Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel systems”

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 955 records · Page 53

Multiple node remote messaging

A method for passing remote messages in a parallel computer system formed as a network of interconnected compute nodes includes that a first compute node (A) sends a single remote message to a remote second compute node (B) in order to control the remote second compute node (B) to send at least one remote message. The method includes various steps including controlling a DMA engine at first compute node (A) to prepare the single remote message to include a first message descriptor and at least one remote message descriptor for controlling the remote second compute node (B) to send at least one remote message, including putting the first message descriptor into an injection FIFO at the first compute node (A) and sending the single remote message and the at least one remote message descriptor to the second compute node (B).

Blumrich, Matthias A↗

DMA engine for repeating communication patterns

A parallel computer system is constructed as a network of interconnected compute nodes to operate a global message-passing application for performing communications across the network. Each of the compute nodes includes one or more individual processors with memories which run local instances of the global message-passing application operating at each compute node to carry out local processing operations independent of processing operations carried out at other compute nodes. Each compute node also includes a DMA engine constructed to interact with the application via Injection FIFO Metadata describing multiple Injection FIFOs where each Injection FIFO may containing an arbitrary number of message descriptors in order to process messages with a fixed processing overhead irrespective of the number of message descriptors included in the Injection FIFO.

Chen, Dong↗

Provisioning a Multi-Tiered Data Staging Area for Extreme-Scale Machines

Massively parallel scientific applications, running on extreme-scale supercomputers, produce hundreds of terabytes of data per run, driving the need for storage solutions to improve their I/O performance. Traditional parallel file systems (PFS) in high performance computing (HPC) systems are unable to keep up with such high data rates, creating a storage wall. In this work, we present a novel multi-tiered storage architecture comprising hybrid node-local resources to construct a dynamic data staging area for extreme-scale machines. Such a staging ground serves as an impedance matching device between applications and the PFS. Our solution combines diverse resources (e.g., DRAM, SSD) in such a way as to approach the performance of the fastest component technology and the cost of the least expensive one. We have developed an automated provisioning algorithm that aids in meeting the checkpointing performance requirement of HPC applications, by using a least-cost storage configuration. We evaluate our approach using both an implementation on a large scale cluster and a simulation driven by six-years worth of Jaguar supercomputer job-logs, and show that our approach, by choosing an appropriate storage configuration, achieves 41.5% cost savings with only negligible impact on performance.

99 GENERAL AND MISCELLANEOUS↗

An Approach to Integrate a Space-Time GIS Data Model with High Performance Computers

In this paper, we describe an approach to integrate a Space-Time GIS data model on a high performance computing platform. The Space-Time GIS data model has been developed on a desktop computing environment. We use the Space-Time GIS data model to generate GIS module, which organizes a series of remote sensing data. We are in the process of porting the GIS module into an HPC environment, in which the GIS modules handle large dataset directly via parallel file system. Although it is an ongoing project, authors hope this effort can inspire further discussions on the integration of GIS on high performance computing platforms.

99 GENERAL AND MISCELLANEOUS↗

Message passing with a limited number of DMA byte counters

A method for passing messages in a parallel computer system constructed as a plurality of compute nodes interconnected as a network where each compute node includes a DMA engine but includes only a limited number of byte counters for tracking a number of bytes that are sent or received by the DMA engine, where the byte counters may be used in shared counter or exclusive counter modes of operation. The method includes using rendezvous protocol, a source compute node deterministically sending a request to send (RTS) message with a single RTS descriptor using an exclusive injection counter to track both the RTS message and message data to be sent in association with the RTS message, to a destination compute node such that the RTS descriptor indicates to the destination compute node that the message data will be adaptively routed to the destination node. Using one DMA FIFO at the source compute node, the RTS descriptors are maintained for rendezvous messages destined for the destination compute node to ensure proper message data ordering thereat. Using a reception counter at a DMA engine, the destination compute node tracks reception of the RTS and associated message data and sends a clear to send (CTS) message to the source node in a rendezvous protocol form of a remote get to accept the RTS message and message data and processing the remote get (CTS) by the source compute node DMA engine to provide the message data to be sent.

97 MATHEMATICS AND COMPUTING↗

Portals 4 network API definition and performance measurement

Portals is a low-level network programming interface for distributed memory massively parallel computing systems designed by Sandia, UNM, and Intel. Portals has been designed to provide high message rates and to provide the flexibility to support a variety of higher-level communication paradigms. This project developed and analyzed an implementation of Portals using shared memory in order to measure and understand the impact of using general-purpose compute cores to handle network protocol processing functions. The goal of this study was to evaluate an approach to high-performance networking software design and hardware support that would enable important DOE modeling and simulation applications to perform well and to provide valuable input to Intel so they can make informed decisions about future network software and hardware products that impact DOE applications.

99 GENERAL AND MISCELLANEOUS↗

Visual Analytics for Roof Savings Calculator Ensembles

The Roof Savings Calculator (RSC) has been deployed for DOE as an industry-consensus, web-based tool for easily running complex building energy simulations. These simulations allow both homeowners and experts to determine building-specific cost and energy savings for modern roof and attic technologies. Using a database of over 3 million RSC simulations for different combinations of parameters, we have built a visual analytics tool to assist in the exploration and identification of features in the data. Since the database contains multiple variables, both categorical and continuous, we employ a coordinated multi-view approach that allows coordinated feature exploration through multiple visualizations at once. The main component of our system, a parallel coordinates view, has been adapted to handle large-scale, mixed data types as are found in RSC simulations. Other visualizations include map coordinated plots, high dynamic range (HDR) line plot rendering, and an intuitive user interface. We demonstrate these techniques with several use cases that have helped identify software and parametric simulation issues.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

List based prefetch

A list prefetch engine improves a performance of a parallel computing system. The list prefetch engine receives a current cache miss address. The list prefetch engine evaluates whether the current cache miss address is valid. If the current cache miss address is valid, the list prefetch engine compares the current cache miss address and a list address. A list address represents an address in a list. A list describes an arbitrary sequence of prior cache miss addresses. The prefetch engine prefetches data according to the list, if there is a match between the current cache miss address and the list address.

97 MATHEMATICS AND COMPUTING↗

Programmable stream prefetch with resource optimization

A stream prefetch engine performs data retrieval in a parallel computing system. The engine receives a load request from at least one processor. The engine evaluates whether a first memory address requested in the load request is present and valid in a table. The engine checks whether there exists valid data corresponding to the first memory address in an array if the first memory address is present and valid in the table. The engine increments a prefetching depth of a first stream that the first memory address belongs to and fetching a cache line associated with the first memory address from the at least one cache memory device if there is not yet valid data corresponding to the first memory address in the array. The engine determines whether prefetching of additional data is needed for the first stream within its prefetching depth. The engine prefetches the additional data if the prefetching is needed.

97 MATHEMATICS AND COMPUTING↗

Routing performance analysis and optimization within a massively parallel computer

An apparatus, program product and method optimize the operation of a massively parallel computer system by, in part, receiving actual performance data concerning an application executed by the plurality of interconnected nodes, and analyzing the actual performance data to identify an actual performance pattern. A desired performance pattern may be determined for the application, and an algorithm may be selected from among a plurality of algorithms stored within a memory, the algorithm being configured to achieve the desired performance pattern based on the actual performance data.

97 MATHEMATICS AND COMPUTING↗

Ordering of guarded and unguarded stores for no-sync I/O

A parallel computing system processes at least one store instruction. A first processor core issues a store instruction. A first queue, associated with the first processor core, stores the store instruction. A second queue, associated with a first local cache memory device of the first processor core, stores the store instruction. The first processor core updates first data in the first local cache memory device according to the store instruction. The third queue, associated with at least one shared cache memory device, stores the store instruction. The first processor core invalidates second data, associated with the store instruction, in the at least one shared cache memory. The first processor core invalidates third data, associated with the store instruction, in other local cache memory devices of other processor cores. The first processor core flushing only the first queue.

97 MATHEMATICS AND COMPUTING↗

RELAP5 Model of a Two-phase ThermoSyphon Experimental Facility for Fuels and Materials Irradiation

The High Flux Isotope Reactor (HFIR) at Oak Ridge National Laboratory (ORNL) does not have a separate materials-irradiation flow loop and requires most materials and all fuel experiments to be placed inside a containment. This is necessary to ensure that internal contaminants such as fission products cannot be released into the primary coolant. As part of the safety basis justification, HFIR also requires that all experiments be able to withstand various accident conditions (e.g., loss of coolant) without generating vapor bubbles on the surface of the experiment in the primary coolant. As with any parallel flow system, HFIR is vulnerable to flow excursion events when vapor is generated in one of those flow paths. The effects of these requirements are to artificially increase experiment temperatures by introducing a barrier between the experimental materials and the HFIR coolant and to reduce experiment heat loads to ensure boiling doesn t occur. A new experimental facility for materials irradiation and testing in the HFIR is currently being developed to overcome these limitations. The new facility is unique in that it will have its own internal cooling flow totally independent of the reactor primary coolant and boiling is permitted. The reactor primary coolant will cool the outside of this facility without contacting the materials inside. The ThermoSyphon Test Loop (TSTL), a full scale prototype of the proposed irradiation facility to be tested outside the reactor, is being designed and fabricated (Ref. 1). The TSTL is a closed system working as a two-phase thermosyphon. A schematic is shown in Fig. 1. The bottom central part is the boiler/evaporator and contains three electric heaters. The vapor generated by the heaters will rise and be condensed in the upper condenser, the condensate will drain down the side walls and be circulated via a downcomer back into the bottom of the boiler. An external flow system provides coolant that simulates the HFIR primary coolant. The two-phase flow code RELAP5-3D (Ref. 2) is the main tool employed in this design. The model has multiple challenges: boiling, condensation and natural convection flows need to be modeled accurately.

RELAP5 ThermoSyphon fuels irradiation↗

List based prefetch

A list prefetch engine improves a performance of a parallel computing system. The list prefetch engine receives a current cache miss address. The list prefetch engine evaluates whether the current cache miss address is valid. If the current cache miss address is valid, the list prefetch engine compares the current cache miss address and a list address. A list address represents an address in a list. A list describes an arbitrary sequence of prior cache miss addresses. The prefetch engine prefetches data according to the list, if there is a match between the current cache miss address and the list address.

97 MATHEMATICS AND COMPUTING↗

Multi-input and binary reproducible, high bandwidth floating point adder in a collective network

To add floating point numbers in a parallel computing system, a collective logic device receives the floating point numbers from computing nodes. The collective logic devices converts the floating point numbers to integer numbers. The collective logic device adds the integer numbers and generating a summation of the integer numbers. The collective logic device converts the summation to a floating point number. The collective logic device performs the receiving, the converting the floating point numbers, the adding, the generating and the converting the summation in one pass. One pass indicates that the computing nodes send inputs only once to the collective logic device and receive outputs only once from the collective logic device.

97 MATHEMATICS AND COMPUTING↗

DMA shared byte counters in a parallel computer

A parallel computer system is constructed as a network of interconnected compute nodes. Each of the compute nodes includes at least one processor, a memory and a DMA engine. The DMA engine includes a processor interface for interfacing with the at least one processor, DMA logic, a memory interface for interfacing with the memory, a DMA network interface for interfacing with the network, injection and reception byte counters, injection and reception FIFO metadata, and status registers and control registers. The injection FIFOs maintain memory locations of the injection FIFO metadata memory locations including its current head and tail, and the reception FIFOs maintain the reception FIFO metadata memory locations including its current head and tail. The injection byte counters and reception byte counters may be shared between messages.

97 MATHEMATICS AND COMPUTING↗

PRELIMINARY COUPLING OF THE MONTE CARLO CODE OPENMC AND THE MULTIPHYSICS OBJECT-ORIENTED SIMULATION ENVIRONMENT (MOOSE) FOR ANALYZING DOPPLER FEEDBACK IN MONTE CARLO SIMULATIONS

In recent years the use of Monte Carlo methods for modeling reactors has become feasible due to the increasing availability of massively parallel computer systems. One of the primary challenges yet to be fully resolved, however, is the efficient and accurate inclusion of multiphysics feedback in Monte Carlo simulations. The research in this paper presents a preliminary coupling of the open source Monte Carlo code OpenMC with the open source Multiphysics Object-Oriented Simulation Environment (MOOSE). The coupling of OpenMC and MOOSE will be used to investigate efficient and accurate numerical methods needed to include multiphysics feedback in Monte Carlo codes. An investigation into the sensitivity of Doppler feedback to fuel temperature approximations using a two dimensional 17x17 PWR fuel assembly is presented in this paper. The results show a functioning multiphysics coupling between OpenMC and MOOSE. The coupling utilizes Functional Expansion Tallies to accurately and efficiently transfer pin power distributions tallied in OpenMC to unstructured finite element meshes used in MOOSE. The two dimensional PWR fuel assembly case also demonstrates that for a simplified model the pin-by-pin doppler feedback can be adequately replicated by scaling a representative pin based on pin relative powers.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

nem_spread Ver. 5.10

Nem_spread reads it's input command file (default name nem_spread.inp), takes the named ExodusII geometry definition and spreads out the geometry (and optionally results) contained in that file out to a parallel disk system. The decomposition is taken from a scalar Nemesis load balance file generated by the companion utility nem_slice.

HENNIGAN, GARY↗

Uranium and strontium fate in waste-weathered sediments: Scaling of molecular processes to predict reactive transport

Objectives of the project: 1. Determine the process coupling that occurs between mineral transformation and contaminant (U and Sr) speciation in acid-uranium waste weathered Hanford sediments. 2. Establish linkages between molecular-scale contaminant speciation and meso-scale contaminant lability, release and reactive transport. 3. Make conjunctive use of molecular- to bench-scale data to constrain the development of a mechanistic, reactive transport model that includes coupling of contaminant sorption-desorption and mineral transformation reactions. Hypotheses tested: - Uranium and strontium speciation in legacy sediments from the U-8 and U-12 Crib sites can be reproduced in bench-scale weathering experiments conducted on unimpacted Hanford sediments from the same formations. - Reactive transport modeling of future uranium and strontium releases from the vadose zone of acid-waste weathered sediments can be effectively constrained by combining molecular-scale information on contaminant bonding environment with grain-scale information on contaminant phase partitioning, and meso-scale kinetic data on contaminant release from the waste-weathered porous media. - Although field contamination and laboratory experiments differ in their diagenetic time scales (decades for field vs. months to years for lab), sediment dissolution, neophase nucleation, and crystal growth reactions that occur during the initial disequilibrium induced by waste-sediment interaction leave a strong imprint that persists over subsequent longer-term equilibration time scales and, therefore, give rise to long-term memory effects. Enabling capabilities developed: Our team developed an iterative measure-model approach that is broadly applicable to elucidate the mechanistic underpinnings of reactive contaminant transport in geomedia subject to active weathering. Experimental design: Hypotheses were tested by comparing (with a similar set of techniques) the geochemical transformations and transport behaviors that occured in bench-scale studies of waste-sediment interaction with parallel model systems studies of homogeneous nucleation and neo-phase dissolution. Initial plans were to compare results with core sample extractions from the acid uranium waste impacted U-8 and U-12 Cribs at Hanford (see original proposal and letter of collaboration from J. Zachara). However, this part of the project was impossible because funding for core extractions were eliminated from the DoE budget. Three distinct crib waste aqueous simulants (whose composition is based on the most up-to-date information from field site investigations) were reacted with Hanford sediments in batch and column systems. Coupling of contaminant uptake to mineral weathering was monitored using a suite of methods both during waste-sediment interaction, and after, when waste-weathered sediments were subjected to infusion with circumneutral background pore water solutions. Our research was designed to adapt as needed to maintain a strong dialogue between laboratory and modeling investigations so that model development was increasingly constrained by emergent data and understanding. Potential impact of the project to DOE: Better prediction of contaminant uranium transport was achieved by employing multi-faceted lines of inquiry to build a strong bridge between molecular- and field-scale information. By focusing multiple lines and scales of observation on a common experimental design, our collaborative team revealed non-linear and emergent behavior in contaminated weathering systems. A goal of the current project was to expand our modeling capabilities, originally focused on hyperalkaline legacy waste streams, to include acidic weathering reactions that, as described above, were expected to result in profoundly different products. We were able to achieve this goal, and showed that these products nonetheless undergo analogous silicate and non-silicate transformation, ripening and aging processes. Our prediction that these weathering reactions would vary with waste stimulant chemistry resulted in data that was incorporated directly into a reactive transport model structure.

54 ENVIRONMENTAL SCIENCES↗