Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel computer architecture”

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 595 records · Page 33

MIC-SVM: Designing A Highly Efficient Support Vector Machine For Advanced Modern Multi-Core and Many-Core Architectures

Support Vector Machine (SVM) has been widely used in data-mining and Big Data applications as modern commercial databases start to attach an increasing importance to the analytic capabilities. In recent years, SVM was adapted to the field of High Performance Computing for power/performance prediction, auto-tuning, and runtime scheduling. However, even at the risk of losing prediction accuracy due to insufficient runtime information, researchers can only afford to apply offline model training to avoid significant runtime training overhead. To address the challenges above, we designed and implemented MICSVM, a highly efficient parallel SVM for x86 based multi-core and many core architectures, such as the Intel Ivy Bridge CPUs and Intel Xeon Phi coprocessor (MIC).

42 ENGINEERING↗

An inertia-free filter line-search algorithm for large-scale nonlinear programming

We present a filter line-search algorithm that does not require inertia information of the linear system. This feature enables the use of a wide range of linear algebra strategies and libraries, which is essential to tackle large-scale problems on modern computing architectures. The proposed approach performs curvature tests along the search step to detect negative curvature and to trigger convexification. We prove that the approach is globally convergent and we implement the approach within a parallel interior-point framework to solve large-scale and highly nonlinear problems. Our numerical tests demonstrate that the inertia-free approach is as efficient as inertia detection via symmetric indefinite factorizations. We also demonstrate that the inertia-free approach can lead to reductions in solution time because it reduces the amount of convexification needed.

Chiang, Nai-Yuan↗

Kokkos Version 2.0

The Kokkos library implements thread-parallel execution policies and shared-memory multidimensional array data structures that enable applications and domain libraries to develop computational kernels that are performance portable across multicore-CPU and manycore-accelerator (e.g. GPU) computing architectures.

SciDAC↗

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↗

GPU acceleration of all-electron electronic structure theory using localized numeric atom-centered basis functions

We present an implementation of all-electron density-functional theory for massively parallel GPU-based platforms, using localized atom-centered basis functions and real-space integration grids. Special attention is paid to domain decomposition of the problem on non-uniform grids, which enables compute- and memory-parallel execution across thousands of nodes for real-space operations, e.g. the update of the electron density, the integration of the real-space Hamiltonian matrix, and calculation of Pulay forces. To assess the performance of our GPU implementation, we performed benchmarks on three different architectures using a 103-material test set. We find that operations which rely on dense serial linear algebra show dramatic speedups from GPU acceleration: in particular, SCF iterations including force and stress calculations exhibit speedups ranging from 4.5 to 6.6. For the architectures and problem types investigated here, this translates to an expected overall speedup between 3–4 for the entire calculation (including non-GPU accelerated parts), for problems featuring several tens to hundreds of atoms. Additional calculations for a 375-atom Bi2Se3 bilayer show that the present GPU strategy scales for large-scale distributed-parallel simulations.

42 ENGINEERING↗

Motion Planning Algorithms for Safety and Quantum Computing Efficiency

Motion planning remains a fundamental problem in robotics. Sampling-based algorithms use randomization to allow efficient solutions to this complex problem. As mobile robots and autonomous vehicles become more prevalent in everyday life, motion planning must be applied to increasingly challenging scenarios. Safety has become a paramount concern in motion planning for ensuring robotic applications enrich human lives. To date, many motion planning techniques to increase safety in the face of uncertain and dynamic environments have been developed. This dissertation first addresses distributional safety of Rapidly-Exploring Random Trees (RRT) through our algorithm W-Safe RRT. To acknowledge distributional uncertainty and poor modeling, W-Safe RRT uses the Wasserstein metric to provide a probabilistic bound on the distributional distance between a robot and obstacles. Human-interpretable environmental agent classification allows online safety margin adaptation. We propose and analyze an integrating region method for online classification that increases actor labeling accuracy based on behavioral feature values when compared to state of the art methods. The method performs class assignments based on local maximum likelihood in a created behavioral feature-space, allowing a notion of classification uncertainty. Model-based methods with safety guarantees can quickly become computationally in tractable, especially with multiple agents, higher dimensions, and plentiful unknowns. Sampling based algorithms have been parallelized for computation with multi-core computers and GPUs. We consider the use of quantum algorithms and computers for sampling-based motion planning for the first time. Quantum computing performs operations on superpositions of states and can solve certain problems much more efficiently than classical computers, but introduces previously unseen challenges. With Quantum-RRT, we recast the motion planning problem into a database-search structure and use Quantum Amplitude Amplification to find reachable states in the database with a quadratic performance increase over classical methods. We address two error sources with this method: quantum measurement and quantum oracle errors. We then extend this method to Parallel Quantum-RRT, which uses a manager-worker architecture with multiple parallel quantum workers to increase database search efficiency. We compare algorithm architectures and characterize probabilities of multiple workers finding solutions. Lastly, we test in simulation the quantum algorithms against classical versions in a wide variety of scenarios, concluding that a similar parallelization improvement is to be found in the quantum case as was found in the parallelization of classical RRT.

97 MATHEMATICS AND COMPUTING↗

A Faster Parallel Algorithm and Efficient Multithreaded Implementations for Evaluating Betweenness Centrality on Massive Datasets

We present a new lock-free parallel algorithm for computing betweenness centralityof massive small-world networks. With minor changes to the data structures, ouralgorithm also achieves better spatial cache locality compared to previous approaches. Betweenness centrality is a key algorithm kernel in HPCS SSCA#2, a benchmark extensively used to evaluate the performance of emerging high-performance computing architectures for graph-theoretic computations. We design optimized implementations of betweenness centrality and the SSCA#2 benchmark for two hardware multithreaded systems: a Cray XMT system with the Threadstorm processor, and a single-socket Sun multicore server with the UltraSPARC T2 processor. For a small-world network of 134 million vertices and 1.073 billion edges, the 16-processor XMT system and the 8-core Sun Fire T5120 server achieve TEPS scores (an algorithmic performance count for the SSCA#2 benchmark) of 160 million and 90 million respectively, which corresponds to more than a 2X performance improvement over the previous parallel implementations. To better characterize the performance of these multithreaded systems, we correlate the SSCA#2 performance results with data from the memory-intensive STREAM and RandomAccess benchmarks. Finally, we demonstrate the applicability of our implementation to analyze massive real-world datasets by computing approximate betweenness centrality for a large-scale IMDb movie-actor network.

97 MATHEMATICS AND COMPUTING↗

Phoenix: A Scalable Streaming Hypergraph Analysis Framework

We present Phoenix, a scalable hypergraph analytics framework for data analytics and knowledge discovery that was implemented on the leadership class computing platforms at Oak Ridge National Laboratory (ORNL). Our software framework comprises a distributed implementation of a streaming server architecture which acts as a gateway for various hypergraph generators/external sources to connect. Phoenix has the capability to utilize diverse hypergraph generators, including HyGen, a very large-scale hypergraph generator developed by ORNL. Phoenix incorporates specific algorithms for efficient data representation by exploiting hidden structures of the hypergraphs. Our experimental results demonstrate Phoenix’s scalable and stable performance on massively parallel computing platforms. Phoenix’s superior performance is due to the merging of high-performance computing with data analytic.

Kurte, Kuldeep↗

Neuromorphic Graph Algorithms

Graph algorithms enable myriad large-scale applications including cybersecurity, social network analysis, resource allocation, and routing. The scalability of current graph algorithm implementations on conventional computing architectures are hampered by the demise of Moore’s law. We present a theoretical framework for designing and assessing the performance of graph algorithms executing in networks of spiking artificial neurons. Although spiking neural networks (SNNs) are capable of general-purpose computation, few algorithmic results with rigorous asymptotic performance analysis are known. SNNs are exceptionally well-motivated practically, as neuromorphic computing systems with 100 million spiking neurons are available, and systems with a billion neurons are anticipated in the next few years. Beyond massive parallelism and scalability, neuromorphic computing systems offer energy consumption orders of magnitude lower than conventional high-performance computing systems. We employ our framework to design and analyze new spiking algorithms for shortest path and dynamic programming problems. Our neuromorphic algorithms are message-passing algorithms relying critically on data movement for computation. For fair and rigorous comparison with conventional algorithms and architectures, which is challenging but paramount, we develop new models of data-movement in conventional computing architectures. This allows us to prove polynomial-factor advantages, even when we assume a SNN consisting of a simple grid-like network of neurons. To the best of our knowledge, this is one of the first examples of a rigorous asymptotic computational advantage for neuromorphic computing.

97 MATHEMATICS AND COMPUTING↗

ExaSGD: 2022 Kernel Thrust Activities

The Kernel Thrust milestone ADSE22-407 covers the development of device-capable optimization algorithms and solvers technologies required by the ExaSGD project’s software stack in order to solve security-constrained alternating current optimal power flow (SC-ACOPF) problems on emerging exascale architectures. To this extent, in FY22 the main objective of the Kernel Thrust was (i) provide sparse optimization solver that runs efficiently on hardware accelerator devices (i.e., NVIDIA and AMD GPUs) to perform intra-node computations, (ii) strengthen the reliability and increase the performance of the mixed-dense sparse (MDS) solver of HiOp for deployment on the FY22 target architectures, Summit and Crusher, and (iii) increase performance by improving the mathematical algorithm and refining the parallel MPI-based implementation of the coarse-grain parallel solver HiOp-PriDec for capabilities deployment on the FY22 target architectures, Summit and Crusher. This document presents the developments and contributions done by the Kernels Thrust Team in FY22 toward completion of the above-mentioned objectives. These contributions progressed along four main development (sub)thrusts: (1) Design and implementation of a sparse optimization solver for use on hardware accelerators; (2) Improvement of the mathematical algorithm and of the parallel implementation of HiOp-PriDec to ensure readiness and efficient coarse-grain parallelism for FY23 target exascale machine; and (3) Support Software and Application Development Thrusts of the exaSGD project in their deployment of the project’s software stack on AMD- and NVIDIA-based architectures. The development of the sparse optimization solver (thrust 1 above) was new in FY22 and resulted in a new sparse solver in HiOp (available as of version 0.6). The second development thrust was a continuation of the efforts from FY21 and improved the mathematical algorithm and the communication strategy of the HiOp-PriDec solver. The last developement thrust is a large collaborative effort. Namely, the project’s teams from multiple labs (LLNL, PNNL, ORNL, and NREL) performed large-scale demonstration of the ExaSGD software stack, namely the optimization solvers of HiOp interfaced with the modeling front-end ExaGO and the stochastic sampler PowerScenarios. These demonstration efforts solved large-scale instances of the SC-ACOPF challenge problem of medium network sizes (10, 000-bus system) and large number of contingencies on Summit (NVIDIA accelerators) and Crusher (AMD accelerators) systems at ORNL.

97 MATHEMATICS AND COMPUTING↗

Pixel-Resolved Long-Context Learning for Turbulence at Exascale: Resolving Small-scale Eddies Toward the Viscous Limit

Turbulence plays a crucial role in multiphysics applications, including aerodynamics, fusion, and combustion. Accurately capturing turbulence's multiscale characteristics is essential for reliable predictions of multiphysics interactions, but remains a grand challenge even for exascale supercomputers and advanced deep learning models. The extreme-resolution data required to represent turbulence, ranging from billions to trillions of grid points, pose prohibitive computational costs for models based on architectures like vision transformers. To address this challenge, we introduce a multiscale hierarchical Turbulence Transformer that reduces sequence length from billions to a few millions and a novel RingX sequence parallelism approach that enables scalable long-context learning. We perform scaling and science runs on the Frontier supercomputer. Our approach demonstrates excellent performance up to 1.1 EFLOPS on 32,768 AMD GPUs, with a scaling efficiency of 94\%. To our knowledge, this is the first AI model for turbulence that can capture small-scale eddies down to the dissipative range in three-dimensional turbulence at high Reynolds numbers.

Yin, Junqi [ORNL] (ORCID:0000000338435520)↗

Compressed basis GMRES on high-performance graphics processing units

Krylov methods provide a fast and highly parallel numerical tool for the iterative solution of many large-scale sparse linear systems. To a large extent, the performance of practical realizations of these methods is constrained by the communication bandwidth in current computer architectures, motivating the investigation of sophisticated techniques to avoid, reduce, and/or hide the message-passing costs (in distributed platforms) and the memory accesses (in all architectures). This article leverages Ginkgo’s memory accessor in order to integrate a communication-reduction strategy into the (Krylov) GMRES solver that decouples the storage format (i.e., the data representation in memory) of the orthogonal basis from the arithmetic precision that is employed during the operations with that basis. Given that the execution time of the GMRES solver is largely determined by the memory accesses, the cost of the datatype transforms can be mostly hidden, resulting in the acceleration of the iterative step via a decrease in the volume of bits being retrieved from memory. Together with the special properties of the orthonormal basis (whose elements are all bounded by 1), this paves the road toward the aggressive customization of the storage format, which includes some floating-point as well as fixed-point formats with mild impact on the convergence of the iterative process. We develop a high-performance implementation of the “compressed basis GMRES” solver in the Ginkgo sparse linear algebra library using a large set of test problems from the SuiteSparse Matrix Collection. We demonstrate robustness and performance advantages on a modern NVIDIA V100 graphics processing unit (GPU) of up to 50% over the standard GMRES solver that stores all data in IEEE double-precision.

97 MATHEMATICS AND COMPUTING↗

Impact of Quad-core Cray XT4 System and Software Stack on Scientific Computation

An upgrade from dual-core to quad-core AMD processor on the Cray XT system at the Oak Ridge National Laboratory (ORNL) Leadership Computing Facility (LCF) has resulted in significant changes in the hardware and software stack, including a deeper memory hierarchy, SIMD instructions and a multi-core aware MPI library. In this paper, we evaluate impact of a subset of these key changes on large-scale scientific applications. We will provide insights into application tuning and optimization process and report on how different strategies yield varying rates of successes and failures across different application domains. For instance, we demonstrate that the vectorization instructions (SSE) provide a performance boost of as much as 50% on fusion and combustion applications. Moreover, we reveal how the resource contentions could limit the achievable performance and provide insights into how application could exploit Petascale XT5 system's hierarchical parallelism.

99 GENERAL AND MISCELLANEOUS↗

DFT-FE 1.0: A massively parallel hybrid CPU-GPU density functional theory code using finite-element discretization

In this work, we present DFT-FE 1.0, building on DFT-FE 0.6 [Comput. Phys. Commun. 246, 106853 (2020)], to conduct fast and accurate large-scale density functional theory (DFT) calculations (reaching ~ 100,000 electrons) on both many-core CPU and hybrid CPU-GPU computing architectures. This work involves improvements in the real-space formulation—via an improved treatment of the electrostatic interactions that substantially enhances the computational efficiency—as well high-performance computing aspects, including the GPU acceleration of all the key compute kernels in DFT-FE. We demonstrate the accuracy by comparing the ground-state energies, ionic forces and cell stresses on a wide-range of benchmark systems against those obtained from widely used DFT codes. Further, we demonstrate the numerical efficiency of our implementation, which yields ~ 20× CPU-GPU speed-up by using GPU acceleration on hybrid CPU-GPU nodes. Notably, owing to the parallel-scaling of the GPU implementation, we obtain wall-times of 80–140 seconds for full ground-state calculations, with stringent accuracy, on benchmark systems containing ~ 6, 000 – 15,000 electrons.

pseudopotential↗

Portability for GPU-accelerated molecular docking applications for cloud and HPC: can portable compiler directives provide performance across all platforms?

High-throughput structure-based screening of drug-like molecules has become a common tool in biomedical research. Recently, acceleration with graphics processing units (GPUs) has provided a large performance boost for molecular docking programs. Both cloud and high-performance computing (HPC) resources have been used for large screens with molecular docking programs; while NVIDIA GPUs have dominated cloud and HPC resources, new vendors such as AMD and Intel are now entering the field, creating the problem of software portability across different GPUs. Ideally, software productivity could be maximized with portable programming models that are able to maintain high performance across architectures. While in many cases compiler directives have been used as an easy way to offload parallel regions of a CPU-based program to a GPU accelerator, they may also be an attractive programming model for providing portability across different GPU vendors, in which case the porting process may proceed in the reverse direction: from low-level, architecture-specific code to higher-level directive-based abstractions. MiniMDock is a new mini-application (miniapp) designed to capture the essential computational kernels found in molecular docking calculations, such as are used in phar-maceutical drug discovery efforts, in order to test different solutions for porting across GPU architectures. Here we extend MiniMDock to GPU offloading with OpenMP directives, and compare to performance of kernels using CUDA and HIP on NVIDIA and AMD GPUs, respectively, as well as across different compilers, exploring performance bottlenecks. We document this reverse-porting process, from highly optimized device code to a higher-level version using directives, compare code structure, and describe barriers that were overcome in this effort.

Thavappiragasam, Mathialakan↗

A Parallel EM Algorithm for Model-Based Clustering Applied to the Exploration of Large Spatio-Temporal Data

We develop a parallel EM algorithm for multivariate Gaussian mixture models and use it to perform model-based clustering of a large climate data set. Three variants of the EM algorithm are reformulated in parallel and a new variant that is faster is presented. All are implemented using the single program, multiple data (SPMD) programming model, which is able to take advantage of the combined collective memory of large distributed computer architectures to process larger data sets. Displays of the estimated mixture model rather than the data allow us to explore multivariate relationships in a way that scales to arbitrary size data. We study the performance of our methodology on simulated data and apply our methodology to a high resolution climate dataset produced by the community atmosphere model (CAM5). This article has supplementary material online.

Chen, Wei-Chen↗

Fast Uncovering of Graph Communities on a Chip: Toward Scalable Community Detection on Multicore and Manycore Platforms

Graph representations are pervasive in scientific and social computing. They serve as vital tools to model the interplay among different interacting entities. In this paper, we visit the problem of community detection, which is one of the most widely used graph operations toward scientific discovery. Community detection refers to the process of identifying tightly-knit subgroups of vertices in a large graph. These sub-groups (or communities) represent vertices that are tied together through common structure or function. Identification of communities could help in understanding the modular organization of complex networks. However, owing to large data sizes and high computational costs, performing community detection at scale has become increasingly challenging. Here, we present a detailed review and analysis of some of the leading computational methods and implementations developed for executing community detection on modern day multicore and manycore architectures. Our goals are to: a) define the problem of community detection and highlight its scientific significance; b) relate to challenges in parallelizing the operation on modern day architectures; c) provide a detailed report and taxonomical classification of the approaches that have been designed for various architectures; and d) finally, provide insights into the strengths and suitability of different architectures for community detection, and a preview into the future trends of the area. It is our hope that this detailed treatment of community detection on parallel architectures can serve as an exemplar study for extending the application of modern day multicore and manycore architectures to other complex graph applications.

community detection, multithreaded platforms↗