hrvatski jezikClear Cookie - decide language by browser settings

Harnessing CUDA dynamic parallelism for the solution of sparse linear systems

Aliaga, José; Davidović, Davor; Pérez, Joaquín; Quintana-Ortí, Enrique S. (2016) Harnessing CUDA dynamic parallelism for the solution of sparse linear systems. In: Joubert, Gerhard; Leather, Hugh; Peters, Frans; Parsons, Mark; Sawyer, Mark, (eds.) Parallel computing : on the road to exascale. pp. 217-226 .

PDF - Accepted Version - article
Download (391kB) | Preview


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.

Item Type: Conference or workshop item published in conference proceedings (UNSPECIFIED)
Uncontrolled Keywords: Graphics processing units (GPUs); CUDA dynamic parallelism; sparse linear systems; iterative solvers; high performance; energy efficiency
Subjects: NATURAL SCIENCES > Mathematics > Algebra
TECHNICAL SCIENCES > Computing > Process Computing
Divisions: Center for Informatics and Computing
Project titleProject leaderProject codeProject type
Network for sustainable ultrascale computing - NESUSUNSPECIFIEDUNSPECIFIEDCOST
Depositing User: Davor Davidović
Date Deposited: 06 Jun 2016 10:39

Actions (login required)

View Item View Item


Downloads per month over past year

Increase Font
Decrease Font
Dyslexic Font