Search NASA⌕ Search

SEARCH · Search NASA

Results for “Memory benchmark”

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 145 records · Page 8

Adding Fault Tolerance to NPB Benchmarks Using ULFM

In the world of high-performance computing, fault tolerance and application resilience are becoming some of the primary concerns because of increasing hardware failures and memory corruptions. While the research community has been investigating various options, from system-level solutions to application-level solutions, standards such as the Message Passing Interface (MPI) are also starting to include such capabilities. The current proposal for MPI fault tolerant is centered around the User-Level Failure Mitigation (ULFM) concept, which provides means for fault detection and recovery of the MPI layer. This approach does not address application-level recovery, which is currently left to application developers. In this work, we present a mod- ification of some of the benchmarks of the NAS parallel benchmark (NPB) to include support of the ULFM capabilities as well as application-level strategies and mechanisms for application-level failure recovery. As such, we present: (i) an application-level library to checkpoint and restore data, (ii) extensions of NPB benchmarks for fault tolerance based on different strategies, (iii) a fault injection tool, and (iv) some preliminary results that show the impact of such fault tolerant strategies on the application execution.

Parchman, Zachary W↗

ELSI: A unified software interface for Kohn–Sham electronic structure solvers

Solving the electronic structure from a generalized or standard eigenproblem is often the bottleneck in large scale calculations based on Kohn-Sham density-functional theory. This problem must be addressed by essentially all current electronic structure codes, based on similar matrix expressions, and by high-performance computation. We here present a unified software interface, ELSI, to access different strategies that address the Kohn-Sham eigenvalue problem. Currently supported algorithms include the dense generalized eigensolver library ELPA, the orbital minimization method implemented in libOMM, and the pole expansion and selected inversion (PEXSI) approach with lower computational complexity for semilocal density functionals. The ELSI interface aims to simplify the implementation and optimal use of the different strategies, by offering (a) a unified software framework designed for the electronic structure solvers in Kohn-Sham density-functional theory; (b) reasonable default parameters for a chosen solver; (c) automatic conversion between input and internal working matrix formats, and in the future (d) recommendation of the optimal solver depending on the specific problem. As a result, comparative benchmarks are shown for system sizes up to 11,520 atoms (172,800 basis functions) on distributed memory supercomputing architectures.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Scalable Work Stealing

Irregular and dynamic parallel applications pose significant challenges to achieving scalable performance on large-scale multicore clusters. These applications often require ongoing, dynamic load balancing in order to maintain efficiency. While effective at small scale, centralized load balancing schemes quickly become a bottleneck on large-scale clusters. Work stealing is a popular approach to distributed dynamic load balancing; however its performance on large-scale clusters is not well understood. Prior work on work stealing has largely focused on shared memory machines. In this work we investigate the design and scalability of work stealing on modern distributed memory systems. We demonstrate high efficiency and low overhead when scaling to 8,192 processors for three benchmark codes: a producer-consumer benchmark, the unbalanced tree search benchmark, and a multiresolution analysis kernel.

99 GENERAL AND MISCELLANEOUS↗

A time convolution less density matrix approach to the nonlinear optical response of a coupled system-bath complex

Time convolution less density matrix theory (TCL) is a powerful and well established tool to investigate strong system-bath coupling for linear optical spectra. We show that TCL equations can be generalised to the nonlinear optical response up to a chosen order in the optical field. This goal is achieved via an time convolution less perturbation scheme for the reduced density matrices of the electronic system. In our approach, the most important results are the inclusion of a electron-phonon coupling non-diagonal in the electronic states and memory effects of the bath: First, the considered model system is introduced. Second, the time evolution of the statistical operator is expanded with respect to the external optical field. This expansion is the starting point to explain how a TCL theory can treat the response up to in a certain order in the external field. Third, new TCL equations, including bath memory effects, are derived and the problem of information loss in the reduced density matrix is analysed. For this purpose, new dimensions are added to the reduced statistical operator to compensate lack of information in comparison with the full statistical operator. The theory is benchmarked with a two level system and applied to a three level system including non-diagonal phonon coupling. In our analysis of pump-probe experiments, the bath memory is influenced by the system state occupied between pump and probe pulse. In particular, the memory of the bath influences the dephasing process of electronic coherences developing during the time interval between pump and probe pulses.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters

In this paper, we propose a framework called FPDeep, which uses a hybrid of model and layer paral- lelism to configure distributed reconfigurable clusters to train DNNs. This approach has numerous benefits. First, the design does not suffer from batch size growth. Second, novel workload and weight partitioning leads to balanced loads of both among nodes. And third, the entire system is fine-grained pipeline. This leads to high parallelism and utilization and also minimizes the time features need to be cached while waiting for back-propagation.

Wang, Tianqi↗

SERVER DEVELOPMENT FOR NSLS-II PHYSICS APPLICATIONS AND PERFORMANCE ANALYSIS

The beam commissioning software framework of NSLS-II project adopts a client/server based architecture to replace the more traditional monolithic high level application approach. The server software under development is available via an open source sourceforge project named epics-pvdata, which consists of modules pvData, pvAccess, pvIOC, and pvService. Examples of two services that already exist in the pvService module are itemFinder, and gather. Each service uses pvData to store in-memory transient data, pvService to transfer data over the network, and pvIOC as the service engine. The performance benchmarking for pvAccess and both gather service and item finder service are presented in this paper. The performance comparison between pvAccess and Channel Access are presented also. For an ultra low emittance synchrotron radiation light source like NSLS II, the control system requirements, especially for beam control are tight. To control and manipulate the beam effectively, a use case study has been performed to satisfy the requirement and theoretical evaluation has been performed. The analysis shows that model based control is indispensable for beam commissioning and routine operation. However, there are many challenges such as how to re-use a design model for on-line model based control, and how to combine the numerical methods for modeling of a realistic lattice with the analytical techniques for analysis of its properties. To satisfy the requirements and challenges, adequate system architecture for the software framework for beam commissioning and operation is critical. The existing traditional approaches are self-consistent, and monolithic. Some of them have adopted a concept of middle layer to separate low level hardware processing from numerical algorithm computing, physics modelling, data manipulating and plotting, and error handling. However, none of the existing approaches can satisfy the requirement. A new design has been proposed by introducing service oriented architecture technology, and client interface is undergoing. The design and implementation adopted a new EPICS implementation, namely epics-pvdata [9], which is under active development. The implementation of this project under Java is close to stable, and binding to other language such as C++ and/or Python is undergoing. In this paper, we focus on the performance benchmarking and comparison for pvAccess and Channel Access, the performance evaluation for 2 services, gather and item finder respectively.

43 PARTICLE ACCELERATORS↗

IP Protection in TinyML

Tiny machine learning (TinyML) is an essential component of emerging smart microcontrollers (MCUs). How- ever, the protection of the intellectual property (IP) of the model is an increasing concern due to the lack of desktop/server-grade resources on these power-constrained devices. In this paper, we propose STML, a system and algorithm co-design to Secure IP of TinyML on MCUs with ARM TrustZone. Our design jointly optimizes memory utilization and latency while ensuring the security and accuracy of emerging models. We implemented a prototype and benchmarked with 7 models, demonstrating STML reduces 40% of model protection runtime overhead on average.

42 ENGINEERING↗

Roofline Analysis in the Intel® Advisor to Deliver Optimized Performance for applications on Intel® Xeon Phi™ Processor

In this session we show, in two case studies, how the roofline feature of Intel Advisor has been utilized to optimize the performance of kernels of the XGC1 and PICSAR codes in preparation for Intel Knights Landing architecture. The impact of the implemented optimizations and the benefits of using the automatic roofline feature of Intel Advisor to study performance of large applications will be presented. This demonstrates an effective optimization strategy that has enabled these science applications to achieve up to 4.6 times speed-up and prepare for future exascale architectures. # Goal/Relevance of Session The roofline model [1,2] is a powerful tool for analyzing the performance of applications with respect to the theoretical peak achievable on a given computer architecture. It allows one to graphically represent the performance of an application in terms of operational intensity, i.e. the ratio of flops performed and bytes moved from memory in order to guide optimization efforts. Given the scale and complexity of modern science applications, it can often be a tedious task for the user to perform the analysis on the level of functions or loops to identify where performance gains can be made. With new Intel tools, it is now possible to automate this task, as well as base the estimates of peak performance on measurements rather than vendor specifications. The goal of this session is to demonstrate how the roofline feature of Intel Advisor can be used to balance memory vs. computation related optimization efforts and effectively identify performance bottlenecks. A series of typical optimization techniques: cache blocking, structure refactoring, data alignment, and vectorization illustrated by the kernel cases will be addressed. # Description of the codes ## XGC1 The XGC1 code [3] is a magnetic fusion Particle-In-Cell code that uses an unstructured mesh for its Poisson solver that allows it to accurately resolve the edge plasma of a magnetic fusion device. After recent optimizations to its collision kernel [4], most of the computing time is spent in the electron push (pushe) kernel, where these optimization efforts have been focused. The kernel code scaled well with MPI+OpenMP but had almost no automatic compiler vectorization, in part due to indirect memory addresses and in part due to low trip counts of low-level loops that would be candidates for vectorization. Particle blocking and sorting have been implemented to increase trip counts of low-level loops and improve memory locality, and OpenMP directives have been added to vectorize compute-intensive loops that were identified by Advisor. The optimizations have improved the performance of the pushe kernel 2x on Haswell processors and 1.7x on KNL. The KNL node-for-node performance has been brought to within 30% of a NERSC Cori phase I Haswell node and we expect to bridge this gap by reducing the memory footprint of compute intensive routines to improve cache reuse. ## PICSAR is a Fortran/Python high-performance Particle-In-Cell library targeting at MIC architectures first designed to be coupled with the PIC code WARP for the simulation of laser-matter interaction and particle accelerators. PICSAR also contains a FORTRAN stand-alone kernel for performance studies and benchmarks. A MPI domain decomposition is used between NUMA domains and a tile decomposition (cache-blocking) handled by OpenMP has been added for shared-memory parallelism and better cache management. The so-called current deposition and field gathering steps that compose the PIC time loop constitute major hotspots that have been rewritten to enable more efficient vectorization. Particle communications between tiles and MPI domain has been merged and parallelized. All considered, these improvements provide speedups of 3.1 for order 1 and 4.6 for order 3 interpolation shape factors on KNL configured in SNC4 quadrant flat mode. Performance is similar between a node of cori phase 1 and KNL at order 1 and better on KNL by a factor 1.6 at order 3 with the considered test case (homogeneous thermal plasma).

97 MATHEMATICS AND COMPUTING↗

Advanced Data Structures for Improved Cyber Resilience and Awareness in Untrusted Environments: LDRD Report

This report summarizes the work performed under the project "Advanced Data Structures for Improved Cyber Resilience and Awareness in Untrusted Environments." The goal of the project was to design, analyze, and test new data structures for cybersecurity applications. We had two major thrusts: 1) using new/improved write-optimized data structures and/or algorithms to better man- age and analyze high-speed massive-volume cyberstreams, and 2) adding security features to data structures at minimum cost. Write optimization allows data structures to better use secondary memory to store and search a larger amount of useful information. Secondary memory is large compared to main memory, but data movement to and from secondary memory must be carefully managed to run quickly enough to keep up with fast streams. The first thrust included managing cyberstreams in parallel, both multi-threaded and distributed, and improving the benchmarking infrastructure for testing new streaming data structures. We considered both (near) real-time discovery of particular patterns, and improved logging for improved forensics. We considered two kinds of security-feature problem. The first was high-performance history- independent external-memory data structures. These provide certain protections to data if a disk is stolen. We also prove some trade-offs between speed and security in this setting. The second data-security problem is more secure data look-up in secret-shared data bases. This report summarizes the project's major accomplishments, with the background to under- stand these accomplishments. It gathers the abstracts and references for the six refereed publications that have appeared as part of this work. We summarize several accomplishments that will be submitted for publication. We then archive one piece of partial work that is not likely to be published in the near future: validation of history-independent data structure implementations.

97 MATHEMATICS AND COMPUTING↗

LDRD final report : managing shared memory data distribution in hybrid HPC applications.

MPI is the dominant programming model for distributed memory parallel computers, and is often used as the intra-node programming model on multi-core compute nodes. However, application developers are increasingly turning to hybrid models that use threading within a node and MPI between nodes. In contrast to MPI, most current threaded models do not require application developers to deal explicitly with data locality. With increasing core counts and deeper NUMA hierarchies seen in the upcoming LANL/SNL 'Cielo' capability supercomputer, data distribution poses an upper boundary on intra-node scalability within threaded applications. Data locality therefore has to be identified at runtime using static memory allocation policies such as first-touch or next-touch, or specified by the application user at launch time. We evaluate several existing techniques for managing data distribution using micro-benchmarks on an AMD 'Magny-Cours' system with 24 cores among 4 NUMA domains and argue for the adoption of a dynamic runtime system implemented at the kernel level, employing a novel page table replication scheme to gather per-NUMA domain memory access traces.

99 GENERAL AND MISCELLANEOUS↗

FastPM: a new scheme for fast simulations of dark matter and haloes

We introduce FASTPM, a highly scalable approximated particle mesh (PM) N-body solver, which implements the PM scheme enforcing correct linear displacement (1LPT) evolution via modified kick and drift factors. Employing a two-dimensional domain decomposing scheme, FASTPM scales extremely well with a very large number of CPUs. In contrast to Comoving-Lagrangian (COLA) approach, we do not require to split the force or track separately the 2LPT solution, reducing the code complexity and memory requirements. We compare FASTPM with different number of steps (N s ) and force resolution factor (B) against three benchmarks: halo mass function from friends-of-friends halo finder; halo and dark matter power spectrum; and cross-correlation coefficient (or stochasticity), relative to a high-resolution TREEPM simulation. We show that the modified time stepping scheme reduces the halo stochasticity when compared to COLA with the same number of steps and force resolution. While increasing N s and B improves the transfer function and cross-correlation coefficient, for many applications FASTPM achieves sufficient accuracy at low N s and B. For example, N s = 10 and B = 2 simulation provides a substantial saving (a factor of 10) of computing time relative to N s = 40, B = 3 simulation, yet the halo benchmarks are very similar at z = 0. We find that for abundance matched haloes the stochasticity remains low even for N s = 5. FASTPM compares well against less expensive schemes, being only 7 (4) times more expensive than 2LPT initial condition generator for N s = 10 (N s = 5). Some of the applications where FASTPM can be useful are generating a large number of mocks, producing non-linear statistics where one varies a large number of nuisance or cosmological parameters, or serving as part of an initial conditions solver.

79 ASTRONOMY AND ASTROPHYSICS↗

Understanding the Performance and Potential of Cloud Computing for Scientific Applications

In this paper, commercial clouds bring a great opportunity to the scientific computing area. Scientific applications usually require significant resources, however not all scientists have access to sufficient high-end computing systems, may of which can be found in the Top500 list. Cloud Computing has gained the attention of scientists as a competitive resource to run HPC applications at a potentially lower cost. But as a different infrastructure, it is unclear whether clouds are capable of running scientific applications with a reasonable performance per money spent. This work studies the performance of public clouds and places this performance in context to price. We evaluate the raw performance of different services of AWS cloud in terms of the basic resources, such as compute, memory, network and I/O. We also evaluate the performance of the scientific applications running in the cloud. This paper aims to assess the ability of the cloud to perform well, as well as to evaluate the cost of the cloud running scientific applications. We developed a full set of metrics and conducted a comprehensive performance evlauation over the Amazon cloud. We evaluated EC2, S3, EBS and DynamoDB among the many Amazon AWS services. We evaluated the memory sub-system performance with CacheBench, the network performance with iperf, processor and network performance with the HPL benchmark application, and shared storage with NFS and PVFS in addition to S3. We also evaluated a real scientific computing application through the Swift parallel scripting system at scale. Armed with both detailed benchmarks to gauge expected performance and a detailed monetary cost analysis, we expect this paper will be a recipe cookbook for scientists to help them decide where to deploy and run their scientific applications between public clouds, private clouds, or hybrid clouds.

97 MATHEMATICS AND COMPUTING↗

Direction-optimizing Label Propagation Framework for Structure Detection in Graphs: Design, Implementation, and Experimental Analysis

Label Propagation is not only a well-known machine learning algorithm for classification but also an effective method for discovering communities and connected components in networks. We propose a new Direction-optimizing Label Propagation Algorithm (DOLPA) framework that enhances the performance of the standard Label Propagation Algorithm (LPA), increases its scalability, and extends its versatility and application scope. As a central feature, the DOLPA framework relies on the use of frontiers and alternates between label push and label pull operations to attain high performance. It is formulated in such a way that the same basic algorithm can be used for finding communities or connected components in graphs by only changing the objective function used. Additionally, DOLPA has parameters for tuning the processing order of vertices in a graph to reduce the number of edges visited and improve the quality of solution obtained. We present the design and implementation of the enhanced algorithm as well as our shared-memory parallelization of it using OpenMP. We also present an extensive experimental evaluation of our implementations using the LFR benchmark and real-world networks drawn from various domains. Compared with an implementation of LPA for community detection available in a widely used network analysis software, we achieve at most five times the F-Score while maintaining similar runtime for graphs with overlapping communities. We also compare DOLPA against an implementation of the Louvain method for community detection using the same LFR-graphs and show that DOLPA achieves about three times the F-Score at just 10% of the runtime. For connected component decomposition, our algorithm achieves orders of magnitude speedups over the basic LP-based algorithm on large-diameter graphs, up to 13.2× speedup over the Shiloach-Vishkin algorithm, and up to 1.6× speedup over Afforest on an Intel Xeon processor using 40 threads.

97 MATHEMATICS AND COMPUTING↗

GraphBench

GraphBench is a benchmark suite for graph pattern mining and graph analysis systems. The benchmark suite is a significant addition to conducting apples-apples comparison of graph analysis software (databases, in-memory tools, triple stores, etc.)

Sukumar, SreenivasR.↗

A uGNI-Based Asynchronous Message-driven Runtime System for Cray Supercomputers with Gemini Interconnect

Gemini as the network for new Cray XE/XT systems features low latency, high bandwidth and strong scalability. Its hardware support for remote direct memory access enables efficient implementation of the global address space programming languages. Although the Generic Network Interface (GNI) is designed to support message-passing applications, it is still challenging to attain good performance for applications written in alternative programming models, such as the message-driven programming model. In our earlier work we showed that CHARM++, an object-oriented message-driven programming model, scales up to the full Jaguar Cray machine. In this paper, we describe a general and light-weight asynchronous Low-level RunTime System (LRTS) for CHARM+, and its implementation on the uGNI software stack for Cray XE systems. Several techniques are presented to exploit the uGNI capability by reducing memory copy and registration overhead, taking advantage of persistent communication, and improving intra-node communication. Our micro-benchmark results demonstrate that the uGNI-based runtime system outperforms the MPI-based implementation by up to 50% in terms of message latency. For communication intensive applications such as N-Queens, this implementation scales up to 15,360 cores of a Cray XE6 machine and is 70% faster than an MPI-based implementation. In molecular dynamics application NAMD, the performance is also considerably improved by as high as 18%.

Asynchronous message-passing↗

GraphBench

GraphBench is a benchmark suite for graph pattern mining and graph analysis systems. The benchmark suite is a significant addition to conducting apples-apples comparison of graph analysis software (databases, in-memory tools, triple stores, etc.)

Sukumar, Sreenivas R.↗

PIPS-SBB: A Parallel Distributed-Memory Branch-and-Bound Algorithm for Stochastic Mixed-Integer Programs

Stochastic mixed-integer programs (SMIPs) deal with optimization under uncertainty at many levels of the decision-making process. When solved as extensive formulation mixed- integer programs, problem instances can exceed available memory on a single workstation. In order to overcome this limitation, we present PIPS-SBB: a distributed-memory parallel stochastic MIP solver that takes advantage of parallelism at multiple levels of the optimization process. We also show promising results on the SIPLIB benchmark by combining methods known for accelerating Branch and Bound (B&B) methods with new ideas that leverage the structure of SMIPs. Finally, we expect the performance of PIPS-SBB to improve further as more functionality is added in the future.

97 MATHEMATICS AND COMPUTING↗

Conditional Point Sampling: A Monte Carlo Method for Radiation Transport in Stochastic Media.

Current methods for stochastic media transport are either computationally expensive or, by nature, approximate. Moreover, none of the well-developed, benchmarked approximate methods can compute the variance caused by the stochastic mixing, a quantity especially important to safety calculations. Therefore, we derive and apply a new conditional probability function (CPF) for use in the recently developed stochastic media transport algorithm Conditional Point Sampling (CoPS), which 1) leverages the full intra-particle memory of CoPS to yield errorless computation of stochastic media outputs in 1D, binary, Markovian-mixed media, and 2) leverages the full inter-particle memory of CoPS and the recently developed Embedded Variance Deconvolution method to yield computation of the variance in transport outputs caused by stochastic material mixing. Numerical results demonstrate errorless stochastic media transport as compared to reference benchmark solutions with the new CPF for this class of stochastic mixing as well as the ability to compute the variance caused by the stochastic mixing via CoPS. Using previously derived, non-errorless CPFs, CoPS is further found to be more accurate than the atomic mix approximation, Chord Length Sampling (CLS), and most of memory-enhanced versions of CLS surveyed. In addition, we study the compounding behavior of CPF error as a function of cohort size (where a cohort is a group of histories that share intra-particle memory) and recommend that small cohorts be used when computing the variance in transport outputs caused by stochastic mixing.

61 RADIATION PROTECTION AND DOSIMETRY↗