Aditya Devarakonda

Aditya Devarakonda

Auto-generated profile, based on publicly available information

Aditya Devarakonda

Wake Forest University, Winston-Salem, NC, USA

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2012 in Journal of Computer and System Sciences
Verified
Journal Article
Closed access
DVDavid Villegas
David Villegas
NBNorman Bobroff
Norman Bobroff
IRIvan Rodero
Ivan Rodero
JDJavier Delgado
Javier Delgado
YLYanbin Liu
Yanbin Liu
MPManish Parashar
Manish Parashar

12 June 2013 in Computing in Science & Engineering
Verified
Journal Article
Closed access
MPManish Parashar
Manish Parashar
MAMoustafa AbdelBaky
Moustafa AbdelBaky
IRIvan Rodero
Ivan Rodero
ADAditya Devarakonda
Aditya Devarakonda
Clouds are rapidly joining high-performance computing (HPC) systems, clusters, and grids as viable platforms for scientific exploration and discovery. As a result, understanding application formulations and usage modes that are meaningful in such a hybrid infrastructure, and how application workflows can effectively utilize it, is critical. Here, three hybrid HPC/grid and cloud cyber infrastructure usage modes are explored: HPC in the Cloud, HPC plus Cloud, and HPC as a Service, presenting illustrative scenarios in each case and outlining benefits, limitations, and research challenges.

1 December 2016
Verified
Conference Paper
Closed access
AGAlex Gittens
Alex Gittens
ADAditya Devarakonda
Aditya Devarakonda
EREvan Racah
Evan Racah
MRMichael Ringenburg
Michael Ringenburg
LGLisa Gerhardt
Lisa Gerhardt
PRPrabhat
Prabhat
We explore the trade-offs of performing linear algebra using Apache Spark, compared to traditional C and MPI implementations on HPC platforms. Spark is designed for data analytics on cluster computing platforms with access to local disks and is optimized for data-parallel tasks. We examine three widely-used and important matrix factorizations: NMF (for physical plausability), PCA (for its ubiquity) and CX (for data interpretability). We apply these methods to 1.6TB particle physics, 2.2TB and 16TB climate modeling and 1.1TB bioimaging data. The data matrices are tall-and-skinny which enable the algorithms to map conveniently into Spark's data-parallel model. We perform scaling experiments on up to 1600 Cray XC40 nodes, describe the sources of slowdowns, and provide tuning guidance to obtain high performance.

2 January 2019 in SIAM Journal on Scientific Computing
Verified
Journal Article
Closed access
ADAditya Devarakonda
Aditya Devarakonda
KFKimon Fountoulakis
Kimon Fountoulakis
JDJames Demmel
James Demmel
MMMichael W. Mahoney
Michael W. Mahoney
Primal and dual block coordinate descent methods are iterative methods for solving regularized and unregularized optimization problems. Distributed-memory parallel implementations of these methods have become popular in analyzing large machine learning datasets. However, existing implementations communicate at every iteration, which, on modern data center and supercomputing architectures, often dominates the cost of floating-point computation. Recent results on communication-avoiding Krylov subspace methods suggest that large speedups are possible by re-organizing iterative algorithms to avoid communication. We show how applying similar algorithmic transformations can lead to primal and dual block coordinate descent methods that only communicate every $s$ iterations---where $s$ is a tuning parameter---instead of every iteration for the regularized least-squares problem. We show that the communication-avoiding variants reduce the number of synchronizations by a factor of $s$ on distributed-memory parallel ...

13 August 2018
Verified
Conference Paper
Open access
SSSaeed Soori
Saeed Soori
ADAditya Devarakonda
Aditya Devarakonda
ZBZachary Blanco
Zachary Blanco
JDJames Demmel
James Demmel
MGMert Gurbuzbalaban
Mert Gurbuzbalaban
MDMaryam Mehri Dehnavi
Maryam Mehri Dehnavi

19 February 2025
Verified
Conference Paper
Open access
ZSZishan Shao
Zishan Shao
ADAditya Devarakonda
Aditya Devarakonda