Raju Rangaswami
Florida International University
84 Papers
448 Citations
Raju Rangaswami is an academic researcher from Florida International University. The author has contributed to research in topics: Cache & Computer science. The author has an hindex of 24, co-authored 79 publications. Previous affiliations of Raju Rangaswami include University of Miami & University of California, Santa Barbara.
Chat about Author
Papers
I/O Deduplication: Utilizing content similarity to improve I/O performance
Ricardo Koller,Raju Rangaswami +1 more
TL;DR: I/O Deduplication is introduced, a storage optimization that utilizes content similarity for improving I/O performance by eliminating I/ O operations and reducing the mechanical delays during I-O operations.
SRCMap: energy proportional storage using dynamic consolidation
Akshat Verma,Ricardo Koller,Luis Useche,Raju Rangaswami +3 more
- 23 Feb 2010
TL;DR: Sample-Replicate-Consolidate Mapping is a storage virtualization layer optimization that enables energy proportionality for dynamic I/O workloads by consolidating the cumulative workload on a subset of physical volumes proportional to the I-O workload intensity.
•Proceedings Article
Driving cache replacement with ML-based LeCaR
Giuseppe Vietri,Liana V. Rodriguez,Wendy A. Martinez,Steven Lyons,Jason Liu,Raju Rangaswami,Ming Zhao,Giri Narasimhan +7 more
- 01 Jan 2018
TL;DR: The ML-based LeCaR (Learning Cache Replacement) is competitive with ARC for relatively large cache sizes, but is markedly superior to it when cache sizes become smaller.
•Proceedings Article
NVMKV: a scalable, lightweight, FTL-aware key-value store
Leonardo Marmol,Swaminathan Sundararaman,Nisha Talagala,Raju Rangaswami +3 more
- 08 Jul 2015
TL;DR: NVMKV is a lightweight KV store that leverages native FTL capabilities such as sparse addressing, dynamic mapping, transactional persistence, and support for high-levels of lock free parallelism.
A modeling approach for estimating execution time of long-running scientific applications
S.M. Sadjadi,Shu Shimizu,Javier Figueroa,Raju Rangaswami,Javier Delgado,H. Duran,Xabriel J. Collazo-Mojica +6 more
- 14 Apr 2008
TL;DR: This paper developed a resource usage model that estimates the execution time of a weather forecasting application in a multi-cluster grid computing environment and developed a model that enables prediction without the need for the application to be profiled first on the target hardware.