Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Nodes”

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.

At least 1,531 records · Page 85

Challenges in Scheduling Aggregation in CyberPhysical Information Processing Systems

Data aggregation (a.k.a reduce operations) is an important element in information processing systems, including MapReduce clusters and cyberphysical networks. Unlike simple sensor networks, all the data in information processing systems must be eventually aggregated. Our goal is to lower overall latency in these systems by intelligently scheduling aggregation on intermediate routing nodes. Unlike previous models, our model explicitly takes into account link latency and computa- tion time. Our model also considers heterogeneous computing capabilities. In order to understand the potential challenges associated with constructing a distributed scheduler that minimizes la- tency, we ve developed a simulation of our model and tested the results of randomly scheduling nodes. Although these experiments were designed to provide data for a null-model, preliminary results have yielded a few interesting observations. We show that in cases where the computation time is larger than transmission time, in-network aggregation can have a large effect (reducing latency by 50% or more), but that naive scheduling can have a detrimental effect. Specifically, we show that when the root node (a.k.a the basestation) is faster than the other nodes, the latency can increase with increased coverage, and that these effects vary with the number of nodes present.

99 GENERAL AND MISCELLANEOUS↗

Power module assembly

A power module assembly of the type suitable for deployment in a vehicular power inverter, wherein the power inverter has a grounded chassis, is provided. The power module assembly comprises a conductive base layer electrically coupled to the chassis, an insulating layer disposed on the conductive base layer, a first conductive node disposed on the insulating layer, a second conductive node disposed on the insulating layer, wherein the first and second conductive nodes are electrically isolated from each other. The power module assembly also comprises a first capacitor having a first electrode electrically connected to the conductive base layer, and a second electrode electrically connected to the first conductive node, and further comprises a second capacitor having a first electrode electrically connected to the conductive base layer, and a second electrode electrically connected to the second conductive node.

42 ENGINEERING↗

Remote direct memory access

Methods, parallel computers, and computer program products are disclosed for remote direct memory access. Embodiments include transmitting, from an origin DMA engine on an origin compute node to a plurality target DMA engines on target compute nodes, a request to send message, the request to send message specifying a data to be transferred from the origin DMA engine to data storage on each target compute node; receiving, by each target DMA engine on each target compute node, the request to send message; preparing, by each target DMA engine, to store data according to the data storage reference and the data length, including assigning a base storage address for the data storage reference; sending, by one or more of the target DMA engines, an acknowledgment message acknowledging that all the target DMA engines are prepared to receive a data transmission from the origin DMA engine; receiving, by the origin DMA engine, the acknowledgement message from the one or more of the target DMA engines; and transferring, by the origin DMA engine, data to data storage on each of the target compute nodes according to the data storage reference using a single direct put operation.

97 MATHEMATICS AND COMPUTING↗

Performing a global barrier operation in a parallel computer

Executing computing tasks on a parallel computer that includes compute nodes coupled for data communications, where each compute node executes tasks, with one task on each compute node designated as a master task, including: for each task on each compute node until all master tasks have joined a global barrier: determining whether the task is a master task; if the task is not a master task, joining a single local barrier; if the task is a master task, joining the global barrier and the single local barrier only after all other tasks on the compute node have joined the single local barrier.

97 MATHEMATICS AND COMPUTING↗

Announcing Supercomputer Summit

Summit is the next leap in leadership-class computing systems for open science. With Summit we will be able to address, with greater complexity and higher fidelity, questions concerning who we are, our place on earth, and in our universe. Summit will deliver more than five times the computational performance of Titan’s 18,688 nodes, using only approximately 3,400 nodes when it arrives in 2017. Like Titan, Summit will have a hybrid architecture, and each node will contain multiple IBM POWER9 CPUs and NVIDIA Volta GPUs all connected together with NVIDIA’s high-speed NVLink. Each node will have over half a terabyte of coherent memory (high bandwidth memory + DDR4) addressable by all CPUs and GPUs plus 800GB of non-volatile RAM that can be used as a burst buffer or as extended memory. To provide a high rate of I/O throughput, the nodes will be connected in a non-blocking fat-tree using a dual-rail Mellanox EDR InfiniBand interconnect. Upon completion, Summit will allow researchers in all fields of science unprecedented access to solving some of the world’s most pressing challenges.

97 MATHEMATICS AND COMPUTING↗

Improving efficiency of a global barrier operation in a parallel computer

Performing a global barrier operation in a parallel computer that includes compute nodes coupled for data communications, where each compute node executes tasks, with one task on each compute node designated as a master task, including: for each task on each compute node until all master tasks have joined a global barrier: determining whether the task is a master task; if the task is not a master task, joining a single local barrier; if the task is a master task, joining the global barrier and the single local barrier only after all other tasks on the compute node have joined the single local barrier.

97 MATHEMATICS AND COMPUTING↗

Reliable Broadcast under Cascading Failures in Interdependent Networks

Reliable broadcast is an essential tool to disseminate information among a set of nodes in the presence of failures. We present a novel study of reliable broadcast in interdependent networks, in which the failures in one network may cascade to another network. In particular, we focus on the interdependency between the communication network and power grid network, where the power grid depends on the signals from the communication network for control and the communication network depends on the grid for power. In this paper, we build a resilient solution to handle crash failures in the communication network that may cause cascading failures and may even partition the network. In order to guarantee that all the correct nodes deliver the messages, we use soft links, which are inactive backup links to non-neighboring nodes that are only active when failures occur. At the core of our work is a fully distributed algorithm for the nodes to predict and collect the information of cascading failures so that soft links can be maintained to correct nodes prior to the failures. In the presence of failures, soft links are activated to guarantee message delivery and new soft links are built accordingly for long term robustness. Our evaluation results show that the algorithm achieves low packet drop rate and handles cascading failures with little overhead.

cascading failures↗

Parallel file system with metadata distributed across partitioned key-value store c

Improved techniques are provided for storing metadata associated with a plurality of sub-files associated with a single shared file in a parallel file system. The shared file is generated by a plurality of applications executing on a plurality of compute nodes. A compute node implements a Parallel Log Structured File System (PLFS) library to store at least one portion of the shared file generated by an application executing on the compute node and metadata for the at least one portion of the shared file on one or more object storage servers. The compute node is also configured to implement a partitioned data store for storing a partition of the metadata for the shared file, wherein the partitioned data store communicates with partitioned data stores on other compute nodes using a message passing interface. The partitioned data store can be implemented, for example, using Multidimensional Data Hashing Indexing Middleware (MDHIM).

97 MATHEMATICS AND COMPUTING↗

NetFlow Dynamics

NetFlow Dynamics is a web-accessible analysis environment for simulating dynamic flows of materials on model networks. Performing a simulation requires both the NetFlow Dynamics application and a network model which is a description of the structure of the nodes and edges of a network including the flow capacity of each edge and the storage capacity of each node, and the sources and sinks of the material flowing on the network. NetFlow Dynamics consists of databases for storing network models, algorithms to calculate flows on networks, and a GIS-based graphical interface for performing simulations and viewing simulation results. Simulated flows are dynamic in the sense that flows on each edge of the network and inventories at each node change with time and can be out of equilibrium with boundary conditions. Any number of network models could be simulated using Net Flow Dynamics. To date, the models simulated have been models of petroleum infrastructure. The main model has been the National Transportation Fuels Model (NTFM), a network of U.S. oil fields, transmission pipelines, rail lines, refineries, tank farms, and distribution terminals. NetFlow Dynamics supports two different flow algorithms, the Gradient Flow algorithm and the Inventory Control algorithm, that were developed specifically for the NetFlow Dynamics application. The intent is to add additional algorithms in the future as needed. The ability to select from multiple algorithms is desirable because a single algorithm never covers all analysis needs. The current algorithms use a demand-driven capacity-constrained formulation which means that the algorithms strive to use all available capacity and stored inventory to meet desired flows to sinks, subject to the capacity constraints of each network component. The current flow algorithms are best suited for problems in which a material flows on a capacity-constrained network representing a supply chain in which the material supplied can be stored at each node of the network. In the petroleum models, the flowing materials are crude oil and refined products that can be stored at tank farms, refineries, or terminals (i.e. the nodes of the network). Examples of other network models that could be simulated are currency flowing in a financial network, agricultural products moving to market, or natural gas flowing on a pipeline network.

Corbet Jr., Thomas F↗

Hiding Critical Targets in Smart Grid Networks

With the integration of advanced communication technologies, the power grid is expected to greatly enhance efficiency and reliability of future power systems. However, since most electrical devices in power grid substations are connected via communication networks, cyber security of these communication networks becomes a critical issue. Real-World incidents such as Stuxnet have shown the feasibility of compromising a device in the power grid network to further launch more sophisticated attacks. To deal with security attacks of this spirit, this paper aims to hide critical targets from compromised internal nodes and hence protect them from further attacks launched by those compromised nodes. In particular, we consider substation networks and propose to add carefully-controlled dummy traffic to a substation network to make critical target nodes indistinguishable from other nodes in network traffic patterns. This paper describes the design and evaluation of such a scheme. Evaluations show that the scheme can effectively protect critical nodes with acceptable communication cost.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Understanding the I/O Performance Gap Between Cori KNL and Haswell

The Cori system at NERSC has two compute partitions with different CPU architectures: a 2,004 node Haswell partition and a 9,688 node KNL partition, which ranked as the 5th most powerful and fastest supercomputer on the November 2016 Top 500 list. The compute partitions share a common storage configuration, and understanding the IO performance gap between them is important, impacting not only to NERSC/LBNL users and other national labs, but also to the relevant hardware vendors and software developers. In this paper, we have analyzed performance of single core and single node IO comprehensively on the Haswell and KNL partitions, and have discovered the major bottlenecks, which include CPU frequencies and memory copy performance. We have also extended our performance tests to multi-node IO and revealed the IO cost difference caused by network latency, buffer size, and communication cost. Overall, we have developed a strong understanding of the IO gap between Haswell and KNL nodes and the lessons learned from this exploration will guide us in designing optimal IO solutions in many-core era.

97 MATHEMATICS AND COMPUTING↗

Representation of activity in images using geospatial temporal graphs

Various technologies pertaining to modeling patterns of activity observed in remote sensing images using geospatial-temporal graphs are described herein. Graphs are constructed by representing objects in remote sensing images as nodes, and connecting nodes with undirected edges representing either distance or adjacency relationships between objects and directed edges representing changes in time. Activity patterns may be discerned from the graphs by coding nodes representing persistent objects like buildings differently from nodes representing ephemeral objects like vehicles, and examining the geospatial-temporal relationships of ephemeral nodes within the graph.

47 OTHER INSTRUMENTATION↗

Multi-petascale highly efficient parallel supercomputer

A Multi-Petascale Highly Efficient Parallel Supercomputer of 100 petaflop-scale includes node architectures based upon System-On-a-Chip technology, where each processing node comprises a single Application Specific Integrated Circuit (ASIC). The ASIC nodes are interconnected by a five dimensional torus network that optimally maximize the throughput of packet communications between nodes and minimize latency. The network implements collective network and a global asynchronous network that provides global barrier and notification functions. Integrated in the node design include a list-based prefetcher. The memory system implements transaction memory, thread level speculation, and multiversioning cache that improves soft error rate at the same time and supports DMA functionality allowing for parallel processing message-passing.

97 MATHEMATICS AND COMPUTING↗

Scalable flexibility control of distributed loads in a power grid

The technology described herein is generally directed towards a distributed optimization technology for the control of aggregation of distributed flexibility resource nodes that operates iteratively until a commanded power profile is produced by aggregated loads. The technology uses a distributed iterative solution in which each node solves a local optimization problem with local constraints and states, while using a global Lagrange multiplier that is based upon information from each other node. The global Lagrange multiplier is determined at an aggregation level using load-specific information that is obtained in a condensed form (e.g., a scalar) from each node at each iteration. The global Lagrange multiplier is broadcasted to the nodes for each new iteration. The technology provides an iterative, distributed solution to the network optimization problem of power tracking of aggregated loads.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

PCIe write request acknowledgment

A PCIe (Peripheral Component Interconnect Express) protocol converter for connection to a central processing unit (CPU) node having a root complex, a CPU memory fabric and CPU memory may include independent PCIe links, a fabric interface and a fabric switch connected to the fabric interface. Each of the links may include an endpoint for connection to the root complex. The fabric switch is connected to the fabric interface of each of the links and is connectable to a remote node. The fabric switch transmits writes of a single write request from the remote node across both links. Each fabric interface is to transmit an acknowledgment to the remote node in response to a write of the writes becoming observable at the CPU node hi Michael, hi Michael,.

97 MATHEMATICS AND COMPUTING↗

Scatter gather using key-value store

Scatter gather operation(s) are performed by accessing a shared memory that is shared amongst nodes interconnected through network(s) and having a CNS shared amongst the nodes. Data is gathered from multiple processes at corresponding multiple nodes into location(s) in the CNS, and tuple(s) having a same tuple name are created in the CNS. The tuple(s) have information referencing the gathered data in the location(s). Alternatively, data that has been gathered using the same tuple name is scattered to multiple processes participating in the CNS. The scattering uses the tuple(s) in the CNS, and is performed from the location(s) into other location(s) at one or multiple nodes for one or multiple processes at the corresponding one or multiple nodes. Both the gathering data and the scattering data may also be performed.

Jacob, Philip↗

Hybrid feature-driven learning system for abnormality detection and localization

A cyber-physical system may have a plurality of monitoring nodes each generating a series of current monitoring node values over time representing current operation of the system. A data-driven features extraction computer platform may receive the series of current monitoring node values and generate current data-driven feature vectors based on the series of current monitoring node values. A residual features extraction computer platform may receive the series of current monitoring node values, execute a system model and utilize a stochastic filter to determine current residual values, and generate current residual-driven feature vectors based on the current residual values. An abnormal detection platform may then receive the current data-driven and residual-driven feature vectors and compare the current data-driven and residual-driven feature vectors with at least one decision boundary associated with an abnormal detection model. An abnormal alert signal may then be transmitted when appropriate based on a result of said comparison.

Abbaszadeh, Masoud↗

Scalable access to shared files in a distributed system

Logic may pre-populate cache of compute nodes allocated to a user's session. Logic may access an image file of a global filesystem, the image file to comprise a first set of one or more files associated with a user session and a second set of one or more files upon which execution of the first set will depend. Logic may store the image file in local data storage of each compute node of a spanning tree of compute nodes allocated for the user session. Logic may unpack the image file based on the data. Logic may configure the local environment of each compute node in the spanning tree to identify a location in local memory of each of the files. And logic may initiate execution of a local filesystem service in each of the compute nodes of the spanning tree.

Oganezov, Alexander↗