Christian Plessl

University of Paderborn

108Publications

15H-index

864Citations

Publications 108

Newest

#1Marco Platzner (University of Paderborn)H-Index: 25

#2Christian Plessl (University of Paderborn)H-Index: 15

#1Heinrich Riebler (University of Paderborn)H-Index: 4

#2Gavin Vaz (University of Paderborn)H-Index: 4

Last.Christian Plessl (University of Paderborn)H-Index: 15

view all 4 authors...

Multi-accelerator platforms combine CPUs and different accelerator architectures within a single compute node. Such systems are capable of processing parallel workloads very efficiently while being more energy efficient than regular systems consisting of CPUs only. However, the architectures of such systems are diverse, forcing developers to port applications to each accelerator using different programming languages, models, tools, and compilers. Developers not only require domain-specific knowl...

#1Heinrich RieblerH-Index: 4

#2Gavin VazH-Index: 4

Last.Christian PlesslH-Index: 15

view all 4 authors...

A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices

#1Dorothee RichtersH-Index: 2

#2Michael LassH-Index: 2

Last.Thomas D. KühneH-Index: 24

view all 5 authors...

We address the general mathematical problem of computing the inverse p-th root of a given matrix in an efficient way. A new method to construct iteration functions that allow calculating arbitrary p-th roots and their inverses of symmetric positive definite matrices is presented. We show that the order of convergence is at least quadratic and that adaptively adjusting a parameter q always leads to an even faster convergence. In this way, a better performance than with previously known iteration ...

#2Michael LassH-Index: 2

Last.Thomas D. KühneH-Index: 24

view all 4 authors...

In scientific computing, the acceleration of atomistic computer simulations by means of custom hardware is finding ever growing application. A major limitation, however, is that the high efficiency in terms of performance and low power consumption entails the massive usage of low-precision computing units. Here, based on the approximate computing paradigm, we present an algorithmic method to rigorously compensate for numerical inaccuracies due to low-accuracy arithmetic operations, yet still obt...

#1Jan Cedric Mertens (TUM: Technische Universität München)

#2Alexander Boschmann (University of Paderborn)H-Index: 6

Last.Christian Plessl (University of Paderborn)H-Index: 15

view all 4 authors...

The purpose of this research was to develop a wearable, low-cost prototype based on real-time kinematic GPS and a microelectromechanical inertial measurement unit to measure the sprinting velocity of an athlete. The software package RTKLIB was used to calculate the RTK-GPS positions and different Kalman filters were implemented to provide a loosely coupled sensor fusion. With this setup, we performed empirical studies to determine whether the velocities obtained by this novel approach are suffic...

A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices

#1Michael Lass (University of Paderborn)H-Index: 2

#2Stephan Mohr (Barcelona Supercomputing Center)H-Index: 7

Last.Christian Plessl (University of Paderborn)H-Index: 15

view all 5 authors...

We present the submatrix method, a highly parallelizable method for the approximate calculation of inverse p-th roots of large sparse symmetric matrices which are required in different scientific applications. Following the idea of Approximate Computing, we allow imprecision in the final result in order to utilize the sparsity of the input matrix and to allow massively parallel execution. For an n x n matrix, the proposed algorithm allows to distribute the calculations over n nodes with only lit...

#1Michael Lass (University of Paderborn)H-Index: 2

#2Thomas D. Kühne (University of Paderborn)H-Index: 24

Last.Christian Plessl (University of Paderborn)H-Index: 15

view all 3 authors...

Approximate computing has shown to provide new ways to improve performance and power consumption of error-resilient applications. While many of these applications can be found in image processing, data classification, or machine learning, we demonstrate its suitability to a problem from scientific computing. Utilizing the self-correcting behavior of iterative algorithms, we show that approximate computing can be applied to the calculation of inverse matrix {p}th roots which are required in ma...

OpenCL-Based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes

#1Tobias Kenter (University of Paderborn)H-Index: 5

#2Gopinat MahaleH-Index: 1

Last.Christian Plessl (University of Paderborn)H-Index: 15

view all 9 authors...

The exploration of FPGAs as accelerators for scientific simulations has so far mostly been focused on small kernels of methods working on regular data structures, for example in the form of stencil computations for finite difference methods. In computational sciences, often more advanced methods are employed that promise better stability, convergence, locality and scaling. Unstructured meshes are shown to be more effective and more accurate, compared to regular grids, in representing computation...

Feb 10, 2018 in PPoPP (ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming)

#1Heinrich Riebler (University of Paderborn)H-Index: 4

#2Gavin Vaz (University of Paderborn)H-Index: 4

Last.Christian Plessl (University of Paderborn)H-Index: 15

view all 4 authors...

Accelerators can offer exceptional performance advantages. However, programmers need to spend considerable efforts on acceleration, without knowing how sustainable the employed programming models, languages and tools are. To tackle this challenge, we propose and demonstrate a new runtime system called HT r OP that is able to automatically generate and execute OpenCL code from sequential CPU code. HT r OP transforms suitable data-parallel loops into independent OpenCL-typical work-items and handl...

12345678910