MRHS multigrid solver for Wilson-clover fermions

11/24/2022
by   Daniel Richtmann, et al.
0

We describe our implementation of a multigrid solver for Wilson-clover fermions, which increases parallelism by solving for multiple right-hand sides (MRHS) simultaneously. The solver is based on Grid and thus runs on all computing architectures supported by the Grid framework. We present detailed benchmarks of the relevant kernels, such as hopping and clover term on the various multigrid levels, intergrid operators, and reductions. The benchmarks were performed on the JUWELS Booster system at Jülich Supercomputing Centre, which is based on Nvidia A100 GPUs. For example, solving a 24^3×128 lattice on 16 GPUs, the overall speedup obtained solely from MRHS is about 10x.

READ FULL TEXT
research
09/04/2019

GPU-based parallelism for ASP-solving

Answer Set Programming (ASP) has become, the paradigm of choice in the f...
research
10/24/2017

Implicit Low-Order Unstructured Finite-Element Multiple Simulation Enhanced by Dense Computation using OpenACC

In this paper, we develop a low-order three-dimensional finite-element s...
research
10/15/2019

Solving Logic Grid Puzzles with an Algorithm that Imitates Human Behavior

We present in this paper our solver for logic grid puzzles. The approach...
research
07/07/2022

Diverse Adaptive Bulk Search: a Framework for Solving QUBO Problems on Multiple GPUs

Quadratic Unconstrained Binary Optimization (QUBO) is a combinatorial op...
research
03/11/2020

Evaluating Abstract Asynchronous Schwarz solvers on GPUs

With the commencement of the exascale computing era, we realize that the...
research
03/11/2020

Evaluating Abstract Asynchronous Schwarz solvers

With the commencement of the exascale computing era, we realize that the...
research
10/25/2017

Performance Portability Strategies for Grid C++ Expression Templates

One of the key requirements for the Lattice QCD Application Development ...

Please sign up or login with your details

Forgot password? Click here to reset