umu.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Eljammaly, Mahmoud
Publications (6 of 6) Show all publications
Eljammaly, M., Karlsson, L. & Kågström, B. (2018). An auto-tuning framework for a NUMA-aware Hessenberg reduction algorithm. In: ICPE '18 Companion of the 2018 ACM/SPEC International Conference on Performance Engineering: . Paper presented at International Conference on Performance Engineering (ICPE 2018), Berlin, Germany, April 9-13, 2018 (pp. 5-8). ACM Digital Library
Open this publication in new window or tab >>An auto-tuning framework for a NUMA-aware Hessenberg reduction algorithm
2018 (English)In: ICPE '18 Companion of the 2018 ACM/SPEC International Conference on Performance Engineering, ACM Digital Library, 2018, , p. 4p. 5-8Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
ACM Digital Library, 2018. p. 4
Keywords
Auto-tuning, Tuning framework, Binning, Search space decomposition, Multistage search, Hessenberg reduction, NUMA-aware
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-154392 (URN)10.1145/3185768.3186304 (DOI)978-1-4503-5629-9 (ISBN)
Conference
International Conference on Performance Engineering (ICPE 2018), Berlin, Germany, April 9-13, 2018
Available from: 2018-12-17 Created: 2018-12-17 Last updated: 2019-06-25Bibliographically approved
Eljammaly, M. (2018). Identification and tuning of algorithmic parameters in parallel matrix computations: Hessenberg reduction and tensor storage format conversion. (Licentiate dissertation). Umeå: Umeå universitet
Open this publication in new window or tab >>Identification and tuning of algorithmic parameters in parallel matrix computations: Hessenberg reduction and tensor storage format conversion
2018 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

This thesis considers two problems in numerical linear algebra and high performance computing (HPC): (i) the parallelization of a new blocked Hessenberg reduction algorithm using Parallel Cache Assignment (PCA) and the tunability of its algorithm parameters, and (ii) storing and manipulating dense tensors on shared memory HPC systems.

The Hessenberg reduction appears in the Aggressive Early Deflation (AED) process for identifying converged eigenvalues in the distributed multishift QR algorithm (state-of-the-art algorithm for computing all eigenvalues for dense square matrices). Since the AED process becomes a parallel bottleneck it motivates a further study of AED components. We present a new Hessenberg reduction algorithm based on PCA which is NUMA-aware and targeting relatively small problem sizes on shared memory systems. The tunability of the algorithm parameters are investigated. A simple off-line tuning is presented and the performance of the new Hessenberg reduction algorithm is compared to its counterparts from LAPACK and ScaLAPACK. The new algorithm outperforms LAPACK in all tested cases and outperforms ScaLAPACK in problems smaller than order 1500, which are common problem sizes for AED in the context of the distributed multishift QR algorithm.

We also investigate automatic tuning of the algorithm parameters. The parameters span a huge search space and it is impractical to tune them using standard auto-tuning and optimization techniques. We present a modular auto-tuning framework which applies: search space decomposition, binning, and multi-stage search to enable searching the huge search space efficiently. The framework using these techniques exposes the underlying subproblems which allows using standard auto-tuning methods to tune them. In addition, the framework defines an abstract interface, which combined with its modular design, allows testing various tuning algorithms.

In the last part of the thesis, the focus is on the problem of storing and manipulating dense tensors. Developing open source tensor algorithms and applications is hard due to the lack of open source software for fundamental tensor operations. We present a software library dten, which includes tools for storing dense tensors in shared memory and converting a tensor storage format from one canonical form to another. The library provides two different ways to perform the conversion in parallel, in-place and out-of-place. The conversion involves moving blocks of contiguous data and are done to maximize the size of the blocks to move. In addition, the library supports tensor matricization for one or two tensors at the same time. The latter case is important in preparing tensors for contraction operations. The library is general purpose and highly flexible.

Place, publisher, year, edition, pages
Umeå: Umeå universitet, 2018. p. 15
Series
Report / UMINF, ISSN 0348-0542 ; UMINF 18.22
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-145345 (URN)978-91-7601-843-9 (ISBN)
Supervisors
Available from: 2018-03-01 Created: 2018-02-28 Last updated: 2018-06-09Bibliographically approved
Eljammaly, M., Karlsson, L. & Kågström, B. (2018). On the Tunability of a New Hessenberg Reduction Algorithm Using Parallel Cache Assignment. In: Wyrzykowski R., Dongarra J., Deelman E., Karczewski K. (Ed.), Parallel Processing and Applied Mathematics. PPAM 2017: Part 1. Paper presented at 12th International Conference on Parallel Processing and Applied Mathematics, PPAM 2017, Lublin, Poland, 10–13 September, 2017 (pp. 579-589). Springer
Open this publication in new window or tab >>On the Tunability of a New Hessenberg Reduction Algorithm Using Parallel Cache Assignment
2018 (English)In: Parallel Processing and Applied Mathematics. PPAM 2017: Part 1 / [ed] Wyrzykowski R., Dongarra J., Deelman E., Karczewski K., Springer, 2018, p. 579-589Conference paper, Published paper (Refereed)
Abstract [en]

The reduction of a general dense square matrix to Hessenberg form is a well known first step in many standard eigenvalue solvers. Although parallel algorithms exist, the Hessenberg reduction is one of the bottlenecks in AED, a main part in state-of-the-art software for the distributed multishift QR algorithm. We propose a new NUMA-aware algorithm that fits the context of the QR algorithm and evaluate the sensitivity of its algorithmic parameters. The proposed algorithm is faster than LAPACK for all problem sizes and faster than ScaLAPACK for the relatively small problem sizes typical for AED.

Place, publisher, year, edition, pages
Springer, 2018
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 10777
Keywords
Hessenberg reduction, Parallel cache assignment, NUMA-aware algorithm, Shared-memory, Tunable parameters, Off-line tuning
National Category
Computer Sciences Computational Mathematics
Identifiers
urn:nbn:se:umu:diva-145342 (URN)10.1007/978-3-319-78024-5_50 (DOI)000458563300050 ()978-3-319-78023-8 (ISBN)978-3-319-78024-5 (ISBN)
Conference
12th International Conference on Parallel Processing and Applied Mathematics, PPAM 2017, Lublin, Poland, 10–13 September, 2017
Note

Available from: 2018-02-28 Created: 2018-02-28 Last updated: 2019-03-06Bibliographically approved
Eljammaly, M., Karlsson, L. & Kågström, B. (2017). An auto-tuning framework for a NUMA-aware Hessenberg reduction algorithm. Umeå: Department of computing science, Umeå university
Open this publication in new window or tab >>An auto-tuning framework for a NUMA-aware Hessenberg reduction algorithm
2017 (English)Report (Other academic)
Abstract [en]

The performance of a recently developed Hessenberg reduction algorithm greatly depends on the values chosen for its tunable parameters. The search space is huge combined with other complications makes the problem hard to solve effectively with generic methods and tools. We describe a modular auto-tuning framework in which the underlying optimization algorithm is easy to substitute. The framework exposes sub-problems of standard auto-tuning type for which existing generic methods can be reused. The outputs of concurrently executing sub-tuners are assembled by the framework into a solution to the original problem.

Place, publisher, year, edition, pages
Umeå: Department of computing science, Umeå university, 2017. p. 14
Series
Report / UMINF, ISSN 0348-0542 ; 17.19
Keywords
Auto-tuning, Tuning framework, Binning, Search space decomposition, Multistage search, Hessenberg reduction, NUMA-aware
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-145297 (URN)
Available from: 2018-02-28 Created: 2018-02-28 Last updated: 2018-06-09Bibliographically approved
Eljammaly, M. & Karlsson, L. (2016). A library for storing and manipulating dense tensors. Umeå: Department of computing science, Umeå university
Open this publication in new window or tab >>A library for storing and manipulating dense tensors
2016 (English)Report (Other academic)
Abstract [en]

Aiming to build a layered infrastructure for high-performance dense tensor applications, we present a library, called dten, for storing and manipulating dense tensors. The library focuses on storing dense tensors in canonical storage formats and converting between storage formats in parallel. In addition, it supports tensor matricization in different ways. The library is general-purpose and provides a high degree of flexibility.

Place, publisher, year, edition, pages
Umeå: Department of computing science, Umeå university, 2016. p. 21
Series
Report / UMINF, ISSN 0348-0542 ; 17.22
Keywords
Dense tensors, canonical storage format, tensor matricization, tensor storage format conversion, out-of-place conversion, in-place conversion
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-145341 (URN)
Available from: 2018-02-28 Created: 2018-02-28 Last updated: 2018-06-09Bibliographically approved
Eljammaly, M., Karlsson, L. & Kågström, B. (2016). Evaluation of the Tunability of a New NUMA-Aware Hessenberg Reduction Algorithm.
Open this publication in new window or tab >>Evaluation of the Tunability of a New NUMA-Aware Hessenberg Reduction Algorithm
2016 (English)Report (Other academic)
Series
Report / UMINF, ISSN 0348-0542 ; 16.21
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-152576 (URN)
Available from: 2018-10-14 Created: 2018-10-14 Last updated: 2018-10-14
Organisations

Search in DiVA

Show all publications