This title appears in the Scientific Report :
2017
Please use the identifier:
http://hdl.handle.net/2128/14664 in citations.
Please use the identifier: http://dx.doi.org/10.1007/978-3-319-58943-5_60 in citations.
Exploiting In-Memory Processing Capabilities for Density Functional Theory Applications
Exploiting In-Memory Processing Capabilities for Density Functional Theory Applications
Processing-in-memory (PIM) is an approach to address the data transport challenge in future HPC architectures and various designs have been explored in the past. Despite, it remains unclear how scien- tific applications could efficiently exploit massively-parallel HPC archi- tectures integrating PIM...
Saved in:
Personal Name(s): | Baumeister, Paul F. (Corresponding author) |
---|---|
Hater, Thorsten / Pleiter, Dirk / Boettiger, Hans / Maurer, Thilo / Brunheroto, Jose R. | |
Contributing Institute: |
Jülich Supercomputing Center; JSC |
Published in: | 60, |
Published in: |
Euro-Par 2016: Parallel Processing Workshops / Desprez, Frederic (Editor) ; Cham : Springer International Publishing, 2017, Chapter 60 ; ISSN: 0302-9743=1611-3349 ; ISBN: 978-3-319-58942-8=978-3-319-58943-5 ; doi:10.1007/978-3-319-58943-5 |
Imprint: |
Cham
Springer International Publishing
2017
|
Physical Description: |
750 - 762 |
ISBN: |
978-3-319-58943-5 978-3-319-58943-5 (electronic) |
DOI: |
10.1007/978-3-319-58943-5_60 |
Conference: | Euro-Par 2016 International Workshops, Grenoble (France), 2016-08-24 - 2016-08-26 |
Document Type: |
Contribution to a book Contribution to a conference proceedings |
Research Program: |
Supercomputer Facility |
Series Title: |
Lecture Notes in Computer Science
10104 |
Link: |
OpenAccess OpenAccess |
Publikationsportal JuSER |
Please use the identifier: http://dx.doi.org/10.1007/978-3-319-58943-5_60 in citations.
Processing-in-memory (PIM) is an approach to address the data transport challenge in future HPC architectures and various designs have been explored in the past. Despite, it remains unclear how scien- tific applications could efficiently exploit massively-parallel HPC archi- tectures integrating PIM modules. In this paper we address this question for material science applications for which we ported relevant kernels to the Active Memory Cube architecture developed by IBM Research. |