Detail publikace

Paralelní dynamický solidifikační model plynulého odlévání oceli na GPU

KLIMEŠ, L. ŠTĚTINA, J.

Český název

Paralelní dynamický solidifikační model plynulého odlévání oceli na GPU

Anglický název

Parallel dynamic solidification model of continuous steel casting on GPU

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

en

Originální abstrakt

Nowadays, dynamic solidification models of continuously cast steel are commonly used in steelworks over the world to control the casting process and to monitor the steel production. Moreover, these models of transient temperature field can also be utilized for optimization of continuous casting, its on-line regulation, or may help operators to solve non-standard or breakdown situations that can occur when casting. In order to solve these problems in real time, parallel computing of dynamic solidification models can favourably be utilized. One of possible approaches is to use parallel computing on graphics processing units (GPUs) that offer a great computing performance in comparison to ordinary computing on CPUs. The paper describes an implementation of the parallel dynamic solidification model with the use of the CUDA architecture and NVIDIA GPUs. A comparison between the use of parallel and non-parallel models is presented and analysed. Results show that parallel computing on GPUs can considerably enhance the computing performance of solidification models and their use and efficiency in other tasks.

Český abstrakt

Dynamické solidifikační modely jsou dnes běžně používané v ocelárnách a hutních provozech po celém světě k řízení a monitoring plynulého odlévání oceli. Tyto modely jsou rovněž často používány pro optimalizaci výrobního procesu, on-line regulaci nebo umožňují řešit poruchové situace. Z důvodu vysoké výpočetní náročnosti je možné pro vývoj těchto modelů použít paralelizaci na grafických kartách, tzv. GPGPU, která nabízí výrazně vyšší výpočetní výkon ve srovnání s CPU. Příspěvek popisuje implementaci paralelního solidifikačního modelu s využítím architektury CUDA and grafických karet NVIDIA. Srovnání mezi použitím běžných CPU modelů a vyvinutého GPU modelu je prezentováno a výsledky potvrzují, že GPGPU přístup může významně zlepšit výpočetní výkon solidifikačních modelů a jejich dalšího efektivního využití. Nowadays, dynamic solidification models of continuously cast steel are commonly used in steelworks over the world to control the casting process and to monitor the steel production. Moreover, these models of transient temperature field can also be utilized for optimization of continuous casting, its on-line regulation, or may help operators to solve non-standard or breakdown situations that can occur when casting. In order to solve these problems in real time, parallel computing of dynamic solidification models can favourably be utilized. One of possible approaches is to use parallel computing on graphics processing units (GPUs) that offer a great computing performance in comparison to ordinary computing on CPUs. The paper describes an implementation of the parallel dynamic solidification model with the use of the CUDA architecture and NVIDIA GPUs. A comparison between the use of parallel and non-parallel models is presented and analysed. Results show that parallel computing on GPUs can considerably enhance the computing performance of solidification models and their use and efficiency in other tasks.

Anglický abstrakt

Nowadays, dynamic solidification models of continuously cast steel are commonly used in steelworks over the world to control the casting process and to monitor the steel production. Moreover, these models of transient temperature field can also be utilized for optimization of continuous casting, its on-line regulation, or may help operators to solve non-standard or breakdown situations that can occur when casting. In order to solve these problems in real time, parallel computing of dynamic solidification models can favourably be utilized. One of possible approaches is to use parallel computing on graphics processing units (GPUs) that offer a great computing performance in comparison to ordinary computing on CPUs. The paper describes an implementation of the parallel dynamic solidification model with the use of the CUDA architecture and NVIDIA GPUs. A comparison between the use of parallel and non-parallel models is presented and analysed. Results show that parallel computing on GPUs can considerably enhance the computing performance of solidification models and their use and efficiency in other tasks.

Klíčová slova česky

dynamický solidifikační model, plynulé odlévání, GPU, GPGPU, paralelní výpočty

Klíčová slova anglicky

dynamic solidification model, continuous casting, GPU, GPGPU, parallel computing

Rok RIV

2013

Vydáno

15.05.2013

Nakladatel

Tanger, s.r.o.

Místo

Ostrava

ISBN

978-80-87294-39-0

Kniha

Conference proceedings of 22nd Conference on metallurgy and materials

Číslo edice

1

Strany od–do

34–39

Počet stran

6

BIBTEX


@inproceedings{BUT99671,
  author="Lubomír {Klimeš} and Josef {Štětina},
  title="Parallel dynamic solidification model of continuous steel casting on GPU",
  booktitle="Conference proceedings of 22nd Conference on metallurgy and materials",
  year="2013",
  month="May",
  pages="34--39",
  publisher="Tanger, s.r.o.",
  address="Ostrava",
  isbn="978-80-87294-39-0"
}