Robert A. van de Geijn

From MaRDI portal
Person:469356

Available identifiers

zbMath Open van-de-geijn.robert-aWikidataQ7351474 ScholiaQ7351474MaRDI QIDQ469356

List of research outcomes

PublicationDate of PublicationType
Supporting Mixed-domain Mixed-precision Matrix Multiplication within the BLIS Framework2022-02-01Paper
Strassen’s Algorithm Reloaded on GPUs2020-11-10Paper
Strassen's Algorithm for Tensor Contraction2018-06-05Paper
Codesign Tradeoffs for High-Performance, Low-Power Linear Algebra Architectures2017-07-12Paper
Algorithm, Architecture, and Floating-Point Unit Codesign of a Matrix Factorization Accelerator2017-06-20Paper
Householder QR Factorization With Randomization for Column Pivoting (HQRRP)2017-05-31Paper
Programming matrix algorithms-by-blocks for thread-level parallelism2017-05-19Paper
High-performance up-and-downdating via householder-like transformations2017-05-19Paper
A Runtime System for Programming Out-of-Core Matrix Algorithms-by-Tiles on Multithreaded Architectures2017-05-19Paper
Parallel Matrix Multiplication: A Systematic Journey2017-01-13Paper
BLIS: A Framework for Rapidly Instantiating BLAS Functionality2016-10-24Paper
Restructuring the Tridiagonal and Bidiagonal QR Algorithms for Performance2015-03-10Paper
Exploiting Symmetry in Tensors for High Performance: Multiplication with Symmetric Tensors2015-01-23Paper
Deriving dense linear algebra libraries2014-11-10Paper
Families of Algorithms for Reducing a Matrix to Condensed Form2014-09-12Paper
Elemental2014-09-12Paper
Sparse direct factorizations through unassembled hyper-matrices2011-11-30Paper
Goal-Oriented and Modular Stability Analysis2011-06-15Paper
Out-of-core solution of linear systems on graphics processors2010-05-21Paper
An Algorithm-by-Blocks for SuperMatrix Band Cholesky Factorization2009-02-03Paper
Accumulating Householder transformations, revisited2008-12-21Paper
Improving the performance of reduction to Hessenberg form2008-12-21Paper
Scalable parallelization of FLAME code via the workqueuing model2008-12-21Paper
Anatomy of high-performance matrix multiplication2008-12-21Paper
A Parallel Eigensolver for Dense Symmetric Matrices Based on Multiple Relatively Robust Representations2005-09-22Paper
The science of deriving dense linear algebra algorithms2005-07-22Paper
Representing linear algebra algorithms in code: the FLAME application program interfaces2005-07-22Paper
Parallel out-of-core computation and updating of the QR factorization2005-07-22Paper
FLAME2005-07-21Paper
Formal derivation of algorithms2005-07-21Paper
Specialized parallel algorithms for solving Lyapunov and Stein equations2002-07-31Paper
https://portal.mardi4nfdi.de/entity/Q27792892002-04-15Paper
A Note On Parallel Matrix Inversion2001-03-19Paper
On global combine operations1999-05-05Paper
https://portal.mardi4nfdi.de/entity/Q42097011998-11-08Paper
Parallelizing the QR Algorithm for the Unsymmetric Algebraic Eigenvalue Problem: Myths and Reality1997-02-24Paper
Parallel performance and scalability for block preconditioned finite element (p) solution of viscous flow1995-07-03Paper
High performance computational kernels for selected segments of a p finite element code1995-07-03Paper
Performance and scalability of finite element analysis for distributed parallel computation1995-01-02Paper
Deferred Shifting Schemes for Parallel QR Methods1993-05-16Paper
Reduction to condensed form for the eigenvalue problem on distributed memory architectures1993-01-17Paper
https://portal.mardi4nfdi.de/entity/Q33617981991-01-01Paper

Research outcomes over time


Doctoral students

No records found.


Known relations from the MaRDI Knowledge Graph

PropertyValue
MaRDI profile typeMaRDI person profile
instance ofhuman


This page was built for person: Robert A. van de Geijn