Search NASA⌕ Search

SEARCH · Search NASA

Results for “dataflow”

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.

71 records · Page 4

Approximate Weighted Matching On Emerging Manycore and Multithreaded Architectures

Graph matching is a prototypical combinatorial problem with many applications in computer science and scientific computing, but algorithms for computing optimal matchings are challenging to parallelize. Approximate matching algorithms provide an alternate route for parallelization, and in many contexts compute near-optimal matchings for large-scale graphs. We present sharedmemory parallel implementations for computing half-approximate weighted matching on state-of-the-art multicore (Intel Nehalem and AMD Magny-Cours), manycore (Nvidia Tesla and Nvidia Fermi) and massively multithreaded (Cray XMT) platforms. We provide two implementations: the first implementation uses shared work queues, and is suited to all these platforms; the second implementation is based on dataflow principles, and exploits the architectural features of the Cray XMT. Using a carefully chosen dataset that exhibits characteristics from a wide range of real-world applications, we show scalable performance across different platforms. In particular, for one instance of the input, an R-MAT graph (RMAT-G), we show speedups of: about 32 on 48 cores of an AMD Magny-Cours; 7 on 8 cores of Intel Nehalem; 3 on Nvidia Tesla and 10 on Nvidia Fermi relative to one core of Intel Nehalem; and 60 on 128 processors of Cray XMT. We demonstrate good weak and strong scaling for graphs with up to a billion edges using up to 12, 800 threads. Given the breadth of this work, we focus on simplicity and portability of software rather than excessive fine-tuning for each platform. To the best of our knowledge, this is the first such large-scale study of the half-approximate weighted matching problem on shared-memory platforms. Driven by the critical enabling role of combinatorial algorithms such as matching in scientific computing and the emergence of informatics applications, there is a growing demand to support irregular computations on current and future computing platforms. In this context, we evaluate the capability of emerging multithreaded platforms to tolerate latency induced by irregular memory access patterns, and to support fine-grained parallelism via light-weight synchronization mechanisms. By contrasting the architectural features of these platforms against the Cray XMT, which is specifically designed to support irregular memory-intensive applications, we delineate the impact of these choices on performance.

Halappanavar, Mahantesh↗

Implementing efficient data compression and encryption in a persistent key-value store for HPC

Recently, persistent data structures, like key-value stores (KVSs), which are stored in a high-performance computing (HPC) system’s nonvolatile memory, provide an attractive solution for a number of emerging challenges like limited I/O performance. Data compression and encryption are two well-known techniques for improving several properties of such data-oriented systems. This article investigates how to efficiently integrate data compression and encryption into persistent KVSs for HPC with the ultimate goal of hiding their costs and complexity in terms of performance and ease of use. Our compression technique exploits deep memory hierarchy in an HPC system to achieve both storage reduction and performance improvement. Our encryption technique provides a practical level of security and enables sharing of sensitive data securely in complex scientific workflows with nearly imperceptible cost. We implement the proposed techniques on top of a distributed embedded KVS to evaluate the benefits and costs of incorporating these capabilities along different points in the dataflow path, illustrating differences in effective bandwidth, latency, and additional computational expense on Swiss National Supercomputing Centre’s Grand Tavé and National Energy Research Scientific Computing Center’s Cori.

97 MATHEMATICS AND COMPUTING↗

Distributed-memory lattice H-matrix factorization

We parallelize the LU factorization of a hierarchical low-rank matrix (H-matrix) on a distributed-memory computer. This is much more difficult than the H-matrix-vector multiplication due to the dataflow of the factorization, and it is much harder than the parallelization of a dense matrix factorization due to the irregular hierarchical block structure of the matrix. Block low-rank (BLR) format gets rid of the hierarchy and simplifies the parallelization, often increasing concurrency. However, this comes at a price of losing the near-linear complexity of the H-matrix factorization. In this work, we propose to factorize the matrix using a “lattice H-matrix” format that generalizes the BLR format by storing each of the blocks (both diagonals and off-diagonals) in the H-matrix format. These blocks stored in the H-matrix format are referred to as lattices. Thus, this lattice format aims to combine the parallel scalability of BLR factorization with the near-linear complexity of H-matrix factorization. We first compare factorization performances using the H-matrix, BLR, and lattice H-matrix formats under various conditions on a shared-memory computer. Our performance results show that the lattice format has storage and computational complexities similar to those of the H-matrix format, and hence a much lower cost of factorization than BLR. In conclusion, we then compare the BLR and lattice H-matrix factorization on distributed-memory computers. Our performance results demonstrate that compared with BLR, the lattice format with the lower cost of factorization may lead to faster factorization on the distributed-memory computer.

97 MATHEMATICS AND COMPUTING↗

A feasibility study on porting the community land model onto accelerators using OpenACC

As environmental models (such as Accelerated Climate Model for Energy (ACME), Parallel Reactive Flow and Transport Model (PFLOTRAN), Arctic Terrestrial Simulator (ATS), etc.) became more and more complicated, we are facing enormous challenges regarding to porting those applications onto hybrid computing architecture. OpenACC appears as a very promising technology, therefore, we have conducted a feasibility analysis on porting the Community Land Model (CLM), a terrestrial ecosystem model within the Community Earth System Models (CESM)). Specifically, we used automatic function testing platform to extract a small computing kernel out of CLM, then we apply this kernel into the actually CLM dataflow procedure, and investigate the strategy of data parallelization and the benefit of data movement provided by current implementation of OpenACC. Even it is a non-intensive kernel, on a single 16-core computing node, the performance (based on the actual computation time using one GPU) of OpenACC implementation is 2.3 time faster than that of OpenMP implementation using single OpenMP thread, but it is 2.8 times slower than the performance of OpenMP implementation using 16 threads. On multiple nodes, MPI_OpenACC implementation demonstrated very good scalability on up to 128 GPUs on 128 computing nodes. This study also provides useful information for us to look into the potential benefits of “deep copy” capability and “routine” feature of OpenACC standards. In conclusion, we believe that our experience on the environmental model, CLM, can be beneficial to many other scientific research programs who are interested to porting their large scale scientific code using OpenACC onto high-end computers, empowered by hybrid computing architecture.

54 ENVIRONMENTAL SCIENCES↗

Advancing the utility of Data flow accelerators: Kokkos backend for Next Silicon

Next Silicon provides a novel reconfigurable accelerator, which is inherently a high-risk, early exploration effort. Higher readiness level for running NNSA mini-apps and initial mission applications on a data-flow accelerator Enable and demonstrate a new Kokkos back-end that directly drives an underlying dataflow accelerator

Garcia de Gonzalo, Simon Pedro [Sandia National La↗

Report on a 2009 mini-demonstration of the ARG-US Radio Frequency Identification (RFID) system in transportation.

The Packaging Certification Program (PCP) of the U.S. Department of Energy (DOE) Environmental Management (EM), Office of Packaging and Transportation (EM-14), has developed a radio frequency identification (RFID) tracking and monitoring system for the management of nuclear materials during storage and transportation. The system, developed by the PCP team at Argonne National Laboratory, consists of hardware (Mk-series sensor tags, fixed and handheld readers, form factor for multiple drum types, seal integrity sensors, and enhanced battery management), software (application programming interface, ARG-US software for local and remote/web applications, secure server and database management), and cellular/satellite communication interfaces for vehicle tracking and item monitoring during transport. The ability of the above system to provide accurate, real-time tracking and monitoring of the status of multiple, certified containers of nuclear materials has been successfully demonstrated in a week-long, 1,700-mile DEMO performed in April 2008. While the feedback from the approximately fifty (50) stakeholders who participated in and/or observed the DEMO progression were very positive and encouraging, two major areas of further improvements - system integration and web application enhancement - were identified in the post-DEMO evaluation. The principal purpose of the MiniDemo described in this report was to verify these two specific improvements. The MiniDemo was conducted on August 28, 2009. In terms of system integration, a hybrid communication interface - combining the RFID item-monitoring features and a commercial vehicle tracking system by Qualcomm - was developed and implemented. In the MiniDemo, the new integrated system worked well in reporting tag status and vehicle location accurately and promptly. There was no incompatibility of components. The robust commercial communication gear, as expected, helped improve system reliability. The MiniDemo confirmed that system integration is technically feasible and reliable with the existing RFID and Qualcomm satellite equipment. In terms of web application, improvements in mapping, tracking, data presentation, and post-incident spatial query reporting were implemented in ARG-US, the application software that manages the dataflow among the RFID tags, readers, and servers. These features were tested in the MiniDemo and found to be satisfactory. The resulting web application is both informative and user-friendly. A joint developmental project is being planned between the PCP and the DOE TRANSCOM that uses the Qualcomm gear in vehicles for tracking and communication of radioactive material shipments across the country. Adding an RFID interface to TRANSCOM is a significant enhancement to the DOE infrastructure for tracking and monitoring shipments of radioactive materials.

42 ENGINEERING↗

Enabling real-time adaptation of machine learning models at x-ray Free Electron Laser facilities with high-speed training optimized computational hardware

The emergence of novel computational hardware is enabling a new paradigm for rapid machine learning model training. For the Department of Energy’s major research facilities, this developing technology will enable a highly adaptive approach to experimental sciences. In this manuscript we present the per-epoch and end-to-end training times for an example of a streaming diagnostic that is planned for the upcoming high-repetition rate x-ray Free Electron Laser, the Linac Coherent Light Source-II. We explore the parameter space of batch size and data parallel training across multiple Graphics Processing Units and Reconfigurable Dataflow Units. We show the landscape of training times with a goal of full model retraining in under 15 min. Although a full from scratch retraining of a model may not be required in all cases, we nevertheless present an example of the application of emerging computational hardware for adapting machine learning models to changing environments in real-time, during streaming data acquisition, at the rates expected for the data fire hoses of accelerator-based user facilities.

97 MATHEMATICS AND COMPUTING↗

Integration of the Trigger and Data Acquisition Systems in ATLAS

During 2006 and the first half of 2007, the installation, integration and commissioning of trigger and data acquisition (TDAQ) equipment in the ATLAS experimental area have progressed. There have been a series of technical runs using the final components of the system already installed in the experimental area. Various tests have been run including ones where level 1 preselected simulated proton-proton events have been processed in a loop mode through the trigger and dataflow chains. The system included the readout buffers containing the events, event building, level 2 and event filter trigger algorithms. The scalability of the system with respect to the number of event building nodes used has been studied and quantities critical for the final system, such as trigger rates and event processing times, have been measured using different trigger algorithms as well as different TDAQ components. This paper presents the TDAQ architecture, the current status of the installation and commissioning and highlights the main test results that validate the system.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Towards Flexible Exascale Stream Processing System Simulation

Stream processing is an important emerging computational model for performing complex operations on and across multi-source, high-volume, unpredictable dataflows. We present Flow, a platform for parallel and distributed stream processing system simulation that provides a flexible modeling environment for analyzing stream processing applications. The Flow stream processing system simulator is a high-performance, scalable simulator that automatically parallelizes chunks of the model space and incurs near-zero synchronization overhead for acyclic stream application graphs. We show promising parallel and distributed event rates exceeding 149 million events per second on a cluster with 512 processor cores.

99 GENERAL AND MISCELLANEOUS↗

Particle In Cell Scalable Application Resource (PICSAR) v2

PICSAR, for Particle-In-Cell Scalable Application Resource, is a high-performance Particle-in-Cell library developed in Fortran 90 and Python. This library was first developed to be coupled with WARP and provide efficient subroutines optimized for Many-Integrated Core (MIC) architectures such as the forthcoming system Cori Phase II that will be equipped with Intel Xeon Phi KNL processors. It is a compact self-contained proxy that adequately portrays the computational loads and dataflow of the more complex WARP code but can also be used by other PIC codes. PICSAR also contains a Fortran stand-alone Particle-In-Cell "mini-app" that includes the key functionalities of a PIC code. This stand-alone code is used for testing implementation performances and to do some benchmarks.

VINCENTI, HENRI↗

OpenCGRA: An Open-Source Unified Framework for Modeling,Testing, and Evaluating CGRAs

Coarse-grained reconfigurable arrays (CGRAs),loosely defined as arrays of functional units (e.g, adder, sub-tractor, multiplier, divider, or larger multi-operation units, butsmaller than a general-purpose core) interconnected through aNetwork-on-Chip, provide higher flexibility than domain-specificASIC accelerators while offering increased hardware efficiencywith respect to fine-grained reconfigurable devices, such as FieldProgrammable Gate Arrays (FPGAs). The fast evolving fieldsof machine learning and edge computing, which are seeing acontinuous flow of novel algorithms and larger models, makeCGRAs ideal target architectures to allow domain specializationwithout loosing too much generality. They also generally offerquicker and more effective reconfigurability than FPGAs, po-tentially allowing adaptation during actual algorithm execution,and implement a dataflow programming paradigm that adaptswell to these emerging workloads. Designing and generating aCGRA, however, still requires to define the type and number ofthe specific functional units, implement their interconnect andthe network topology, and perform its simulation and validation,given a variety of workloads of interest.In this paper, we propose OpenCGRA, a Python-based unifiedframework that integrates generation, modeling, testing and eval-uation for CGRAs. OpenCGRA is the first open-source integratedframework able to support the full top-to-bottom design flow forspecializing and implementing CGRAs: modeling at different ab-straction levels (functional level, cycle level, register-transfer level),generation, simulation, testing at different granularities (unit test-ing, integration testing, property-based testing), and characteriza-tion (area, power, and timing). OpenCGRAs will be made availableon GitHub.

CGRA, synthesis↗

Architecture Of A Multi-channel Data Streaming Device With An Fpga As A Coprocessor

The design of a data acquisition system often involves the integration of a Field Programmable Gate Array (FPGA) with analog front-end components to achieve precise timing and control. Reuse of these hardware systems can be difficult since they need to be tightly coupled to the communications interface and timing requirements of the specific ADC used. A hybrid design exploring the use of FPGA as a coprocessor to a traditional CPU in a dataflow architecture is presented. Reduction in the volume of data and gradual transitioning of data processing away from a hard real-time environment are both discussed. Chief design concerns, including data throughput and precise synchronization with external stimuli, are addressed. The discussion is illustrated by the implementation of a multi-channel digital integrator, a device based entirely on commercial off-the-shelf (COTS) equipment.

Nogiec, Jerzy M.↗

Open-source FPGA-ML codesign for the MLPerf Tiny Benchmark

We present our development experience and recent results for the MLPerf Tiny Inference Benchmark on field-programmable gate array (FPGA) platforms. We use the open-source hls4ml and FINN workflows, which aim to democratize AI-hardware codesign of optimized neural networks on FPGAs. We present the design and implementation process for the keyword spotting, anomaly detection, and image classification benchmark tasks. The resulting hardware implementations are quantized, configurable, spatial dataflow architectures tailored for speed and efficiency and introduce new generic optimizations and common workflows developed as a part of this work. The full workflow is presented from quantization-aware training to FPGA implementation. The solutions are deployed on system-on-chip (Pynq-Z2) and pure FPGA (Arty A7-100T) platforms. The resulting submissions achieve latencies as low as 20 $\mu$s and energy consumption as low as 30 $\mu$J per inference. We demonstrate how emerging ML benchmarks on heterogeneous hardware platforms can catalyze collaboration and the development of new techniques and more accessible tools.

Borras, Hendrik↗

Towards Lightweight Data Integration Using Multi-Workflow Provenance and Data Observability

Modern large-scale scientific discovery requires multidisciplinary collaboration across diverse computing facilities, including High Performance Computing (HPC) machines and the Edge-to-Cloud continuum. Integrated data analysis plays a crucial role in scientific discovery, especially in the current AI era, by enabling Responsible AI development, FAIR, Reproducibility, and User Steering. However, the heterogeneous nature of science poses challenges such as dealing with multiple supporting tools, cross-facility environments, and efficient HPC execution. Building on data observability, adapter system design, and provenance, we propose MIDA: an approach for lightweight runtime Multi-workflow Integrated Data Analysis. MIDA defines data observability strategies and adaptability methods for various parallel systems and machine learning tools. With observability, it intercepts the dataflows in the background without requiring instrumentation while integrating domain, provenance, and telemetry data at runtime into a unified database ready for user steering queries. We conduct experiments showing end-to-end multi-workflow analysis integrating data from Dask and MLFlow in a real distributed deep learning use case for materials science that runs on multiple environments with up to 276 GPUs in parallel. We show near-zero overhead running up to 100,000 tasks on 1,680 CPU cores on the Summit supercomputer.

Santos Souza, Renan↗

A scalable approach to solving dense linear algebra problems on hybrid CPU-GPU systems

Aiming to fully exploit the computing power of all CPUs and all graphics processing units (GPUs) on hybrid CPU-GPU systems to solve dense linear algebra problems, in this paper we design a class of heterogeneous tile algorithms to maximize the degree of parallelism, to minimize the communication volume, and to accommodate the heterogeneity between CPUs and GPUs. The new heterogeneous tile algorithms are executed upon our decentralized dynamic scheduling runtime system, which schedules a task graph dynamically and transfers data between compute nodes automatically. The runtime system uses a new distributed task assignment protocol to solve data dependencies between tasks without any coordination between processing units. By overlapping computation and communication through dynamic scheduling, we are able to attain scalable performance for the double-precision Cholesky factorization and QR factorization. Finally, our approach demonstrates a performance comparable to Intel MKL on shared-memory multicore systems and better performance than both vendor (e.g., Intel MKL) and open source libraries (e.g., StarPU) in the following three environments: heterogeneous clusters with GPUs, conventional clusters without GPUs, and shared-memory systems with multiple GPUs.

97 MATHEMATICS AND COMPUTING↗

Software Defined Architectures for Data Analytics

Data analytics applications increasingly are complex workflows composed of phases with very different program behaviors (e.g., graph algorithms and machine learning, algorithms operating on sparse an dense data structures, etc). To reach the levels of efficiency required to process these workflows in real time, upcoming architectures will need to leverage even more workload specialization. If, at one end, we may find even more heterogenous processors composed by a myriad of specialized processing elements, at the other end we may see novel reconfigurable architectures, composed of sets of functional units and memories interconnected with (re)configurable on-chip networks, able to adapt dynamically to adapt the workload characteristics. Field Programmable Gate Arrays are more and more used for accelerating various workloads and, in particular, inferencing in machine learning, providing higher efficiency than other solutions. However, their fine grained nature still leads to issues for the design software and still makes dynamic reconfiguration impractical. Future, more coarse-grained architectures could offer the features to execute diverse workloads at high efficiency while providing better reconfiguration mechanisms for dynamic adaptability. Nevertheless, we argue that the challenges for reconfigurable computing remain in the software. In this position paper, we describe a possible toolchain for reconfigurable architectures targeted at data analytics.

FPGA, Dataflow, Reconfigurable Architectures, Soft↗

Programming Abstractions for Managing Workflows on Tiered Storage Systems

Scientific workflows in High Performance Computing (HPC) environments are processing large amounts of data. The storage hierarchy on HPC systems is getting deeper, driven by new technologies (NVRAMs, SSDs, etc.) There is a need for new programming abstractions that allow users to seamlessly manage data at the workflow level on multi-tiered storage systems, and provide optimal workflow performance and use of storage resources. In previous work, we introduced a software architecture Managing Data on Tiered Storage for Scientific Workflows (MaDaTS) that used a Virtual Data Space (VDS) abstraction to hide the complexities of the underlying storage system while allowing users to control data management strategies. In this article, we detail the data-centric programming abstractions that allow users to manage a workflow around its data on the storage layer. The programming abstractions simplify data management for scientific workflows on multi-tiered storage systems, without affecting workflow performance or storage capacity. We measure the overheads and effectiveness introduced by the programming abstractions of MaDaTS. Our results show that these abstractions can optimally use the storage capacity in lesser capacity storage tiers, and simplify data management without adding any performance overheads.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗