Realisation of the double sweep method by using a Sleptsov net

Kostikov, Alexander; Zaitsev, Nikolay D.; Subotin, Oleg V.

doi:10.1080/17445760.2021.1945054

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Though a place of SN stores a nonnegative integer number, we can represent integer, rational, and floating numbers by a cortege of places, subnets for corresponding operations have been presented in [28]. As for the arrays and matrices, multidimensional as well, the most efficient implementation uses explicitly generated matrix computing structures, similar to shown in an example for solving Laplace equation in a single step for each iteration.…”

Section: An Overview Of Sleptsov Net Computing Paradigmmentioning

confidence: 99%

Virtual Machine and Integrated Developer Environment for Sleptsov Net Computing

Zaitsev

Shmeleva

Zhang

et al. 2023

Parallel Process. Lett.

View full text Add to dashboard Cite

Modern computing is a path of violations and transformations coming from an intrinsically concurrent application domain into a sequence of instructions and then back to concurrency with OpenMP, MPI and CUDA/OpenCL. Why we create so many difficulties? Sleptsov Net Computing (SNC) maps a task into an appropriate computing structure implemented as a re-configurable multidimensional sparse matrix of computing memory. It has entirely graphical mass parallel language for concurrent programming and a framework of techniques for concurrent program verification to develop reliable software. Estimated efficiency of SNC is higher than 50% compared to actual less that 1% efficiency of the most powerful supercomputers. It yields hyper-performance capable of efficient control of hyper-sonic objects, colliders, thermonuclear reaction. This paper presents an open source prototype VM and IDE for SNC with a view on upcoming hardware implementation of the corresponding computer.

show abstract

Section: An Overview Of Sleptsov Net Computing Paradigmmentioning

confidence: 99%