Energy-Efficient Computing for Extreme-Scale Science

Donofrio, David; Oliker, Leonid; Shalf, John; Wehner, Michael; Rowen, Chris; Krueger, Jens; Kamil, Shoaib; Mohiyuddin, Marghoob

doi:10.1109/mc.2009.353

Cited by 48 publications

(27 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With a fabrication-less design flow, it is possible not only to tailor the core architecture (out-of-order, cache sizes, vector widths, frequencies, etc.) but also the entire node (including memory) and system (including network) designs to match the computational needs of a scientific problem [11,23,36,40]. Although one may discount this approach, several systems have successfully adopted it, including D.E.…”

Section: Future Directionsmentioning

confidence: 99%

Advances in Cross-Cutting Ideas for Computational Climate Science

Ng¹,

Evans²,

Caldwell³

et al. 2017

View full text Add to dashboard Cite

Rockville, MDCover Clockwise, beginning with the top of the cube:Description: Mesh representation of the coastlines of Greenland within the CISM-Albany model using a new algebraic multigrid solver, an ice sheet component option within ACME.Courtesy of Ray Tuminaro, Mauro Perego, Irina Tezaur, Andrew Salinger, Sandia National Laboratories, and Stephen Price, Los Alamos National Laboratory.Description: Monthly averaged Sea Surface Temperature from years 71-100 of a test simulation of the beta v1 ACME model with active ocean, sea ice, atmosphere, and land surface components.Courtesy of Milena Veneziani, Los Alamos National Laboratory, and the DOE ACME ocean model development team.Description: Snapshot of instantaneous integrated water vapor from a development version of the ACME model atmosphere component.Courtesy of Kate Evans, Oak Ridge National Laboratory, and the DOE ACME atmosphere model development team.

show abstract

Section: Future Directionsmentioning

confidence: 99%

Advances in Cross-Cutting Ideas for Computational Climate Science

Ng¹,

Evans²,

Caldwell³

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Recent work in architectural specialization include the Anton molecular dynamics platform that achieved two orders magnitude improvement over existing supercomputing systems at a fraction of the power requirements [38]. Finally, our group has conducted a detailed exploration of Green Flash, a manycore processor design for high-performance systems based on embedded computing low-power architectures, specifically targeted for ultra-high resolution climate simulations [45,11]. Green Wave and Green Flash are different parameterizations of the same 128-core, local store augmented architecture.…”

Section: Related Workmentioning

confidence: 99%

“…This approach minimizes the amount of design custom logic, which in turn reduces verification costs and design uncertainty. Extensive exploration of our Green Flash climate-simulation design have shown this to be an effective approach [45,11].…”

Section: Green Wave Architecturementioning

confidence: 99%

See 1 more Smart Citation

Hardware/software co-design for energy-efficient seismic modeling

Krueger

Donofrio

Shalf

et al. 2011

Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis

Self Cite

View full text Add to dashboard Cite

Reverse Time Migration (RTM) has become the standard for high-quality imaging in the seismic industry. RTM relies on PDE solutions using stencils that are 8 t h order or larger, which require large-scale HPC clusters to meet the computational demands. However, the rising power consumption of conventional cluster technology has prompted investigation of architectural alternatives that offer higher computational efficiency. In this work, we compare the performance and energy efficiency of three architectural alternatives -the Intel Nehalem X5530 multicore processor, the NVIDIA Tesla C2050 GPU, and a general-purpose manycore chip design optimized for high-order wave equations called "Green Wave." We have developed an FPGA-accelerated architectural simulation platform to accurately model the power and performance of the Green Wave design. Results show that across highly-tuned high-order RTM stencils, the Green Wave implementation can offer up to 8× and 3.5× energy efficiency improvement per node respectively, compared with the Nehalem and GPU platforms. These results point to the enormous potential energy advantages of our hardware/software co-design methodology.

show abstract

“…The future extreme scale computing systems [13,35] are facing several challenges in architecture, energy constraints, memory scaling, limited I/O, and scalability of software stacks. As the scientific simulations running on such systems continue to scale, the possibility of hardware/software component failures will become too significant to ignore.…”

Section: Introductionmentioning

confidence: 99%

Data Compression for the Exascale Computing Era - Survey

Son

Chen

Hendrix

et al. 2014

JSFI

View full text Add to dashboard Cite

While periodic checkpointing has been an important mechanism for tolerating faults in highperformance computing (HPC) systems, it is cost-prohibitive as the HPC system approaches exascale. Applying compression techniques is one common way to mitigate such burdens by reducing the data size, but they are often found to be less effective for scientific datasets. Traditional lossless compression techniques that look for repeated patterns are ineffective for scientific data in which high-precision data is used and hence common patterns are rare to find. In this paper, we present a comparison of several lossless and lossy data compression algorithms and discuss their methodology under the exascale environment. As data volume increases, we discover an increasing trend of new domain-driven algorithms that exploit the inherent characteristics exhibited in many scientific dataset, such as relatively small changes in data values from one simulation iteration to the next or among neighboring data. In particular, significant data reduction has been observed in lossy compression. This paper also discusses how the errors introduced by lossy compressions are controlled and the tradeoffs with the compression ratio.

show abstract

Energy-Efficient Computing for Extreme-Scale Science

Cited by 48 publications

References 5 publications

Advances in Cross-Cutting Ideas for Computational Climate Science

Advances in Cross-Cutting Ideas for Computational Climate Science

Hardware/software co-design for energy-efficient seismic modeling

Data Compression for the Exascale Computing Era - Survey

Contact Info

Product

Resources

About