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 1,531 records · Page 85

Synchronization for CXL Based Memory

Compute Express Link (CXL) is an important emerging standard for disaggregated memory. While this standard provisions coherency across numerous hosts and devices, implementing hardware support for type three devices is challenging. In this work, we look at the overhead of software synchronization and using software-based coherency. Moreover, we discuss the limits of software-based coherency in fully expressing modern synchronization techniques for a CXL-based disaggregate memory system. We demonstrate our approach using a CXL hardware prototype and running a version of the famous Peterson Lock (enhanced to run with more than two threads). We analyze its performance and share how more advanced synchronization techniques might interact with software-based coherence CXL hardware and program execution models.

High Performance Computing (HPC)↗

Insights from Optimizing HPL Performance on Exascale Systems: A Comparative Analysis of Panel Factorization

High performance LINPACK (HPL) remains the primary benchmark for evaluating supercomputing performance. It includes many parts with substantial internal complexity, and its performance is affected by a large number of parameters that interact in ways that are difficult to predict on large-scale heterogeneous supercomputer systems. We present a comprehensive performance analysis of HPL on Frontier, the world’s first exascale supercomputer, which achieved HPL performance of 1.35 exaflops. Through empirical parameter tuning, detailed modeling, and comparative evaluation, we uncover critical performance insights, share lessons learned, and outline best practices for effective parameter tuning on exascale systems. We introduce and evaluate two novel PDFACT strategies: a dedicated-thread (DT) variant and a GPU-based variant (GPUPDFACT) implementation using HIP cooperative groups, demonstrating that GPU-based factorization outperforms conventional CPU-based PDFACT on Frontier’s architecture. Our findings establish key performance factors for HPL on exascale systems and offer valuable guidance for future high-performance computing and benchmarking efforts.

Lu, Hao [ORNL] (ORCID:000000018941870X)↗

CORE-BFS: Communication-Optimized REctangular-partitioned BFS Achieving 160.845 TeraTEPS on Frontier Supercomputer

Distributed Breadth-First Search (BFS) is fundamental to many large-scale graph applications, but its performance on parallel systems is often limited by high communication overhead. This paper presents CORE-BFS, an extremely scalable GPU-based BFS implementation that introduces a unique rectangular 2D partitioning-based design for Frontier supercomputer. To further improve performance, we propose four key optimizations: (1) Rectangular 2D-partition specific data formats that use two compressed row and one compressed column status array bitmaps combined with a Double Compressed Sparse Row (DCSR) format per partition, reducing memory footprint and inter-rank traffic; (2) Adaptive frontier & communication strategy that unifies top-down and bottom-up traversal on the rectangular layout, uses lazy synchronization in top-down levels, and switches variants based on frontier size to minimize communication overhead; (3) Frontier-split degree-aware update that maps frontier vertices to thread-centric, wavefront-centric, and block-centric kernels based on their degree to improve GPU utilization and memory coalescing; (4) Row-reduction pipeline that overlaps bottom-up adjacency list processing with row-wise bitmap reduction to hide inter-rank latency. Together, these techniques increase parallelism while reducing memory and communication overhead. On the Graph500 benchmark, CORE - BFS scales up to 9,248 Frontier nodes with scale-42 graphs and reaches 160.845 TTEPS, delivering a 5.42 × speedup over our previous Frontier implementation.

Yang, Haoshen [Rutgers University]↗

Determination of performance characteristics of scientific applications on IBM Blue Gene/Q

The IBM Blue Gene®/Q platform presents scientists and engineers with a rich set of hardware features such as 16 cores per chip sharing a Level 2 cache, a wide SIMD (single-instruction, multiple-data) unit, a five-dimensional torus network, and hardware support for collective operations. Especially important is the feature related to cores that have four “hardware threads,” which makes it possible to hide latencies and obtain a high fraction of the peak issue rate from each core. All of these hardware resources present unique performance-tuning opportunities on Blue Gene/Q. We provide an overview of several important applications and solvers and study them on Blue Gene/Q using performance counters and Message Passing Interface profiles. We also discuss how Blue Gene/Q tools help us understand the interaction of the application with the hardware and software layers and provide guidance for optimization. Furthermore, on the basis of our analysis, we discuss code improvement strategies targeting Blue Gene/Q. Information about how these algorithms map to the Blue Gene® architecture is expected to have an impact on future system design as we move to the exascale era.

97 MATHEMATICS AND COMPUTING↗

AlGaN/GaN High Electron Mobility Transistor Grown and Fabricated on ZrTi Metallic Alloy Buffer Layers

AlGaN/GaN high electron mobility transistors (HEMTs) were demonstrated for structures grown on ZrTi metallic alloy buffer layers, which provided lattice matching of the in-plane lattice parameter (“a-parameter”) to hexagonal GaN. The quality of the GaN buffer layer and HEMT structure were confirmed with X-ray 2θ and rocking scans as well as cross-section transmission electron microscopy (TEM) images. The X-ray 2θ scans showed full widths at half maximum (FWHM) of 0.06°, 0.05° and 0.08° for ZrTi alloy, GaN buffer layer, and the entire HEMT structure, respectively. TEM of the lower section of the HEMT structure containing the GaN buffer layer and the AlN/ZrTi/AlN stack on the Si substrate showed that it was important to grow AlN on the top of ZrTi prior to growing the GaN buffer layer. Finally, the estimated threading dislocation (TD) density in the GaN channel layer of the HEMT structure was in the 10 8 cm -2 range.

36 MATERIALS SCIENCE↗

Understanding the effects of PEMFC contamination from balance of plant assembly aids materials: In situ studies

In this study, in situ performance data were measured to assess the degree of contamination from leachates of five families of balance of plant (BOP) materials (i.e., 2-part adhesive, grease, thread lock/seal, silicone adhesive/seal and urethane adhesive/seal) broadly classified as assembly aids that may be used as adhesives and lubricants in polymer electrolyte membrane fuel cell (PEMFC) systems. Leachate solutions, derived from soaking the materials in deionized (DI) water at elevated temperature, were infused into the fuel cell to determine the effect of the leachates on fuel cell performance. During the contamination phase of the experiments, leachate solution was introduced through a nebulizer into the cathode feed stream of a 50 cm 2 PEMFC operating at 0.2 A/cm 2 at 80°C and 32%RH. Voltage loss and high frequency resistance (HFR) were measured as a function of time and electrochemical surface area (ECA) before and after contamination were compared. Two procedures of recovery, one self-induced recovery with DI water and one driven recovery through cyclic voltammetry (CV) were investigated. Finally, performance results measured before and after contamination and after CV recovery are compared and discussed.

14 SOLAR ENERGY↗

Compiler-Directed File Layout Optimization for Hierarchical Storage Systems

File layout of array data is a critical factor that effects the behavior of storage caches, and has so far taken not much attention in the context of hierarchical storage systems. The main contribution of this paper is a compiler-driven file layout optimization scheme for hierarchical storage caches. This approach, fully automated within an optimizing compiler, analyzes a multi-threaded application code and determines a file layout for each disk-resident array referenced by the code, such that the performance of the target storage cache hierarchy is maximized. We tested our approach using 16 I/O intensive application programs and compared its performance against two previously proposed approaches under different cache space management schemes. Our experimental results show that the proposed approach improves the execution time of these parallel applications by 23.7% on average.

Ding, Wei↗

From Physics Model to Results: An Optimizing Framework for Cross-Architecture Code Generation

Starting from a high-level problem description in terms of partial differential equations using abstract tensor notation, the Chemora framework discretizes, optimizes, and generates complete high performance codes for a wide range of compute architectures. Chemora extends the capabilities of Cactus, facilitating the usage of large-scale CPU/GPU systems in an efficient manner for complex applications, without low-level code tuning. Chemora achieves parallelism through MPI and multi-threading, combining OpenMP and CUDA. Optimizations include high-level code transformations, efficient loop traversal strategies, dynamically selected data and instruction cache usage strategies, and JIT compilation of GPU code tailored to the problem characteristics. The discretization is based on higher-order finite differences on multi-block domains. Chemora's capabilities are demonstrated by simulations of black hole collisions. This problem provides an acid test of the framework, as the Einstein equations contain hundreds of variables and thousands of terms.

Blazewicz, Marek↗

Optimized Data Transfers Based on the OpenCL Event Management Mechanism

In standard OpenCL programming, hosts are supposed to control their compute devices. Since compute devices are dedicated to kernel computation, only hosts can execute several kinds of data transfers such as internode communication and file access. These data transfers require one host to simultaneously play two or more roles due to the need for collaboration between the host and devices. The codes for such data transfers are likely to be system-specific, resulting in low portability. Here, this article proposes an OpenCL extension that incorporates such data transfers into the OpenCL event management mechanism. Unlike the current OpenCL standard, the main thread running on the host is not blocked to serialize dependent operations. Hence, an application can easily use the opportunities to overlap parallel activities of hosts and compute devices. In addition, the implementation details of data transfers are hidden behind the extension, and application programmers can use the optimized data transfers without any tricky programming techniques. The evaluation results show that the proposed extension can use the optimized data transfer implementation and thereby increase the sustained data transfer performance by about 18% for a real application accessing a big data file.

97 MATHEMATICS AND COMPUTING↗

Livermore Random I/O Testbench

LRIOT is a test bench framework that is designed to generate sophisticated I/O rates that can stress high-performance memory and storage systems, such as non-volatile random access memories (NVRAM)and storage class memory. Furthermore, LRIOT provides the capabilities to mix multiple types of concurrency, namely threading and task parallelism, as well as distributed execution using Message Passing Interface (MPI) libraries. It will be used by algorithm designers to generate access patterns that mimic their application's behavior, and by system designers to test high-performance NVRAM storage.

Source record↗

perf-dump

perf-dump is a library for dumping performance data in much the same way physics simulations dump checkpoints. It records per-process, per-timestep, per-phase, and per-thread performance counter data and dumps this large data periodically into an HDF5 data file.

Gamblin, T.↗

Tomopy: A Python toolbox to perform X-Ray data proessing and image reconstruction.

Tomopy is a Python toolbox to perform x-ray data processing, image reconstruction and data exchange tasks at synchrotron facilities. The dependencies of the software are currently as follows: -Python related python standard library (http://docs.python.org/2/library/) numpy (http://www.numpy.org/) scipy (http://scipy.org/) matplotlib (http://matplotlip.org/) sphinx (http://sphinx-doc.org) pil (http://www.pythonware.com/products/pil/) pyhdf (http://pysclint.sourceforge.net/pyhdf/) h5py (http://www.h5py.org) pywt (http://www.pybytes.com/pywavelets/) file.py (https://pyspec.svn.sourceforge.net/svnroot/pyspec/trunk/pyspec/ccd/files.py) -C/C++ related: gridec (anonymous?? C-code written back in 1997 that uses standard C library) fftw (http://www.fftw.org/) tomoRecon (multi-threaded C++ verion of gridrec. Author: Mark Rivers from APS. http://cars9.uchicago.edu/software/epics/tomoRecon.html) epics (http://www.aps.anl.gov/epics/)

Source record↗

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↗

Jali - Unstructured Mesh Infrastructure for Multi-Physics Applications

Jali is a parallel unstructured mesh infrastructure library designed for use by multi-physics simulations. It supports 2D and 3D arbitrary polyhedral meshes distributed over hundreds to thousands of nodes. Jali can read write Exodus II meshes along with fields and sets on the mesh and support for other formats is partially implemented or is (https://github.com/MeshToolkit/MSTK), an open source general purpose unstructured mesh infrastructure library from Los Alamos National Laboratory. While it has been made to work with other mesh frameworks such as MOAB and STKmesh in the past, support for maintaining the interface to these frameworks has been suspended for now. Jali supports distributed as well as on-node parallelism. Support of on-node parallelism is through direct use of the the mesh in multi-threaded constructs or through the use of "tiles" which are submeshes or sub-partitions of a partition destined for a compute node.

Garimella, RaoV↗

Comb

Comb is a communication performance benchmarking tool. It is used to determine performance tradeoffs in implementing communication patterns on high performance computing (HPC) platforms. At its core comb runs combinations of communication patterns with execution patterns, and memory spaces. The current set of capabilities Comb provides includes: o Configurable structured mesh halo exchange communication. o A variety of communication patterns based on grouping messages. o A variety of execution patterns including serial, openmp threading, cuda, cuda batched kernels, and cuda persistent kernels. o A variety of memory spaces including default system allocated memory, pinned host memory, cuda device memory, and cuda managed memory with different cuda memory advice.

Burmark, Jason↗

LOGAN: High-Performance X-Drop Pairwise Alignment on GPU (LOGAN) v1.0

Pairwise sequence alignment is one of the most computationally intensive kernels in genomic data analysis, accounting for more than 90% of the run time for key bioinformatics applications. This method is particularly expensive for third-generation sequences due to the high computational expense of analyzing these long read lengths (1Kb-1Mb). Given the quadratic overhead of exact pairwise algorithms such as Smith-Waterman, for long alignments, the community primarily relies on approximate algorithms that search only for high-quality alignments and stop early when one is not found. In this work, we present the first GPU optimization of the popular X-drop alignment algorithm, named LOGAN. Results show that our high-performance multi-GPU LOGAN implementation achieves up to 181.6 GCUPS and speed-ups up to 6.6x and 30.7x using 1 and 6 NVIDIA Tesla V100, respectively, over the state-of-the-art software running on two IBM Power9 processors using 168 threads, with equivalent accuracy. We also demonstrate a 2.3x LOGAN speed-up versus ksw2, a state-of-art vectorized algorithm for sequence alignment implemented in minimap2. To highlight the impact of our work on a real-world application, we couple the LOGAN aligner with a many-to-many long-read alignment software called BELLA, and demonstrate that our implementation improves the overall BELLA runtime by up to 10.6x. Finally, we adapt the Roofline model for our optimized kernel and demonstrate that our implementation is near-optimal on the NVIDIA Tesla V100s.

Guidi, Giulia↗

Multispecies Hypersonic Flow Simulator

MHYSA is a conservative finite-difference code to solve the 1D, 2D, and 3D multispecies Navier-Stokes equations for hypersonic flow applications. It supports Cartesian grids only and has the option of including immersed boundaries. - Solves 1D Euler and 2D and 3D Navier-Stokes equations. - Solves the PDEs over Cartesian grids. - Written entirely in C and uses the MPICH library. It also uses OpenMP threads but this is a work-inprogress. - Can be compiled with PETSc (http://www.mcs.anl.gov/petsc/), if available, where it can use PETSc's time integration module TS (http://www.mcs.anl.gov/petsc/petsc-current/src/ts/). - For 3-dimensional simulations, the immersed boundaries can be used to solve over non-Cartesian geometries. MHYSA has been developed to be scalable, and apart from the usual functionalities to solve a system of PDEs on distributed architectures, it provides scalable file I/O functions.

Ghosh, Debojyoti↗

C version of mpibind

C version of mpibind, an algorithm to map MPI tasks, threads, and GPU kernels to the hardware.

LOUSSERT, ARTHUR TT↗