3rd Workshop on Data Locality


Monday 29.08.2019, 09:00 - 12:45


SUB/HG, Papendiek 14, 37073 Göttingen, Vortragsraum, 1. floor right ► Map


A well-known handicap for HPC applications running on modern highly parallelized and heterogeneous HPC platforms is that an increasing amount of time is spent in communication and data transfers; thus, it is necessary to design, implement and validate new approaches to optimize process placement and data locality management. The goal of this workshop is to gather the community around this subject.

Workshop Chair

  • Emmanuel Jeannot, INRIA/LaBRI, Bordeaux, France


9:00 – 9:15
Emmanuel Jeannot,
INRIA/LaBRI, Bordeaux, France
Welcome and introduction of the workshop

9:15 – 10:10
Leonel Sousa
, Universidade de Lisboa (UL), Lisbon, Portugal
Invited talk Application Characterization with Cache-Aware Roofline Model

10:10 – 10:30
Karl Fürlinger
, Ludwig-Maximilians-University (LMU) Munich, Germany
Poster session presentation

10:30 – 11:00 am Coffee Break

11:00 – 11:25
Kernel Merge, Nabeeh Jumah and Julian Kunkel
Optimizing Memory Bandwidth Efficiency with User-Preferred

11:25 – 11:50
Brice Goglin and Andrès Rubio Proaño
Opportunities for Partitioning Non-Volatile Memory DIMMs between Co-scheduled Jobs on HPC Nodes

11:50 – 12:45
Didem Unat
, Koç Universitesi İstanbul, Turkey 
Invited talk: Programming for Data Locality and Parallelism




We use cookies in order to design and continuously improve our website for you. By continuing to use the website, you agree to the use of cookies. You can find further information on this in our privacy policy.