collaborators

6 papers

cs.DC2018

Decoupled Strategy for Imbalanced Workloads in MapReduce Frameworks

Sergio Rivas-Gomez, Sai Narasimhamurthy, Keeran Brabazon +3

In this work, we consider the integration of MPI one-sided communication and non-blocking I/O in HPC-centric MapReduce frameworks. Using a decoupled strategy, we aim to overlap the…

cs.DC2018

MPI Windows on Storage for HPC Applications

Sergio Rivas-Gomez, Roberto Gioiosa, Ivy Bo Peng +4

Upcoming HPC clusters will feature hybrid memories and storage devices per compute node. In this work, we propose to use the MPI one-sided communication model and MPI windows as un…

cs.DC2018

Characterizing Deep-Learning I/O Workloads in TensorFlow

Steven W. D. Chien, Stefano Markidis, Chaitanya Prasad Sishtla +4

The performance of Deep-Learning (DL) computing frameworks rely on the performance of data ingestion and checkpointing. In fact, during the training, a considerable high number of…

cs.DC2018

The SAGE Project: a Storage Centric Approach for Exascale Computing

Sai Narasimhamurthy, Nikita Danilov, Sining Wu +8

SAGE (Percipient StorAGe for Exascale Data Centric Computing) is a European Commission funded project towards the era of Exascale computing. Its goal is to design and implement a B…

cs.DC2018

Exploring Scientific Application Performance Using Large Scale Object Storage

Steven Wei-der Chien, Stefano Markidis, Rami Karim +2

One of the major performance and scalability bottlenecks in large scientific applications is parallel reading and writing to supercomputer I/O systems. The usage of parallel file s…

cs.DC2018

SAGE: Percipient Storage for Exascale Data Centric Computing

Sai Narasimhamurthy, Nikita Danilov, Sining Wu +7

We aim to implement a Big Data/Extreme Computing (BDEC) capable system infrastructure as we head towards the era of Exascale computing - termed SAGE (Percipient StorAGe for Exascal…