HTCaaS: Leveraging Distributed Supercomputing Infrastructures for Large-Scale Scientific Computing
Uloženo v:
| Název: | HTCaaS: Leveraging Distributed Supercomputing Infrastructures for Large-Scale Scientific Computing |
|---|---|
| Autoři: | Jik-soo Kim, Seungwoo Rho, Seoyoung Kim, Sangwan Kim, Seokkyoo Kim, Soonwook Hwang |
| Přispěvatelé: | The Pennsylvania State University CiteSeerX Archives |
| Zdroj: | http://datasys.cs.iit.edu/events/MTAGS13/p02.pdf. |
| Sbírka: | CiteSeerX |
| Témata: | Many-Task Computing, HT- CaaS, Multi-level Scheduling, Dynamic Fairnes |
| Popis: | In this paper, we present the HTCaaS (High-Throughput Computing as a Service) which aims to provide researchers with ease of exploring large-scale and complex scientific prob-lems by leveraging national supercomputing infrastructures in Korea. HTCaaS allows users to efficiently submit a large number of jobs at once by effectively managing and exploit-ing of all available computing resources. HTCaaS exploits a synthesis of well known techniques and its own intelligent scheduling algorithm to effectively support multiple users independently submitting large numbers of tasks to a col-lection of geographically distributed computing resources. Throughout our micro-benchmark and protein docking ex-periments, we show that our HTCaaS can provide a single efficient job management system that can support the most challenging scientific applications. |
| Druh dokumentu: | text |
| Popis souboru: | application/pdf |
| Jazyk: | English |
| Relation: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.646.9632; http://datasys.cs.iit.edu/events/MTAGS13/p02.pdf |
| Dostupnost: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.646.9632 http://datasys.cs.iit.edu/events/MTAGS13/p02.pdf |
| Rights: | Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
| Přístupové číslo: | edsbas.F79B27B8 |
| Databáze: | BASE |
Nájsť tento článok vo Web of Science | Abstrakt: | In this paper, we present the HTCaaS (High-Throughput Computing as a Service) which aims to provide researchers with ease of exploring large-scale and complex scientific prob-lems by leveraging national supercomputing infrastructures in Korea. HTCaaS allows users to efficiently submit a large number of jobs at once by effectively managing and exploit-ing of all available computing resources. HTCaaS exploits a synthesis of well known techniques and its own intelligent scheduling algorithm to effectively support multiple users independently submitting large numbers of tasks to a col-lection of geographically distributed computing resources. Throughout our micro-benchmark and protein docking ex-periments, we show that our HTCaaS can provide a single efficient job management system that can support the most challenging scientific applications. |
|---|