E
Evangelos Georganas
Researcher at Intel
Publications - 47
Citations - 1280
Evangelos Georganas is an academic researcher from Intel. The author has contributed to research in topics: Deep learning & Computer science. The author has an hindex of 13, co-authored 43 publications receiving 925 citations. Previous affiliations of Evangelos Georganas include University of California & Lawrence Berkeley National Laboratory.
Papers
More filters
Journal ArticleDOI
A whole-genome shotgun approach for assembling and anchoring the hexaploid bread wheat genome
Jarrod Chapman,Martin Mascher,Aydin Buluc,Kerrie Barry,Evangelos Georganas,Evangelos Georganas,Adam M. Session,Veronika Strnadova,Jerry Jenkins,Sunish K. Sehgal,Sunish K. Sehgal,Leonid Oliker,Jeremy Schmutz,Katherine Yelick,Katherine Yelick,Uwe Scholz,Robbie Waugh,Jesse Poland,Gary J. Muehlbauer,Nils Stein,Daniel S. Rokhsar,Daniel S. Rokhsar +21 more
TL;DR: In this paper, a sequence assembly representing 9.1 Gbp of the highly repetitive 16 Gbp genome of hexaploid wheat, Triticum aestivum, and 7.1 gb of this assembly to chromosomal locations is presented.
Posted Content
A Study of BFLOAT16 for Deep Learning Training
Dhiraj D. Kalamkar,Dheevatsa Mudigere,Naveen Mellempudi,Dipankar Das,Kunal Banerjee,Sasikanth Avancha,Dharma Teja Vooturi,Nataraj Jammalamadaka,Jianyu Huang,Hector Yuen,Jiyan Yang,Jongsoo Park,Alexander Heinecke,Evangelos Georganas,Sudarshan Srinivasan,Abhisek Kundu,Misha Smelyanskiy,Bharat Kaul,Pradeep Dubey +18 more
TL;DR: The results show that deep learning training using BFLOAT16 tensors achieves the same state-of-the-art (SOTA) results across domains as FP32 tensors in the same number of iterations and with no changes to hyper-parameters.
Proceedings Article
Mixed Precision Training of Convolutional Neural Networks using Integer Operations
Dipankar Das,Naveen Mellempudi,Dheevatsa Mudigere,Dhiraj D. Kalamkar,Sasikanth Avancha,Kunal Banerjee,Srinivas Sridharan,Karthik Vaidyanathan,Bharat Kaul,Evangelos Georganas,Alexander Heinecke,Pradeep Dubey,Jesus Corbal,Nikita Shustrov,Roman S. Dubtsov,Evarist Fomenko,Vadim O. Pirogov +16 more
TL;DR: This paper proposed a shared exponent representation of tensors and developed a Dynamic Fixed Point (DFP) scheme suitable for common neural network operations for Integer Fused-Multiply-and-Accumulate (FMA) operations.
Proceedings ArticleDOI
Parallel de bruijn graph construction and traversal for de novo genome assembly
Evangelos Georganas,Aydin Buluc,Jarrod Chapman,Leonid Oliker,Daniel S. Rokhsar,Katherine Yelick +5 more
TL;DR: A novel algorithm is provided that leverages one-sided communication capabilities of the Unified Parallel C (UPC) to facilitate the requisite fine-grained parallelism and avoidance of data hazards, while analytically proving its scalability properties.
Proceedings ArticleDOI
HipMer: an extreme-scale de novo genome assembler
Evangelos Georganas,Aydin Buluc,Jarrod Chapman,Steven Hofmeyr,Chaitanya Aluru,Rob Egan,Leonid Oliker,Daniel S. Rokhsar,Katherine Yelick +8 more
TL;DR: HipMer is presented, the first high-quality end-to-end de novo assembler designed for extreme scale analysis, via efficient parallelization of the Meraculous code, and significantly improves scalability of parallel k-mer analysis for complex repetitive genomes that exhibit skewed frequency distributions.