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
No fulltext has been uploaded. References only!
Conference Paper | Published | English

No fulltext has been uploaded

Editor
Bonati, Claudio ; Lamanna, Gianluca ; D'Elia, Massimo ; Sozzi, Marco
Abstract
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.
Publishing Year
Conference
GPU Computing in High-Energy Physics (GPUHEP2014)
Location
Pisa, Italy
Conference Date
2014-09-10 – 2014-09-12
PUB-ID

Cite this

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.
This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Sources

arXiv 1411.4439

Inspire 1328508

Search this title in

Google Scholar