Energy Footprint of Advanced Dense Numerical Linear Algebra Using Tile Algorithms on Multicore Architectures

We propose to study the impact on the energy footprint of two advanced algorithmic strategies in the context of high performance dense linear algebra libraries: (1) mixed precision algorithms with iterative refinement allow to run at the peak performance of single precision floating-point arithmetic...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2012 International Conference on Cloud and Green Computing S. 274 - 281
Hauptverfasser: Dongarra, J., Ltaief, Hatem, Luszczek, P., Weaver, V. M.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.11.2012
Schlagworte:
Dense Linear Algebra
Dynamic Scheduling
Heuristic algorithms
Libraries
Linear algebra
Mixed Precision Algorithms
Parallel processing
Plasmas
Power Consumption
Power measurement
PowerPack
RAPL
Tile Algorithms
Tiles
Tree Reduction
ISBN:1467330272, 9781467330275
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We propose to study the impact on the energy footprint of two advanced algorithmic strategies in the context of high performance dense linear algebra libraries: (1) mixed precision algorithms with iterative refinement allow to run at the peak performance of single precision floating-point arithmetic while achieving double precision accuracy and (2) tree reduction technique exposes more parallelism when factorizing tall and skinny matrices for solving over determined systems of linear equations or calculating the singular value decomposition. Integrated within the PLASMA library using tile algorithms, which will eventually supersede the block algorithms from LAPACK, both strategies further excel in performance in the presence of a dynamic task scheduler while targeting multicore architecture. Energy consumption measurements are reported along with parallel performance numbers on a dual-socket quad-core Intel Xeon as well as a quad-socket quad-core Intel Sandy Bridge chip, both providing component-based energy monitoring at all levels of the system, through the Power Pack framework and the Running Average Power Limit model, respectively.
ISBN:1467330272
9781467330275
DOI:10.1109/CGC.2012.113