[Education | Research | Research Groups | Publications | Research Grants | Software | Teaching | Busy hours |(Curriculum Vitae EN/TR)]

Murat Manguoglu
Department of Computer Engineering A407
Middle East Technical University, 06800 Ankara , Turkey

Office: (+90) 312 210 5551
Office hours: Thursdays 14:00-15:00 (unless some ther events overlap it in my calendar below)
Voicemail (for US): (765)2379699 (please leave a message and I will call you back)
Fax: (+90) 312 210 5544
Email: manguoglu(at)ceng.metu.edu.tr or murat.manguoglu(at)gmail.com
Note: I do not respond to unsolicited email applications for summer internships.

Phd. Purdue'09, Computer Science and a specialization in Computational Science (phd family tree)
MSc. the University of Utah'04, Computational Engineering and Science
BSc. METU'02, Electrical and Electronics Engineering

Research Interests: Parallel Computing and Numerical Linear Algebra

Research Groups: METU Parallel Processing Lab and Purdue High Performance Sparse Matrix Computations Group

Research Grants and Awards:

Manguoglu M; Turkish Academy of Sciences Distinguished Young Scientist Award (2013-2016)

Manguoglu M (PI); TUBITAK Career Award EEAG111E238; (1/5/2012 -1/5/2014) ; Parallel Solution of Sparse Linear Systems

Manguoglu M (PI); METU BAP-08-11-2011-128; (1/7/2011 - 31/12/2013); Solution of Linear Systems on Parallel Computers

Manguoglu M (researcher); The Partnership for Advanced Computing in Europe First Implementation Phase (PRACE-1IP), European Community's Seventh Fram Programme (FP7/2007- 2013) under grant agreement no: RI-261557; (2/6/2011-2/6/2012)

Sameh A and Manguoglu M(co-PI); from Intel Corporation; (1/6/2009 - 31/5/2010); Towards an Adaptive Library for Solving Large Sparse Linear Systems

Manguoglu M (researcher); various projects during (2005-2010); NSF (NSF-CCF-0635169), DARPA/AFRL (FA8750-06-1-0233), DOE (DE-FC52-08NA28617) and funding from Intel Corporation

Selected refereed publications :

(A local preprint or postprint PDF of the papers are provided whenever allowed by the publisher, see http://www.sherpa.ac.uk/romeo/ for the specific rules of different publishers. For the final copy of any paper please follow publisher links provided or email me)

Torun FS, Manguoglu M, Aykanat C, Parallel minimum norm solution of sparse block diagonal column overlapped underdetermined systems, ACM Transactions on Mathematical Software,43(4), pp. 31:1--31:21, 2017 ~PDF

Bolukbasi ES, Manguoglu M, A Multithreaded Recursive and Nonrecursive Parallel Sparse Direct Solver , Advances in Computational Fluid-Structure Interactions, Springer-Birkhauser (book chapter, editors: Y. Bazilevs and K. Takizawa), 2016 ~ Publisher's version

Uzunca M, Karasozen B, Manguoglu M,Adaptive discontinuous Galerkin methods for nonlinear diffusion-convection-reaction equations, Computers and Chemical Engineering, 63, pp.24-37, 2014 ~ PDF Publisher's version

Manguoglu M, Parallel solution of sparse linear systems, High Performance Scientific Computing, Springer (book chapter, editors:M. Berry, K. Gallivan, E. Gallopoulos, A. Grama, B. Philippe, Y. Saad and F. Saied), 2012 Publisher's version

Manguoglu M, Koyuturk M, Sameh A, Grama A, Weighted Matrix Ordering and Parallel Banded Preconditioners for Iterative Linear System Solvers, SIAM Journal on Scientific Computing, 32(3), pp.1201-1216, 2010 ~ PDF Publisher's version

Naumov M, Manguoglu M, Sameh A, A tearing-based hybrid parallel sparse linear system solver , Journal of Computational and Applied Mathematics, Volume 234, Issue 10, pp.3025-3038, 2010 ~ Publisher's version

Mikkelsen CCK, Manguoglu M , Analysis of the Truncated Spike Algorithm, SIAM Journal on Matrix Analysis and Applications, 30(4), pp.1500-1519,2008, ~ PDF Publisher's version

Manguoglu M, Sameh A, Tezduyar T, Sathe S, A nested iterative scheme for computation of incompressible flows in long domains, Computational Mechanics, 43(1),pp.73-80 , 2008, ~ PDF Publisher's version

(Follow the link for a complete list of my publications)

Software development:

Sparse matrix reordering into 2x2 block form using the largest eigenvector of the Laplacian (Matlab)
DDPS Solver: for general sparse linear systems (MPI/OpenMP)
PSPIKE Solver: for general sparse linear systems (MPI/OpenMP)
SPIKE Solver: for banded systems that are dense within the band (MPI)
MCFiedler: for computing the Fiedler vector using the TraceMin algorithm (MPI)


CENG478 Introduction to Parallel Computing [Spring 2017]

Travel and Conference Schedule

19h International Conference on Finite Elements in Flow Problems, 5-7 April 2017
5. Ulusal Yuksek Basarimli Hesaplama Konferansi, 14-15 September 2017

Busy hours:

updated on April, 2017