Portable and Efficient Dense Linear Algebra in the Beginning of the Exascale Era

Autor: Mark Gates, Asim YarKhan, Dalal Sukkari, Kadir Akbudak, Sebastien Cayrols, Daniel Bielich, Ahmad Abdelfattah, Mohammed Al Farhan, Jack Dongarra

Publikováno v: Kadir Akbudak

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71fac2d269c2826222f1dd073b78f71e
https://doi.org/10.1109/p3hpc56579.2022.00009

Extreme-Scale Task-Based Cholesky Factorization Toward Climate and Weather Prediction Applications

Autor: Yu Pei, Kadir Akbudak, A. Mikhalev, Qinglei Cao, David E. Keyes, Jack Dongarra, George Bosilca, Hatem Ltaief

Publikováno v: Cao, Q, Pei, Y, Akbudak, K, Mikhalev, A, Bosilca, G, Ltaief, H, Keyes, D & Dongarra, J 2020, Extreme-Scale Task-Based Cholesky Factorization Toward Climate and Weather Prediction Applications . in PASC '20: Proceedings of the Platform for Advanced Scientific Computing Conference . pp. 1-11 . https://doi.org/10.1145/3394277.3401846
PASC

Climate and weather can be predicted statistically via geospatial Maximum Likelihood Estimates (MLE), as an alternative to running large ensembles of forward models. The MLE-based iterative optimization procedure requires the solving of large-scale l

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::309d88e859f4a1b8e9c3d427c8aea121
https://www.research.manchester.ac.uk/portal/en/publications/extremescale-taskbased-cholesky-factorization-toward-climate-and-weather-prediction-applications(e7d819e0-22f1-4ff4-aa78-61f481293973).html

Performance Analysis of Tile Low-Rank Cholesky Factorization Using PaRSEC Instrumentation Tools

Autor: A. Mikhalev, Thomas Herauldt, Kadir Akbudak, Jack Dongarra, Yu Pei, Hatem Ltaief, Quinglei Cao, George Bosilca, David E. Keyes

Publikováno v: 2019 IEEE/ACM International Workshop on Programming and Performance Visualization Tools (ProTools).

This paper highlights the necessary development of new instrumentation tools within the PaRSE task-based runtime system to leverage the performance of low-rank matrix computations. In particular, the tile low-rank (TLR) Cholesky factorization represe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5a7bcbdb8a2e546ff6f063bf305a62ee
https://doi.org/10.1109/protools49597.2019.00009

Alleviating the pressure on memory for seismic modeling

Autor: Rached Abdelkhalak, David E. Keyes, Hatem Ltaief, V. Etienne, Kadir Akbudak, Thierry Tonellot

Publikováno v: Scopus-Elsevier

Summary This paper describes two methods to improve the performance of a FDTD solver for the first order formulation of the 3D acoustic wave equation. Based on spatial and temporal cache blocking techniques, these methods enable to maximize bandwidth

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2746382bf9775677bdec23718ffe417b
https://doi.org/10.3997/2214-4609.201903281

Partitioning Models for Scaling Parallel Sparse Matrix-Matrix Multiplication

Autor: Oguz Selvitopi, Cevdet Aykanat, Kadir Akbudak

Publikováno v: Akbudak, Kadir; Selvitopi, Oguz; & Aykanat, Cevdet. (2018). Partitioning Models for Scaling Parallel Sparse Matrix-Matrix Multiplication. ACM Transactions on Parallel Computing, 4(3), 1-34. doi: 10.1145/3155292. Lawrence Berkeley National Laboratory: Retrieved from: http://www.escholarship.org/uc/item/8gv8w406
ACM Transactions on Parallel Computing
ACM Transactions on Parallel Computing, vol 4, iss 3

We investigate outer-product--parallel, inner-product--parallel, and row-by-row-product--parallel formulations of sparse matrix-matrix multiplication (SpGEMM) on distributed memory architectures. For each of these three formulations, we propose a hyp

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ca184265f193e1a5f2a94412c7e67f9
http://www.escholarship.org/uc/item/8gv8w406