Object-Oriented Implementation of Algebraic Multi-grid Solver for Lattice QCD on SIMD Architectures and GPU Clusters

Kanamori, Issaku; Ishikawa, Ken-ichi; Matsufuru, Hideo

doi:10.1007/978-3-030-86976-2_15

Cited by 9 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use single precision for the multigrid preconditioner. The general structure of our implementation which does not use QWS is found in [6].…”

Section: Implementation Detailsmentioning

confidence: 99%

“…In the figure, the setup time, which is necessary to prepare the null space vectors and called only once for each configuration, is also piled as a light color box to each elapsed time of the multigrid solver. LDDHMC is always the fastest to solve one equation Although the efficiency is lower, a SAP preconditioner without QWS is also available in Bridge++ and can be combined with the multigrid solver [6]. because of the large overhead of the multigrid solver due to the setup process to generate null space vectors.…”

Section: Performancementioning

confidence: 99%

“…It is desirable, however, to minimize the machine-specific codes to reduce the cost of the implementation as well as the maintenance. We successfully prepared a framework for multigrid solver using Bridge++ code set [6], where only machine-specific fermion operators and some basic linear algebra routines are needed. The multigrid solver contains several solvers: an outer solver, a smoother, and a coarse grid solver.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multigrid Solver on Fugaku

Ishikawa¹,

Kanamori²,

Matsufuru³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

We report an implementation of a multigrid solver for the Clover fermion on supercomputer Fugaku, which uses A64FX CPU with Arm architecture. On Fugaku, a highly optimized implementation of BiCGStab solver with domain decomposed preconditioner for the Clover fermion, called QCD Wide SIMD library (QWS), is available. We use the preconditioner in QWS as a smoother of the multigrid solver. Our implementation shows reasonably good scaling and performance. The code is developed by using Bridge++ code framework and its extension.

show abstract

“…We use single precision for the multigrid preconditioner. The general structure of our implementation which does not use QWS is found in [6].…”

Section: Implementation Detailsmentioning

confidence: 99%

Section: Performancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multigrid Solver on Fugaku

Ishikawa¹,

Kanamori²,

Matsufuru³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent supercomputers, however, adopt a variety of architecture: multi-core parallel machines with wide SIMD (A64FX and Intel processors), and clusters with accelerator devices such as GPUs, PEZY-SC, and vector processors (NEC SX-Aurora). Soon after the first public release of Bridge++ in 2012 [2], we had started to investigate possible extensions of our code to exploit these new architectures while keeping the readability and portability, as well as to develop tuning techniques for them [3,4,5,6,7,8]. Recently we have constructed a framework to incorporate the tuned codes as an alternative part to the previously developed Bridge++ code, and decided to release it as version 2.0.…”

Section: Introductionmentioning

confidence: 99%

“…Some details of the implementation have been reported in Ref. [8] together with that of a multi-grid solver.…”

Section: Introductionmentioning

confidence: 99%

General purpose lattice QCD code set Bridge++ 2.0 for high performance computing

Akahoshi

Aoki

Aoyama

et al. 2022

J. Phys.: Conf. Ser.

Self Cite

View full text Add to dashboard Cite

Bridge++ is a general-purpose code set for a numerical simulation of lattice QCD aiming at a readable, extensible, and portable code while keeping practically high performance. The previous version of Bridge++ is implemented in double precision with a fixed data layout. To exploit the high arithmetic capability of new processor architecture, we extend the Bridge++ code so that optimized code is available as a new branch, i.e., an alternative to the original code. This paper explains our strategy of implementation and displays application examples to the following architectures and systems: Intel AVX-512 on Xeon Phi Knights Landing, Arm A64FX-SVE on Fujitsu A64FX (Fugaku), NEC SX-Aurora TSUBASA, and GPU cluster with NVIDIA V100.

show abstract

Parametric Optimization on HPC Clusters with Geneva

Weßner

Berlich

Schwarz

et al. 2023

Comput Softw Big Sci

View full text Add to dashboard Cite

Many challenges of today’s science are parametric optimization problems that are extremely complex and computationally intensive to calculate. At the same time, the hardware for high-performance computing is becoming increasingly powerful. Geneva is a framework for parallel optimization of large-scale problems with highly nonlinear quality surfaces in grid and cloud environments. To harness the immense computing power of high-performance computing clusters, we have developed a new networking component for Geneva—the so-called MPI Consumer—which makes Geneva suitable for HPC. Geneva is most prominent for its evolutionary algorithm, which requires repeatedly evaluating a user-defined cost function. The MPI Consumer parallelizes the computation of the candidate solutions’ cost functions by sending them to remote cluster nodes. By using an advanced multithreading mechanism on the master node and by using asynchronous requests on the worker nodes, the MPI Consumer is highly scalable. Additionally, it provides fault tolerance, which is usually not the case for MPI programs but becomes increasingly important for HPC. Moreover, the MPI Consumer provides a framework for the intuitive implementation of fine-grained parallelization of the cost function. Since the MPI Consumer conforms to the standard paradigm of HPC programs, it vastly improves Geneva’s user-friendliness on HPC clusters. This article gives insight into Geneva’s general system architecture and the system design of the MPI Consumer as well as the underlying concepts. Geneva—including the novel MPI Consumer—is publicly available as an open source project on GitHub (https://github.com/gemfony/geneva) and is currently used for fundamental physics research at GSI in Darmstadt, Germany.

show abstract

Object-Oriented Implementation of Algebraic Multi-grid Solver for Lattice QCD on SIMD Architectures and GPU Clusters

Cited by 9 publications

References 22 publications

Multigrid Solver on Fugaku

Multigrid Solver on Fugaku

General purpose lattice QCD code set Bridge++ 2.0 for high performance computing

Parametric Optimization on HPC Clusters with Geneva

Contact Info

Product

Resources

About