A survey on software methods to improve the energy efficiency of parallel computing
Energy consumption is one of the top challenges for achieving the next generation of
supercomputing. Codesign of hardware and software is critical for improving energy …
supercomputing. Codesign of hardware and software is critical for improving energy …
Analyzing and mitigating the impact of manufacturing variability in power-constrained supercomputing
A key challenge in next-generation supercomputing is to effectively schedule limited power
resources. Modern processors suffer from increasingly large power variations due to the …
resources. Modern processors suffer from increasingly large power variations due to the …
Hardware and Software Solutions for Energy‐Efficient Computing in Scientific Programming
Energy consumption is one of the major issues in today's computer science, and an
increasing number of scientific communities are interested in evaluating the tradeoff …
increasing number of scientific communities are interested in evaluating the tradeoff …
Global extensible open power manager: A vehicle for HPC community collaboration on co-designed energy management solutions
J Eastep, S Sylvester, C Cantalupo, B Geltz… - … Conference, ISC High …, 2017 - Springer
The power scaling challenge associated with Exascale systems is a well-known issue. In
this work, we introduce the Global Extensible Open Power Manager (GEOPM): a tree …
this work, we introduce the Global Extensible Open Power Manager (GEOPM): a tree …
A reconfiguration algorithm for power-aware parallel applications
In current computing systems, many applications require guarantees on their maximum
power consumption to not exceed the available power budget. On the other hand, for some …
power consumption to not exceed the available power budget. On the other hand, for some …
Performance modeling under resource constraints using deep transfer learning
Tuning application parameters for optimal performance is a challenging combinatorial
problem. Hence, techniques for modeling the functional relationships between various input …
problem. Hence, techniques for modeling the functional relationships between various input …
Energy-efficient application resource scheduling using machine learning classifiers
Resource scheduling in high performance computing (HPC) usually aims to minimize
application runtime rather than optimize for energy efficiency. Most existing research on …
application runtime rather than optimize for energy efficiency. Most existing research on …
A runtime and non-intrusive approach to optimize edp by tuning threads and cpu frequency for openmp applications
J Schwarzrock, CC de Oliveira, M Ritt… - … on Parallel and …, 2020 - ieeexplore.ieee.org
Efficiently exploiting thread-level parallelism has been challenging. Many parallel
applications are not sufficiently balanced or CPU-bound to take advantage of the increasing …
applications are not sufficiently balanced or CPU-bound to take advantage of the increasing …
Infrastructure and api extensions for elastic execution of mpi applications
I Comprés, A Mo-Hellenbrand, M Gerndt… - Proceedings of the 23rd …, 2016 - dl.acm.org
Dynamic Processes support was added to MPI in version 2.0 of the standard. This feature of
MPI has not been widely used by application developers in part due to the performance cost …
MPI has not been widely used by application developers in part due to the performance cost …
Uncore power scavenger: A runtime for uncore power conservation on hpc systems
The US Department of Energy (DOE) has set a power target of 20-30MW on the first
exascale machines. To achieve one exaflop under this power constraint, it is necessary to …
exascale machines. To achieve one exaflop under this power constraint, it is necessary to …