skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: An Adaptive Core-specific Runtime for Energy Efficiency.

Abstract

Abstract not provided.

Authors:
; ; ;
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1425317
Report Number(s):
SAND2017-2272C
651336
DOE Contract Number:
AC04-94AL85000
Resource Type:
Conference
Resource Relation:
Conference: Proposed for presentation at the 31st IEEE International Parallel & Distributed Processing Symposium (IPDPS 2017) held May 29-5, 2017 in Orlando, FL.
Country of Publication:
United States
Language:
English

Citation Formats

Bhalachandra, Sridutt, Porterfield, Allan, Olivier, Stephen Lecler, and Prins, Jan F. An Adaptive Core-specific Runtime for Energy Efficiency.. United States: N. p., 2017. Web. doi:10.1109/IPDPS.2017.114.
Bhalachandra, Sridutt, Porterfield, Allan, Olivier, Stephen Lecler, & Prins, Jan F. An Adaptive Core-specific Runtime for Energy Efficiency.. United States. doi:10.1109/IPDPS.2017.114.
Bhalachandra, Sridutt, Porterfield, Allan, Olivier, Stephen Lecler, and Prins, Jan F. Wed . "An Adaptive Core-specific Runtime for Energy Efficiency.". United States. doi:10.1109/IPDPS.2017.114. https://www.osti.gov/servlets/purl/1425317.
@article{osti_1425317,
title = {An Adaptive Core-specific Runtime for Energy Efficiency.},
author = {Bhalachandra, Sridutt and Porterfield, Allan and Olivier, Stephen Lecler and Prins, Jan F.},
abstractNote = {Abstract not provided.},
doi = {10.1109/IPDPS.2017.114},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Wed Mar 01 00:00:00 EST 2017},
month = {Wed Mar 01 00:00:00 EST 2017}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • One class of scientific and engineering applications involves structured meshes. One example of a code in this class is a flame modelling code developed at the Naval Research Laboratory (NRL). The numerical model used in the NRL flame code is predominantly based on structured finite volume methods. The chemistry process of the reactive flow is modeled by a system of ordinary differential equations which is solved independently at each grid point. Thus, though the model uses a mesh structure, the workload at each grid point can vary considerably. It is this feature that requires the use of both structured andmore » unstructured methods in the same code. We have applied the Multiblock PARTI and CHAOS runtime support libraries to parallelize the NRL flame code with minimal changes to the sequential code. We have also developed parallel algorithms to carry out dynamic load balancing. It has been observed that the overall performance scales reasonably up to 256 Paragon processors and that the total runtime on a 256-node Paragon is about half that of a single processor Cray C90.« less
  • In this paper we discuss the runtime support required for the parallelization of unstructured data-parallel applications on nonuniform and adaptive environments. The approach presented is reasonably general and is applicable to a wide variety of regular as well as irregular applications. We present performance results for the solution of an unstructured mesh on a cluster of heterogeneous workstations.
  • U.S. residential and commercial buildings currently use about 39 quadrillion Btu (quads) of energy per year and account for 0.6 gigatonnes (GT) of carbon emitted to the atmosphere (38% of U.S. total emissions of 1.6 GT and approximately 9% of the world fossil-fuel related anthropogenic emissions of 6.7 GT). The U.S. government has long funded buildings-related energy efficiency research and implementation programs to reduce energy consumption in buildings and to reduce air pollution and carbon emissions that result in global warming. These programs also have value in adapting the U.S. residential and commercial building stock to a potentially warmer world.more » Analyses conducted by the Intergovernmental Panel on Climate Change (IPCC) show that the world’s climate could warm relative to1990 by 0.4°C to 1.2°C by the year 2030 and by 1.4°C to 5.8°C by the end of the 21st century. This paper shows that the effect of the regional projected warming on energy consumption in U.S. residential and commercial buildings is a net decrease ranging from about 5% in 2020 to as much as 20% in 2080, but with an increase of as much as 25% in temperature-sensitive electricity demand. Calculations of the potential value of U.S. Department of Energy (DOE) buildings-related energy efficiency programs on future U.S. energy consumption show site energy savings in 2020 of more than 2 quads, which would more than offset the growth in temperature-sensitive energy consumption due to climate and growth in building stock combined, and would be worth between $28 and $33 billion.« less
  • The insatiable demand of high performance computing is being driven by the most computationally intensive applications such as computational chemistry, climate modeling, nuclear physics, etc. The last couple of decades have observed a tremendous rise in supercomputers with architectures ranging from traditional clusters to system-on-a-chip in order to achieve the petaflop computing barrier. However, with advent of petaflop-plus computing, we have ushered in an era where power efficient system software stack is imperative for execution on exascale systems and beyond. At the same time, computationally intensive applications are exploring programming models beyond traditional message passing, as a combination of Partitionedmore » Global Address Space (PGAS) languages and libraries, providing one-sided communication paradigm with put, get and accumulate primitives. To support the PGAS models, it is critical to design power efficient and high performance one-sided communication runtime system. In this paper, we design and implement PASCoL, a high performance power aware one-sided communication library using Aggregate Remote Memory Copy Interface (ARMCI), the communication runtime system of Global Arrays. For various communication primitives provided by ARMCI, we study the impact of Dynamic Voltage/Frequency Scaling (DVFS) and a combination of interrupt (blocking)/polling based mechanisms provided by most modern interconnects. We implement our design and evaluate it with synthetic benchmarks using an InfiniBand cluster. Our results indicate that PASCoL can achieve significant reduction in energy consumed per byte transfer without additional penalty for various one-sided communication primitives and various message sizes and data transfer patterns.« less