Careers | Phone Book | A - Z Index

Oguz Selvitopi

Oguz Selvitopi
Postdoctoral Research Fellow
Computer Science
Lawrence Berkeley National Laboratory
1 Cyclotron Road
059-4024B, MS 59R4104
Berkeley, CA 94720

Oguz Selvitopi is postdoctoral research fellow in the Performance and Algorithms group of Computer Science Department at Lawrence Berkeley National Laboratory. His research interests are high performance computing, parallel sparse matrix computations, combinatorial scientific computing, and bioinformatics. Oguz received his Ph.D. in computer engineering from Bilkent University, Turkey in 2016.

Journal Articles

Kadir Akbudak, R. Oguz Selvitopi, Cevdet Aykanat, "Partitioning Models for Scaling Parallel Sparse Matrix-Matrix Multiplication", ACM Transactions on Parallel Computing (TOPC), April 1, 2018, 4, 3, doi: 10.1145/3155292

R. Oguz Selvitopi, Seher Acer, Cevdet Aykanat, "A Recursive Hypergraph Bipartitioning Framework for Reducing Bandwidth and Latency Costs Simultaneously", IEEE Transactions on Parallel and Distributed Systems (TPDS), February 1, 2017, 28, 2:345-358, doi: 10.1109/TPDS.2016.2577024

Seher Acer, R. Oguz Selvitopi, Cevdet Aykanat, "Improving performance of sparse matrix dense matrix multiplication on large-scale parallel systems", Journal of Parallel Computing (PARCO), November 10, 2016, 59:71-96, doi: 10.1016/j.parco.2016.10.001

R. Oguz Selvitopi, Cevdet Aykanat, "Reducing latency cost in 2D sparse matrix partitioning models", Journal of Parallel Computing (PARCO), September 1, 2016, 57:1-24, doi: 10.1016/j.parco.2016.04.004

R. Oguz Selvitopi, Muhammet Mustafa Ozdal, Cevdet Aykanat, "A Novel Method for Scaling Iterative Solvers: Avoiding Latency Overhead of Parallel Sparse-Matrix Vector Multiplies", IEEE Transactions on Parallel and Distributed Systems (TPDS), March 1, 2015, 26, 3:632-645, doi: 10.1109/TPDS.2014.2311804

Ata Turk, R. Oguz Selvitopi, Hakan Ferhatosmanoglu, Cevdet Aykanat, "Temporal Workload-Aware Replicated Partitioning for Social Networks", IEEE Transactions on Knowledge and Data Engineering (TKDE), November 16, 2014, 26, 11:2832-2845, doi: 10.1109/TKDE.2014.2302291

R. Oguz Selvitopi, Ata Turk, Cevdet Aykanat, "Replicated partitioning for undirected hypergraphs", Journal of Parallel and Distributed Computing (JPDC), April 1, 2012, 72:547-563, doi: 10.1016/j.jpdc.2012.01.004

Conference Papers

Seher Acer, R. Oguz Selvitopi, Cevdet Aykanat, "Addressing Volume and Latency Overheads in 1D-parallel Sparse Matrix-Vector Multiplication", European Conference on Parallel Processing (Euro-Par), Springer, August 1, 2017, 625-637, doi: 10.1007/978-3-319-64203-1_45

Book Chapters

R. Oguz Selvitopi, Kadir Akbudak, Cevdet Aykanat, "Parallelization of Sparse Matrix Kernels for Big Data Applications", Resource Management for Big Data Platforms, edited by Pop F., Kołodziej J., Di Martino B. , (Springer: October 28, 2016) Pages: 367-382 doi: 10.1007/978-3-319-44881-7_17