Conjugate gradient solvers on Intel Xeon Phi and NVIDIA GPUs

Kaczmarek O, Schmidt C, Steinbrecher P, Wagner M (2015)
In: Proceedings, GPU Computing in High-Energy Physics (GPUHEP2014) : Pisa, Italy, September 10-12, 2014. Bonati C, Lamanna G, D'Elia M, Sozzi M (Eds); 157-162.

Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Konferenzbeitrag | Veröffentlicht | Englisch
Herausgeber
; ; ;
Abstract / Bemerkung
Lattice Quantum Chromodynamics simulations typically spend most of theruntime in inversions of the Fermion Matrix. This part is therefore frequentlyoptimized for various HPC architectures. Here we compare the performance of theIntel Xeon Phi to current Kepler-based NVIDIA Tesla GPUs running a conjugategradient solver. By exposing more parallelism to the accelerator throughinverting multiple vectors at the same time, we obtain a performance greaterthan 300 GFlop/s on both architectures. This more than doubles the performanceof the inversions. We also give a short overview of the Knights Cornerarchitecture, discuss some details of the implementation and the effortrequired to obtain the achieved performance.
Erscheinungsjahr
Titel des Konferenzbandes
Proceedings, GPU Computing in High-Energy Physics (GPUHEP2014) : Pisa, Italy, September 10-12, 2014
Seite
157-162
Konferenz
GPU Computing in High-Energy Physics (GPUHEP2014)
Konferenzort
Pisa, Italy
Konferenzdatum
2014-09-10 – 2014-09-12
PUB-ID

Zitieren

Kaczmarek O, Schmidt C, Steinbrecher P, Wagner M. Conjugate gradient solvers on Intel Xeon Phi and NVIDIA GPUs. In: Bonati C, Lamanna G, D'Elia M, Sozzi M, eds. Proceedings, GPU Computing in High-Energy Physics (GPUHEP2014) : Pisa, Italy, September 10-12, 2014. 2015: 157-162.
Kaczmarek, O., Schmidt, C., Steinbrecher, P., & Wagner, M. (2015). Conjugate gradient solvers on Intel Xeon Phi and NVIDIA GPUs. In C. Bonati, G. Lamanna, M. D'Elia, & M. Sozzi (Eds.), Proceedings, GPU Computing in High-Energy Physics (GPUHEP2014) : Pisa, Italy, September 10-12, 2014 (pp. 157-162).
Kaczmarek, O., Schmidt, C., Steinbrecher, P., and Wagner, M. (2015). “Conjugate gradient solvers on Intel Xeon Phi and NVIDIA GPUs” in Proceedings, GPU Computing in High-Energy Physics (GPUHEP2014) : Pisa, Italy, September 10-12, 2014, Bonati, C., Lamanna, G., D'Elia, M., and Sozzi, M. eds. 157-162.
Kaczmarek, O., et al., 2015. Conjugate gradient solvers on Intel Xeon Phi and NVIDIA GPUs. In C. Bonati, et al., eds. Proceedings, GPU Computing in High-Energy Physics (GPUHEP2014) : Pisa, Italy, September 10-12, 2014. pp. 157-162.
O. Kaczmarek, et al., “Conjugate gradient solvers on Intel Xeon Phi and NVIDIA GPUs”, Proceedings, GPU Computing in High-Energy Physics (GPUHEP2014) : Pisa, Italy, September 10-12, 2014, C. Bonati, et al., eds., 2015, pp.157-162.
Kaczmarek, O., Schmidt, C., Steinbrecher, P., Wagner, M.: Conjugate gradient solvers on Intel Xeon Phi and NVIDIA GPUs. In: Bonati, C., Lamanna, G., D'Elia, M., and Sozzi, M. (eds.) Proceedings, GPU Computing in High-Energy Physics (GPUHEP2014) : Pisa, Italy, September 10-12, 2014. p. 157-162. (2015).
Kaczmarek, Olaf, Schmidt, Christian, Steinbrecher, Patrick, and Wagner, Mathias. “Conjugate gradient solvers on Intel Xeon Phi and NVIDIA GPUs”. Proceedings, GPU Computing in High-Energy Physics (GPUHEP2014) : Pisa, Italy, September 10-12, 2014. Ed. Claudio Bonati, Gianluca Lamanna, Massimo D'Elia, and Marco Sozzi. 2015. 157-162.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Quellen

arXiv: 1411.4439

Inspire: 1328508

Suchen in

Google Scholar