLAN/SIGBED International Conference on …, 2012
542012
Fbgemm: Enabling high-performance low-precision deep learning inference
D Khudia, J Huang, P Basu, S Deng, H Liu, J Park, M Smelyanskiy
arXiv preprint arXiv:2101.05615, 2021
462021
Low cost control flow protection using abstract control signatures
DS Khudia, SA Mahlke
LCTES, 3-12, 2013
452013
Post-silicon bug diagnosis with inconsistent executions
A DeOrio, DS Khudia, V Bertacco
2011 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 755-761, 2011
362011
Quality control for approximate accelerators by error prediction
DS Khudia, B Zamirai, M Samadi, S Mahlke
IEEE Design & Test 33 (1), 43-50, 2015
342015
BugMD: Automatic mismatch diagnosis for bug triaging
B Mammo, M Furia, V Bertacco, S Mahlke, DS Khudia
2016 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 1-7, 2016
222016
Location-aware cache management for many-core processors with deep cache hierarchy
J Park, RM Yoo, DS Khudia, CJ Hughes, D Kim
Proceedings of the International Conference on High Performance Computing …, 2013
182013
Efficient soft-error detection for low-precision deep learning recommendation models
S Li, J Huang, PTP Tang, D Khudia, J Park, HD Dixit, Z Chen
2022 IEEE International Conference on Big Data (Big Data), 1556-1563, 2022
132022
Open-sourcing FBGEMM for state-of-the-art server-side inference
DS Khudia, P Basu, S Deng
engineering. fb. com/ml-applications/fbgemm, 2018
132018
Low-precision hardware architectures meet recommendation model inference at scale
Z Deng, J Park, PTP Tang, H Liu, J Yang, H Yuen, J Huang, D Khudia, ...
IEEE Micro 41 (5), 93-100, 2021
102021
Llm inference performance engineering: Best practices
M Agarwal, A Qureshi, LLN Sardana, J Quevedo, D Khudia
Oct, 2023
92023
Mosaicbert: A bidirectional encoder optimized for fast pretraining
J Portes, A Trott, S Havens, D King, A Venigalla, M Nadeem, N Sardana, ...
Advances in Neural Information Processing Systems 36, 3106-3130, 2023
62023
Mosaicbert: How to train bert with a lunch money budget
J Portes, AR Trott, S Havens, D King, A Venigalla, M Nadeem, N Sardana, ...
Workshop on Efficient Systems for Foundation Models@ ICML2023, 2023
62023
System and method for statistical post-silicon validation
V Bertacco, A Deorio, DS Khudia
US Patent 9,411,007, 2016
52016
Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications. CoRR abs/1811.09886 (2018)
J Park, M Naumov, P Basu, S Deng, A Kalaiah, DS Khudia, J Law, ...
arXiv preprint arXiv:1811.09886, 2018
32018
Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale
J Park, PTP Tang, H Liu, H Yuen, J Huang, D Khudia, X Wei, E Wen, ...
arXiv preprint arXiv:2105.12676, 2021
2021
Apparatus and method for implementing a scratchpad memory using priority hint
CJ Hughes, DS Khudia, D Kim, JS Park, RM Yoo
US Patent 9,158,702, 2015
2015
The system can't perform the operation now. Try again later.
Articles 1–20