J
J. Ravi
Researcher at North Carolina State University
Publications - 5
Citations - 33
J. Ravi is an academic researcher from North Carolina State University. The author has contributed to research in topics: Computer science & Cache. The author has an hindex of 1, co-authored 1 publications receiving 29 citations.
Papers
More filters
Journal ArticleDOI
Transitions in creep mechanisms and creep anisotropy in Zr1Nb1Sn0.2Fe sheet
K. Linga Murty,J. Ravi,Wiratmo +2 more
TL;DR: In this paper, the creep characteristics of a Zr1Nb-1Sn-0.2Fe alloy sheet were investigated at temperatures from 773 to 923 K and at stresses ranging from 9 to 150 MPa along both the rolling and transverse directions, with diffusional viscous creep at low stresses, viscous-glide-controlled microcreep in the intermediate stress regime and the climb of edge dislocations at high stresses.
Proceedings ArticleDOI
HDF5 Cache VOL: Efficient and Scalable Parallel I/O through Caching Data on Node-local Storage
Huihuo Zheng,Venkatram Vishwanath,Quincey Koziol,Houjun Tang,J. Ravi,John Mainzer,Surendra Byna +6 more
TL;DR: This paper designed this to move data asynchronously between the caching storage layer and a parallel file system to overlap the data movement overhead in performing I/O with compute phases, thus achieving faster time-to-solution in scientific simulations.
Runway: In-transit Data Compression on Heterogeneous HPC Systems
TL;DR: Runway as mentioned in this paper is a runtime framework that enables computation on in-transit data with an object storage abstraction, which is designed to be extensible to execute user-defined functions at runtime.
Proceedings ArticleDOI
Runway: In-transit Data Compression on Heterogeneous HPC Systems
TL;DR: Runway as discussed by the authors is a runtime framework that enables computation on in-transit data with an object storage abstraction, which is designed to be extensible to execute user-defined functions at runtime.
Evaluating Asynchronous Parallel I/O on HPC Systems
TL;DR: In this article , the authors perform a systematic study of various factors affecting the performance and efficacy of asynchronous I/O, and develop a performance model to estimate the aggregate I /O bandwidth achievable by iterative applications.