|On large-batch training for deep learning: Generalization gap and sharp minima|
NS Keskar, D Mudigere, J Nocedal, M Smelyanskiy, PTP Tang
arXiv preprint arXiv:1609.04836, 2016
|Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU|
VW Lee, C Kim, J Chhugani, M Deisher, D Kim, AD Nguyen, N Satish, ...
Proceedings of the 37th annual international symposium on Computer …, 2010
|Applied machine learning at facebook: A datacenter infrastructure perspective|
K Hazelwood, S Bird, D Brooks, S Chintala, U Diril, D Dzhulgakov, ...
2018 IEEE International Symposium on High Performance Computer Architecture …, 2018
|Efficient sparse matrix-vector multiplication on x86-based many-core processors|
X Liu, M Smelyanskiy, E Chow, P Dubey
Proceedings of the 27th international ACM conference on International …, 2013
|Deep learning recommendation model for personalization and recommendation systems|
M Naumov, D Mudigere, HJM Shi, J Huang, N Sundaraman, J Park, ...
arXiv preprint arXiv:1906.00091, 2019
|Design and implementation of the linpack benchmark for single and multi-node systems based on intel® xeon phi coprocessor|
A Heinecke, K Vaidyanathan, M Smelyanskiy, A Kobotov, R Dubtsov, ...
2013 IEEE 27th International Symposium on Parallel and Distributed …, 2013
|Exploring simd for molecular dynamics, using intel® xeon® processors and intel® xeon phi coprocessors|
SJ Pennycook, CJ Hughes, M Smelyanskiy, SA Jarvis
2013 IEEE 27th International symposium on parallel and distributed …, 2013
|Glow: Graph lowering compiler techniques for neural networks|
N Rotem, J Fix, S Abdulrasool, G Catron, S Deng, R Dzhabarov, N Gibson, ...
arXiv preprint arXiv:1805.00907, 2018
|Convergence of recognition, mining, and synthesis workloads and its implications|
YK Chen, J Chhugani, P Dubey, CJ Hughes, D Kim, S Kumar, VW Lee, ...
Proceedings of the IEEE 96 (5), 790-807, 2008
|The architectural implications of facebook's dnn-based personalized recommendation|
U Gupta, CJ Wu, X Wang, M Naumov, B Reagen, D Brooks, B Cottel, ...
2020 IEEE International Symposium on High Performance Computer Architecture …, 2020
|Can traditional programming bridge the ninja performance gap for parallel computing applications?|
N Satish, C Kim, J Chhugani, H Saito, R Krishnaiyer, M Smelyanskiy, ...
2012 39th Annual International Symposium on Computer Architecture (ISCA …, 2012
|Anatomy of high-performance many-threaded matrix multiplication|
TM Smith, R Van De Geijn, M Smelyanskiy, JR Hammond, FG Van Zee
2014 IEEE 28th International Parallel and Distributed Processing Symposium …, 2014
|A study of BFLOAT16 for deep learning training|
D Kalamkar, D Mudigere, N Mellempudi, D Das, K Banerjee, S Avancha, ...
arXiv preprint arXiv:1905.12322, 2019
|Petascale high order dynamic rupture earthquake simulations on heterogeneous supercomputers|
A Heinecke, A Breuer, S Rettenberger, M Bader, AA Gabriel, C Pelties, ...
SC'14: Proceedings of the International Conference for High Performance …, 2014
|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
|Mapping high-fidelity volume rendering for medical imaging to CPU, GPU and many-core architectures|
M Smelyanskiy, D Holmes, J Chhugani, A Larson, DM Carmean, ...
IEEE transactions on visualization and computer graphics 15 (6), 1563-1570, 2009
|qHiPSTER: The quantum high performance software testing environment|
M Smelyanskiy, NPD Sawaya, A Aspuru-Guzik
arXiv preprint arXiv:1601.07195, 2016
|Practical optimization for hybrid quantum-classical algorithms|
GG Guerreschi, M Smelyanskiy
arXiv preprint arXiv:1701.01450, 2017
|Vector instructions to enable efficient synchronization and parallel reduction operations|
M Smelyanskiy, S Kumar, D Kim, J Chhugani, C Kim, CJ Hughes, VW Lee, ...
US Patent 9,513,905, 2016
|The BLIS framework: Experiments in portability|
FG Van Zee, TM Smith, B Marker, TM Low, RAVD Geijn, FD Igual, ...
ACM Transactions on Mathematical Software (TOMS) 42 (2), 1-19, 2016