Search NASA⌕ Search

SEARCH · Search NASA

Results for “BLAS”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Inference-Engine v0.1.0

Given a pre-trained neural network, Inference-Engine performs maps network inputs to outputs by executing the forward pass through the provided network. Although the predominant programming language for machine-learning is Python, most high-performance computing (HPC) applications are written in Fortran, C, or C++. Inference-Engine aims to support HPC programs and is written in Fortran, a language with a large feature set supporting interoperability with C. This software exposes concurrency in a portable way by using standard language features that some modern Fortran compilers can exploit with various optimizations, including offloading computation to a Graphics Processing Unit (GPU). In particular, this software makes extensive use of Fortran's "do concurrent" parallel loop construct, implicitly parallel array statements, and pure procedures that can be invoked inside "do concurrent" blocks. Inference-Engine also supports dynamic choice of inference methods at runtime. Two current options include one method that uses Fortran's "dot_product" intrinsic function inside "do concurrent" blocks and another method that instead uses Fortran' "matmul" array intrinsic function. We plan to investigate automatic compiler offloading of "do concurrent" calculations to GPUs and compile-time substitution of optimized libraries such as the Basic Linear Algebra Library (BLAS) for "matmul" invocations. We also envision the potential for the choice of which method to use could happen at program launch based on in situ performance measurements on any given platform.

Rouson, Damian↗
DOE OSTI2024

A graphics processing unit accelerated sparse direct solver and preconditioner with block low rank compression

We present the GPU implementation efforts and challenges of the sparse solver package STRUMPACK. The code is made publicly available on github with a permissive BSD license. STRUMPACK implements an approximate multifrontal solver, a sparse LU factorization which makes use of compression methods to accelerate time to solution and reduce memory usage. Multiple compression schemes based on rank-structured and hierarchical matrix approximations are supported, including hierarchically semi-separable, hierarchically off-diagonal butterfly, and block low rank. Here, in this paper, we present the GPU implementation of the block low rank (BLR) compression method within a multifrontal solver. Our GPU implementation relies on highly optimized vendor libraries such as cuBLAS and cuSOLVER for NVIDIA GPUs, rocBLAS and rocSOLVER for AMD GPUs and the Intel oneAPI Math Kernel Library (oneMKL) for Intel GPUs. Additionally, we rely on external open source libraries such as SLATE (Software for Linear Algebra Targeting Exascale), MAGMA (Matrix Algebra on GPU and Multi-core Architectures), and KBLAS (KAUST BLAS). SLATE is used as a GPU-capable ScaLAPACK replacement. From MAGMA we use variable sized batched dense linear algebra operations such as GEMM, TRSM and LU with partial pivoting. KBLAS provides efficient (batched) low rank matrix compression for NVIDIA GPUs using an adaptive randomized sampling scheme. The resulting sparse solver and preconditioner runs on NVIDIA, AMD and Intel GPUs. Interfaces are available from PETSc, Trilinos and MFEM, or the solver can be used directly in user code. We report results for a range of benchmark applications, using the Perlmutter system from NERSC, Frontier from ORNL, and Aurora from ALCF. For a high frequency wave equation on a regular mesh, using 32 Perlmutter compute nodes, the factorization phase of the exact GPU solver is about 6.5× faster compared to the CPU-only solver. The BLR-enabled GPU solver is about 13.8× faster than the CPU exact solver. For a collection of SuiteSparse matrices, the STRUMPACK exact factorization on a single GPU is on average 1.9× faster than NVIDIA’s cuDSS solver.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Advances in Mixed Precision Algorithms: 2021 Edition

Over the last year, the ECP xSDK-multiprecision effort has made tremendous progress in developing and deploying new mixed precision technology and customizing the algorithms for the hardware deployed in the ECP flagship supercomputers. The effort also has succeeded in creating a cross-laboratory community of scientists interested in mixed precision technology and now working together in deploying this technology for ECP applications. In this report, we highlight some of the most promising and impactful achievements of the last year. Among the highlights we present are: Mixed precision IR using a dense LU factorization and achieving a 1.8× speedup on Spock; results and strategies for mixed precision IR using a sparse LU factorization; a mixed precision eigenvalue solver; Mixed Precision GMRES-IR being deployed in Trilinos, and achieving a speedup of 1.4× over standard GMRES; compressed Basis (CB) GMRES being deployed in Ginkgo and achieving an average 1.4× speedup over standard GMRES; preparing hypre for mixed precision execution; mixed precision sparse approximate inverse preconditioners achieving an average speedup of 1.2×; and detailed description of the memory accessor separating the arithmetic precision from the memory precision, and enabling memory-bound low precision BLAS 1/2 operations to increase the accuracy by using high precision in the computations without degrading the performance. We emphasize that many of the highlights presented here have also been submitted to peer-reviewed journals or established conferences, and are under peer-review or have already been published.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Advances in Mixed Precision Algorithms: 2021 Edition

Over the last year, the ECP xSDK-multiprecision effort has made tremendous progress in developing and deploying new mixed precision technology and customizing the algorithms for the hardware deployed in the ECP flagship supercomputers. The effort also has succeeded in creating a cross-laboratory community of scientists interested in mixed precision technology and now working together in deploying this technology for ECP applications. In this report, we highlight some of the most promising and impactful achievements of the last year. Among the highlights we present are • Mixed precision IR using a dense LU factorization and achieving a 1.8× speedup on Spock; • Results and strategies for mixed precision IR using a sparse LU factorization; • A mixed precision eigenvalue solver; • Mixed Precision GMRES-IR being deployed in Trilinos, and achieving a speedup of 1.4× over standard GMRES; • Compressed Basis (CB) GMRES being deployed in Ginkgo and achieving an average 1.4× speedup over standard GMRES; • Preparing hypre for mixed precision execution; • Mixed precision sparse approximate inverse preconditioners achieving an average speedup of 1.2×; • Detailed description of the memory accessor separating the arithmetic precision from the memory precision, and enabling memory-bound low precision BLAS 1/2 operations to increase the accuracy by using high precision in the computations without degrading the performance. We emphasize that many of the highlights presented here have also been submitted to peer-reviewed journals or established conferences, and are under peer-review or have already been published.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

On the Efficient Evaluation of the Exchange Correlation Potential on Graphics Processing Unit Clusters

The predominance of Kohn–Sham density functional theory (KS-DFT) for the theoretical treatment of large experimentally relevant systems in molecular chemistry and materials science relies primarily on the existence of efficient software implementations which are capable of leveraging the latest advances in modern high-performance computing (HPC). With recent trends in HPC leading toward increasing reliance on heterogeneous accelerator-based architectures such as graphics processing units (GPU), existing code bases must embrace these architectural advances to maintain the high levels of performance that have come to be expected for these methods. In this work, we purpose a three-level parallelism scheme for the distributed numerical integration of the exchange-correlation (XC) potential in the Gaussian basis set discretization of the Kohn–Sham equations on large computing clusters consisting of multiple GPUs per compute node. In addition, we purpose and demonstrate the efficacy of the use of batched kernels, including batched level-3 BLAS operations, in achieving high levels of performance on the GPU. We demonstrate the performance and scalability of the implementation of the purposed method in the NWChemEx software package by comparing to the existing scalable CPU XC integration in NWChem.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Evaluation of Graph Analytics Frameworks Using the GAP Benchmark Suite

The analysis of connected data is an increasingly important application in high-performance computing. Such analyses can reveal fraudulent patterns in financial transactions, optimize telecommunications networks, predict information flow in social networks, etc. However, the landscape of graph analytics is highly diverse. Graph algorithms stress processor architectures differently, and no one graph can represent all topologies. Consequently, no single approach or framework is expected to be optimal for all graph analytics problems. To help make sense of this diverse landscape, we evaluated four approaches to graph analytics: GraphBLAS, Galois, BGL17, GraphIt; and compare them against hand-tuned implementations that take advantage of hardware features on our test platform. Graph- BLAS formulates graph analytics as sparse linear algebra. Galois provides syntactic constructs for data parallelism over irregular data structures. BGL17 is a generic C++ template library for implementing graph algorithms. GraphIt provides a domain- specific language to describe and optimize graph algorithms. We use the GAP Benchmark Suite to establish baseline performance and guide the side-by-side evaluation of each framework. GAP consists of 30 tests: six graph analytics algorithms (breadth- first search, single-source shortest path, PageRank, betweenness centrality, connected components, and triangle counting) run on five graphs, each with different topological characteristics (e.g., high diameter, skewed degree distribution, high average degree). High-performance reference implementations are included for each benchmark algorithm. Because a graph can be loaded into memory a number of ways (e.g., flat file on disk, compressed sparse format, data frames, retrieved from SQL or NoSQL databases), our evaluation focused on computational performance rather than I/O. Our results show the relative strengths of each framework.

Graph algorithms, Benchmarking, shared-memory prog↗
DOE OSTI2022

Improving the Performance of DGEMM with MoA and Cache-Blocking: Preprint

The goal of this paper is to demonstrate performance enhancements of the high performance dense linear algebra matrix-matrix multiply DGEMM kernel, widely implemented by vendors in the basic linear algebra subroutine BLAS library. The mathematics of arrays (MoA) paradigm due to Mullin (1988) results in contiguous memory accesses in combination with Church-Rosser complete language constructs optimized for target processor architectures [3]. Our performance studies demonstrate that the MoA implementation of DGEMM combined with optimal cache-blocking strategies results in at least a 25% performance gain on both Intel Xeon Skylake and IBM Power-9 processors over the vendor supplied Intel MKL and IBM ESSL basic linear algebra libraries. Results are presented for the NREL Eagle and ORNL Summit supercomputers.

cache-blocking↗
DOE OSTI2022

Threaded Multi-Core GEMM with MoA and Cache-Blocking: Preprint

A threaded multi-core implementation of the high performance dense linear algebra matrix-matrix multiply GEMM kernel is described. This kernel is widely implemented by vendors in the basic linear algebra subroutine BLAS library. The mathematics of arrays (MoA) paradigm due to Mullin (1988) results in contiguous memory accesses by employing outer-product forms. Our performance studies demonstrate that the MoA implementation of double precision DGEMM combined with optimal cache-blocking strategies results in at least a 25% performance gain on the Intel Xeon Skylake processor over the vendor supplied Intel MKL basic linear algebra libraries. Results are presented for the NREL Eagle supercomputer. The multi-core DGEMM achieves over 100 GigaFlops/sec with eight openMP threads.

cache-blocking↗
DOE OSTI2023

Atomic Diffusion, Segregation, and Grain Boundary Migration in Nickel-Based Alloys from Molecular Dynamics Simulations

Grain boundary diffusion and metal mobility in alloys control material performance in many applications and yet remain poorly understood at a mechanistic level. With advances in accessible time and length scales for computational molecular simulations, and recent force field developments, we now possess tools to help unravel those mechanisms. Using large-scale molecular dynamics simulations, here we examined vacancy-mediated diffusion processes in Ni-5Cr alloy with low and high-energy grain boundaries. We show that atomic diffusion inside the grain boundary plane is about four times higher than bulk diffusion, at any temperature, and exhibits a typical Arrhenius behavior with a very small energy barrier (0~.8 eV for Cr and 0.7 eV for Ni within 1300-1600 K). Additionally, the fastest diffusing species inverts; Cr diffusion was faster than Ni in the bulk but slower in the grain boundaries. This is attributed to the creation of high cohesive energy clusters of Cr at the grain boundary. Grain boundary migration was also observed to be temperature dependent and appears to be two times higher in the 5% Cr alloy than in pure Ni, highlighting the important role of the alloying element on grain boundary motion.

Simonnin, Pauline GN↗
DOE OSTI2021

Radiation-Enhanced Anion Transport in Hematite

The influence of radiation-induced (1 MeV energy H+ to ~0.1 dpa at 450°C), non-equilibrium point defect populations on mass transport is studied with an integrated campaign of experimental and theoretical methods. Using epitaxial thin films of hematite with embedded 18O tracer layers and nanoscale atom probe tomography measurements, it is shown that anion self-diffusion is enhanced by at least 2 orders of magnitude under irradiation compared to thermal diffusion alone. Complementary scanning transmission electron microscopy of vacuum annealed specimens, reveals associated microstructural changes in the oxide films, including local phase transformation to Fe3O4 and the development of nanoscale voids from vacancy coalescence. Point defect formation and migration energies were computed from density functional theory and applied within the context of chemical rate theory to analyze contributions from both interstitial and vacancy mechanisms to self-diffusion in thermal and irradiation conditions. Comparisons are made between calculated, literature and newly measured self-diffusion values, revealing good agreement on the magnitude of radiation-enhanced anion diffusion. Further, the model suggests a transition from vacancy to interstitialcy mechanisms at low temperatures and high oxygen activity, consistent with the varied activation energies reported from prior studies.

iron oxides, isotopic tracers, atom probe tomograp↗
DOE OSTI2024

Readout optimization of multi-amplifier sensing charge-coupled devices for single-quantum measurement

The non-destructive readout capability of the Skipper Charge Coupled Device (CCD) has been demonstrated to reduce the noise limitation of conventional silicon devices to levels that allow single-photon or single-electron counting. The noise reduction is achieved by taking multiple measurements of the charge in each pixel. These multiple measurements come at the cost of extra readout time, which has been a limitation for the broader adoption of this technology in particle physics, quantum imaging, and astronomy applications. This work presents recent results of a novel sensor architecture that uses multiple non-destructive floating-gate amplifiers in series to achieve sub-electron readout noise in a thick, fully-depleted silicon detector to overcome the readout time overhead of the Skipper-CCD. This sensor is called the Multiple-Amplifier Sensing Charge-Coupled Device (MAS-CCD) can perform multiple independent charge measurements with each amplifier, and the measurements from multiple amplifiers can be combined to further reduce the readout noise. We will show results obtained for sensors with 8 and 16 amplifiers per readout stage in new readout operations modes to optimize its readout speed. The noise reduction capability of the new techniques will be demonstrated in terms of its ability to reduce the noise by combining the information from the different amplifiers, and to resolve signals in the order of a single photon per pixel. The first readout operation explored here avoids the extra readout time needed in the MAS-CCD to read a line of the sensor associated with the extra extent of the serial register. The second technique explore the capability of the MAS-CCD device to perform a region of interest readout increasing the number of multiple samples per amplifier in a targeted region of the active area of the device.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Effects of Radiation-Induced Defects on Corrosion

The next generation of nuclear reactors will expose materials to conditions that, in some cases, are even more extreme than those in current fission reactors, inevitably leading to new materials science challenges. Radiation-induced damage and corrosion are two key phenomena that must be understood both independently and synergistically, but their interactions are often convoluted. In the light water reactor community, a tremendous amount of work has been done to illuminate irradiation-corrosion effects, and similar efforts are under way for heavy liquid metal and molten salt environments. While certain effects, such as radiolysis and irradiation-assisted stress corrosion cracking, are reasonably well established, the basic science of how irradiation-induced defects in the base material and the corrosion layer influence the corrosion process still presents many unanswered questions. In this review, we summarize the work that has been done to understand these coupled extremes, highlight the complex nature of this problem, and identify key knowledge gaps.

36 MATERIALS SCIENCE↗
DOE OSTI2025

The Linear Collider Facility (LCF) at CERN

In this paper we outline a proposal for a Linear Collider Facility as the next flagship project for CERN. It offers the opportunity for a timely, cost-effective and staged construction of a new collider that will be able to comprehensively map the Higgs boson's properties, including the Higgs field potential, thanks to a large span in centre-of-mass energies and polarised beams. A comprehensive programme to study the Higgs boson and its closest relatives with high precision requires data at centre-of-mass energies from the Z pole to at least 1 TeV. It should include measurements of the Higgs boson in both major production mechanisms, ee -> ZH and ee -> vvH, precision measurements of gauge boson interactions as well as of the W boson, Higgs boson and top-quark masses, measurement of the top-quark Yukawa coupling through ee ->ttH, measurement of the Higgs boson self-coupling through HH production, and precision measurements of the electroweak couplings of the top quark. In addition, ee collisions offer discovery potential for new particles complementary to HL-LHC.

43 PARTICLE ACCELERATORS↗
DOE OSTI2023

The Sluggish Diffusion of Cations in CeO 2 Probed through Molecular Dynamics and Metadynamics Simulations

Cation diffusion in fluorite‐structured CeO 2 , though far slower than anion diffusion, is an important, high‐temperature process because it governs diverse fabrication and degradation phenomena. Herein, cation diffusion is studied by means of classical molecular dynamics and metadynamics simulations. Three different mechanisms are examined: migration involving an isolated cerium vacancy, migration involving a cerium vacancy in a defect associate with an oxygen vacancy, and migration involving a cation divacancy. For each mechanism, defect diffusion coefficients are calculated as a function of temperature, from which the respective activation enthalpy of defect migration is obtained. Through comparisons with experimental cation diffusion data (specifically, of the absolute magnitude of the cation diffusivity as well as its activation enthalpy), it is concluded that cation diffusion takes place predominantly neither by isolated vacancies nor by cation vacancy–oxygen vacancy associates but by cation divacancies.

36 MATERIALS SCIENCE↗
DOE OSTI2025

On the Structure–Property Relationship of Semi‐Coherent FeCr 2 O 4 /Cr 2 O 3 Spinel/Corundum Interfaces

Abstract Oxide heterointerfaces are extremely common in both natural and artificial composite structures, including corroded structural materials. Often, key properties such as segregation and atomic transport are dictated by the structure of these interfaces. However, despite this critical link, very few heterointerfaces have been studied in any detail at the atomic scale. Here, one important oxide heterointerface is examined, between spinel and corundum, using the chemical system FeCr 2 O 4 /Cr 2 O 3 as a representative and technologically important case. Using atomistic simulation techniques, it is found that the structure, particularly the local chemistry, of the interface depends on the crystal chemistry at the interface. This atomic and chemical structure further impacts important properties such as defect segregation and mass transport. It is found that defects can nucleate at some regions of these interfaces and migrate back and forth across the corundum layer, suggesting high atomic mobility that may be important for the evolution of spinel/corundum composite structures in extreme conditions.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Lattice Relaxations in Bixbyite‐Structured Rare‐Earth Sesquioxides

This report examines atomic relaxations in rare‐earth sesquioxides with the cubic bixbyite crystal structure. In particular, the experimentally determined unit cell atom positions in bixbyite compounds are compared to “ideal” bixbyite atom positions, where the concept of ideality is based on similarities between the bixbyite and fluorite crystal structures. Analyses indicate that all rare‐earth sesquioxide compounds deviate from ideality in similar ways and that there is a trend wherein the magnitudes of these atomic deviations decrease with increasing cationic size. The deviations from an ideal, fluorite‐like structure produce highly distorted coordination polyhedra and variations in metal‐oxygen bond lengths. A modified bond valence sum analysis revealed that the first nearest neighbor cation‐anion bond length variations lead to large (20%) variations in cation‐anion bond strength. This report also provides a qualitative analysis regarding the accuracy of atomic relaxed deviation parameters, based on x‐ray diffraction measurements. The analysis indicates that uncertainties in the accuracy of measured oxygen relaxed deviation parameters in bixbyite sesquioxides are likely much greater than the published uncertainties.

36 MATERIALS SCIENCE↗