Search NASA⌕ Search

SEARCH · Search NASA

Results for “cache”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
NASA NTRS2012

Initial SEE Testing of Maestro

We have reported on initial SEE sensitivity of the full 49-core Maestro device. Supporting the low-level structures and qualitative system observation goals of phase 1 of testing. Observed sensitivities found to be consistent with Boeing predictions. Highlighted by the L1 data cache sensitivity which drives the rates on the current Maestro device. Presented details to the hardware and software setups that show where the limitations - highlighting future work. Key future work includes testing with memory and IO ports.

cache sensitivity↗
NASA NTRS2012

Rotary Percussive Sample Acquisition Tool

As part of a potential Mars Sample Return campaign NASA is studying a sample caching mission to Mars, with a possible 2018 launch opportunity. As such, a Sample Acquisition Tool (SAT) has been developed in support of the Integrated Mars Sample Acquisition and Handling (IMSAH) architecture as it relates to the proposed Mars Sample Return (MSR) campaign. The tool allows for core generation and capture directly into a sample tube. In doing so, the sample tube becomes the fundamental handling element within the IMSAH sample chain reducing the risk associated with sample contamination as well as the need to handle a sample of unknown geometry. The tool's functionality was verified utilizing a proposed rock test suite that encompasses a series of rock types that have been utilized in the past to qualify Martian surface sampling hardware. The corresponding results have shown the tool can effectively generate, fracture, and capture rock cores while maintaining torque margins of no less than 50% with an average power consumption of no greater than 90W and a tool mass of less than 6kg.

Sample Acquisition and Caching (SAC)↗
DOE OSTI2022

Performance assessment of ensembles of in situ workflows under resource constraints

Summary Scientific breakthroughs in biomolecular methods and improvements in hardware technology have shifted from a long‐running simulation to a large set of shorter simulations running simultaneously, called an ensemble. In an ensemble, simulations are usually coupled with analyses of data produced by the simulations. In situ methods can be used to analyze large volumes of data generated by scientific simulations at runtime (i.e., simulations and analyses are performed concurrently). In this work, we study the execution of ensemble‐based simulations paired with in situ analyses using in‐memory staging methods. Using an ensemble of molecular dynamics in situ workflows with multiple simulations and analyses, we first show that collecting traditional metrics such as makespan, instructions per cycle, memory usage, or cache miss ratio is not sufficient to characterize complex behaviors of ensembles. We propose a method to evaluate the performance of ensembles of workflows that captures multiple resource usage aspects: resource efficiency, resource allocation, and resource provisioning. Experimental results demonstrate that the proposed method can effectively distinguish the performance of different component placements in an ensemble with up to 32 ensemble members. By evaluating different co‐location scenarios, our proposed performance indicators demonstrate benefits of co‐locating simulation and coupled analyses within a compute node.

Do, Tu Mai Anh↗
DOE OSTI2022

Just-in-Time Compilation and Link-Time Optimization for OpenMP Target Offloading

Following the mass adoption of external accelerators for high performance computing, the overall performance of many applications has become increasingly dependent on relatively small accelerated kernels. As static analysis is fundamentally limited by dynamic values and external definitions, standard ahead-of-time compilation is not always sufficient to achieve the best performance. Furthermore, many users looking to port an existing application to run on an external accelerator will not want to fundamentally restructure their programs. These and other problems can be addressed through both link-time optimization (LTO) and just-in-time (JIT) compilation, but until now had sparse and inconsistent support from the compiler. In this work, we present a new compilation method that enables device-side LTO as well as a transparent JIT compilation tool-chain for OpenMP target offloading. Our contributions include an entirely new device linking and embedding scheme to enable LTO as well as a novel JIT engine to efficiently optimize OpenMP offloading regions at run-time. We also introduce a persistent caching system to improve end-to-end runtime using the JIT engine and minimize kernel launching overheads. We measure the performance of our LTO and JIT implementation via several real-world scientific applications. With our optimizations we observe significant improvements through LTO on large applications as well as significant end-to-end execution time improvement using JIT.

Tian, Shilei↗
DOE OSTI2025

Benchmarking Operators in Deep Neural Networks for Improving Performance Portability of SYCL

SYCL is a portable programming model for heterogeneous computing, so it is important to obtain reasonable performance portability of SYCL. Towards the goal of better understanding and improving performance portability of SYCL for machine learning workloads, we have been developing benchmarks for basic operators in deep neural networks (DNNs). These operators could be offloaded to heterogeneous computing devices such as graphics processing units (GPUs) to speed up computation. In this paper, we introduce the benchmarks, evaluate the performance of the operators on GPU-based systems, and describe the causes of the performance gap between the SYCL and Compute Unified Device Architecture (CUDA) kernels. We find that the causes are related to the utilization of the texture cache for read-only data, optimization of the memory accesses with strength reduction, use of local memory, and register usage per thread. We hope that the efforts of developing benchmarks for studying performance portability will stimulate discussion and interactions within the community.

Jin, Zheming [ORNL] (ORCID:000000027197780X)↗
DOE OSTI2016

Optimizing Excited-State Electronic-Structure Codes for Intel Knights Landing: A Case Study on the BerkeleyGW Software

We profile and optimize calculations performed with the BerkeleyGW code on the Xeon-Phi architecture. BerkeleyGW depends both on hand-tuned critical kernels as well as on BLAS and FFT libraries. We describe the optimization process and performance improvements achieved. We discuss a layered parallelization strategy to take advantage of vector, thread and node-level parallelism. We discuss locality changes (including the consequence of the lack of L3 cache) and effective use of the on-package high-bandwidth memory. We show preliminary results on Knights-Landing including a roofline study of code performance before and after a number of optimizations. We find that the GW method is particularly well-suited for many-core architectures due to the ability to exploit a large amount of parallelism over plane-wave components, band-pairs, and frequencies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Delaunay walk for fast nearest neighbor: accelerating correspondence matching for ICP

Point set registration algorithms such as Iterative Closest Point (ICP) are commonly utilized in time-constrained environments like robotics. Finding the nearest neighbor of a point in a reference 3D point set is a common operation in ICP and frequently consumes at least 90% of the computation time. We introduce a novel approach to performing the distance-based nearest neighbor step based on Delaunay triangulation. This greedy algorithm finds the nearest neighbor of a query point by traversing the edges of the Delaunay triangulation created from a reference 3D point set. Our work integrates the Delaunay traversal into the correspondences search of ICP and exploits the iterative aspect of ICP by caching previous correspondences to expedite each iteration. An algorithmic analysis and comparison is conducted showing an order of magnitude speedup for both serial and vector processor implementation.

3d point cloud processing↗
DOE OSTI2021

Perseverance’s Scanning Habitable Environments with Raman and Luminescence for Organics and Chemicals (SHERLOC) Investigation

The Scanning Habitable Environments with Raman and Luminescence for Organics and Chemicals (SHERLOC) is a robotic arm-mounted instrument on NASA’s Perseverance rover. SHERLOC has two primary boresights. The Spectroscopy boresight generates spatially resolved chemical maps using fluorescence and Raman spectroscopy coupled to microscopic images (10.1 μm/pixel). The second boresight is a Wide Angle Topographic Sensor for Operations and eNgineering (WATSON); a copy of the Mars Science Laboratory (MSL) Mars Hand Lens Imager (MAHLI) that obtains color images from microscopic scales (~13 μm/pixel) to infinity. SHERLOC Spectroscopy focuses a 40 μs pulsed deep UV neon-copper laser (248.6 nm), to a ~100 μm spot on a target at a working distance of ~48 mm. Fluorescence emissions from organics, and Raman scattered photons from organics and minerals, are spectrally resolved with a single diffractive grating spectrograph with a spectral range of 250 to ~370 nm. Because the fluorescence and Raman regions are naturally separated with deep UV excitation (<250 nm), the Raman region ~ 800 – 4000 cm -1 (250 to 273 nm) and the fluorescence region (274 to ~370 nm) are acquired simultaneously without time gating or additional mechanisms. SHERLOC science begins by using an Autofocus Context Imager (ACI) to obtain target focus and acquire 10.1 μm/pixel greyscale images. Chemical maps of organic and mineral signatures are acquired by the orchestration of an internal scanning mirror that moves the focused laser spot across discrete points on the target surface where spectra are captured on the spectrometer detector. ACI images and chemical maps (< 100 μm/mapping pixel) will enable the first Mars in situ view of the spatial distribution and interaction between organics, minerals, and chemicals important to the assessment of potential biogenicity (containing CHNOPS). Single robotic arm placement chemical maps can cover areas up to 7x7 mm in area and, with the < 10 min acquisition time per map, larger mosaics are possible with arm movements. This microscopic view of the organic geochemistry of a target at the Perseverance field site, when combined with the other instruments, such as Mastcam-Z, PIXL, and SuperCam, will enable unprecedented analysis of geological materials for both scientific research and determination of which samples to collect and cache for Mars sample return.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Persistent Sampling: Enhancing the Efficiency of Sequential Monte Carlo

Sequential Monte Carlo (SMC) samplers are powerful tools for Bayesian inference but suffer from high computational costs due to their reliance on large particle ensembles for accurate estimates. We introduce persistent sampling (PS), an extension of SMC that systematically retains and reuses particles from all prior iterations to construct a growing, weighted ensemble. By leveraging multiple importance sampling and resampling from a mixture of historical distributions, PS mitigates the need for excessively large particle counts, directly addressing key limitations of SMC such as particle impoverishment and mode collapse. Crucially, PS achieves this without additional likelihood evaluations-weights for persistent particles are computed using cached likelihood values. This framework not only yields more accurate posterior approximations but also produces marginal likelihood estimates with significantly lower variance, enhancing reliability in model comparison. Furthermore, the persistent ensemble enables efficient adaptation of transition kernels by leveraging a larger, decorrelated particle pool. Experiments on high-dimensional Gaussian mixtures, hierarchical models, and non-convex targets demonstrate that PS consistently outperforms standard SMC and related variants, including recycled and waste-free SMC, achieving substantial reductions in mean squared error for posterior expectations and evidence estimates, all at reduced computational cost. PS thus establishes itself as a robust, scalable, and efficient alternative for complex Bayesian inference tasks.

Karamanis, Minas↗
DOE OSTI2021

Tonal Emergence: An agent-based model of tonal coordination

Humans have a remarkable capacity for coordination. Our ability to interact and act jointly in groups is crucial to our success as a species. Joint Action (JA) research has often concerned itself with simplistic behaviors in highly constrained laboratory tasks. But there has been a growing interest in understanding complex coordination in more open-ended contexts. In this regard, collective music improvisation has emerged as a fascinating model domain for studying basic JA mechanisms in an unconstrained and highly sophisticated setting. A number of empirical studies have begun to elucidate coordination mechanisms underlying joint musical improvisation, but these empirical findings have yet to be cached out in a working computational model. The present work fills this gap by presenting TonalEmergence, an idealized agent-based model of improvised musical coordination. TonalEmergence models the coordination of notes played by improvisers to generate harmony (i.e., tonality), by simulating agents that stochastically generate notes biased towards maximizing harmonic consonance given their partner’s previous notes. Here, the model replicates an interesting empirical result from a previous study of professional jazz pianists: feedback loops of mutual adaptation between interacting agents support the production of consonant harmony. The model is further explored to show how complex tonal dynamics, such as the production and dissolution of stable tonal centers, are supported by agents that are characterized by (i) a tendency to strive toward consonance, (ii) stochasticity, and (iii) a limited memory for previously played notes. TonalEmergence thus provides a grounded computational model to simulate and probe the coordination mechanisms underpinning one of the more remarkable feats of human cognition: collective music improvisation.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2018

Pushing memory bandwidth limitations through efficient implementations of Block-Krylov space solvers on GPUs

Lattice quantum chromodynamics simulations in nuclear physics have benefited from a tremendous number of algorithmic advances such as multigrid and eigenvector deflation. These improve the time to solution but do not alleviate the intrinsic memory-bandwidth constraints of the matrix-vector operation dominating iterative solvers. Batching this operation for multiple vectors and exploiting cache and register blocking can yield a super-linear speed up. Block-Krylov solvers can naturally take advantage of such batched matrix-vector operations, further reducing the iterations to solution by sharing the Krylov space between solves. However, practical implementations typically suffer from the quadratic scaling in the number of vector-vector operations. Here, using the QUDA library, we present an implementation of a block-CG solver on NVIDIA GPUs which reduces the memory-bandwidth complexity of vector-vector operations from quadratic to linear. We present results for the HISQ discretization, showing a 5x speedup compared to highly-optimized independent Krylov solves on NVIDIA's SaturnV cluster.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2018

Large-scale GW calculations on pre-exascale HPC systems

The ab initio GW approach is a rigorous Green’s-function-based framework that can be employed to compute electronic excitation properties of a wide variety of materials such as extended systems, molecules, as well as confined and nanostructured materials with a very satisfactory accuracy. However, GW calculations on complex systems are often hindered by the high computational cost associated with the method. Here, in this study, we demonstrate how to significantly speedup GW calculations with a novel algorithm for the computationally intense kernel based on a non-blocking chunked cyclic communication scheme that minimizes latency in MPI messages, allows for overlapping of communication and computation, and improves cache usage in matrix multiplication operations. The optimized version of the code, implemented in the BerkeleyGW software package, is capable of scaling well to the full Cori computer at NERSC (Cray XC40) and achieves over 11 Peta FLOP/s of sustained performance. We showcase our work by performing large-scale GW calculations of defect structures on silicon, which require simulation cells containing over 1700 atoms, and which can now be efficiently executed in just a few minutes on large pre-exascale high-performance computing systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

PFHydro: A New Watershed-Scale Model for Post-Fire Runoff Simulation

Runoff increases after wildfires that burn vegetation and create a condition of soil-water repellence (SWR). A new post-fire watershed hydrological model, PFHydro, was created to explicitly simulate vegetation interception and SWR effects for four burn severity categories: high, medium, low severity and unburned. The model was applied to simulate post-fire runoff from the Upper Cache Creek Watershed in California, USA. Nash–Sutcliffe modeling efficiency (NSE) was used to assess model performance. The NSE was 0.80 and 0.88 for pre-fire water years (WY) 2000 and 2015, respectively. NSE was 0.88 and 0.93 for WYs 2016 (first year post-fire) and 2017 respectively. The simulated percentage of surface runoff in total runoff of WY 2016 was about six times that of pre-fire WY 2000 and three times that of WY 2015. The modeling results suggest that SWR is an important factor for post-fire runoff generation. In conclusion, the model was successful at simulating SWR behavior.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2016

Holocene cold storage practices on the eastern Snake River Plain: A risk-mitigation strategy for lean times

Previous archaeological research in southern Idaho has suggested that climate change over the past 8000 years was not dramatic enough to alter long-term subsistence practices in the region. However, recent isotopic analyses of bison remains from cold storage caves on the Snake River Plain contest this hypothesis. Our results, when examined against an archaeoclimate model, suggest that cold storage episodes coincided with drier, warmer phases that likely reduced forage and water, and thus limited the availability of bison on the open steppe. Within this context we build a risk model to illustrate how environment might have motivated cold storage behaviors. Caching bison in cold lava tubes would have mitigated both intra-annual and inter-annual food shortages under these conditions. This analysis also suggests that skeletal fat, more than meat, may have influenced the selection, transport and storage of bison carcass parts. We deciphered when and how cold storage caves which was used to provide a more comprehensive understanding of foraging behaviors in a broad range of hunting-gathering economies.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2019

Predicting content consumption from content-to-content relationships

As the majority of Internet traffic today is attributed to content-centric applications, there has been ever-increasing demand for highly scalable and efficient content delivery. An accurate prediction on future content consumption is essential for such demand. To address such an issue, this paper introduces a new computational approach, Content Network (CN) that can capture the relations among contents, and its potential applications. We conduct a measurement study to investigate how contents are inter-related from the viewpoint of content spreading on one of the popular BitTorrent portals: The Pirate Bay. Based on the large-scale dataset that contains 18 K torrents and 9 M users, we construct the CN and investigate its structural properties. Our key finding is that contents in the same community in the CN (i) belong to the same content category with 94% probability, (ii) are uploaded by the same content publisher with 76% probability, and (iii) have the similar titles with 51% probability, which implies that contents in the same community collectively contain common (shared) interests of users. Our trace-driven study demonstrates that the proposed CN model is useful in (i) content recommendation for increasing sales and (ii) content caching for networking efficiency. We believe our work can provide an important insight for content stakeholders, e.g., content providers for efficient publishing strategies, network engineers for networking efficiency, or content marketers for accurate recommendation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Two-level main memory co-design: Multi-threaded algorithmic primitives, analysis, and simulation

A challenge in computer architecture is that processors often cannot be fed data from DRAM as fast as CPUs can consume it. Therefore, many applications are memory-bandwidth bound. With this motivation and the realization that traditional architectures (with all DRAM reachable only via bus) are insufficient to feed groups of modern processing units, vendors have introduced a variety of non-DDR 3D memory technologies (Hybrid Memory Cube (HMC),Wide I/O 2, High Bandwidth Memory (HBM)). These offer higher bandwidth and lower power by stacking DRAM chips on the processor or nearby on a silicon interposer. We will call these solutions “near-memory,” and if user-addressable, “scratchpad.” High-performance systems on the market now offer two levels of main memory: near-memory on package and traditional DRAM further away. In the near term we expect the latencies near-memory and DRAM to be similar. Here, it is natural to think of near-memory as another module on the DRAM level of the memory hierarchy. Vendors are expected to offer modes in which the near memory is used as cache, but we believe that this will be inefficient.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Data preservation at the Fermilab Tevatron

The Fermilab Tevatron collider's data-taking run ended in September 2011, yielding a dataset with rich scientific potential. The CDF and D0 experiments each have approximately 9 PB of collider and simulated data stored on tape. A large computing infrastructure consisting of tape storage, disk cache, and distributed grid computing for physics analysis with the Tevatron data is present at Fermilab. The Fermilab Run II data preservation project intends to keep this analysis capability sustained through the year 2020 and beyond. To achieve this goal, we have implemented a system that utilizes virtualization, automated validation, and migration to new standards in both software and data storage technology and leverages resources available from currently-running experiments at Fermilab. Lastly, these efforts have also provided useful lessons in ensuring long-term data access for numerous experiments, and enable high-quality scientific output for years to come.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2016

An asynchronous traversal engine for graph-based rich metadata management

Rich metadata in high-performance computing (HPC) systems contains extended information about users, jobs, data files, and their relationships. Property graphs are a promising data model to represent heterogeneous rich metadata flexibly. Specifically, a property graph can use vertices to represent different entities and edges to record the relationships between vertices with unique annotations. The high-volume HPC use case, with millions of entities and relationships, naturally requires an out-of-core distributed property graph database, which must support live updates (to ingest production information in real time), low-latency point queries (for frequent metadata operations such as permission checking), and large-scale traversals (for provenance data mining). Among these needs, large-scale property graph traversals are particularly challenging for distributed graph storage systems. Most existing graph systems implement a "level synchronous" breadth-first search algorithm that relies on global synchronization in each traversal step. This performs well in many problem domains; but a rich metadata management system is characterized by imbalanced graphs, long traversal lengths, and concurrent workloads, each of which has the potential to introduce or exacerbate stragglers (i.e., abnormally slow steps or servers in a graph traversal) that lead to low overall throughput for synchronous traversal algorithms. Previous research indicated that the straggler problem can be mitigated by using asynchronous traversal algorithms, and many graph-processing frameworks have successfully demonstrated this approach. Such systems require the graph to be loaded into a separate batch-processing framework instead of being iteratively accessed, however. In this work, we investigate a general asynchronous graph traversal engine that can operate atop a rich metadata graph in its native format. We outline a traversal-aware query language and key optimizations (traversal-affiliate caching and execution merging) necessary for efficient performance. We further explore the effect of different graph partitioning strategies on the traversal performance for both synchronous and asynchronous traversal engines. Our experiments show that the asynchronous graph traversal engine is more efficient than its synchronous counterpart in the case of HPC rich metadata processing, where more servers are involved and larger traversals are needed. Furthermore, the asynchronous traversal engine is more adaptive to different graph partitioning strategies.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗