Data Movement Dominates: Advanced Memory Technology to Address the Real Exascale Power Problem

Bergman, Keren

doi:10.2172/1151423

Title: Data Movement Dominates: Advanced Memory Technology to Address the Real Exascale Power Problem

Full Record
Other Related Research

Abstract

Energy is the fundamental barrier to Exascale supercomputing and is dominated by the cost of moving data from one point to another, not computation. Similarly, performance is dominated by data movement, not computation. The solution to this problem requires three critical technologies: 3D integration, optical chip-to-chip communication, and a new communication model. The central goal of the Sandia led "Data Movement Dominates" project aimed to develop memory systems and new architectures based on these technologies that have the potential to lower the cost of local memory accesses by orders of magnitude and provide substantially more bandwidth. Only through these transformational advances can future systems reach the goals of Exascale computing with a manageable power budgets. The Sandia led team included co-PIs from Columbia University, Lawrence Berkeley Lab, and the University of Maryland. The Columbia effort of Data Movement Dominates focused on developing a physically accurate simulation environment and experimental verification for optically-connected memory (OCM) systems that can enable continued performance scaling through high-bandwidth capacity, energy-efficient bit-rate transparency, and time-of-flight latency. With OCM, memory device parallelism and total capacity can scale to match future high-performance computing requirements without sacrificing data-movement efficiency. When we consider systems with integrated photonics, links to memorymore »« less

Authors:: Bergman, Keren

Publication Date:: Thu Aug 28 00:00:00 EDT 2014

Research Org.:: Columbia Univ., New York, NY (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

Contributing Org.:: Sandia National Laboratories

OSTI Identifier:: 1151423

Report Number(s):: DOE-COLUMBIA-0005114
FC02-10ER25990

DOE Contract Number:: SC0005114

Resource Type:: Technical Report

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING; Interconnection Networks, Memory, Energy Efficient Computing, Optical Interconnects

Citation Formats


                    Bergman, Keren. Data Movement Dominates: Advanced Memory Technology to Address the Real Exascale Power Problem.  United States: N. p., 2014. 
        Web.  doi:10.2172/1151423.

Copy to clipboard


                    Bergman, Keren. Data Movement Dominates: Advanced Memory Technology to Address the Real Exascale Power Problem.  United States.  https://doi.org/10.2172/1151423

Copy to clipboard


                    Bergman, Keren. 2014.  
        "Data Movement Dominates: Advanced Memory Technology to Address the Real Exascale Power Problem".  United States.  https://doi.org/10.2172/1151423.  https://www.osti.gov/servlets/purl/1151423.

Copy to clipboard


                    
@article{osti_1151423,

  title        = {Data Movement Dominates: Advanced Memory Technology to Address the Real Exascale Power Problem},

  author       = {Bergman, Keren},

  abstractNote = {Energy is the fundamental barrier to Exascale supercomputing and is dominated by the cost of moving data from one point to another, not computation. Similarly, performance is dominated by data movement, not computation. The solution to this problem requires three critical technologies: 3D integration, optical chip-to-chip communication, and a new communication model. The central goal of the Sandia led "Data Movement Dominates" project aimed to develop memory systems and new architectures based on these technologies that have the potential to lower the cost of local memory accesses by orders of magnitude and provide substantially more bandwidth. Only through these transformational advances can future systems reach the goals of Exascale computing with a manageable power budgets. The Sandia led team included co-PIs from Columbia University, Lawrence Berkeley Lab, and the University of Maryland. The Columbia effort of Data Movement Dominates focused on developing a physically accurate simulation environment and experimental verification for optically-connected memory (OCM) systems that can enable continued performance scaling through high-bandwidth capacity, energy-efficient bit-rate transparency, and time-of-flight latency. With OCM, memory device parallelism and total capacity can scale to match future high-performance computing requirements without sacrificing data-movement efficiency. When we consider systems with integrated photonics, links to memory can be seamlessly integrated with the interconnection network-in a sense, memory becomes a primary aspect of the interconnection network. At the core of the Columbia effort, toward expanding our understanding of OCM enabled computing we have created an integrated modeling and simulation environment that uniquely integrates the physical behavior of the optical layer. The PhoenxSim suite of design and software tools developed under this effort has enabled the co-design of and performance evaluation photonics-enabled OCM architectures on Exascale computing systems.},

  doi          = {10.2172/1151423},

  url          = {https://www.osti.gov/biblio/1151423},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {Thu Aug 28 00:00:00 EDT 2014},

  month        = {Thu Aug 28 00:00:00 EDT 2014}

}

Copy to clipboard

Technical Report:

View Technical Report (0.37 MB)

https://doi.org/10.2172/1151423

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Photonic Memory Controller Module (P-MCM)

Technical Report Watts, Michael; Vermeulen, Diedrik; Moss, Ben; ...

The Department of Energy has a persistent and strong need for high performance super computers to be used in applications spanning from climate change to nuclear process simulations. However, as the computational speed required by the cloud computing and high-performance computing continues to scale up, the required memory bandwidth is not keeping pace. This is one of the many issues referred to as the “Memory Wall.” Conventional electronic interconnects are simply not able to tackle this problem due to the inherent power consumption challenges of communicating high data rate links over distances beyond the chip scale. The lacking bandwidth-density, limitedmore »« less
Data Locality Enhancement of Dynamic Simulations for Exascale Computing (Final Report)

Technical Report Shen, Xipeng

The development of modern processors exhibits two trends that complicate the optimizations of modern software. The first is the increasing sensitivity of processors' throughput to irregularities in computation. With more processors produced through a massive integration of simple cores, future systems will increasingly favor regular data-level parallel computations, but deviate from the needs of applications with complex patterns. Some evidences are already shown on Graphic Processing Units (GPU): Irregular data accesses (e.g., indirect references A[D[i]]) and conditional branches are limiting many GPU applications' performance at a level an order of magnitude lower than the peak of GPU. The second hardwaremore »« less
https://doi.org/10.2172/1576175

Full Text Available
Optically connected memory for disaggregated data centers

Journal Article Gonzalez, Jorge; Palma, Mauricio; Hattink, Maarten; ... - Journal of Parallel and Distributed Computing

Recent advances in integrated photonics enable the implementation of reconfigurable, high-bandwidth, and low energy-per-bit interconnects in next-generation data centers. We propose and evaluate an Optically Connected Memory (OCM) architecture that disaggregates the main memory from the computation nodes in data centers. OCM is based on micro-ring resonators (MRRs), and it does not require any modification to the DRAM memory modules. We calculate energy consumption from real photonic devices and integrate them into a system simulator to evaluate performance. Here, our results show that (1) OCM is capable of interconnecting four DDR4 memory channels to a computing node using two fibersmore »« less
https://doi.org/10.1016/j.jpdc.2022.01.013

Full Text Available
Enabling Exascale Hardware and Software Design through Scalable System Virtualization (Final Report)

Technical Report Dinda, Peter

The purpose of this project has been to extend the state of the art of systems software for high-end computing (HEC) platforms, and to use systems software to better enable the evaluation of potential future HEC platforms, for example exascale platforms. Such platforms, and their systems software, have the goal of providing scientific computation at new scales, thus enabling new research in the physical sciences and engineering. Over time, the innovations in systems software for such platforms also become applicable to more widely used computing clusters, data centers, and clouds. This was a five-institution project, centered on the Palacios virtualmore »« less
https://doi.org/10.2172/1172772

Full Text Available
Scientific Application Requirements for Leadership Computing at the Exascale

Technical Report Ahern, Sean; Alam, Sadaf; Fahey, Mark; ...

The Department of Energy s Leadership Computing Facility, located at Oak Ridge National Laboratory s National Center for Computational Sciences, recently polled scientific teams that had large allocations at the center in 2007, asking them to identify computational science requirements for future exascale systems (capable of an exaflop, or 1018 floating point operations per second). These requirements are necessarily speculative, since an exascale system will not be realized until the 2015 2020 timeframe, and are expressed where possible relative to a recent petascale requirements analysis of similar science applications [1]. Our initial findings, which beg further data collection, validation, andmore »« less
https://doi.org/10.2172/1081802

Full Text Available

Similar Records