Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Multiple processors”

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 37 records · Page 2

PFLOTRAN: Reactive Flow & Transport Code for Use on Laptops to Leadership-Class Supercomputers

PFLOTRAN, a next-generation reactive flow and transport code for modeling subsurface processes, has been designed from the ground up to run efficiently on machines ranging from leadership-class supercomputers to laptops. Based on an object-oriented design, the code is easily extensible to incorporate additional processes. It can interface seamlessly with Fortran 9X, C and C++ codes. Domain decomposition parallelism is employed, with the PETSc parallel framework used to manage parallel solvers, data structures and communication. Features of the code include a modular input file, implementation of high-performance I/O using parallel HDF5, ability to perform multiple realization simulations with multiple processors per realization in a seamless manner, and multiple modes for multiphase flow and multicomponent geochemical transport. Chemical reactions currently implemented in the code include homogeneous aqueous complexing reactions and heterogeneous mineral precipitation/dissolution, ion exchange, surface complexation and a multirate kinetic sorption model. PFLOTRAN has demonstrated petascale performance using 2{sup 17} processor cores with over 2 billion degrees of freedom. Accomplishments achieved to date include applications to the Hanford 300 Area and modeling CO{sub 2} sequestration in deep geologic formations.

58 GEOSCIENCES↗

Portable and Transparent Message Compression in MPI Libraries to Improve the Performance and Scalability of Parallel Applications

The goal of this project has been to develop a lossless compression algorithm for message-passing libraries that can accelerate HPC systems by reducing the communication time. Because both compression and decompression have to be performed in software in real time, the algorithm has to be extremely fast while still delivering a good compression ratio. During the first half of this project, they designed a new compression algorithm called FPC for scientific double-precision data, made the source code available on the web, and published two papers describing its operation, the first in the proceedings of the Data Compression Conference and the second in the IEEE Transactions on Computers. At comparable average compression ratios, this algorithm compresses and decompresses 10 to 100 times faster than BZIP2, DFCM, FSD, GZIP, and PLMI on the three architectures tested. With prediction tables that fit into the CPU's L1 data acache, FPC delivers a guaranteed throughput of six gigabits per second on a 1.6 GHz Itanium 2 system. The C source code and documentation of FPC are posted on-line and have already been downloaded hundreds of times. To evaluate FPC, they gathered 13 real-world scientific datasets from around the globe, including satellite data, crash-simulation data, and messages from HPC systems. Based on the large number of requests they received, they also made these datasets available to the community (with permission of the original sources). While FPC represents a great step forward, it soon became clear that its throughput was too slow for the emerging 10 gigabits per second networks. Hence, no speedup can be gained by including this algorithm in an MPI library. They therefore changed the aim of the second half of the project. Instead of implementing FPC in an MPI library, they refocused their efforts to develop a parallel compression algorithm to further boost the throughput. After all, all modern high-end microprocessors contain multiple CPUs on a single die and will undoubtedly contain even larger numbers of CPUs in the future. Hence, a compute node in a parallel system is likely to have multiple processors per interconnection link. Thus, they investigated how to best exploit multiple CPUs to compress and decompress data for a single link, i.e., they developed a parallel version of the FPC algorithm called pFPC. On a 4-core 3 GHz Xeon system, pFPC exceeds 10 gigabits per second both in compression and decompression throughput while still reaching a compression ratio of 18%, which is reasonable for their double-precision floating-point datasets. At half this throughput, it achieves a 41% compression ratio. Moreover, the algorithm scales well to four cores and promises even higher throughputs on larger machines. Additional results and a description of the pFPC algorithm have recently been published in the proceedings of the Data Compression Conference. The C source code of pFPC is also publicly available.

97 MATHEMATICS AND COMPUTING↗

Recovery Act: SeaMicro Volume Server Power Reduction Research Development

Cloud data centers are projected to be the fastest growing segment of the server market through 2015, according to IDC. Increasingly people and businesses rely on the Cloud to deliver digital content quickly and efficiently. Recovery Act funding from the Department of Energy has helped SeaMicro's technologies enhance the total cost of operation, performance and energy efficiency in large data center and Cloud environments. SeaMicro's innovative supercomputer fabric connects thousands of processor cores, memory, storage and input/output traffic. The company's fabric supports multiple processor instruction sets. Current systems featuring SeaMicro technology typically use one quarter the power and take one sixth the space of traditional servers with the same compute performance, yet deliver up to 12 times the bandwidth per core. Mozilla and eHarmony are two customers successfully using SeaMicro's technology. Numerous non-public customers have been successfully using the SeaMicro product in test and production facilities. As a result of the Recovery Act funding from the U.S. Department of Energy, more than 50 direct jobs were created at SeaMicro. To date, they primarily have been high-value, engineering jobs. Hardware, software and manufacturing engineering positions have been created, as well as sales and sales engineering. The positions have allowed SeaMicro to significantly accelerate engineering development and accelerate commercialization. As a result, commercialization and delivery to market are months ahead of initial schedule. Additional jobs were indirectly created through the development of the SeaMicro product. Through many years of research and hard work prior to receipt of public funding, SeaMicro was awarded 2 patents for its work. SeaMicro's product led the way for industry leaders to reconsider the market for low power servers and create new product lines. With valuable support of the U.S. Department of Energy and through SeaMicro's product, the market has been reshaped by the company's unique approach and ground breaking technology.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Allocating application to group of consecutive processors in fault-tolerant deadlock-free routing path defined by routers obeying same rules for path selection

In a multiple processor computing apparatus, directional routing restrictions and a logical channel construct permit fault tolerant, deadlock-free routing. Processor allocation can be performed by creating a linear ordering of the processors based on routing rules used for routing communications between the processors. The linear ordering can assume a loop configuration, and bin-packing is applied to this loop configuration. The interconnection of the processors can be conceptualized as a generally rectangular 3-dimensional grid, and the MC allocation algorithm is applied with respect to the 3-dimensional grid.

97 MATHEMATICS AND COMPUTING↗

Low latency memory access and synchronization

A low latency memory system access is provided in association with a weakly-ordered multiprocessor system. Bach processor in the multiprocessor shares resources, and each shared resource has an associated lock within a locking device that provides support for synchronization between the multiple processors in the multiprocessor and the orderly sharing of the resources. A processor only has permission to access a resource when it owns the lock associated with that resource, and an attempt by a processor to own a lock requires only a single load operation, rather than a traditional atomic load followed by store, such that the processor only performs a read operation and the hardware locking device performs a subsequent write operation rather than the processor. A simple prefetching for non-contiguous data structures is also disclosed. A memory line is redefined so that in addition to the normal physical memory data, every line includes a pointer that is large enough to point to any other line in the memory, wherein the pointers to determine which memory line to prefetch rather than some other predictive algorithm. This enables hardware to effectively prefetch memory access patterns that are non-contiguous, but repetitive.

Blumrich, Matthias A↗

Method for prefetching non-contiguous data structures

A low latency memory system access is provided in association with a weakly-ordered multiprocessor system. Each processor in the multiprocessor shares resources, and each shared resource has an associated lock within a locking device that provides support for synchronization between the multiple processors in the multiprocessor and the orderly sharing of the resources. A processor only has permission to access a resource when it owns the lock associated with that resource, and an attempt by a processor to own a lock requires only a single load operation, rather than a traditional atomic load followed by store, such that the processor only performs a read operation and the hardware locking device performs a subsequent write operation rather than the processor. A simple perfecting for non-contiguous data structures is also disclosed. A memory line is redefined so that in addition to the normal physical memory data, every line includes a pointer that is large enough to point to any other line in the memory, wherein the pointers to determine which memory line to prefect rather than some other predictive algorithm. This enables hardware to effectively prefect memory access patterns that are non-contiguous, but repetitive.

97 MATHEMATICS AND COMPUTING↗

Development Status of the PEBBLES Code for Pebble Mechanics: Improved Physical Models and Speed-up

PEBBLES is a code for simulating the motion of all the pebbles in a pebble bed reactor. Since pebble bed reactors are packed randomly and not precisely placed, the location of the fuel elements in the reactor is not deterministically known. Instead, when determining operating parameters the motion of the pebbles can be simulated and stochastic locations can be found. The PEBBLES code can output information relevant for other simulations of the pebble bed reactors such as the positions of the pebbles in the reactor, packing fraction change in an earthquake, and velocity profiles created by recirculation. The goal for this level three milestone was to speedup the PEBBLES code through implementation on massively parallel computer. Work on this goal has resulted in speeding up both the single processor version and creation of a new parallel version of PEBBLES. Both the single processor version and the parallel running capability of the PEBBLES code have improved since the fiscal year start. The hybrid MPI/OpenMP PEBBLES version was created this year to run on the increasingly common cluster hardware profile that combines nodes with multiple processors that share memory and a cluster of nodes that are networked together. The OpenMP portions use the Open Multi-Processing shared memory parallel processing model to split the task across processors in a single node that shares memory. The Message Passing Interface (MPI) portion uses messages to communicate between different nodes over a network. The following are wall clock speed up for simulating an NGNP-600 sized reactor. The single processor version runs 1.5 times faster compared to the single processor version at the beginning of the fiscal year. This speedup is primarily due to the improved static friction model described in the report. When running on 64 processors, the new MPI/OpenMP hybrid version has a wall clock speed up of 22 times compared to the current single processor version. When using 88 processors, a speed up of 23 times is achieved. This speedup and other improvements of PEBBLES combine to make PEBBLES more capable and more useful for simulation of a pebble bed reactor. This report details the implementation and effects of the speedup work done over the course of the fiscal year.

10 SYNTHETIC FUELS↗

Development Status of the PEBBLES Code for Pebble Mechanics: Improved Physical Models and Speed-up

PEBBLES is a code for simulating the motion of all the pebbles in a pebble bed reactor. Since pebble bed reactors are packed randomly and not precisely placed, the location of the fuel elements in the reactor is not deterministically known. Instead, when determining operating parameters the motion of the pebbles can be simulated and stochastic locations can be found. The PEBBLES code can output information relevant for other simulations of the pebble bed reactors such as the positions of the pebbles in the reactor, packing fraction change in an earthquake, and velocity profiles created by recirculation. The goal for this level three milestone was to speedup the PEBBLES code through implementation on massively parallel computer. Work on this goal has resulted in speeding up both the single processor version and creation of a new parallel version of PEBBLES. Both the single processor version and the parallel running capability of the PEBBLES code have improved since the fiscal year start. The hybrid MPI/OpenMP PEBBLES version was created this year to run on the increasingly common cluster hardware profile that combines nodes with multiple processors that share memory and a cluster of nodes that are networked together. The OpenMP portions use the Open Multi-Processing shared memory parallel processing model to split the task across processors in a single node that shares memory. The Message Passing Interface (MPI) portion uses messages to communicate between different nodes over a network. The following are wall clock speed up for simulating an NGNP-600 sized reactor. The single processor version runs 1.5 times faster compared to the single processor version at the beginning of the fiscal year. This speedup is primarily due to the improved static friction model described in the report. When running on 64 processors, the new MPI/OpenMP hybrid version has a wall clock speed up of 22 times compared to the current single processor version. When using 88 processors, a speed up of 23 times is achieved. This speedup and other improvements of PEBBLES combine to make PEBBLES more capable and more useful for simulation of a pebble bed reactor. This report details the implementation and effects of the speedup work done over the course of the fiscal year.

10 SYNTHETIC FUELS↗

Evaluation of the Computing Systems for Yucca Mountain Repository TSPA-LA Model Operational Readiness

Sandia National Laboratories (SNL) was tasked to conduct an evaluation of the legacy computing systems of the now-closed Yucca Mountain Project (YMP) to maintain the operational readiness of the computing infrastructure (computer hardware and software) and knowledge capability for total system performance assessment (TSPA) type analysis, in the event that the License Application (LA) review by the U.S. Nuclear Regulatory Commission (NRC) is re-started and involves additional requests for information (RAIs). Six problem areas or components of the computing system were identified and subsequently resolved or improved to ensure the operational readiness of the TSPA-LA model capability on the server cluster. As part of this readiness review, the legacy TSPA computational cluster that was relocated from the SNL YMP Lead Lab Project Office in Las Vegas, Nevada to the SNL offices in Albuquerque, New Mexico was replaced with new hardware. Three floating licenses of Goldsim Version 9.60.300 were installed on the new cluster head node, and its distributed processing capability was mapped on the cluster processors. Other supporting software was tested and installed to support the TSPA- type analysis on the server cluster. TSPA-LA modeling cases were tested and verified for the model reproducibility on the current server cluster. All test runs were executed on multiple processors on the server cluster utilizing the Goldsim distributed processing capability, and all runs were completed successfully. The model reproducibility verification was evaluated by two approaches: numerical value comparison and graphical comparison, and the analysis demonstrated an excellent reproducibility of the TSPA-LA model runs on the server cluster. The current server cluster and supporting software systems are fully operational to support TSPA-LA type analysis.

97 MATHEMATICS AND COMPUTING↗

Reproduction of the Yucca Mountain Project TSPA-LA Model Runs using TSPA Computing Systems

Sandia National Laboratories (SNL) conducted an evaluation of total system performance assessment (TSPA) related computing systems for the previously considered Yucca Mountain Project (YMP). This was done to maintain the operational readiness of the computing infrastructure (computer hardware and software) and knowledge capability for total system performance assessment (TSPA) type analysis, as directed by the National Nuclear Security Administration (NNSA), DOE 2010. This work is a continuation of the ongoing readiness evaluation reported in Lee and Hadgu (2014). The current work examined main components of the computing system identified in the previous work (Lee and Hadgu, 2014) to ensure the operational readiness of the TSPA-LA model capability on the server cluster. The TSPA computing hardware and storage system were replaced in late 2014 to maintain core capability and improve computation efficiency. One floating license of GoldSim Version 9.60.300 was installed on the upgraded cluster head node, and its distributed processing capability was mapped on the cluster processors. Other supporting software was tested and installed to support the TSPA-type analysis on the server cluster. All the TSPA-LA modeling cases were tested and verified for the model reproducibility on the upgraded 2014 server cluster (CL2014). All test runs were executed on multiple processors on the server cluster utilizing the GoldSim distributed processing capability, and all runs completed successfully. The model reproducibility verification was evaluated by two approaches: numerical value comparison and graphical comparison. The analysis demonstrated an excellent reproducibility of the TSPA-LA model runs on the upgraded server cluster. The 2014 server cluster and supporting software systems are fully operational to support TSPA- LA type analysis.

97 MATHEMATICS AND COMPUTING↗

Reproduction of the Yucca Mountain Project TSPA-LA Model Runs using TSPA Computing Systems

Sandia National Laboratories (SNL) conducted an evaluation of total system performance assessment (TSPA) related computing systems for the previously considered Yucca Mountain Project (YMP). This was done to maintain the operational readiness of the computing infrastructure (computer hardware and software) and knowledge capability for total system performance assessment (TSPA) type analysis, as directed by the National Nuclear Security Administration (NNSA), DOE 2010. This work is a continuation of the ongoing readiness evaluation reported in Lee and Hadgu (2014). The current work examined main components of the computing system identified in the previous work (Lee and Hadgu, 2014) to ensure the operational readiness of the TSPA-LA model capability on the server cluster. The TSPA computing hardware and storage system were replaced in late 2014 to maintain core capability and improve computation efficiency. One floating license of GoldSim Version 9.60.300 was installed on the upgraded cluster head node, and its distributed processing capability was mapped on the cluster processors. Other supporting software was tested and installed to support the TSPA-type analysis on the server cluster. All the TSPA-LA modeling cases were tested and verified for the model reproducibility on the upgraded 2014 server cluster (CL2014). All test runs were executed on multiple processors on the server cluster utilizing the GoldSim distributed processing capability, and all runs completed successfully. The model reproducibility verification was evaluated by two approaches: numerical value comparison and graphical comparison. The analysis demonstrated an excellent reproducibility of the TSPA-LA model runs on the upgraded server cluster. The 2014 server cluster and supporting software systems are fully operational to support TSPA- LA type analysis.

97 MATHEMATICS AND COMPUTING↗

Integrating Fault-Tolerance into the Monte Carlo Application Toolkit

High-performance computer systems have passed the petascale mark, and the next decade will witness a drive towards exascale systems. Extrapolating from current hardware trends it is evident that exascale class systems will require a significantly larger number of cores than current petascale systems, and advanced architectures which include heterogeneous processors are gaining popularity. Such an increase in component count will decrease system mean time to interrupt (MTTI), resulting in greater emphasis on application fault tolerance. The additional memory requirements of exascale systems combined with the slow increase in hard drive write bandwidth will exclude current checkpoint/restart (C/R) techniques as a reliable means of fault tolerance. The current C/R approach to handling failures typically aborts the entire application and requires restarting the application, which is clearly an inefficient solution when utilizing 1000+ processors. Unless improvements are made in resilience and fault tolerance, it is predicted that the work throughput on the largest supercomputers could drop below 10% by 2015. As part of the ”Application Enablement for Next Generation Platforms” milestone, we addressed the shortcomings and limitations of C/R by developing a fault-tolerant component which would be integrated into the Monte Carlo Application Toolkit (MCATK) and demonstrated the ability to continue static K-effective calculations even in the presence of multiple processor failures. In section 2, we provide details about the milestone tasks. Section 3 describes the fault-tolerant framework, its integration into MCATK and its failure recovery scheme. We also describe FT-MPI, a fault-tolerant MPI implementation which provides the capabilities needed for an MPI-based application to survive and continue past failures. Section 4 reports future work that we hope to build upon the current accomplishments.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Multilevel Graph Partitioning for Three-Dimensional Discrete Fracture Network Flow Simulations

We present a topology-based method for mesh-partitioning in three-dimensional discrete fracture network (DFN) simulations that takes advantage of the intrinsic multi-level nature of a DFN. DFN models are used to simulate flow and transport through low-permeability fractured media in the subsurface by explicitly representing fractures as discrete entities. The governing equations for flow and transport are numerically integrated on computational meshes generated on the interconnected fracture networks. Modern high-fidelity DFN simulations require high-performance computing on multiple processors where performance and scalability depends partially on obtaining a high-quality partition of the mesh to balance work-loads and minimize communication across all processors. The discrete structure of a DFN naturally lends itself to various graph representations, which can be thought of as coarse-scale representations of the computational mesh. Using this concept, we develop two applications of the multilevel graph partitioning algorithm to partition the mesh of a DFN. In the first, we project a partition of the graph based on the DFN topology onto the mesh of the DFN and in the second, this DFN-based projection is used as the initial condition for further partitioning refinement of the mesh. We compare the performance of these methods with standard multi-level graph partitioning using graph-based metrics (cut, imbalance, partitioning time), computational-based metrics (FLOPS, iterations, solver time), and total run time. The DFN-based and the mesh-based partitioning methods are comparable in terms of the graph-based metrics, but the time required to obtain the partition is several orders of magnitude faster using the DFN-based partitions. The computation-based metrics show comparable performance between both methods so, in combination, the DFN-based partitions are several orders of magnitude faster than the mesh-based partition. Furthermore, the method which uses the DFN-partition solution as the initial condition of the mesh partition provided cut and imbalance values that were close to the mesh-based partition but in a fraction of the time. In turn, this hybrid method outperformed both of the other methods in terms of the total run time.

58 GEOSCIENCES↗

Distributed non-negative matrix factorization with determination of the number of latent features

The holistic analysis and understanding of the latent (that is, not directly observable) variables and patterns buried in large datasets is crucial for data-driven science, decision making and emergency response. Such exploratory analyses require devising unsupervised learning methods for data mining and extraction of the latent features, and non-negative matrix factorization (NMF) is one of the prominent such methods. NMF is based on compute-intense non-convex constrained minimization, which, for large datasets requires fast and distributed algorithms. However, current parallel implementations of NMF fail to estimate the number of latent features. In practice, identifying these features is both difficult and significant for pattern recognition and latent feature analysis, especially for large dense matrices. Here, we introduce a distributed NMF algorithm coupled with distributed custom clustering followed by a stability analysis on dense data, which we call DnMFk, to determine the number of latent variables. The results on synthetic data and the classical Swimmer data set demonstrate the accuracy of model determination while scaling nearly linearly across multiple processors for large data. Further, we employ DnMFk to determine the number of hidden features from a terabyte matrix.

97 MATHEMATICS AND COMPUTING↗

Temporal coarse-graining method to simulate the movement of atoms

We propose a novel method to simulate the movement of atoms at finite temperature. The main idea of our method is to derive “renormalized,” or coarse-grained in time, dynamics from the Euler–Maruyama scheme, which is the standard method for solving the stochastic differential equations numerically. Based on this renormalization, we propose a new algorithm for solving overdamped Langevin equations. We test our renormalization scheme on two models and demonstrate that the results obtained by this method are consistent with those obtained by the standard method. Our algorithm performs better than the standard scheme, especially at low temperatures and with multiple processors.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Robust and efficient overset grid assembly for partitioned unstructured meshes

This paper presents a method to perform efficient and automated Overset Grid Assembly (OGA) on a system of overlapping unstructured meshes in a parallel computing environment where all meshes are partitioned into multiple mesh-blocks and processed on multiple cores. The main task of the overset grid assembler is to identify, in parallel, among all points in the overlapping mesh system, at which points the flow solution should be computed (field points), interpolated (receptor points), or ignored (hole points). Point containment search or donor search, an algorithm to efficiently determine the cell that contains a given point, is the core procedure necessary for accomplishing this task. Donor search is particularly challenging for partitioned unstructured meshes because of the complex irregular boundaries that are often created during partitioning. Another challenge arises because of the large variation in the type of mesh-block overlap and the resulting large load imbalance on multiple processors. Desirable traits for the grid assembly method are efficiency (requiring only a small fraction of the solver time), robustness (correct identification of all point types), and full automation (no user input required other than the mesh system). Additionally, the method should be scalable, which is an important challenge due to the inherent load imbalance. This paper describes a fully-automated grid assembly method, which can use two different donor search algorithms. One is based on the use of auxiliary grids and Exact Inverse Maps (EIM), and the other is based on the use of Alternating Digital Trees (ADT). The EIM method is demonstrated to be more efficient than the ADT method, while retaining robustness. An adaptive load re-balance algorithm is also designed and implemented, which considerably improves the scalability of the method.

97 MATHEMATICS AND COMPUTING↗

multiPhATE: bioinformatics pipeline for functional annotation of phage isolates

To address the need for improved phage annotation tools that scale, we created an automated throughput annotation pipeline: multiple-genome Phage Annotation Toolkit and Evaluator (multiPhATE). multiPhATE is a throughput pipeline driver that invokes an annotation pipeline (PhATE) across a user-specified set of phage genomes. This tool incorporates a de novo phage gene calling algorithm and assigns putative functions to gene calls using protein-, virus- and phage-centric databases. multiPhATE’s modular construction allows the user to implement all or any portion of the analyses by acquiring local instances of the desired databases and specifying the desired analyses in a configuration file. We demonstrate multiPhATE by annotating two newly sequenced Yersinia pestis phage genomes. Within multiPhATE, the PhATE processing pipeline can be readily implemented across multiple processors, making it adaptable for throughput sequencing projects. Software documentation assists the user in configuring the system.

59 BASIC BIOLOGICAL SCIENCES↗

Parallel Hybrid Metaheuristics with Distributed Intensification and Diversification for Large-scale Optimization in Big Data Statistical Analysis

Important insights into many problems that are traditionally analyzed via statistical models can be obtained by re-formulating and evaluating within a large-scale optimization framework. The theoretical underpinnings of the statistical model often shift the goal of the solution space traversal from a traditional search for a single optimal solution to a traversal with the purpose of yielding a set of high quality, independent solutions. We examine statistical frameworks with astronomical solution spaces where the independence requirement constitutes a significant additional challenge for standard optimization methodologies. We design a hybrid metaheuristic with specialized intensification and diversification protocols in the base search algorithm. We extend our algorithm to the high-performance-computing realm using the Stampede2 supercomputer. We experimentally demonstrate the effectiveness of our algorithm to utilize multiple processors to collaboratively hill climb, broadcast messages to one another regarding landscape characteristics, diversify across the solution landscape, and request aid in climbing particularly difficult peaks.

Cho, Wendy K. Tam↗