Search NASA⌕ Search

SEARCH · Search NASA

Results for “data reuse”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Evaluating Spatial Accelerator Architectures with Tiled Matrix-Matrix Multiplication.

There is a growing interest in custom spatial accelerators for machine learning applications. These accelerators employ a spatial array of processing elements (PEs) interacting via custom buffer hierarchies and networks-on-chip. The efficiency of these accelerators comes from employing optimized dataflow (i.e., spatial/temporal partitioning of data across the PEs and fine-grained scheduling) strategies to optimize data reuse. The focus of this work is to evaluate these accelerator architectures using a tiled general matrix-matrix multiplication (GEMM) kernel. To do so, we develop a framework that finds optimized mappings (dataflow and tile sizes) for a tiled GEMM for a given spatial accelerator and workload combination, leveraging an analytical cost model for runtime and energy. Finally, our evaluations over five spatial accelerators demonstrate that the tiled GEMM mappings systematically generated by our framework achieve high performance on various GEMM workloads and accelerators.

42 ENGINEERING↗
DOE OSTI2017

Cache Locality Optimization for Recursive Programs

We present an approach to optimize the cache locality for recursive programs by dynamically splicing--recursively interleaving--the execution of distinct function invocations. By utilizing data effect annotations, we identify concurrency and data reuse opportunities across function invocations and interleave them to reduce reuse distance. We present algorithms that efficiently track effects in recursive programs, detect interference and dependencies, and interleave execution of function invocations using user-level (non-kernel) lightweight threads. To enable multi-core execution, a program is parallelized using a nested fork/join programming model. Our cache optimization strategy is designed to work in the context of a random work stealing scheduler. We present an implementation using the MIT Cilk framework that demonstrates significant improvements in sequential and parallel performance, competitive with a state-of-the-art compile-time optimizer for loop programs and a domain- specific optimizer for stencil programs.

Lifflander, Jonathan↗
DOE OSTI2022

MemHC: An Optimized GPU Memory Management Framework for Accelerating Many-body Correlation

The many-body correlation function is a fundamental computation kernel in modern physics computing applications, e.g., Hadron Contractions in Lattice quantum chromodynamics (QCD). This kernel is both computation and memory intensive, involving a series of tensor contractions, and thus usually runs on accelerators like GPUs. Existing optimizations on many-body correlation mainly focus on individual tensor contractions (e.g., cuBLAS libraries and others). In contrast, this work discovers a new optimization dimension for many-body correlation by exploring the optimization opportunities among tensor contractions. More specifically, it targets general GPU architectures (both NVIDIA and AMD) and optimizes many-body correlation’s memory management by exploiting a set of memory allocation and communication redundancy elimination opportunities: first, GPU memory allocation redundancy: the intermediate output frequently occurs as input in the subsequent calculations; second, CPU-GPU communication redundancy: although all tensors are allocated on both CPU and GPU, many of them are used (and reused) on the GPU side only, and thus, many CPU/GPU communications (like that in existing Unified Memory designs) are unnecessary; third, GPU oversubscription: limited GPU memory size causes oversubscription issues, and existing memory management usually results in near-reuse data eviction, thus incurring extra CPU/GPU memory communications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Software-Hardware Co-design of Heterogeneous SmartNIC System for Recommendation Models Inference and Training

Deep Learning Recommendation Models (DLRMs) are critical applications in various domains and have evolved as one of the single largest machine learning applications. Trillions of DLRM parameters exceed the on-chip memory capacity of GPUs. Large-scale multi-node systems are required for distributed DLRM inference and training, which suffer from the all-to-all communication bottleneck, mainly limiting the scalability of ever-growing DLRMs. In recent years, SmartNICs have evolved with coupled computation and communication capabilities providing opportunities for a powerful heterogeneous device in the system. However, there isn't such a distributed system that fully leverages the abundant smartNIC resources that resolve the scalability issue of DLRMs. In this work, we proposed a software-hardware co-design of a heterogeneous smartNIC system that resolves the communication bottleneck of distributed DLRMs, mitigates the memory bandwidth pressure, and improves computation efficiency. We provide a set of smartNIC designs of cache systems (including local cache and remote cache) and smartNIC computation kernels which reduce data movement, relieve memory lookup intensity, and improve the GPU's computation efficiency. In addition, we propose a graph algorithm that improves the data locality of queries within batches which optimizes the overall system performance with higher data reuse. Our evaluation shows that our system achieves 2.1x latency speedup for inference and 1.6x throughput speedup for training.

Guo, Anqi↗
DOE OSTI2023

FLASH: FPGA-Accelerated Smart Switches with GCN Case Study

Some communication switches, e.g., the Mellanox SHArP and those in the IBM BlueGene clusters, are augmented to process packets at the application level with fixed-function collectives. This approach, however, lacks flexibility, which limits their applicability in diverse and dynamic workloads. Recently, a new type of programmable packet processor, which uses high-level languages, e.g., P4, has emerged as possible candidates. P4-based switches, however, fall short in certain applications, including machine learning, where capabilities not currently supported by P4 are needed. These include more complex calculation, such as sparse computation and fused multiply-accumulate, data-intensive floating point operations, data reuse, and significant memory. The problem addressed here is that such a switch augmentation needs to support: a large amount of state, significant flexible compute capability, and ease of programming, all while maintaining full functionality, including ensuring high throughput, and demonstrating utility. In this work, we propose a programmable look-aside-type accelerator that can be embedded into, or attached to, existing communication switch pipelines and that is capable of processing packets at line-rate. The proposed in-switch accelerator is based on mixing an ISA (subset of RISC-V instructions) with dataflow graphs (found in CGRAs). To augment performance, vector instructions are also supported. To facilitate usability, we have developed a complete toolchain to compile user-provided C/C++ codes to appropriate back-end instructions for configuring the accelerator. While this approach is flexible enough to support various workloads, in this paper, we consider Graph Convolutional Networks (GCNs) as a case study. Experimental results show that this approach considerably improves the performance of distributed GCN applications.

Haghi, Pouya↗
DOE OSTI2017

Efficient Machine Learning Approach for Optimizing Scientific Computing Applications on Emerging HPC Architectures

Efficient parallel implementations of scientific applications on multi-core CPUs with accelerators such as GPUs and Xeon Phis is challenging. This requires - exploiting the data parallel architecture of the accelerator along with the vector pipelines of modern x86 CPU architectures, load balancing, and efficient memory transfer between different devices. It is relatively easy to meet these requirements for highly structured scientific applications. In contrast, a number of scientific and engineering applications are unstructured. Getting performance on accelerators for these applications is extremely challenging because many of these applications employ irregular algorithms which exhibit data-dependent control-ow and irregular memory accesses. Furthermore, these applications are often iterative with dependency between steps, and thus making it hard to parallelize across steps. As a result, parallelism in these applications is often limited to a single step. Numerical simulation of charged particles beam dynamics is one such application where the distribution of work and memory access pattern at each time step is irregular. Applications with these properties tend to present significant branch and memory divergence, load imbalance between different processor cores, and poor compute and memory utilization. Prior research on parallelizing such irregular applications have been focused around optimizing the irregular, data-dependent memory accesses and control-ow during a single step of the application independent of the other steps, with the assumption that these patterns are completely unpredictable. We observed that the structure of computation leading to control-ow divergence and irregular memory accesses in one step is similar to that in the next step. It is possible to predict this structure in the current step by observing the computation structure of previous steps. In this dissertation, we present novel machine learning based optimization techniques to address the parallel implementation challenges of such irregular applications on different HPC architectures. In particular, we use supervised learning to predict the computation structure and use it to address the control-ow and memory access irregularities in the parallel implementation of such applications on GPUs, Xeon Phis, and heterogeneous architectures composed of multi-core CPUs with GPUs or Xeon Phis. We use numerical simulation of charged particles beam dynamics simulation as a motivating example throughout the dissertation to present our new approach, though they should be equally applicable to a wide range of irregular applications. The machine learning approach presented here use predictive analytics and forecasting techniques to adaptively model and track the irregular memory access pattern at each time step of the simulation to anticipate the future memory access pattern. Access pattern forecasts can then be used to formulate optimization decisions during application execution which improves the performance of the application at a future time step based on the observations from earlier time steps. In heterogeneous architectures, forecasts can also be used to improve the memory performance and resource utilization of all the processing units to deliver a good aggregate performance. We used these optimization techniques and anticipation strategy to design a cache-aware, memory efficient parallel algorithm to address the irregularities in the parallel implementation of charged particles beam dynamics simulation on different HPC architectures. Experimental result using a diverse mix of HPC architectures shows that our approach in using anticipation strategy is effective in maximizing data reuse, ensuring workload balance, minimizing branch and memory divergence, and in improving resource utilization.

Arumugam, Kamesh↗
DOE OSTI2020

Multigrid-Reduction-in-Time for the Rotating Shallow Water Equations

We consider multilevel time-parallel methods for the numerical solution of the rotating shallow water equations. In particular, the multigrid-reduction-in-time (MGRIT) algorithm is used for the parallel time integration. An asymptotic model is used at the coarse levels while the full model is employed at the finer levels. The asymptotic model is well-suited for highly oscillatory partial differential equations like the rotating shallow water equations because it can accurately and stably take the required large time-steps on coarse levels. Our work exploits the flexibility of the MGRIT algorithm in terms of the number of levels and relaxation schemes to show some computational benefits, especially with respect to FCF-relaxation and data reuse.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Evaluating Spatial Accelerator Architectures with Tiled Matrix-Matrix Multiplication

There is a growing interest in custom spatial accelerators for machine learning applications. These accelerators employ a spatial array of processing elements (PEs) interacting via custom buffer hierarchies and networks-on-chip. The efficiency of these accelerators comes from employing optimized dataflow (i.e., spatial/temporal partitioning of data across the PEs and fine-grained scheduling) strategies to optimize data reuse. The focus of this work is to evaluate these accelerator architectures using a tiled general matrix-matrix multiplication (GEMM) kernel. To do so, we develop a framework that finds optimized mappings (dataflow and tile sizes) for a tiled GEMM for a given spatial accelerator and workload combination, leveraging an analytical cost model for runtime and energy. Our evaluations over five spatial accelerators demonstrate that the tiled GEMM mappings systematically generated by our framework achieve high performance on various GEMM workloads and accelerators.

43 PARTICLE ACCELERATORS↗
NASA NTRS1998

On the Efficacy of Source Code Optimizations for Cache-Based Systems

Obtaining high performance without machine-specific tuning is an important goal of scientific application programmers. Since most scientific processing is done on commodity microprocessors with hierarchical memory systems, this goal of "portable performance" can be achieved if a common set of optimization principles is effective for all such systems. It is widely believed, or at least hoped, that portable performance can be realized. The rule of thumb for optimization on hierarchical memory systems is to maximize temporal and spatial locality of memory references by reusing data and minimizing memory access stride. We investigate the effects of a number of optimizations on the performance of three related kernels taken from a computational fluid dynamics application. Timing the kernels on a range of processors, we observe an inconsistent and often counterintuitive impact of the optimizations on performance. In particular, code variations that have a positive impact on one architecture can have a negative impact on another, and variations expected to be unimportant can produce large effects. Moreover, we find that cache miss rates - as reported by a cache simulation tool, and confirmed by hardware counters - only partially explain the results. By contrast, the compiler-generated assembly code provides more insight by revealing the importance of processor-specific instructions and of compiler maturity, both of which strongly, and sometimes unexpectedly, influence performance. We conclude that it is difficult to obtain performance portability on modern cache-based computers, and comment on the implications of this result.

VanderWijngaart, Rob F.↗
NASA NTRS1998

On the Efficacy of Source Code Optimizations for Cache-Based Systems

Obtaining high performance without machine-specific tuning is an important goal of scientific application programmers. Since most scientific processing is done on commodity microprocessors with hierarchical memory systems, this goal of "portable performance" can be achieved if a common set of optimization principles is effective for all such systems. It is widely believed, or at least hoped, that portable performance can be realized. The rule of thumb for optimization on hierarchical memory systems is to maximize temporal and spatial locality of memory references by reusing data and minimizing memory access stride. We investigate the effects of a number of optimizations on the performance of three related kernels taken from a computational fluid dynamics application. Timing the kernels on a range of processors, we observe an inconsistent and often counterintuitive impact of the optimizations on performance. In particular, code variations that have a positive impact on one architecture can have a negative impact on another, and variations expected to be unimportant can produce large effects. Moreover, we find that cache miss rates-as reported by a cache simulation tool, and confirmed by hardware counters-only partially explain the results. By contrast, the compiler-generated assembly code provides more insight by revealing the importance of processor-specific instructions and of compiler maturity, both of which strongly, and sometimes unexpectedly, influence performance. We conclude that it is difficult to obtain performance portability on modern cache-based computers, and comment on the implications of this result.

VanderWijngaart, Rob F.↗
NASA NTRSDate not supplied

Beyond Fair: Engagement, Data Usability, and Open Community Productivity through the NASA Open Science Data Repository

The FAIR principle (findable, accessible, interoperable, and reusable) governs the storage and sharing of NASA space biology and health data[1]. These guiding principles maximize reuse of data and the reproducibility of scientific findings. The NASA Open Science Data Repository (OSDR; an expansion of NASA GeneLab) was built on the FAIR principles and houses over 500 studies and close to 1000 datasets from decades of space life sciences experiments. OSDR embodies the FAIR principles through data governance that includes mediated, embargoed, and fully open access data. The FAIR data governance principles were recently proposed to be expanded to encompass a FAIREST framework for assessing research data repositories (FAIR + Engagement, Social connections, and Trust)[2]. FAIREST emphasizes the importance of data repositories engaging with the scientific community and gaining the trust of researchers regarding data quality. Trust also refers to the TRUST principles developed for assessment of digital repositories: Transparency, Responsibility, User Focus, Sustainability, Technology[3]. We present the “Open Science for Life in Space” Analysis Working Groups (AWGs) as evidence regarding the power of engagement, social connections, and trust which has enhanced OSDR’s capabilities and productivity. AWG members engage in two main activities. One, members provide feedback on OSDR scientific standards for data ingestion, curation, and reuse (study, subject and assay metadata; processing pipelines; dataset formats and uniformed structures for machine-readability). Two, AWG members collaborate to mine-reuse OSDR data to conduct scientific analysis. With nearly 800 active members, the AWGs have resulted in 32 publications re-using OSDR data and contributed many papers in two major special issues in Cell (2020) and Nature (2024). AWGs also serve as networking groups, facilitate social connections between researchers at all levels of experience, and also have a social online ‘Forum’ used to keep members informed on projects and opportunities. This community-centric, productive, and trustworthy data culture has resulted in a broader effect with international space agencies, academics, and the commercial space sector wanting to submit their data to OSDR. Ten studies of Inspiration 4 data were recently publicly released by OSDR, as were some JAXA human data. Coming up soon in OSDR are data submissions from the European Space Agency, Virgin Galactic PIs, and SpaceX Polaris Dawn. A major benefit of OSDR is the array of standardized and uniformly formatted data (which was developed through AWG member consensus), from which visualization tools, analysis tools, and machine learning models can be built or trained. This talk will cover the Multi-Study Visualization Tool, the Environmental Data Application, RadLab, and a UCSF-NSF funded knowledge graph biomedical health discovery tool ‘SPOKE’ currently being integrated with OSDR. OSDR also provides training programs in bioinformatics and machine learning to improve the scientific community’s awareness of data availability and to boost their ability to perform data analysis. The increasing engagement of the scientific community and the public with technologies powered by artificial intelligence (AI) heightens the need for data analysis to be transparent. The AI for Life in Space initiative leverages the data products provided in OSDR to train AI models, with an emphasis on explainable and trustworthy AI, which would not be possible without FAIR data and metadata. Overall, here we will demonstrate the importance for NASA life sciences data repositories to adhere to the FAIREST framework, by providing examples and success stories from different aspects of OSDR.

data↗
DOE OSTI2025

A standards perspective on genomic data reusability and reproducibility

Genomic and metagenomic sequence data provides an unprecedented ability to re-examine findings, offering a transformative potential for advancing research, developing computational tools, enhancing clinical applications, and fostering scientific collaboration. However, effective and ethical reuse of genomics data is hampered by numerous technical and social challenges. The International Microbiome and Multi’Omics Standards Alliance (IMMSA, https://www.microbialstandards.org/) and the Genomic Standards Consortium (GSC, https://gensc.org) hosted a 5-part seminar series “A Year of Data Reuse” in 2024 to explore challenges and opportunities of data reuse and reproducibility across disparate domains of the genomic sciences. Addressing these challenges will require a multifaceted approach, including common metadata reporting, clear communication, standardized protocols, improved data management infrastructure, ethical guidelines, and collaborative policies that prioritize transparency and accessibility. We offer strategies to enable responsible and technically feasible data reuse, recognition of data reproducibility challenges, and emphasizing the importance of cross-disciplinary efforts in the pursuit of open science and data-driven innovation.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS1978

Skylab reuse study, reference data, part 1

The accommodations provided by the airlock module and the orbital workshop were completely examined with the thought of total reactivation as an enhancement to the STS long duration missions. Each subsystem is described and a summary of subsystem performance during the Skylab missions is presented. End-of-mission status and the status of today for each subsystem is shown together with refurbishment/resupply requirements and refurb kit descriptions to restore Skylab to full operational capability. An inspection/refurbishment and operations plan for Skylab is included. The initial Shuttle-tended operational activity would provide a safe, effective phase of Skylab rehabilitation while simultaneously benefitting the Orbiter crew through the addition of private accommodations, off-duty recreation area, and physical conditioning equipment. This period would also permit exercising selected onboard experiments.

Source record↗
NASA NTRS1978

Skylab reuse study, reference data. Part 2: Appendixes

Contents: (1) evaluations of the dysbarism risk associated with a Skylab revisit by shuttle; (2) mission model/payload data sheets; (3) life sciences utilization of on-board Skylab medical facilities; (4) airlock module description; and (5) orbital workshop description.

Source record↗
DOE OSTI2011

Easy Web Interfaces to IDL Code for NSTX Data Analysis

Reusing code is a well-known Software Engineering practice to substantially increase the efficiency of code production, as well as to reduce errors and debugging time. A variety of "Web Tools" for the analysis and display of raw and analyzed physics data are in use on NSTX [1], and new ones can be produced quickly from existing IDL [2] code. A Web Tool with only a few inputs, and which calls an IDL routine written in the proper style, can be created in less than an hour; more typical Web Tools with dozens of inputs, and the need for some adaptation of existing IDL code, can be working in a day or so. Efficiency is also increased for users of Web Tools because o f the familiar interface of the web browser, and not needing X-windows, accounts, passwords, etc. Web Tools were adapted for use by PPPL physicists accessing EAST data stored in MDSplus with only a few man-weeks of effort; adapting to additional sites should now be even easier. An overview of Web Tools in use on NSTX, and a list of the most useful features, is also presented.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2018

The OpenACC data model: Preliminary study on its major challenges and implementations

This paper describes how the OpenACC data model is implemented in current OpenACC compilers, ranging from research compilers (OpenUH and OpenARC) to a commercial compiler (the PGI OpenACC compiler). First, we summarize various memory architectures in today’s accelerator systems. We then describe details and issues in implementing the OpenACC data model in three different OpenACC compilers. This includes managing page tables, asynchronous data transfers, asynchronous memory allocate and free, host data construct, aliasing on a data directive, reusing device memory, partially present data, and adjacent data. We also discusses ongoing work to manage large, complex dynamic data structures. We measured the present table lookups, device memory allocation, pinned memory allocation, and managed memory in the three OpenACC compilers using eight OpenACC applications (seven from the SPEC ACCEL benchmark suite and a shock-hydrodynamics mini-application called LULESH).

97 MATHEMATICS AND COMPUTING↗