Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 815878

Harnessing CUDA Dynamic Parallelism for the Solution of Sparse Linear Systems


Aliaga, José; Davidović, Davor; Pérez, Joaquín; Quintana-Ortí, Enrique S.
Harnessing CUDA Dynamic Parallelism for the Solution of Sparse Linear Systems // Advances in Parallel Computing Volume 27: Parallel Computing: On the Road to Exascale / Joubert, G.R., Leather, H., Parsons, M., Peters, F., Sawyer, M. (ur.).
Edinburgh, Ujedinjeno Kraljevstvo: IOS Press, 2016. str. 217-226 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


CROSBI ID: 815878 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Harnessing CUDA Dynamic Parallelism for the Solution of Sparse Linear Systems

Autori
Aliaga, José ; Davidović, Davor ; Pérez, Joaquín ; Quintana-Ortí, Enrique S.

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Advances in Parallel Computing Volume 27: Parallel Computing: On the Road to Exascale / Joubert, G.R., Leather, H., Parsons, M., Peters, F., Sawyer, M. - : IOS Press, 2016, 217-226

ISBN
978-1-61499-620-0

Skup
International Conference on Parallel Computing (PARCO) 2015

Mjesto i datum
Edinburgh, Ujedinjeno Kraljevstvo, 1-4.09.2015

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Graphics processing units (GPUs); CUDA dynamic parallelism; sparse linear systems; iterative solvers; high performance; energy efficiency

Sažetak
We leverage CUDA dynamic parallelism to reduce execution time while significantly reducing energy consumption of the Conjugate Gradient (CG) method for the iterative solution of sparse linear systems on graphics processing units (GPUs). Our new implementation of this solver is launched from the CPU in the form of a single “parent” CUDA kernel, which invokes other “child” CUDA kernels. The CPU can then continue with other work while the execution of the solver proceeds asynchronously on the GPU, or block until the execution is completed. Our experiments on a server equipped with an Intel Core i7-3770K CPU and an NVIDIA “Kepler” K20c GPU illustrate the benefits of the new CG solver.

Izvorni jezik
Engleski

Znanstvena područja
Matematika, Računarstvo



POVEZANOST RADA


Ustanove:
Institut "Ruđer Bošković", Zagreb

Profili:

Avatar Url Davor Davidović (autor)

Citiraj ovu publikaciju

Aliaga, José; Davidović, Davor; Pérez, Joaquín; Quintana-Ortí, Enrique S.
Harnessing CUDA Dynamic Parallelism for the Solution of Sparse Linear Systems // Advances in Parallel Computing Volume 27: Parallel Computing: On the Road to Exascale / Joubert, G.R., Leather, H., Parsons, M., Peters, F., Sawyer, M. (ur.).
Edinburgh, Ujedinjeno Kraljevstvo: IOS Press, 2016. str. 217-226 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Aliaga, J., Davidović, D., Pérez, J. & Quintana-Ortí, E. (2016) Harnessing CUDA Dynamic Parallelism for the Solution of Sparse Linear Systems. U: Joubert, G.R., Leather, H., Parsons, M., Peters, F., Sawyer, M. (ur.)Advances in Parallel Computing Volume 27: Parallel Computing: On the Road to Exascale.
@article{article, year = {2016}, pages = {217-226}, keywords = {Graphics processing units (GPUs), CUDA dynamic parallelism, sparse linear systems, iterative solvers, high performance, energy efficiency}, isbn = {978-1-61499-620-0}, title = {Harnessing CUDA Dynamic Parallelism for the Solution of Sparse Linear Systems}, keyword = {Graphics processing units (GPUs), CUDA dynamic parallelism, sparse linear systems, iterative solvers, high performance, energy efficiency}, publisher = {IOS Press}, publisherplace = {Edinburgh, Ujedinjeno Kraljevstvo} }
@article{article, year = {2016}, pages = {217-226}, keywords = {Graphics processing units (GPUs), CUDA dynamic parallelism, sparse linear systems, iterative solvers, high performance, energy efficiency}, isbn = {978-1-61499-620-0}, title = {Harnessing CUDA Dynamic Parallelism for the Solution of Sparse Linear Systems}, keyword = {Graphics processing units (GPUs), CUDA dynamic parallelism, sparse linear systems, iterative solvers, high performance, energy efficiency}, publisher = {IOS Press}, publisherplace = {Edinburgh, Ujedinjeno Kraljevstvo} }




Contrast
Increase Font
Decrease Font
Dyslexic Font