Search NASA⌕ Search

Engineering topics

Luszczek, Piotr

Publications and source records attributed to Luszczek, Piotr.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Numerical eigen-spectrum slicing, accurate orthogonal eigen-basis, and mixed-precision eigenvalue refinement using OpenMP data-dependent tasks and accelerator offload

Performing a variety of numerical computations efficiently and, at the same time, in a portable fashion requires both an overarching design followed by a number of implementation strategies. All of these are exemplified below as we present transitioning the PLASMA numerical library from relying on dependence-driven large tasks to achieving utilization of fine grain tasking and offload to hardware accelerators while keeping its core dependence sets: OpenMP source code pragmas and runtime for most system-level functionality and basic low-level numerical kernels provided directly by hardware vendors or open source projects with vendor contributions. We also present new algorithmic methods and their efficient parallel implementations including fine grained tasking for eigen-spectrum slicing and offload for mixed-precision eigenvalue refinement. We provide performance, scaling, and numerical results showing sizable gains over the available solutions from either the open source and vendor-provided packages.

Luszczek, Piotr↗
DOE OSTI2024

Batched Sparse Linear Algebra Phase 2

The purpose of the work was to help LLNL develop a broadly applicable set of capabilities that focus on batched sparse linear functionality and its software implementation. The enablement occurred in a broader scope of the Exascale Computing Program (ECP) with an eye on the xSDK collection of applications and libraries. These served as the main dissemination targets and in the end benefitted from this project’s outcomes.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Batched Sparse Linear Algebra Phase 2 (Final Report)

The purpose of the work was to help LLNL develop a broadly applicable set of capabilities that focus on batched sparse linear functionality and its software implementation. The enablement occurred in a broader scope of the Exascale Computing Program (ECP) with an eye on the xSDK collection of applications and libraries. These served as the main dissemination targets and in the end benefitted from this project’s outcomes.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Batched Sparse Linear Algebra (Final Report for Subcontract B648960)

This report finalizes design specifications for developing batched kernels for small tensor operations for unassembled matrix-free iterative solvers, batched solvers for partially assembled operators, and batched solvers with support for various sparse formats. The outcome of the project milestones is a set of interfaces to Batched Sparse LA solvers running on hardware accelerators for use in ECP Libraries and Applications. It is part of the development of sparse batched kernels, solvers/preconditioners as well as creating interoperability in xSDK libraries with sparse and dense batched functions to benefit ECP applications. The participants included representatives from ECP libraries (not limited to the xSDK project), applications, and vendors (AMD, Intel, and NVIDIA). Batched sparse linear algebra solvers form the new frontier for algorithmic development and performance engineering. Many applications (ECP and non-ECP alike) require simultaneous solutions of small linear systems of equations that are structurally sparse. To move towards high hardware utilization, it is important to provide these applications with appropriate interfaces to efficient batched sparse solvers running on modern hardware accelerators. We present interface designs in use by HPC software libraries supporting batched sparse linear algebra and the development of sparse batched kernel codes for solvers and preconditioners. We also address the potential interoperability opportunities to keep the software portable between the major hardware accelerators from AMD, Intel, and NVIDIA. The presented interface specifications includes batched band, sparse iterative, and sparse direct solvers. This report summarizes progress in Kokkos Kernels and the xSDK libraries MAGMA, Ginkgo, hypre, SUNDIALS, and SuperLU_dist.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

High-Performance GMRES Mixed-Precision (HPG-MxP) Benchmark

SAND2024-08539O The High Performance GMRES Mixed-Precision (HPG-MxP) is a benchmark for ranking high-performance supercomputers, allowing use of mixed-precision. Similar to HPCG benchmark, it is designed to profile the computers' capabilities to perform the computational and communication tasks that are commonly found in important classes of real-world applications. At the same time, like HPL-MxP benchmark, it allows the use of mixed-precision arithmetic, while ensuring the double-precision accuracy of the computed solution. 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↗
DOE OSTI2023

Combining multitask and transfer learning with deep Gaussian processes for autotuning-based performance engineering

We combine deep Gaussian processes (DGPs) with multitask and transfer learning for the performance modeling and optimization of HPC applications. Deep Gaussian processes merge the uncertainty quantification advantage of Gaussian processes (GPs) with the predictive power of deep learning. Multitask and transfer learning allow for improved learning efficiency when several similar tasks are to be learned simultaneously and when previous learned models are sought to help in the learning of new tasks, respectively. A comparison with state-of-the-art autotuners shows the advantage of our approach on two application problems. In this article, we combine DGPs with multitask and transfer learning to allow for both an improved tuning of an application parameters on problems of interest but also the prediction of parameters on any potential problem the application might encounter.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Challenges of and Opportunities for a Large Diverse Software Team

A large software team consisting of members with different expertise, skillsets, personalities, ethnicities, and involving collaboration on a large and complex software product presents many technical and cultural challenges, but also provides unique opportunities. In this article, we discuss the essential issues we faced when successfully transforming a collection of various independently developed software libraries into one large integrated product: the eXtreme-scale scientific Software Development Kit (xSDK). Furthermore, we argue it is just as important to pay attention to cultural challenges, such as establishment of reliable communication channels that considers, among others, differences in personalities and backgrounds as well as overcoming geographical separation and time-zone distribution when collaborating, as technical challenges. Finally, we discuss opportunities stemming from participating in a large diverse software team, such as increased internal expertise, variety of skillsets, broadened connections to external experts, and access to a larger pool of ideas or solutions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Assessment of Local Observation of Atomic Ordering in Alloys via the Radial Distribution Function: A Computational and Experimental Approach

As a powerful analytical technique, atom probe tomography (APT) has the capacity to acquire the spatial distribution of millions of atoms from a complex sample. However, extracting information at the Ångstrom-scale on atomic ordering remains a challenge due to the limits of the APT experiment and data analysis algorithms. The development of new computational tools enable visualization of the data and aid understanding of the physical phenomena such as disorder of complex crystalline structures. Here, we report progress towards this goal using two steps. We describe a computational approach to evaluate atomic ordering in the crystal structure by generating radial distribution functions (RDF). Atomic ordering is rendered as the Fractional Cumulative Radial Distribution Function (FCRDF) which allows for greater visibility of local compositions at short range in the structure. Further, we accommodate in the analysis additional parameters such as uncertainty in the atomic coordinates and the atomic abundance to ascertain short-range ordering in APT data sets. We applied the FCRDF analysis to synthetic and experimental APT data sets for Ni 3 Al. The ability to observe a signal of atomic ordering consistent with the known L1 2 crystal structure is heavily dependent on spatial uncertainty, irrespective of abundance. Detection of atomic ordering is subject to an upper limit of spatial uncertainty of atoms described with Gaussian distributions with a standard deviation of 1.3 Å. The FCRDF analysis was also applied to the APT data set for a six-component alloy, Al 1.3 CoCrCuFeNi. In this case, we are currently able to visualize elemental segregation at the nanoscale, though unambiguous identification of atomic ordering at the Ångstrom (nearest-neighbor) scale remains a goal.

36 MATERIALS SCIENCE↗
DOE OSTI2021

OpenMP application experiences: Porting to accelerated nodes

As recent enhancements to the OpenMP specification become available in its implementations, there is a need to share the results of experimentation in order to better understand the OpenMP implementation’s behavior in practice, to identify pitfalls, and to learn how the implementations can be effectively deployed in scientific codes. We report on experiences gained and practices adopted when using OpenMP to port a variety of ECP applications, mini-apps and libraries based on different computational motifs to accelerator-based leadership-class high-performance supercomputer systems at the United States Department of Energy. Additionally, we identify important challenges and open problems related to the deployment of OpenMP. Through our report of experiences, we find that OpenMP implementations are successful on current supercomputing platforms and that OpenMP is a promising programming model to use for applications to be run on emerging and future platforms with accelerated nodes.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Materials Fingerprinting Classification

Significant progress in many classes of materials could be made with the availability of experimentally-derived large datasets composed of atomic identities and three-dimensional coordinates. Methods for visualizing the local atomic structure, such as atom probe tomography (APT), which routinely generate datasets comprised of millions of atoms, are an important step in realizing this goal. However, state-of-the-art APT instruments generate noisy and sparse datasets that provide information about elemental type, but obscure atomic structures, thus limiting their subsequent value for materials discovery. The application of a materials fingerprinting process, a machine learning algorithm coupled with topological data analysis, provides an avenue by which here-to-fore unprecedented structural information can be extracted from an APT dataset. As a proof of concept, the material fingerprint is applied to high-entropy alloy APT datasets containing body-centered cubic (BCC) and face-centered cubic (FCC) crystal structures. A local atomic configuration centered on an arbitrary atom is assigned a topological descriptor, with which it can be characterized as a BCC or FCC lattice with near perfect accuracy, despite the inherent noise in the dataset. Finally, this successful identification of a fingerprint is a crucial first step in the development of algorithms which can extract more nuanced information, such as chemical ordering, from existing datasets of complex materials.

36 MATERIALS SCIENCE↗
DOE OSTI2021

A survey of numerical linear algebra methods utilizing mixed-precision arithmetic

The efficient utilization of mixed-precision numerical linear algebra algorithms can offer attractive acceleration to scientific computing applications. Especially with the hardware integration of low-precision special-function units designed for machine learning applications, the traditional numerical algorithms community urgently needs to reconsider the floating point formats used in the distinct operations to efficiently leverage the available compute power. In this study, we provide a comprehensive survey of mixed-precision numerical linear algebra routines, including the underlying concepts, theoretical background, and experimental results for both dense and sparse linear algebra problems.

97 MATHEMATICS AND COMPUTING↗