Using simulation to design extreme-scale applications and architectures: Programming model exploration.
Abstract not provided.
SEARCH · Search NASA
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Abstract not provided.
Abstract not provided.
The third Neuro-Inspired Computational Elements (NICE) Workshop was held February 23-25, 2015 in Albuquerque, New Mexico. The goal of the Workshop was to bring together researchers from different scientific disciplines and application areas to provide a common point from which to develop the next generation of information processing/computing architectures that go beyond stored program architecture and Moore’s Law limits. Conventional, stored program architecture systems are designed for algorithmic and exact calculations. Many high impact problems, however, involve large, noisy, incomplete, “natural” data sets that do not lend themselves to convenient solutions from current systems. This Workshop series has focused on addressing these problems by building upon the convergence among neuroscience, microelectronics, and computational systems to develop new architectures designed to handle these natural data sets. An international group of nearly 100 registered attendees with a wide range of expertise and experience (e.g., neuroscience, systems, microelectronics, applications, and potential funding agencies) participated in this year’s event by offering knowledgeable insight regarding: Applications that look for solutions beyond the capabilities of current computational systems; Technical approaches that are at the early to middle stages of development for new computational systems; Pathways and resources to accelerate the development of these new systems.
There are many technologies available to the nuclear power industry to improve efficiency in plant work activities. These range from new control room technologies to those for mobile field workers. They can make a positive impact on a wide range of performance objectives – increase in productivity, human error reduction, validation of results, accurate transfer of data, and elimination of repetitive tasks. It is expected that the industry will more and more turn to these technologies to achieve these operational efficiencies to lower costs. At the same time, this will help utilities manage a looming staffing problem as the inevitable retirement wave of the more seasoned workers affects both staffing levels and knowledge retention. A barrier to this wide-scale implementation of new technologies for operational efficiency is the lack of a comprehensive digital architecture that can support the real-time information exchanges needed to achieve the desired operational efficiencies. This project will define an advanced digital architecture that will accommodate the entire range of system, process, and plant worker activity to enable the highest degree of integration, thereby creating maximum efficiency and productivity. This pilot project will consider a range of open standards that are suitable for the various data and communication requirements of a seamless digital environment. It will map these standards into an overall architecture to support the II&C developments of this research program.
The Digital Architecture effort is a part of the Department of Energy (DOE) sponsored Light-Water Reactor Sustainability (LWRS) Program conducted at Idaho National Laboratory (INL). The LWRS program is performed in close collaboration with industry research and development (R&D) programs that provides the technical foundations for licensing and managing the long-term, safe, and economical operation of current nuclear power plants (NPPs). One of the primary missions of the LWRS program is to help the U.S. nuclear industry adopt new technologies and engineering solutions that facilitate the continued safe operation of the plants and extension of the current operating licenses. Therefore, a major objective of the LWRS program is the development of a seamless digital environment for plant operations and support by integrating information from plant systems with plant processes for nuclear workers through an array of interconnected technologies. In order to get the most benefits of the advanced technology suggested by the different research activities in the LWRS program, the nuclear utilities need a digital architecture in place to support the technology. A digital architecture can be defined as a collection of information technology (IT) capabilities needed to support and integrate a wide-spectrum of real-time digital capabilities for nuclear power plant performance improvements. It is not hard to imagine that many processes within the plant can be largely improved from both a system and human performance perspective by utilizing a plant wide (or near plant wide) wireless network. For example, a plant wide wireless network allows for real time plant status information to easily be accessed in the control room, field workers’ computer-based procedures can be updated based on the real time plant status, and status on ongoing procedures can be incorporated into smart schedules in the outage command center to allow for more accurate planning of critical tasks. The goal of the digital architecture project is to provide a long-term strategy to integrate plant systems, plant processes, and plant workers. This include technologies to improve nuclear worker efficiency and human performance; to offset a range of plant surveillance and testing activities with new on-line monitoring technologies; improve command, control, and collaboration in settings such as outage control centers and work execution centers; and finally to improve operator performance with new operator aid technologies for the control room. The requirements identified through the activities in the Digital Architecture project will be used to estimate the amount of traffic on the network and hence estimating the minimal bandwidth needed.
We present preliminary results of the Roofline Toolkit for multicore, many core, and accelerated architectures. This paper focuses on the processor architecture characterization engine, a collection of portable instrumented micro benchmarks implemented with Message Passing Interface (MPI), and OpenMP used to express thread-level parallelism. These benchmarks are specialized to quantify the behavior of different architectural features. Compared to previous work on performance characterization, these microbenchmarks focus on capturing the performance of each level of the memory hierarchy, along with thread-level parallelism, instruction-level parallelism and explicit SIMD parallelism, measured in the context of the compilers and run-time environments. We also measure sustained PCIe throughput with four GPU memory managed mechanisms. By combining results from the architecture characterization with the Roofline model based solely on architectural specifications, this work offers insights for performance prediction of current and future architectures and their software systems. To that end, we instrument three applications and plot their resultant performance on the corresponding Roofline model when run on a Blue Gene/Q architecture.
In the early 2000s, industry switched to multicore microprocessors to address semiconductors' speed and power limits. However, the change was unsuccessful, leading to dire claims that “Moore's law is ending.” In conclusion, this column suggests that while the approach was sound, it needed a deeper architectural transformation. Industry has since discovered a suitable architecture, but work remains on software to support it.
This paper proposes a reference framework for a transactive energy market based on blockchain. The framework was designed based on the engineering requirements of a distribution-scale market; including participant needs, expected market transactions, and the cybersecurity constructs required to support a fair, secure and efficient market operation. It leverages the existing blockchain primitives to provide clear value propositions to the transactive market, including identity management (access control), data security (integrity), resiliency (decentralization, scalability and performance). The validity of the proposed framework is demonstrated using a real-time 5-min double-auction market. The results highlight its benefits while providing strong validation of applicability to blockchain within transactive energy systems.
Explore the source record for details and available documents.
Explore the source record for details and available documents.
The third Neuro-Inspired Computational Elements (NICE) Workshop was held February 23-25, 2015 in Albuquerque, New Mexico. The goal of the Workshop was to bring together researchers from different scientific disciplines and application areas to provide a common point from which to develop the next generation of information processing/computing architectures that go beyond stored program architecture and Moore’s Law limits.
Charge‐programmed 3D printing enables the fabrication of 3D electronics with lightweight and high precision via selective patterning of metals. This selective metal deposition is catalyzed by Pd nanoparticles that are specifically immobilized onto the charged surface and promises to fabricate a myriad of complex electronic devices with self‐sensing, actuation, and structural elements assembled in a designed 3D layout. However, the achievable property space and the material‐performance correlation of the charge‐programmed printing remain unexplored. Herein, a series of photo‐curable resins are designed for unveiling how the charge and crosslink densities synergistically impact the nanocatalyst‐guided selective deposition in catalytic efficiency and properties of the 3D printed charge‐programmed architectures, leading to high‐quality 3D patterning of solid and liquid metals. The findings offer a wide tunability of the structural properties of the printed electronics, ranging from stiff to extreme flexibility. Capitalizing on these results, the printing and successful application of an ultralight‐weight and deployable 3D multi‐layer antenna system operating at an ultrahigh‐frequency of 19 GHz are demonstrated.
Traditional high performance computing (HPC) systems were designed from a compute-centric perspective, with an emphasis on high floating point performance. As scientific and analytics applications become more data intensive, there is a need to rethink HPC system architectures, programming models, runtime systems, and tools with a focus on scalable data intensive computing. Industry approaches supporting data intensive applications have been highly successful, leading many in the HPC community to search for ways to adapt them to HPC hardware and software contexts. Conversely, industry looks to the HPC community for their expertise in designing, deploying, and using extremely large and high performance computing systems. This special issue contains seven articles, each of which is an extended version of a paper presented in the 2015 International Workshop on Data Intensive Scalable Computing Systems (DISCS-2015) held in Austin, Texas on November 15, 2015. The workshop program included papers that ranged from programming models to systems software to storage, each with a strong focus on data intensive computing.
Here, we investigate how to port the standard interior-point method to new exascale architectures for block-structured nonlinear programs with state equations. Computationally, we decompose the interior-point algorithm into two successive operations: the evaluation of the derivatives and the solution of the associated Karush-Kuhn-Tucker (KKT) linear system. Our method accelerates both operations using two levels of parallelism. First, we distribute the computations on multiple processes using coarse parallelism. Second, each process uses SIMD/GPU accelerators locally to accelerate the operations using fine-grained parallelism. The KKT system is reduced by eliminating the inequalities and the state variables from the corresponding equations. We demonstrate our method's capability on the supercomputer Polaris, a testbed for the future exascale Aurora system. Each node is equipped with four GPUs, a setup amenable to our two-level approach. Our experiments on the stochastic optimal power flow problem show that the reduction method is 50x faster than the sparse linear solver HSL MA57 running in serial on the CPU, and 6x faster than Pardiso running in parallel on CPU on the same number of processes.
All activities of the Exascale Co-design Center for Materials in Extreme Environments (ExMatEx) are focused on the two ultimate goals of the project: (1) demonstrating and delivering a prototype scale-bridging materials science application based upon adaptive physics refinement, and (2) identifying the requirements for the exascale ecosystem that are necessary to perform computational materials science simulations (both single- and multi-scale). During the first year of ExMatEx, our focus was on establishing how we do computational materials science, by developing an initial suite of flexible proxy applications. These “proxy apps” are the primary vehicle for the co-design process, involving assessments and tradeoff evaluations both within the ExMatEx team, and with the entire exascale ecosystem. These interactions have formed the basis of our second year activities. The set of artifacts from these co-design interactions are the lessons learned, that are used to re-express the applications and algorithms within the context of emerging architectures, programming models, and runtime systems.
All activities of the Exascale Co-design Center for Materials in Extreme Environments (Ex- MatEx) are focused on the two ultimate goals of the project: (1) demonstrating and delivering a prototype scale-bridging materials science application based upon adaptive physics refinement, and (2) identifying the requirements for the exascale ecosystem that are necessary to perform computational materials science simulations (both single- and multi-scale). During the first year of ExMatEx, our focus was on establishing how we do computational materials science, by developing an initial suite of flexible proxy applications. These “proxy apps” are the primary vehicle for the co-design process, involving assessments and tradeoff evaluations both within the ExMatEx team, and with the entire exascale ecosystem. These interactions have formed the basis of our second year activities. The set of artifacts from these co-design interactions are the lessons learned, that are used to re-express the applications and algorithms within the context of emerging architectures, programming models, and runtime systems.
This Technical Support Document documents the technical analysis and design guidance for large hospitals to achieve whole-building energy savings of at least 50% over ANSI/ASHRAE/IESNA Standard 90.1-2004 and represents a step toward determining how to provide design guidance for aggressive energy savings targets. This report documents the modeling methods used to demonstrate that the designrecommendations meet or exceed the 50% goal. EnergyPlus was used to model the predicted energy performance of the baseline and low-energy buildings to verify that 50% energy savings are achievable. Percent energy savings are based on a nominal minimally code-compliant building and whole-building, net site energy use intensity. The report defines architectural-program characteristics for typicallarge hospitals, thereby defining a prototype model; creates baseline energy models for each climate zone that are elaborations of the prototype models and are minimally compliant with Standard 90.1-2004; creates a list of energy design measures that can be applied to the prototype model to create low-energy models; uses industry feedback to strengthen inputs for baseline energy models andenergy design measures; and simulates low-energy models for each climate zone to show that when the energy design measures are applied to the prototype model, 50% energy savings (or more) are achieved.