Search NASA⌕ Search

SEARCH · Search NASA

Results for “Threading”

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

Spherical Region Queries on Multicore Architectures

In this short paper, we report the performance of multiple thread-parallel algorithms for spherical region queries on multicore architectures motivated by a challenging data analytics application in materials science. Performances of two tree-based algorithms and a naive algorithm are compared to identify the length scales at which these approaches perform optimally. The optimal algorithm is then used to scale the driving materials science application, which is shown to deliver over 17X speedup using 32 OpenMP threads on data sets containing many millions of atoms.

Lu, Hao↗

The Minos Computing Library: Efficient Parallel Programming for Extremely Heterogeneous Systems

Hardware specialization has become the silver bullet to achieve efficient high performance, from Systems-on-Chip systems, where hardware specialization can be ``extreme'', to large-scale HPC systems. As the complexity of the systems increases, so does the complexity of programming such architectures in a portable way. This work introduces the Minos Computing Library (MCL), as system software, programming model, and programming model runtime that facilitate programming extremely heterogeneous systems. MCL supports the execution of several multi-threaded applications within the same compute node, performs asynchronous execution of application tasks, efficiently balances computation across hardware resources, and provides performance portability. We show that code developed on a personal desktop automatically scales up to fully utilize powerful workstations with 8 GPUs and down to power-efficient embedded systems. MCL provides up to 17.5x speedup over OpenCL on NVIDIA DGX-1 systems and up to 1.88x speedup on single-GPU systems. In multi-application workloads, MCL dynamically resource allocation provides up to 2.43x performance improvement over manual, static allocation of computing resources.

Gioiosa, Roberto↗

Evaluation of OpenAI Codex for HPC Parallel Programming Models Kernel Generation

We evaluate AI-assisted generative capabilities on fundamental numerical kernels in high-performance computing (HPC), including AXPY, GEMV, GEMM, SpMV, Jacobi Stencil, and CG. We test the generated kernel codes for a variety of language-supported programming models, including (1) C++ (e.g., OpenMP [including offload], OpenACC, Kokkos, SyCL, CUDA, and HIP), (2) Fortran (e.g., OpenMP [including offload] and OpenACC), (3) Python (e.g., numpy, Numba, cuPy, and pyCUDA), and (4) Julia (e.g., Threads, CUDA.jl, AMDGPU.jl, and KernelAbstractions.jl). We use the GitHub Copilot capabilities powered by the GPT-based OpenAI Codex available in Visual Studio Code as of April 2023 to generate a vast amount of implementations given simple + + prompt variants. To quantify and compare the results, we propose a proficiency metric around the initial 10 suggestions given for each prompt. Results suggest that the OpenAI Codex outputs for C++ correlate with the adoption and maturity of programming models. For example, OpenMP and CUDA score really high, whereas HIP is still lacking. We found that prompts from either a targeted language such as Fortran or the more general purpose Python can benefit from adding code keywords, while Julia prompts perform acceptably well for its mature programming models (e.g., Threads and CUDA.jl). We expect for these benchmarks to provide a point of reference for each programming model's community. Overall, understanding the convergence of large language models, AI, and HPC is crucial due to its rapidly evolving nature and how it is redefining human-computer interactions.

Godoy, William↗

Exploring Architectural-Aware Affinity Policies in Modern HPC Runtimes

Modern commodity and High-Performance Computing (HPC) systems are evolving with complex CPU architectures. These architectures now feature higher core and NUMA domain counts and implement features such as hyperthreading. When considering significant differences in hardware configurations, library availability, and hardware-tailored system/software stacks, which could substantially vary from one system to another, performance portability is hard to achieve. Throughout the years, this trend resulted in an increasingly high burden on application developers to fine-tune their workloads for each architecture. This work explores how hardware-dependent aspects such as locality/process/thread affinity affect performance in modern CPU architectures. We focus our study on the Global Memory and Threading (GMT) distributed runtime system as a representative of Partitioned Global Address Space (PGAS) software stacks commonly adopted for productivity. In particular, to appreciate performance implications, we evaluate GMT’s thread affinity policies, and, introduce two new ones which exploit architectural awareness. Finally, we explore alternative NUMA configurations via different process bindings and perform a scalability study on three HPC clusters with varying CPU architectures and NUMA layouts. Our analysis indicates that more complex architectures are more affected by affinity and binding policies and highlights the importance of setting proper runtime configurations to achieve superior performance.

Di Dio Lavore, Ian↗

Divergence Reduction in Monte Carlo Neutron Transport with On-GPU Asynchronous Scheduling

While Monte Carlo Neutron Transport (MCNT) is near-embarrasingly parallel, the effectively unpredictable lifetime of neutrons can lead to divergence when MCNT is evaluated on GPUs. Divergence is the phenomenon of adjacent threads in a warp executing different control flow paths; on GPUS, it reduces performance because each work group may only execute one path at a time. The process of Thread Data Remapping (TDR) resolves these discrepancies by moving data across hardware such that data in the same warp will be processed through similar paths. A common issue among prior implementations of TDR is the synchronous nature of its remapping and processing cycles, which exhaustively sort data produced by prior processing passes and exhaustively evaluate the sorted data. In another work, we defined a method of remapping data through an asynchronous scheduler which allows for work to be stored in shared memory and deferred arbitrarily until that work is a viable option for low-divergence evaluation. This article surveys a wider set of cases, with the goal of characterizing performance trends across a more comprehensive set of parameters. These parameters include cross sections of scattering/capturing/fission, use of implicit capture, source neutron counts, simulation time spans, and tuned memory allocations. Across these cases, we have recorded minimum and average execution times, as well as a heuristically tuned near-optimal memory allocation size for both synchronous and asynchronous scheduling. Across the collected data, it is shown that the asynchronous method is faster and more memory efficient in the majority of cases, and that it requires less tuning to achieve competitive performance.

Computer Science↗

Characterizing and Mitigating Work Time Inflation in Task Parallel Programs

Task parallelism raises the level of abstraction in shared memory parallel programming to simplify the development of complex applications. However, task parallel applications can exhibit poor performance due to thread idleness, scheduling overheads, and work time inflation – additional time spent by threads in a multithreaded computation beyond the time required to perform the same work in a sequential computation. We identify the contributions of each factor to lost efficiency in various task parallel OpenMP applications and diagnose the causes of work time inflation in those applications. Increased data access latency can cause significant work time inflation in NUMA systems. Our locality framework for task parallel OpenMP programs mitigates this cause of work time inflation. Our extensions to the Qthreads library demonstrate that locality-aware scheduling can improve performance up to 3X compared to the Intel OpenMP task scheduler.

Olivier, Stephen L.↗

Dax v. 1.0

The Dax Toolkit enables the fine-grained concurrency for data analysis and visualization required to drive multi-core processors, many-core GPU accelerators, and emerging architectures for exascale computing. Dax simplifies the design of finely threaded algorithms by characterizing them in per element operations, which we call worklets. Worklets simplify design because they can behave as serial processes without the complications of memory clashes or other race conditions. Yet worklets can be scheduled on a practically unlimited number of threads, thereby making effective utilization of many processing cores. Operations coordinated across elements are encapsulated in a few versatile communicative operations that are adapted to the specifics of computing devices.

SciDAC↗

Sci-Vis Framework

SVF is a full featured OpenGL 3d framework that allows for rapid creation of complex visualizations. The SVF framework handles much of the lifecycle and complex tasks required for a 3d visualization. Unlike a game framework SVF was designed to use fewer resources, work well in a windowed environment, and only render when necessary. The scene also takes advantage of multiple threads to free up the UI thread as much as possible. Shapes (actors) in the scene are created by adding or removing functionality (through support objects) during runtime. This allows a highly flexible and dynamic means of creating highly complex actors without the code complexity (it also helps overcome the lack of multiple inheritance in Java.) All classes are highly customizable and there are abstract classes which are intended to be subclassed to allow a developer to create more complex and highly performant actors. There are multiple demos included in the framework to help the developer get started and shows off nearly all of the functionality. Some simple shapes (actors) are already created for you such as text, bordered text, radial text, text area, complex paths, NURBS paths, cube, disk, grid, plane, geometric shapes, and volumetric area. It also comes with various camera types for viewing that can be dragged, zoomed, and rotated. Picking or selecting items in the scene can be accomplished in various ways depending on your needs (raycasting or color picking.) The framework currently has functionality for tooltips, animation, actor pools, color gradients, 2d physics, text, 1d/2d/3d textures, children, blending, clipping planes, view frustum culling, custom shaders, and custom actor states

Arthur Bleeker, PNNL↗

PcapDB: Search Optimized Packet Capture, Version 0.1.0.0

PcapDB is a packet capture system designed to optimize the captured data for fast search in the typical (network incident response) use case. The technology involved in this software has been submitted via the IDEAS system and has been filed as a provisional patent. It includes the following primary components: capture: The capture component utilizes existing capture libraries to retrieve packets from network interfaces. Once retrieved the packets are passed to additional threads for sorting into flows and indexing. The sorted flows and indexes are passed to other threads so that they can be written to disk. These components are written in the C programming language. search: The search components provide a means to find relevant flows and the associated packets. A search query is parsed and represented as a search tree. Various search commands, written in C, are then used resolve this tree into a set of search results. The tree generation and search execution management components are written in python. interface: The PcapDB web interface is written in Python on the Django framework. It provides a series of pages, API's, and asynchronous tasks that allow the user to manage the capture system, perform searches, and retrieve results. Web page components are written in HTML,CSS and Javascript.

Ferrell, Paul↗

RMA-MT Benchmarks

The RMA-MT benchmarks are a suite of performance tests for multi-threaded Message Passing Interface (MPI) Remote Memory Access (RMA) implementations. The suite includes tests for bandwidth and latency with any number of threads. This suite was originally developed and release by Sandia National Laboratory. LANL modifications to the suite include a complete re-write of much of the source code, bi-directional bandwidth, and message rate tests.

Hjelm, Nathan↗

Grappolo

Community detection has become a fundamental operation in numerous graph-theoretic applications. It is used to reveal natural divisions that exist within real world networks without imposing prior size or cardinality constraints on the set of communities. Despite its potential for application, there is only limited support for community detection on large-scale parallel computers, largely owing to the irregular and inherently sequential nature of the underlying heuristics. In this paper, we present parallelization heuristics for fast community detection using the Louvain method as the serial template. The Louvain method is an iterative heuristic for modularity optimization. Originally developed by Blondel et al. in 2008, the method has become increasingly popular owing to its ability to detect high modularity community partitions in a fast and memory-efficient manner. However, the method is also inherently sequential, thereby limiting its scalability. Here, we observe certain key properties of this method that present challenges for its parallelization, and consequently propose heuristics that are designed to break the sequential barrier. For evaluation purposes, we implemented our heuristics using OpenMP multithreading, and tested them over real world graphs derived from multiple application domains (e.g., internet, citation, biological). Compared to the serial Louvain implementation, our parallel implementation is able to produce community outputs with a higher modularity for most of the inputs tested, in comparable number of iterations, while providing real speedups of up to 8x using 32 threads. In addition, our parallel implementation was able to exhibit weak scaling properties on up to 32 threads.

Halappanavar, Mahantesh↗

GNATFinder

SAND2023-05510O GNATFinder is a software tool for extracting graphical neural activity threads (GNATs) from spiking neural networks. GNATFinder efficiently extracts GNATs from spiking neural network data. A GNAT is a graph that represents the causal relationships between individual spikes in a spiking network using a combination of the network connectivity structure and the timing of individual spikes. The software allows for identifying similar, repeating threads that often reappear in a dataset. Using quadtree data structures to recursively subdivide the time interval over which spikes were produced by the spiking network, GNATFinder allows for efficient pairwise comparisons of spike times to determine the degree of causal relatedness among all pairs of spikes in a dataset. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

SciDAC↗

Energy Exascale Earth System Model v2.0.1

First patch release of v2.0.0 Changes since v2.0.0 [Important change] Fix ocean threading bug seen in debug cases on Chrysalis with Intel 20.0.4. Was introduced around time of v2.0.0 tag. Does not change v2.0.0 answers on Chrysalis because those didn't use threading or debugging. [EAM] Add semi-lagrangian tracer transport for theta-l (F90 and C++), add new algorithm for finding tropopause, add DSCREAM to allow v2 and SCREAM settings in same code such as adjust_ps [EAM-MMF] 60L default, allow C++ back end of RRTMGP (EAM too). [EAMxx] add nu-top functionality, fix forcing functor, add ttype9 and dcmip2012 tests 2.1, 2.2, and 3 HOMME: remove obsolete remap algs, option to specify dynamics alg indep of tracer, new sponge layer, add imex tests [ELM] Add topography-based subgrid (topounits), add FATES-ELM Nitro., Phos. and CH4 coupling, add land-use ts for NARRM, add lulc for SSP3 RCP7, Fix nutrient fertilization exp test and carbon isotope flux, Fix xactive lnd dry deposition, add lake water storage option, fix plant hydraulics 2d params, fix carbon budget calc, fix soil nutrient conc. bug, fix mosart dam bug, add test for new ELM, MOSART features, fix bug in O3 dry dep stomatal resistances, fix plant hydraulics restart BFB error, update mkmapdata. [MOSART] fix bug for reading the latitude from an unstructured input file, fix oversat in bubble test. [MPAS-ocean] Add CFC11, CFC12 tracers, add 2D spherical transport tests, fix del4 tracer mixing, add MARBL ocean tracer mixing, modify harmonic analysis options, add GPU port of vmix routines, fix calc of ML-averaged BV freq. [MPAS-seaice] Change extents of initial polar disks for oRRS18to6v3 grid, fix ice BGC with MARBL, update spherical test cases, fix DON coupling, Remove Cf from sea ice constants. [MPAS-landice] add CRYO1850-4xCO2 compset [CIME] add GCP, ANL GCE, Spock, Perlmutter, deprecate config_compilers.xml, fix and clean-up cmake macros, fix slurm bindings, refactor CIME internal testing, cleanup SCORPIO perf data, allow position independent compset naming, [also] update v2 benchmarking suite, extend e3sm_prod with throughput and memory checks

E3SM Project, DOE↗

Multi-core performance studies of a Monte Carlo neutron transport code

Performance results are presented for a multi-threaded version of the OpenMC Monte Carlo neutronics code using OpenMP in the context of nuclear reactor criticality calculations. Our main interest is production computing, and thus we limit our approach to threading strategies that both require reasonable levels of development effort and preserve the code features necessary for robust application to real-world reactor problems. Several approaches are developed and the results compared on several multi-core platforms using a popular reactor physics benchmark. A broad range of performance studies are distilled into a simple, consistent picture of the empirical performance characteristics of reactor Monte Carlo algorithms on current multi-core architectures.

97 MATHEMATICS AND COMPUTING↗

Reaching bandwidth saturation using transparent injection parallelization

Although logically available, applications may not exploit enough instantaneous communication concurrency to maximize network utilization on HPC systems. This is exacerbated in hybrid programming models that combine single program multiple data with OpenMP or CUDA. We present the design of a “multi-threaded” runtime able to transparently increase the instantaneous network concurrency and to provide near saturation bandwidth, independent of the application configuration and dynamic behavior. The runtime offloads communication requests from application level tasks to multiple communication servers. The servers use system specific performance models to attain network saturation. Our techniques alleviate the need for spatial and temporal application level message concurrency optimizations. Experimental results show improved message throughput and bandwidth by as much as 150% for 4 KB messages on InfiniBand and by as much as 120% for 4 KB messages on Cray Aries. For more complex operations such as all-to-all collectives, we observe as much as 30% speedup. This translates into 23% speedup on 12,288 cores for a NAS FT implemented using FFTW. We observe as much as 76% speedup on 1500 cores for an already optimized UPC+OpenMP geometric multigrid application using hybrid parallelism. For the geometric multigrid GPU implementation, we observe as much as 44% speedup on 512 GPUs.

Chaimov, Nicholas↗

Reverse-Mode Algorithmic Differentiation of an OpenMP-Parallel Compressible Flow Solver

y Reverse-mode algorithmic differentiation (AD) is an established method for obtaining adjoint derivatives of computer simulation applications. In computational fluid dynamics (CFD), adjoint derivatives of a cost function output such as drag or lift with respect to design parameters such as surface coordinates or geometry control points are a key ingredient for shape optimization, uncertainty quantification and flow control. The computational cost of CFD applications and their derivatives makes it essential to use high-performance computing hardware efficiently, including multi- and many-core architectures. Nevertheless, OpenMP is not supported in most AD tools, and previously shown methods achieve poor scalability of the derivative code. We present the AD of an OpenMP-parallelized finite volume compressible flow solver for unstructured meshes. Our approach enables us to reuse the parallelization of the original code in the computation of adjoint derivatives. The method works by identifying code segments that can be differentiated in reverse-mode without changing their memory access pattern. The OpenMP parallelization is integrated into the derivative code during the build process in a way that is robust to modifications of the original code and independent of the OpenMP support of the differentiation tool. We show the scalability of our adjoint CFD solver on test cases ranging from thousands to millions of finite volume mesh cells on CPUs with up to 16 threads as well as on an Intel XeonPhi card with 236 threads. We demonstrate that our approach is more practical to implement for production-sized CFD codes and produces more efficient adjoint derivative code than previously shown AD methods.

Huckelheim, Jan↗

Refining HPCToolkit for application performance analysis at exascale

As part of the US Department of Energy’s Exascale Computing Project (ECP), Rice University has been refining its HPCToolkit performance tools to better support measurement and analysis of applications executing on exascale supercomputers. To efficiently collect performance measurements of GPU-accelerated applications, HPCToolkit employs novel non-blocking data structures to communicate performance measurements between tool threads and application threads. To attribute performance information in detail to source lines, loop nests, and inlined call chains, HPCToolkit performs parallel analysis of large CPU and GPU binaries involved in the execution of an exascale application to rapidly recover mappings between machine instructions and source code. To analyze terabytes of performance measurements gathered during executions at exascale, HPCToolkit employs distributed-memory parallelism, multithreading, sparse data structures, and out-of-core streaming analysis algorithms. To support interactive exploration of profiles up to terabytes in size, HPCToolkit’s hpcviewer graphical user interface uses out-of-core methods to visualize performance data. The result of these efforts is that HPCToolkit now supports collection, analysis, and presentation of profiles and traces of GPU-accelerated applications at exascale. These improvements have enabled HPCToolkit to efficiently measure, analyze and explore terabytes of performance data for executions using as many as 64K MPI ranks and 64K GPU tiles on ORNL’s Frontier supercomputer. HPCToolkit’s support for measurement and analysis of GPU-accelerated applications has been employed to study a collection of open-science applications developed as part of ECP. This paper reports on these experiences, which provided insight into opportunities for tuning applications, strengths and weaknesses of HPCToolkit itself, as well as unexpected behaviors in executions at exascale.

Adhianto, Laksono↗

Effect of tool pin features on process response variables during friction stir welding of dissimilar aluminum alloys

In this article, the effect of pin features and orientation/placement of the materials on advancing side were investigated for friction stir welding (FSW) of dissimilar aluminum alloys AA2050 and AA6061. Pins for FSW were produced with a 2.12 mm pitch thread having three flats/flutes. Three sets of rotational speed/welding speed were used to perform a series of welds in a butt joint arrangement. The results show that, joint quality, process response variables and welding temperature are highly affected by pin features and material orientation in FSW. Defect free joints with effective material transportation in the weld nugget zone were obtained when welding was performed with AA2050 on the advancing side. The tool also encounters less in-plane reaction force for welding with 2050 on the advancing side. Pin with thread+3 flats produces quality welds at low rotational and travel speed regardless of the location of alloys on advancing or retreating side.

36 MATERIALS SCIENCE↗