Search NASA⌕ Search

SEARCH · Search NASA

Results for “Memory 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 163 records · Page 9

miniVite: A Graph Analytics Benchmarking Tool for Massively Parallel Systems

Benchmarking of high performance computing sys-tems can help provide critical insights for ef?cient design of computing systems and software applications. Although a large number of tools for benchmarking exist, there is a lack of rep-resentative benchmarks for the class of irregular computations as exempli?ed by graph analytics. In this paper, we propose miniVite as a representative graph analytics benchmark tool to test a variety of distributed-memory systems. Graph clustering, popularly known as community detection, is a prototypical graph operation used in numerous scienti?c computing and analytics applications. The goal of clustering is to partition a graph into clusters (or communities) such that each cluster consists of vertices that are densely connected within the cluster and sparsely connected to the rest of the graph. Modu-larity optimization is a popular technique for identifying clusters in a graph. Ef?cient parallelization of modularity optimization-based algorithms is challenging. One successful approach was conceived in Vite, a distributed-memory implementation of the Louvain algorithm that incorporates several heuristics. We introduce miniVite as a representative but simpli?ed variant of Vite, to serve as a prototypical graph analytics benchmarking tool. Unlike other graph-based methods such as breadth-?rst search and betweenness centrality, miniVite represents highly complex computational patterns stressing a variety of system features, which can provide crucial insight for co-design of future computing systems.

community detection, parallel, MPI↗

An OpenACC-Based Unified Programming Model for Multi-accelerator Systems

This paper proposes a novel SPMD programming model of OpenACC. Our model integrates the different granularities of parallelism from vector-level parallelism to node-level parallelism into a single, unified model based on OpenACC. It allows programmers to write programs for multiple accelerators using a uniform programming model whether they are in shared or distributed memory systems. We implement a prototype of our model and evaluate its performance with a GPU-based supercomputer using three benchmark applications.

Accelerators↗

Understanding the Interplay between Hardware Errors and User Job Characteristics on the Titan Supercomputer

Designing dependable supercomputers begins with an understanding of errors in real-world, large-scale systems. The Titan supercomputer at Oak Ridge National Laboratory provides a unique opportunity to investigate errors when an actual system is actively used by multiple concurrent users and workloads from diverse domains at varying scales. This study presents a thorough analysis of 6, 908, 497 hardware errors from 18, 688 compute nodes of Titan for 312, 215 user jobs over a 3-year time period. Through careful joining of two system logs – the Machine Check Architecture (MCA) log and the job scheduler log – we show the correlated pattern of hardware errors for each job and user, in addition to individual descriptive statistics of errors, jobs, and users. Since the majority of hardware errors are memory errors, this study also shows the importance of error correcting in memory systems.

Lim, Seung-Hwan↗

Dynamics of the stochastic Lorenz chaotic system with long memory effects

Little seems to be known about the ergodic dynamics of stochastic systems with fractional noise. This paper is devoted to discern such long time dynamics through the stochastic Lorenz chaotic system (SLCS) with long memory effects. By a truncation technique, the SLCS is proved to generate a continuous stochastic dynamical system Λ. Based on the Krylov-Bogoliubov criterion, the required Lyapunov function is further established to ensure the existence of the invariant measure of Λ. Meanwhile, the uniqueness of the invariant measure of Λ is proved by examining the strong Feller property, together with an irreducibility argument. Therefore, the SLCS has exactly one adapted stationary solution.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Design and testing of the first 2D Prototype Vertically Integrated Pattern Recognition Associative Memory

An associative memory-based track finding approach has been proposed for a Level 1 tracking trigger to cope with increasing luminosities at the LHC. The associative memory uses a massively parallel architecture to tackle the intrinsically complex combinatorics of track finding algorithms, thus avoiding the typical power law dependence of execution time on occupancy and solving the pattern recognition in times roughly proportional to the number of hits. This is of crucial importance given the large occupancies typical of hadronic collisions. The design of an associative memory system capable of dealing with the complexity of HL-LHC collisions and with the short latency required by Level 1 triggering poses significant, as yet unsolved, technical challenges. For this reason, an aggressive R&D program has been launched at Fermilab to advance state of-the-art associative memory technology, the so called VIPRAM (Vertically Integrated Pattern Recognition Associative Memory) project. The VIPRAM leverages emerging 3D vertical integration technology to build faster and denser Associative Memory devices. The first step is to implement in conventional VLSI the associative memory building blocks that can be used in 3D stacking, in other words, the building blocks are laid out as if it is a 3D design. In this paper, we report on the first successful implementation of a 2D VIPRAM demonstrator chip (protoVIPRAM00). The results show that these building blocks are ready for 3D stacking.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Early Performance Results on 4th Gen Intel(R) Xeon (R) Scalable Processors with DDR and Intel(R) Xeon(R) processors, codenamed Sapphire Rapids with HBM

The Crossroads supercomputer was designed to simulate some of the most complex physical devices in the world. These simulations routinely require 1/2 petabyte or more of system memory running on thousands of compute nodes for months at a time on the most powerful supercomputers. Improvements in time to solutions for these workloads can have major impact on our mission capabilities. In this paper we present early results of representative application workloads on 4th Gen Intel Xeon and Intel Xeon Processors codenamed Sapphire Rapids with HBM. These results demonstrate an extremely promising 8.57x improvement (node to node) over our prior generation Intel Broadwell (BDW) based HPC systems. No code modifications were required to achieve this speedup, providing a compelling path forward toward major reductions in time to solution and the complexity of physical systems that can be simulated in the future.

97 MATHEMATICS AND COMPUTING↗

Hardware Evaluation Outreach: Application development Challenges Now and for the Exascale Era

The intent of this document is to assist the programmer in understanding details of contemporary and Exascale hardware system design and how these designs provide opportunities and place constraints on next-generation simulation software design. We attempt to clarify hardware organization and component details for our most current and Exascale systems to help program developers understand how software needs to change in order to take best advantage of the performance available. Exascale success is specifically defined for ECP as a 50x improvement over baseline in the aggregate "capability volume" on several KPP axes, of which raw floating point performance is only one, but also includes characteristics such as problem size, system memory size, node memory size, power, and efficiency. This multi-axis approach is particularly important to understand in the context of delivered improvements in real applications, since, for instance, the floating point computation may comprise less than 10% of the actual computational work required. Given the Exascale requirements and the constraints these requirements put on the performance expectations of fundamental system components, the programmer will be forced to re-think several application implementation details in order to achieve exaflop performance on these systems. The remainder of this document aims to present more detail on Exascale era system hardware and the specific areas that the programmer should address to extract performance from these systems. We attempt to give the programmer guidance at both a high- and low-level, providing some abstract suggestions on how to refactor codes given the expected system architectures and some low-level recommendations on how to implement these modifications. We also include a section on training resources that are helpful for both programmers that are just beginning to understand code modifications for contemporary and Exascale systems and for those that have done some refactoring and are now trying to extract maximal application performance from these systems.

97 MATHEMATICS AND COMPUTING↗

Exploring Hardware Support For Scaling Irregular Applications on Multi-node Multi-core Architectures

With the recent emergence of large-scale knowledge dis- covery, data mining and social network analysis, irregular applications have gained renewed interest. Classic cache-based high-performance architectures do not provide optimal performances with such kind of workloads, mainly due to the very low spatial and temporal locality of the irregular control and memory access patterns. In this paper, we present a multi-node, multi-core, fine-grained multi-threaded shared-memory system architecture specifically designed for the execution of large-scale irregular applications, and built on top of three pillars, that we believe are fundamental to support these workloads. First, we offer transparent hardware support for Partitioned Global Address Space (PGAS) to provide a large globally-shared address space with no software library overhead. Second, we employ multi-threaded multi-core processing nodes to achieve the necessary latency tolerance required by accessing global memory, which potentially resides in a remote node. Finally, we devise hardware support for inter-thread synchronization on the whole global address space. We first model the performances by using an analytical model that takes into account the main architecture and application characteristics. We describe the hardware design of the proposed cus- tom architectural building blocks that provide support for the above- mentioned three pillars. Finally, we present a limited-scale evaluation of the system on a multi-board FPGA prototype with typical irregular kernels and benchmarks. The experimental evaluation demonstrates the architecture performance scalability for different configurations of the whole system.

FPGA↗

Design and performance of a scalable, parallel statistics toolkit.

Most statistical software packages implement a broad range of techniques but do so in an ad hoc fashion, leaving users who do not have a broad knowledge of statistics at a disadvantage since they may not understand all the implications of a given analysis or how to test the validity of results. These packages are also largely serial in nature, or target multicore architectures instead of distributed-memory systems, or provide only a small number of statistics in parallel. This paper surveys a collection of parallel implementations of statistics algorithm developed as part of a common framework over the last 3 years. The framework strategically groups modeling techniques with associated verification and validation techniques to make the underlying assumptions of the statistics more clear. Furthermore it employs a design pattern specifically targeted for distributed-memory parallelism, where architectural advances in large-scale high-performance computing have been focused. Moment-based statistics (which include descriptive, correlative, and multicorrelative statistics, principal component analysis (PCA), and k-means statistics) scale nearly linearly with the data set size and number of processes. Entropy-based statistics (which include order and contingency statistics) do not scale well when the data in question is continuous or quasi-diffuse but do scale well when the data is discrete and compact. We confirm and extend our earlier results by now establishing near-optimal scalability with up to 10,000 processes.

99 GENERAL AND MISCELLANEOUS↗

Fundamental Mechanisms Driving the Amorphous to Crystalline Phase Transformation

Phase transformations are ubiquitous, fundamental phenomena that lie at the heart of many structural, optical and electronic properties in condensed matter physics and materials science. Many transformations, especially those occurring under extreme conditions such as rapid changes in the thermodynamic state, are controlled by poorly understood processes involving the nucleation and quenching of metastable phases. Typically these processes occur on time and length scales invisible to most experimental techniques ({micro}s and faster, nm and smaller), so our understanding of the dynamics tends to be very limited and indirect, often relying on simulations combined with experimental study of the ''time infinity'' end state. Experimental techniques that can directly probe phase transformations on their proper time and length scales are therefore key to providing fundamental insights into the whole area of transformation physics and materials science. LLNL possesses a unique dynamic transmission electron microscope (DTEM) capable of taking images and diffraction patterns of laser-driven material processes with resolution measured in nanometers and nanoseconds. The DTEM has previously used time-resolved diffraction patterns to quantitatively study phase transformations that are orders of magnitude too fast for conventional in situ TEM. More recently the microscope has demonstrated the ability to directly image a reaction front moving at {approx}13 nm/ns and the nucleation of a new phase behind that front. Certain compound semiconductor phase change materials, such as Ge{sub 2}Sb{sub 2}Te{sub 5} (GST), Sb{sub 2}Te and GeSb, exhibit a technologically important series of transformations on scales that fall neatly into the performance specifications of the DTEM. If a small portion of such material is heated above its melting point and then rapidly cooled, it quenches into an amorphous state. Heating again with a less intense pulse leads to recrystallization into a vacancy-stabilized metastable rock salt structure. Each transformation takes {approx}10-100 ns, and the cycle can be driven repeatedly a very large number of times with a nanosecond laser such as the DTEM's sample drive laser. These materials are widely used in optical storage devices such as rewritable CDs and DVDs, and they are also applied in a novel solid state memory technology - phase change memory (PCM). PCM has the potential to produce nonvolatile memory systems with high speed, extreme density, and very low power requirements. For PCM applications several materials properties are of great importance: the resistivities of both phases, the crystallization temperature, the melting point, the crystallization speed, reversibility (number of phase-transformation cycles without degradation) and stability against crystallization at elevated temperature. For a viable technology, all these properties need to have good scaling behavior, as dimensions of the memory cells will shrink with every generation. In this LDRD project, we used the unique single-shot nanosecond in situ experimentation capabilities of the DTEM to watch these transformations in GST on the time and length scales most relevant for device applications. Interpretation of the results was performed in conjunction with atomistic and finite-element computations. Samples were provided by collaborators at IBM and Stanford University. We observed, and measured the kinetics of, the amorphous-crystalline and melting-solidification transitions in uniform thin-film samples. Above a certain threshold, the crystal nucleation rate was found to be enormously high (with many nuclei appearing per cubic {micro}m even after nanosecond-scale incubation times), in agreement with atomistic simulation and consistent with an extremely low nucleation barrier. We developed data reduction techniques based on principal component analysis (PCA), revealing the complex, multi-dimensional evolution of the material while suppressing noise and irrelevant information. Using a novel specimen geometry, we also achieved repeated switching between the amorphous and crystalline phases enabling in situ study of structural change after phase cycling, which is relevant to device performance. We also observed the coupling between the phase transformations and the evolution of morphology on the nanometer scale, revealing the gradual development of striations in uniform films and preferential melting at sharp edges in laser-heated nanopatterned GST. This nonuniform melting, interpreted through simulation as being a direct result of geometrical laser absorption effects, appears to be responsible for a marked loss in morphological stability even at moderate laser intensities and may be an important factor in the longevity of nanostructured phase change materials in memory applications.

36 MATERIALS SCIENCE↗

A Next-Generation Parallel File System Environment for the OLCF

When deployed in 2008/2009 the Spider system at the Oak Ridge National Laboratory s Leadership Computing Facility (OLCF) was the world s largest scale Lustre parallel file system. Envisioned as a shared parallel file system capable of delivering both the bandwidth and capacity requirements of the OLCF s diverse computational environment, Spider has since become a blueprint for shared Lustre environments deployed worldwide. Designed to support the parallel I/O requirements of the Jaguar XT5 system and other smallerscale platforms at the OLCF, the upgrade to the Titan XK6 heterogeneous system will begin to push the limits of Spider s original design by mid 2013. With a doubling in total system memory and a 10x increase in FLOPS, Titan will require both higher bandwidth and larger total capacity. Our goal is to provide a 4x increase in total I/O bandwidth from over 240GB=sec today to 1TB=sec and a doubling in total capacity. While aggregate bandwidth and total capacity remain important capabilities, an equally important goal in our efforts is dramatically increasing metadata performance, currently the Achilles heel of parallel file systems at leadership. We present in this paper an analysis of our current I/O workloads, our operational experiences with the Spider parallel file systems, the high-level design of our Spider upgrade, and our efforts in developing benchmarks that synthesize our performance requirements based on our workload characterization studies.

99 GENERAL AND MISCELLANEOUS↗

Recent developments in DYNSUB: New models, code optimization and parallelization

DYNSUB is a high-fidelity coupled code system consisting of the reactor simulator DYN3D and the sub-channel code SUBCHANFLOW. It describes nuclear reactor core behavior with pin-by-pin resolution for both steady-state and transient scenarios. In the course of the coupled code system's active development, super-homogenization (SPH) and generalized equivalence theory (GET) discontinuity factors may be computed with and employed in DYNSUB to compensate pin level homogenization errors. Because of the largely increased numerical problem size for pin-by-pin simulations, DYNSUB has bene fitted from HPC techniques to improve its numerical performance. DYNSUB's coupling scheme has been structurally revised. Computational bottlenecks have been identified and parallelized for shared memory systems using OpenMP. Comparing the elapsed time for simulating a PWR core with one-eighth symmetry under hot zero power conditions applying the original and the optimized DYNSUB using 8 cores, overall speed up factors greater than 10 have been observed. The corresponding reduction in execution time enables a routine application of DYNSUB to study pin level safety parameters for engineering sized cases in a scientific environment. (authors)

97 MATHEMATICS AND COMPUTING↗

Tuning collective communication for Partitioned Global Address Space programming models

Partitioned Global Address Space (PGAS) languages offer programmers the convenience of a shared memory programming style combined with locality control necessary to run on large-scale distributed memory systems. Even within a PGAS language programmers often need to perform global communication operations such as broadcasts or reductions, which are best performed as collective operations in which a group of threads work together to perform the operation. In this study we consider the problem of implementing collective communication within PGAS languages and explore some of the design trade-offs in both the interface and implementation. In particular, PGAS collectives have semantic issues that are different than in send–receive style message passing programs, and different implementation approaches that take advantage of the one-sided communication style in these languages. We present an implementation framework for PGAS collectives as part of the GASNet communication layer, which supports shared memory, distributed memory and hybrids. The framework supports a broad set of algorithms for each collective, over which the implementation may be automatically tuned. In conclusion, we demonstrate the benefit of optimized GASNet collectives using application benchmarks written in UPC, and demonstrate that the GASNet collectives can deliver scalable performance on a variety of state-of-the-art parallel machines including a Cray XT4, an IBM BlueGene/P, and a Sun Constellation system with InfiniBand interconnect.

97 MATHEMATICS AND COMPUTING↗

Performance of particle in cell methods on highly concurrent computational architectures

Particle in cell (PIC) methods are effective in computing Vlasov-Poisson system of equations used in simulations of magnetic fusion plasmas. PIC methods use grid based computations, for solving Poisson’s equation or more generally Maxwell’s equations, as well as Monte-Carlo type methods to sample the Vlasov equation. The presence of two types of discretizations, deterministic field solves and Monte-Carlo methods for the Vlasov equation, pose challenges in understanding and optimizing performance on today large scale computers which require high levels of concurrency. These challenges arises from the need to optimize two very different types of processes and the interactions between them. Modern cache based high-end computers have very deep memory hierarchies and high degrees of concurrency which must be utilized effectively to achieve good performance. The effective use of these machines requires maximizing concurrency by eliminating serial or redundant work and minimizing global communication. A related issue is minimizing the memory traffic between levels of the memory hierarchy because performance is often limited by the bandwidths and latencies of the memory system. This paper discusses some of the performance issues, particularly in regard to parallelism, of PIC methods. The gyrokinetic toroidal code (GTC) is used for these studies and a new radial grid decomposition is presented and evaluated. Scaling of the code is demonstrated on ITER sized plasmas with up to 16K Cray XT3/4 cores.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Memory and rejuvenation in glassy systems

Here, the memory effect in a single crystal spin glass (Cu 0.92 Mn 0.08 ) has been measured using 1 Hz ac susceptibility measurements over a reduced temperature range of 0.4 - 0.7 T g and a model of the memory effect has been developed. A double-waiting-time protocol is carried out where the spin glass is first allowed to age at a temperature below T g , T w$_{1}$ , followed by a second aging 4 K lower, T w$_{2}$ . The 4 K separation is sufficient to ensure rejuvenation has occurred. The model is based on calculating overlaps between the growth of the correlation lengths at the two temperatures. It accounts for the absolute magnitude of the memory effect as a function of both waiting times and temperatures. The data can be explained by the memory loss being a function of the relative change in the correlated volume at the first waiting temperature due to growth in the correlations at the second waiting temperature.

36 MATERIALS SCIENCE↗

A matrix-algebraic formulation of distributed-memory maximal cardinality matching algorithms in bipartite graphs

We describe parallel algorithms for computing maximal cardinality matching in a bipartite graph on distributed-memory systems. Unlike traditional algorithms that match one vertex at a time, our algorithms process many unmatched vertices simultaneously using a matrix-algebraic formulation of maximal matching. This generic matrix-algebraic framework is used to develop three efficient maximal matching algorithms with minimal changes. The newly developed algorithms have two benefits over existing graph-based algorithms. First, unlike existing parallel algorithms, cardinality of matching obtained by the new algorithms stays constant with increasing processor counts, which is important for predictable and reproducible performance. Second, relying on bulk-synchronous matrix operations, these algorithms expose a higher degree of parallelism on distributed-memory platforms than existing graph-based algorithms. We report high-performance implementations of three maximal matching algorithms using hybrid OpenMP-MPI and evaluate the performance of these algorithm using more than 35 real and randomly generated graphs. On real instances, our algorithms achieve up to 200 × speedup on 2048 cores of a Cray XC30 supercomputer. Even higher speedups are obtained on larger synthetically generated graphs where our algorithms show good scaling on up to 16,384 cores.

97 MATHEMATICS AND COMPUTING↗

Performance of particle in cell methods on highly concurrent computational architectures

Particle in cell (PIC) methods are effective in computing Vlasov-Poisson system of equations used in simulations of magnetic fusion plasmas. PIC methods use grid based computations, for solving Poisson’s equation or more generally Maxwell’s equations, as well as Monte-Carlo type methods to sample the Vlasov equation. The presence of two types of discretizations, deterministic field solves and Monte-Carlo methods for the Vlasov equation, pose challenges in understanding and optimizing performance on today large scale computers which require high levels of concurrency. These challenges arises from the need to optimize two very different types of processes and the interactions between them. Modern cache based high-end computers have very deep memory hierarchies and high degrees of concurrency which must be utilized effectively to achieve good performance. The effective use of these machines requires maximizing concurrency by eliminating serial or redundant work and minimizing global communication. A related issue is minimizing the memory traffic between levels of the memory hierarchy because performance is often limited by the bandwidths and latencies of the memory system. This paper discusses some of the performance issues, particularly in regard to parallelism, of PIC methods. The gyrokinetic toroidal code (GTC) is used for these studies and a new radial grid decomposition is presented and evaluated. Scaling of the code is demonstrated on ITER sized plasmas with up to 16K Cray XT3/4 cores.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

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↗