Numerical hydrodynamics simulation of astrophysical flows at Intel Xeon Phi supercomputers

I. M. Kulikov; I. G. Chernykh; E. I. Vorobyov; A. V. Snytnikov; D. V. Weins; A. A. Moskovsky; A. B. Shmelev; V. A. Protasov; A. A. Serenko; V. E. Nenashev; V. A. Vshivkov; A. S. Rodionov; B. M. Glinsky; A. V. Tutukov

Numerical hydrodynamics simulation of astrophysical flows at Intel Xeon Phi supercomputers

I. M. Kulikov, I. G. Chernykh, E. I. Vorobyov, A. V. Snytnikov, D. V. Weins, A. A. Moskovsky, A. B. Shmelev, V. A. Protasov, A. A. Serenko, V. E. Nenashev, V. A. Vshivkov, A. S. Rodionov, B. M. Glinsky, A. V. Tutukov

Результат исследования: Научные публикации в периодических изданиях › статья по материалам конференции › рецензирование

Аннотация

In this paper we present the AstroPhi code for numerical simulation of astrophysical flows at Intel Xeon Phi supercomputers. The co-design of a computational astrophysics model is described. The parallel implementation and scalability tests of the AstroPhi code are presented. The results of simulation of interaction between intergalactic wind and a disk galaxy are provided. For AstroPhi code a 134x speed-up with one Intel Xeon Phi accelerator and 75% weak scaling efficiency on 224x Intel Xeon Phi accelerators was obtained. We obtained the peak performance on a 7168 × 1024 × 1024 mesh size using 53760 RSC PetaStream threads.

Язык оригинала	английский
Страницы (с-по)	205-220
Число страниц	16
Журнал	CEUR Workshop Proceedings
Том	1576
Состояние	Опубликовано - 2016
Событие	10th Annual International Scientific Conference on Parallel Computing Technologies, PCT 2016 - Arkhangelsk, Российская Федерация Продолжительность: 29 мар 2016 → 31 мар 2016

Другие файлы и ссылки

Link to publication in Scopus

Fingerprint

Подробные сведения о темах исследования «Numerical hydrodynamics simulation of astrophysical flows at Intel Xeon Phi supercomputers». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать

Kulikov, I. M., Chernykh, I. G., Vorobyov, E. I., Snytnikov, A. V., Weins, D. V., Moskovsky, A. A., Shmelev, A. B., Protasov, V. A., Serenko, A. A., Nenashev, V. E., Vshivkov, V. A., Rodionov, A. S., Glinsky, B. M., & Tutukov, A. V. (2016). Numerical hydrodynamics simulation of astrophysical flows at Intel Xeon Phi supercomputers. CEUR Workshop Proceedings, 1576, 205-220.

Kulikov, I. M. ; Chernykh, I. G. ; Vorobyov, E. I. ; Snytnikov, A. V. ; Weins, D. V. ; Moskovsky, A. A. ; Shmelev, A. B. ; Protasov, V. A. ; Serenko, A. A. ; Nenashev, V. E. ; Vshivkov, V. A. ; Rodionov, A. S. ; Glinsky, B. M. ; Tutukov, A. V. / Numerical hydrodynamics simulation of astrophysical flows at Intel Xeon Phi supercomputers. В: CEUR Workshop Proceedings. 2016 ; Том 1576. стр. 205-220.

@article{f19cc2e124a34952bec74675b228871b,

title = "Numerical hydrodynamics simulation of astrophysical flows at Intel Xeon Phi supercomputers",

abstract = "In this paper we present the AstroPhi code for numerical simulation of astrophysical flows at Intel Xeon Phi supercomputers. The co-design of a computational astrophysics model is described. The parallel implementation and scalability tests of the AstroPhi code are presented. The results of simulation of interaction between intergalactic wind and a disk galaxy are provided. For AstroPhi code a 134x speed-up with one Intel Xeon Phi accelerator and 75% weak scaling efficiency on 224x Intel Xeon Phi accelerators was obtained. We obtained the peak performance on a 7168 × 1024 × 1024 mesh size using 53760 RSC PetaStream threads.",

keywords = "High performance computing, Intel Xeon Phi accelerators, Numerical astrophysics",

author = "Kulikov, {I. M.} and Chernykh, {I. G.} and Vorobyov, {E. I.} and Snytnikov, {A. V.} and Weins, {D. V.} and Moskovsky, {A. A.} and Shmelev, {A. B.} and Protasov, {V. A.} and Serenko, {A. A.} and Nenashev, {V. E.} and Vshivkov, {V. A.} and Rodionov, {A. S.} and Glinsky, {B. M.} and Tutukov, {A. V.}",

year = "2016",

language = "English",

volume = "1576",

pages = "205--220",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

note = "10th Annual International Scientific Conference on Parallel Computing Technologies, PCT 2016 ; Conference date: 29-03-2016 Through 31-03-2016",

}

Numerical hydrodynamics simulation of astrophysical flows at Intel Xeon Phi supercomputers. / Kulikov, I. M.; Chernykh, I. G.; Vorobyov, E. I.; Snytnikov, A. V.; Weins, D. V.; Moskovsky, A. A.; Shmelev, A. B.; Protasov, V. A.; Serenko, A. A.; Nenashev, V. E.; Vshivkov, V. A.; Rodionov, A. S.; Glinsky, B. M.; Tutukov, A. V.

В: CEUR Workshop Proceedings, Том 1576, 2016, стр. 205-220.

Результат исследования: Научные публикации в периодических изданиях › статья по материалам конференции › рецензирование

TY - JOUR

T1 - Numerical hydrodynamics simulation of astrophysical flows at Intel Xeon Phi supercomputers

AU - Kulikov, I. M.

AU - Chernykh, I. G.

AU - Vorobyov, E. I.

AU - Snytnikov, A. V.

AU - Weins, D. V.

AU - Moskovsky, A. A.

AU - Shmelev, A. B.

AU - Protasov, V. A.

AU - Serenko, A. A.

AU - Nenashev, V. E.

AU - Vshivkov, V. A.

AU - Rodionov, A. S.

AU - Glinsky, B. M.

AU - Tutukov, A. V.

PY - 2016

Y1 - 2016

N2 - In this paper we present the AstroPhi code for numerical simulation of astrophysical flows at Intel Xeon Phi supercomputers. The co-design of a computational astrophysics model is described. The parallel implementation and scalability tests of the AstroPhi code are presented. The results of simulation of interaction between intergalactic wind and a disk galaxy are provided. For AstroPhi code a 134x speed-up with one Intel Xeon Phi accelerator and 75% weak scaling efficiency on 224x Intel Xeon Phi accelerators was obtained. We obtained the peak performance on a 7168 × 1024 × 1024 mesh size using 53760 RSC PetaStream threads.

AB - In this paper we present the AstroPhi code for numerical simulation of astrophysical flows at Intel Xeon Phi supercomputers. The co-design of a computational astrophysics model is described. The parallel implementation and scalability tests of the AstroPhi code are presented. The results of simulation of interaction between intergalactic wind and a disk galaxy are provided. For AstroPhi code a 134x speed-up with one Intel Xeon Phi accelerator and 75% weak scaling efficiency on 224x Intel Xeon Phi accelerators was obtained. We obtained the peak performance on a 7168 × 1024 × 1024 mesh size using 53760 RSC PetaStream threads.

KW - High performance computing

KW - Intel Xeon Phi accelerators

KW - Numerical astrophysics

UR - http://www.scopus.com/inward/record.url?scp=84978468529&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84978468529

VL - 1576

SP - 205

EP - 220

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

T2 - 10th Annual International Scientific Conference on Parallel Computing Technologies, PCT 2016

Y2 - 29 March 2016 through 31 March 2016

ER -