José María González-Linares

José María González-Linares

Auto-generated profile, based on publicly available information

José María González-Linares

University of Malaga

Research Focus & Metrics

Academic Career Length

28Years (1999-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2012 in Journal of Parallel and Distributed Computing
Verified
Journal Article
Closed access
JLJuan Gómez Luna
Juan Gómez Luna
JGJosé María González-Linares
José María González-Linares
JBJosé Ignacio Benavides
José Ignacio Benavides
NGNicolás Guil
Nicolás Guil

11 December 2012 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
JLJuan Gómez Luna
Juan Gómez Luna
JGJose Maria Gonzalez-Linares
Jose Maria Gonzalez-Linares
JBJose Ignacio Benavides Benitez
Jose Ignacio Benavides Benitez
NGNicolás Guil
Nicolás Guil
GPU application implementations using scatter approaches will fall into write contention due to atomic updates of output elements, if these result from more than one input element. Colliding threads will be serialized, seriously harming performance. Dealing with these issues requires a proper understanding of the behavior of the scratchpad or shared memory under conflicting accesses caused by concurrent threads. Thus, this paper presents an exhaustive microbenchmark-based analysis of atomic additions in shared memory that quantifies the impact of access conflicts on latency and throughput. This analysis has led us to discover the lock mechanism that enables atomic updates to shared memory and to propose a performance model to estimate the latency penalties due to collisions by position or bank conflicts. Then, we have derived experiments from this model that show us the way to optimize applications using atomic operations. Position and bank conflicts can be diminished by replication and padding, respectively. The benefits of such techniques are illustrated with the optimization of two widely used voting processes: the centroid updating step in k-means clustering, and histogram calculation.

20 July 2012 in Machine Vision and Applications
Verified
Journal Article
Closed access
PDF file
JLJuan Gómez Luna
Juan Gómez Luna
GLGonzález- Linares
González- Linares
JMJosé María
José María
JBJosé Ignacio Benavides
José Ignacio Benavides
NGNicolás Guil
Nicolás Guil

1 June 1999 in Pattern Recognition
Verified
Journal Article
Closed access
NGNicolás Guil
Nicolás Guil
JGJ.M. Gonzalez-Linares
J.M. Gonzalez-Linares
EZE.L. Zapata
E.L. Zapata

6 February 2014
Verified
Conference Paper
Open access
PDF file
ISI-Jui Sung
I-Jui Sung
JLJuan Gómez Luna
Juan Gómez Luna
JGJosé María González-Linares
José María González-Linares
NGNicolás Guil
Nicolás Guil
WHWen-Mei W. Hwu
Wen-Mei W. Hwu

3 July 2007
Verified
Book Chapter
Closed access
PDF file
NGNicolás Guil
Nicolás Guil
JGJ. M. González-Linares
J. M. González-Linares
JCJulián Ramos Cózar
Julián Ramos Cózar
EZE. L. Zapata
E. L. Zapata