Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel computer architecture”

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 829 records · Page 46

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↗

Fast tree-based algorithms for DBSCAN for low-dimensional data on GPUs

DBSCAN is a well-known density-based clustering algorithm to discover arbitrary shape clusters. While conceptually simple in serial, the algorithm is challenging to efficiently parallelize on manycore GPU architectures. Common pitfalls, such as asynchronous range query calls, result in high thread execution divergence in many implementations. In this paper, we propose a new framework for GPU-accelerated DBSCAN, and describe two tree-based algorithms within that framework. Both algorithms fuse the search for neighbors with updating cluster information, but differ in their treatment of dense regions of the data. We show that the time taken to compute clusters is at most twice that of determination of the neighbors. We compare the proposed algorithms with existing CPU and GPU implementations, and demonstrate their competitiveness and performance using a fast traversal structure (bounding volume hierarchy) for low dimensional data. We also show that the memory usage can be reduced by processing object neighbors dynamically without storing them.

Prokopenko, Andrey↗

Leaky Buddies: Cross-Component Covert Channels on Integrated CPU-GPU Systems

Graphics Processing Units (GPUs) are ubiquitous components used across the range of today’s computing plat- forms, from phones and tablets, through personal computers, to high-end server class platforms. With the increasing importance of graphics and video workloads, recent processors are shipped with GPU devices that are integrated on the same chip. Integrated GPUs share some resources with the CPU and as a result, there is a potential for microarchitectural attacks from the GPU to the CPU or vice versa. We consider the potential for covert channel attacks that arise either from shared microarchitectural components (such as caches) or through shared contention domains (e.g., shared buses). We illustrate these two types of channels by developing two reliable covert channel attacks. The first covert channel uses the shared LLC cache in Intel’s integrated GPU architectures. The second is a contention based channel targeting the ring bus connecting the CPU and GPU to the LLC. This is the first demonstrated microarchitectural attack crossing the component boundary (GPU to CPU or vice versa). Cross-component channels introduce a number of new challenges that we had to overcome since they occur across heterogeneous components that use different computation models and are interconnected using asymmetric memory hierarchies. We also exploit GPU parallelism to increase the bandwidth of the communication, even without relying on a common clock. The LLC based channel achieves a bandwidth of 120 kbps with a low error rate of 2%, while the contention based channel delivers up to 400 kbps with a 0.8% error rate. We also demonstrate a proof- of-concept prime-and-probe side channel attack that probes the full LLC from the GPU.

Cyber secruity, high performance comptuing, Hetero↗

Collective I/O Tuning Using Analytical and Machine-Learning Models

The ever larger demand of scientific applications for computation and data is currently driving a continuous increase in scale of parallel computers. The inherent complexity of scaling up a computing systems in terms of both hardware and software stack exposes an increasing number of factors impacting the performance and complicating the process of optimization. In particular, the optimization of parallel I/O has become increasingly challenging due to increasing storage hierarchy and well known performance variability of shared storage systems. This paper focuses on model-based autotuning of the two-phase collective I/O algorithm from a popular MPI distribution on the Blue Gene/Q architecture. We propose a novel hybrid model, constructed as a composition of analytical models for communication and storage operations and black-box models for the performance of the individual operations. We perform an in-depth study of the complexity involved in performance modeling including architecture, software stack and noise. In particular we address this challenges of modeling the performance of shared storage systems by building a benchmark that helps synthesizing factors such as topology, file caching, and noise. The experimental results show that the hybrid approach produces significantly better results than state-of-the-art machine learning approaches and shows a higher robustness to noise, at the cost of a higher modeling complexity

I/O performance modeling↗

Towards exascale for wind energy simulations

We examine large-eddy-simulation modeling approaches and computational performance of two open-source computational fluid dynamics codes for the simulation of atmospheric boundary layer flows that are of direct relevance to wind energy production. The first code, NekRS, is a high-order, unstructured-grid, spectral element code. The second code, AMR-Wind, is a second-order, block-structured, finite-volume code with adaptive mesh refinement capabilities. The objective of this study is to co-develop these codes in order to improve model fidelity and performance for each. These features will be critical for running ABL-based applications such as wind farm analysis on advanced computing architectures. To this end, we investigate the performance of NekRS and AMR-Wind on the Oak Ridge Leadership Facility supercomputers Summit, using 4 to 800 nodes (24 to 4,800 NVIDIA V100 GPUs), and Crusher, the testbed for the Frontier exascale system, using 18 to 384 Graphics Compute Dies on AMD MI250X GPUs. We compare strong- and weak-scaling capabilities, linear solver performance, and time to solution. We also identify leading inhibitors to parallel scaling.

17 WIND ENERGY↗

Computational mechanics for geosystems management to support the energy and natural resources mission.

U.S. energy needs - minimizing climate change, mining and extraction technologies, safe waste disposal - require the ability to simulate, model, and predict the behavior of subsurface systems. They propose development of a coupled thermal, hydrological, mechanical, chemistry (THMC) modeling capability for massively parallel applications that can address these critical needs. The goal and expected outcome of this research is a state-of-the-art, extensible, simulation capability, based upon SIERRA Mechanics, to address multiphase, multicomponent reactive transport coupled to nonlinear geomechanics in heterogeneous (geologic) porous materials. The THMC code provides a platform for integrating research in numerical mathematics and algorithms for chemically reactive multiphase systems with computer science research in adaptive coupled solution control and framework architecture.

54 ENVIRONMENTAL SCIENCES↗

Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models

Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been recently reported that successfully solve PDEs, with examples including deep feed forward networks, generative networks, and deep encoder-decoder networks. However, practical adoption of these approaches is limited by the difficulty in training these models, especially to make predictions at large output resolutions (≥1024×1024). Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models - training in reasonable time as well as distributing the storage requirements. Our framework provides several out of the box functionality including (a) loss integrity independent of number of processes, (b) synchronized batch normalization, and (c) distributed higher-order optimization methods. We show excellent scalability of this framework on both cloud as well as HPC clusters, and report on the interplay between bandwidth, network topology and bare metal vs cloud. We deploy this approach to train generative models of sizes hitherto not possible, showing that neural PDE solvers can be viably trained for practical applications. We also demonstrate that distributed higher-order optimization methods are 2-3× faster than stochastic gradient-based methods and provide minimal convergence drift with higher batch-size.

PDEs↗

Efficient Routing of Quantum LDPC Codes on Programmable 2D Toric Architectures

Quantum low-density parity-check codes are promising candidates towards scalable fault-tolerant quantum computation. Among these, bivariate bicycle (BB) codes offer superior encoding rates and large code distance compared to surface codes. However, their requirement on long-range stabilizer measurements poses significant challenges for implementation on realistic hardware with limited connectivity, such as superconducting circuit platforms. In this work, we introduce a novel hardware-software co-design that leverages a programmable communication network architecture to address these limitations. Our approach utilizes a 2D toric network of oscillators as a flexible communication fabric linking qubits at each site. Such architecture significantly reduces the number of long-range couplers required from O ( n ) to O (√ n ). Dual-rail qubits, along with native gates including Swap-Wait-Swap gates and beamsplitter SWAPs, ensure that long-range two-qubit gates can be executed with high fidelity and low latency. To further enhance performance, our qubit layout and routing algorithm utilize symmetries of the codes and enable maximum parallelism for long-range two-qubit gates, maintaining a low syndrome extraction cycle duration and scalability over the code length. We perform circuit-level simulation with realistic noise modeling based on experimental hardware parameters, observing an logical error rate per logical qubit per cycle of 3.06% for [[18,4,4]] BB code, 2.6× less than the existing experimental result. These findings provide a practical roadmap and identify key technological advancements needed to achieve low-overhead fault-tolerant quantum computing at scale.

Liu, Kun [Yale Univ., New Haven, CT (United States↗

On the Use of Hyperpolarized Helium MRI for Conformal Avoidance Lung Radiotherapy

We wanted to illustrate the feasibility of using hyperpolarized helium magnetic resonance imaging (HPH-MRI) to obtain functional information that may assist in improving conformal avoidance of ventilating lung tissue during thoracic radiotherapy. HPH-MRI images were obtained from a volunteer patient and were first fused with a proton density-weighted (PD{sub w}) MRI to provide corresponding anatomic detail; they were then fused with the treatment planning computed tomography scan of a patient from our treatment planning database who possessed equivalent thoracic dimensions. An optimized treatment plan was then generated using the TomoTherapy treatment planning system, designating the HPH-enhancing regions as ventilation volume (VV). A dose-volume histogram compares the dosimetry of the lungs as a paired organ, the VV, and the lungs minus the VV. The clinical consequences of these changes was estimated using a bio-effect model, the parallel architecture model, or the local damage (f{sub dam}) model. Model parameters were chosen from published studies linking the incidence of grade 3+ pneumonitis, with the dose and volume irradiated. For two hypothetical treatment plans of 60 Gy in 30 fractions delivered to a right upper-lobe lung mass, one using and one ignoring the VV as an avoidance structure, the mean normalized total dose (NTD{sub mean}) values for the lung subvolumes were: lungs = 12.5 Gy{sub 3}vs. 13.52 Gy{sub 3}, VV = 9.94 Gy{sub 3}vs. 13.95 Gy{sub 3}, and lungs minus VV = 16.69 Gy{sub 3}vs. 19.16 Gy{sub 3}. Using the f{sub dam} values generated from these plans, one would predict a reduction of the incidence of grade 3+ radiation pneumonitis from 12%-4% when compared with a conventionally optimized plan. The use of HPH-MRI to identify ventilated lung subvolumes is feasible and has the potential to be incorporated into conformal avoidance treatment planning paradigms. A prospective clinical study evaluating this imaging technique is being developed.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Frontier (HPE Cray EX) Exascale Supercomputer at the Oak Ridge Leadership Computing Facility

Frontier is the HPE Cray EX exascale supercomputer deployed and operated by the Oak Ridge Leadership Computing Facility (OLCF) at Oak Ridge National Laboratory (ORNL). Frontier is designed for large-scale modeling, simulation, and AI workloads and is built from HPE Cray EX system architecture with AMD CPUs and AMD Instinct GPU accelerators connected by the HPE Slingshot interconnect. System composition (representative production configuration): Frontier is composed of approximately 74 cabinets with 128 compute nodes per cabinet (~9,400 compute nodes total). Each compute node contains one 64-core AMD EPYC CPU and four AMD Instinct MI250X GPUs. Nodes are connected using HPE Slingshot (Slingshot-200 class) networking with multiple NIC ports per node providing high injection bandwidth. Frontier is connected to the Orion parallel file system (multi-tier Lustre) providing a large, center-wide high-performance storage namespace. Operational context: Frontier entered public prominence as the first system to reach No. 1 on the TOP500 list in May 2022 (HPL benchmark), establishing the first widely recognized exascale-era performance milestone. The system supports DOE Office of Science mission workloads and enables leadership-class computational science and AI for open science users.

AMD EPYC↗

Mixed Integer Nonlinear Programming Approaches to Enhance Resiliency and Response Strategies in Critical Infrastructure

Motivation. Critical infrastructures are large, complex engineered systems that must be operated robustly under abnormal conditions resulting from natural hazards or intentional acts. For example, electric power systems must be robust to line faults, water utilities must rapidly mitigate contamination incidents, and computing networks must adapt to adversarial intrusions to protect critical information. Problem. It is difficult for decision-makers within resiliency analysis in critical infrastructure to optimize designs and develop effective response strategies that can account for uncertainties. Facing incomplete information and the sheer scope that a natural hazard or attack vector may incorporate, response can be ineffective without reliable, scalable decision support tools. These problems are intrinsically nonlinear and involve discrete decisions, and unfortunately, existing off-the-shelf mathematical programming methods cannot support optimization-based decision-making of these nonlinear at scale. Method/Approach and Results. This project emphasized development of fundamental optimization strategies that supported real- time mitigation and response for critical infrastructures. In particular, the project developed multi- tree approaches based on piecewise outer-approximations for solution of mixed-integer nonlinear programming (MINLP) problems. These techniques alternate between an MILP or MISOCP relaxation to obtain a lower bound and candidate discrete solutions and an NLP subproblem to obtain upper bounds. Using tailored relaxations based on problem structure, these methods were used to solve several key applications in resilience and response of critical infrastructure. This work resulted in two open-source, copyrighted software packages: CORAMIN (https://github.com/Coramin/Coramin) -- an object-oriented mathematical programming framework that supports tailored multi-tree algorithms for solution of large- scale mixed-integer nonlinear programming; and EGRET (Electrical Grid Research and Engineering Toolkit) (https://github.com/grid- parity-exchange/Egret) -- a declarative mathematical programming framework built upon CORAMIN and Pyomo for formulation and solution of resilience and operations problems in power grid systems. Furthermore, these tools resulted in several important published results, including the following: The first known global optimization approach that could solve the unit-commitment problem with nonlinear power flow constraints on medium-sized test problems; Improved parallel optimization-based bounds tightening and strengthening of relaxations of AC power flow constraints; and, Optimization-based approaches for improved grid resilience and use of demand response to improve grid resilience with reduction in capital requirements. Result Implications. This project developed first-of-a-kind algorithms for decision-making in critical infrastructure resilience operations and planning, as well as a next-generation toolkit for MINLP researchers. These approaches leveraged high-performance computing architectures to solve some of the largest, most challenging nonlinear discrete optimization problems to global optimality, and these successes were captured in open-source software to enable optimization-based decision-making, and efficient solution of MINLP formulations for electric power transmission grids.

24 POWER TRANSMISSION AND DISTRIBUTION↗

FunM2C: A Filter for Uncertainty Visualization of Multivariate Data on Multi-Core Devices

Uncertainty visualization is an emerging research topic in data visualization because neglecting uncertainty in visualization can lead to inaccurate assessments. In this paper, we study the propagation of multivariate data uncertainty in visualization. Although there have been a few advancements in probabilistic uncertainty visualization of multivariate data, three critical challenges remain to be addressed. First, the state-of-the-art probabilistic uncertainty visualization framework is limited to bivariate data (two variables). Second, existing uncertainty visualization algorithms use computationally intensive techniques and lack support for cross-platform portability. Third, as a consequence of the computational expense, integration into production visualization tools is impractical. In this work, we address all three issues and make a threefold contribution. First, we take a step to generalize the state-of-the-art probabilistic framework for bivariate data to multivariate data with an arbitrary number of variables. Second, through utilization of VTK-m’s shared-memory parallelism and cross-platform compatibility features, we demonstrate acceleration of multivariate uncertainty visualization on different many-core architectures, including OpenMP and AMD GPUs. Third, we demonstrate the integration of our algorithms with the ParaView software. We demonstrate the utility of our algorithms through experiments on multivariate simulation data with three and four variables.

Hari, Gautam↗

SU-E-T-531: Performance Evaluation of Multithreaded Geant4 for Proton Therapy Dose Calculations in a High Performance Computing Facility

Purpose: To evaluate the efficiency of multithreaded Geant4 (Geant4-MT, version 10.0) for proton Monte Carlo dose calculations using a high performance computing facility. Methods: Geant4-MT was used to calculate 3D dose distributions in 1×1×1 mm3 voxels in a water phantom and patient's head with a 150 MeV proton beam covering approximately 5×5 cm2 in the water phantom. Three timestamps were measured on the fly to separately analyze the required time for initialization (which cannot be parallelized), processing time of individual threads, and completion time. Scalability of averaged processing time per thread was calculated as a function of thread number (1, 100, 150, and 200) for both 1M and 50 M histories. The total memory usage was recorded. Results: Simulations with 50 M histories were fastest with 100 threads, taking approximately 1.3 hours and 6 hours for the water phantom and the CT data, respectively with better than 1.0 % statistical uncertainty. The calculations show 1/N scalability in the event loops for both cases. The gains from parallel calculations started to decrease with 150 threads. The memory usage increases linearly with number of threads. No critical failures were observed during the simulations. Conclusion: Multithreading in Geant4-MT decreased simulation time in proton dose distribution calculations by a factor of 64 and 54 at a near optimal 100 threads for water phantom and patient's data respectively. Further simulations will be done to determine the efficiency at the optimal thread number. Considering the trend of computer architecture development, utilizing Geant4-MT for radiotherapy simulations is an excellent cost-effective alternative for a distributed batch queuing system. However, because the scalability depends highly on simulation details, i.e., the ratio of the processing time of one event versus waiting time to access for the shared event queue, a performance evaluation as described is recommended.

60 APPLIED LIFE SCIENCES↗

Supporting the Development of Resilient Message Passing Applications using Simulation

An emerging aspect of high-performance computing (HPC) hardware/software co-design is investigating performance under failure. The work in this paper extends the Extreme-scale Simulator (xSim), which was designed for evaluating the performance of message passing interface (MPI) applications on future HPC architectures, with fault-tolerant MPI extensions proposed by the MPI Fault Tolerance Working Group. xSim permits running MPI applications with millions of concurrent MPI ranks, while observing application performance in a simulated extreme-scale system using a lightweight parallel discrete event simulation. The newly added features offer user-level failure mitigation (ULFM) extensions at the simulated MPI layer to support algorithm-based fault tolerance (ABFT). The presented solution permits investigating performance under failure and failure handling of ABFT solutions. The newly enhanced xSim is the very first performance tool that supports ULFM and ABFT.

Engelmann, Christian↗

Scalable Deep Learning-Based Microarchitecture Simulation on GPUs

Cycle-accurate microarchitecture simulators are essential tools for designers to architect, estimate, optimize, and manufacture new processors that meet specific design expectations. However, conventional simulators based on discrete-event methods often require an exceedingly long time-to-solution for the simulation of applications and architectures at full complexity and scale. Given the excitement around wielding the machine learning (ML) hammer to tackle various architecture problems, there have been attempts to employ ML to perform architecture simulations, such as Ithemal and SimNet. However, the direct application of existing ML approaches to architecture simulation may be even slower due to overwhelming memory traffic and stringent sequential computation logic. This work proposes the first graphics processing unit (GPU)-based microarchitecture simulator that fully unleashes the potential of GPUs to accelerate state-of-the-art ML-based simulators. First, considering the application traces are loaded from central processing unit (CPU) to GPU for simulation, we introduce various designs to reduce the data movement cost between CPUs and GPUs. Second, we propose a parallel simulation paradigm that partitions the application trace into sub-traces to simulate them in parallel with rigorous error analysis and effective error correction mechanisms. Combined, this scalable GPU-based simulator outperforms by orders of magnitude the traditional CPU-based simulators and the state-of-the-art ML-based simulators, i.e., SimNet and Ithemal.

97 MATHEMATICS AND COMPUTING↗

The Portals 4.0 Network Programming Interface

This report presents a specification for the Portals 4.0 network programming interface. Portals 4.0 is intended to allow scalable, high-performance network communication between nodes of a parallel computing system. Portals 4.0 is well suited to massively parallel processing and embedded systems. Portals 4.0 represents an adaption of the data movement layer developed for massively parallel processing platforms, such as the 4500-node Intel TeraFLOPS machine. Sandia’s Cplant cluster project motivated the development of Version 3.0, which was later extended to Version 3.3 as part of the Cray Red Storm machine and XT line. Version 4.0 is targeted to the next generation of machines employing advanced network interface architectures that support enhanced offload capabilities.

Barrett, Brian W.↗

The portals 4.0.1 network programming interface.

This report presents a specification for the Portals 4.0 network programming interface. Portals 4.0 is intended to allow scalable, high-performance network communication between nodes of a parallel computing system. Portals 4.0 is well suited to massively parallel processing and embedded systems. Portals 4.0 represents an adaption of the data movement layer developed for massively parallel processing platforms, such as the 4500-node Intel TeraFLOPS machine. Sandia s Cplant cluster project motivated the development of Version 3.0, which was later extended to Version 3.3 as part of the Cray Red Storm machine and XT line. Version 4.0 is targeted to the next generation of machines employing advanced network interface architectures that support enhanced offload capabilities. 3

Barrett, Brian W.↗

Universal Design Curves for Elastomeric Direct Ink-Writing Architectures

Direct ink writing of silicone elastomers enables printing with precise control of porosity and mechan- ical properties of ordered cellular solids, suitable for shock absorption and stress mitigation applications. With the ability to manipulate structure and feedstock stiffness, the design space becomes challenging to parse to obtain a solution producing a desired mechanical response. Here we derive an analytical design approach for a specific architecture. Results from finite element simulations and quasi-static mechanical tests of two different parallel strand architectures were analyzed to understand the structure-property relationships under compressive strain. Combining effective stiffness-density scaling with least squares optimization of the stress responses yielded general response curves parameterized by resin modulus and strand spacing. An analytical expression of these curves serves as a reduced order model, which, when optimized, provides a rapid design capability for filament-based 3D printed structures. As a demonstration, the optimal design of a face-centered tetragonal architecture is computed that satisfies prescribed minimum and maximum load constraints.

36 MATERIALS SCIENCE↗