Search NASA⌕ Search

SEARCH · Search NASA

Results for “Data Transfer”

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 955 records · Page 53

Fast and effective reordering of columns within supernodes using partition refinement

In this paper, we consider the problem of computing a triangular factorization of a sparse symmetric matrix using Gaussian elimination. We assume that the sparse matrix has been permuted using a fill-reducing ordering algorithm. When the matrix is symmetric positive definite, the sparsity structure of the triangular factor can be determined once the fill-reducing ordering has been computed. Thus, an efficient numerical factorization scheme can be designed so that only the nonzero entries are stored and operated on. On modern architectures, the positions of the nonzero entries in the triangular factor play a big role in determining the efficiency. It is desirable to have dense blocks in the factor so that the computation can be cast in terms of level-3 BLAS as much as possible. On architectures with GPUs, for example, it is also desirable for these dense blocks to be as large as possible in order to reduce the times to transfer data between the main CPU and the GPUs. We address the problem of locally refining the ordering so that the number of dense blocks is reduced and the sizes of these dense blocks are increased in the triangular factor.

Jacquelin, Mathias↗

Algorithms for high-throughput disk-to-disk sorting, In: SC '13 Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis

In this paper, we present a new out-of-core sort algorithm, designed for problems that are too large to fit into the aggregate RAM available on modern supercomputers. We analyze the performance including the cost of IO and demonstrate the fastest (to the best of our knowledge) reported throughput using the canonical sortBenchmark on a general-purpose, production HPC resource running Lustre. By clever use of available storage and a formulation of asynchronous data transfer mechanisms, we are able to almost completely hide the computation (sorting) behind the IO latency. This latency hiding enables us to achieve comparable execution times, including the additional temporary IO required, between a large sort problem (5TB) run as a single, in-RAM sort and our out-of-core approach using 1/10th the amount of RAM. In our largest run, sorting 100TB of records using 1792 hosts, we achieved an end-to-end throughput of 1.24TB/min using our general-purpose sorter, improving on the current Daytona record holder by 65%.

Computer Science↗

TCP Throughput Profiles Using Measurements over Dedicated Connections

Wide-area data transfers in high-performance computing infrastructures are increasingly being carried over dynamically provisioned dedicated network connections that provide high capacities with no competing traffic. We present extensive TCP throughput measurements and time traces over a suite of physical and emulated 10 Gbps connections with 0-366 ms round-trip times (RTTs). Contrary to the general expectation, they show significant statistical and temporal variations, in addition to the overall dependencies on the congestion control mechanism, buffer size, and the number of parallel streams. We analyze several throughput profiles that have highly desirable concave regions wherein the throughput decreases slowly with RTTs, in stark contrast to the convex profiles predicted by various TCP analytical models. We present a generic throughput model that abstracts the ramp-up and sustainment phases of TCP flows, which provides insights into qualitative trends observed in measurements across TCP variants: (i) slow-start followed by well-sustained throughput leads to concave regions; (ii) large buffers and multiple parallel streams expand the concave regions in addition to improving the throughput; and (iii) stable throughput dynamics, indicated by a smoother Poincare map and smaller Lyapunov exponents, lead to wider concave regions. These measurements and analytical results together enable us to select a TCP variant and its parameters for a given connection to achieve high throughput with statistical guarantees.

Rao, Nageswara S.↗

Distributed caching for processing raw arrays

As applications continue to generate multi-dimensional data at exponentially increasing rates, fast analytics to extract meaningful results is becoming extremely important. The database community has developed array databases that alleviate this problem through a series of techniques. In-situ mechanisms provide direct access to raw data in the original format---without loading and partitioning. Parallel processing scales to the largest datasets. In-memory caching reduces latency when the same data are accessed across a workload of queries. However, we are not aware of any work on distributed caching of multi-dimensional raw arrays. In this paper, we introduce a distributed framework for cost-based caching of multi-dimensional arrays in native format. Given a set of files that contain portions of an array and an online query workload, the framework computes an effective caching plan in two stages. First, the plan identifies the cells to be cached locally from each of the input files by continuously refining an evolving R-tree index. In the second stage, an optimal assignment of cells to nodes that collocates dependent cells in order to minimize the overall data transfer is determined. We design cache eviction and placement heuristic algorithms that consider the historical query workload. A thorough experimental evaluation over two real datasets in three file formats confirms the superiority -- by as much as two orders of magnitude -- of the proposed framework over existing techniques in terms of cache overhead and workload execution time.

Zhao, Weijie↗

Exploring the Use of Novel Spatial Accelerators in Scientific Applications

Driven by the need to find alternative accelerators which can viably replace GPUs in next-generation Supercomputing systems, this paper proposes a methodology to enable agile application/hardware co-design. The application-first methodology provides the ability to come up with design of accelerators while working with real-world workloads, available accelerators, and system software. The iterative design process targets a set of kernels in a workload for performance estimates that can prune the design space for later phases of detailed architectural evaluations. To this effect, in this paper, a novel data-parallel device model is introduced that simulates the latency of performance-sensitive operations in an accelerator including data transfers and kernel computation using multi-core CPUs. The use of off-the-shelf simulators, such as pre-RTL simulator Aladdin or multiple tools available for exploring the design of deep neural network accelerators (e.g., Timeloop) is demonstrated for evaluation of various accelerator designs using applications with realistic inputs. Examples of multiple device configurations that are instantiable in a system are explored to evaluate the performance benefit of deploying novel accelerators. The proposed device is integrated with a programming model and system software to potentially explore the impacts of high-level programming languages/compilers and low-level effects such as task scheduling on multiple accelerators. We analyze our methodology for a set of applications that represent high-performance computing (HPC) and graph analytics. The applications include a computational chemistry kernel realized using tensor contractions, triangle counting, GraphSAGE and Breadth-first Search. These applications include kernels such as dense matrix-dense matrix multiplication, sparse matrix-spare matrix multiplication, and sparse matrix-dense vector multiplication. Our results indicate potential performance benefits and insights for system design by including accelerators that realize these kernels along-side general purpose accelerators.

AI, codesign, Accelerated Computing, Modeling and ↗

Design and analysis of CXL performance models for tightly-coupled heterogeneous computing

Truly heterogeneous systems enable partitioned workloads to be mapped to the hardware that nets the best performance. However, current practice requires that inter-device communication between different vendors' hardware use host memory as an intermediary step. To date, there are no widely adopted solutions that allow accelerators to directly transfer data. A new cache-coherent protocol, CXL, aims to facilitate easier, fine-grained sharing between accelerators. In this work we analyze existing methods for designing heterogeneous applications that target GPUs and FPGAs working collaboratively, followed by an exploration to show the benefits of a CXL-enabled system. Specifically, we develop a test application that utilizes both an NVIDIA P100 GPU and a Xilinx U250 FPGA to show current communication limitations. From this application, we capture overall execution time and throughput measurements on the FPGA and GPU. We use these measurements as inputs to novel CXL performance models to show that using CXL caching instead of host memory results in a 1.31X speedup, while a more tightly-coupled pipelined implementation using CXL-enabled hardware would result in a speedup of 1.45X.

Cabrera, Anthony↗

IRIS-MASH: Efficient Multi-device Asynchronous Multi-Stream Heterogeneous Computing

In the rapidly evolving field of high-performance computing (HPC), effectively leveraging heterogeneous devices through asynchronous task programming is paramount. This paper presents a robust asynchronous task programming model tailored for a multi-device, multi-stream execution environment that incorporates a diverse array of heterogeneous computing units, including GPUs from various vendors and other accelerators. Current state-of-the-art task programming models provide methodologies to support asynchronous task executions, but they typically handle homogeneous devices using native programming languages, while support for heterogeneous devices is limited to frameworks like OpenCL. This gap presents significant challenges in abstracting heterogeneous devices to harness their true asynchronous capabilities effectively using their native programming languages. By implementing asynchronous task execution, our model significantly boosts the performance of tiled algorithm task graphs through overlapping data transfers with computation and enabling the simultaneous execution of multiple kernels. We integrate this approach into a heterogeneous Intelligent Runtime System (IRIS) and assess its performance using a suite of tiled algorithm benchmarks from the heterogeneous math kernels library (MatRIS) based on IRIS. Experimental results demonstrate a performance improvement ranging from 1.6 × to 2 × over IRIS without asynchronous support, and a notable 22% performance enhancement compared to established runtime systems such as StarPU and PaRSEC. This approach significantly improves computation efficiency of HPC workflows and provides a solid base for future exploration and development in the area of asynchronous task programming in heterogeneous systems.

Miniskar, Narasinga Rao [ORNL] (ORCID:000000018259↗

flume-plugins Version 1.0

Flume-plugins are plugins for Apache Flume, which are used for managing data transferred through Apache Flume.

Chu, A.L.↗

Build and Execute Environment

At exascale, the challenge becomes to develop applications that run at scale and use exascale platforms reliably, efficiently, and flexibly. Workflows become much more complex because they must seamlessly integrate simulation and data analytics. They must include down-sampling, post-processing, feature extraction, and visualization. Power and data transfer limitations require these analysis tasks to be run in-situ or in-transit. We expect successful workflows will comprise multiple linked simulations along with tens of analysis routines. Users will have limited development time at scale and, therefore, must have rich tools to develop, debug, test, and deploy applications. At this scale, successful workflows will compose linked computations from an assortment of reliable, well-defined computation elements, ones that can come and go as required, based on the needs of the workflow over time. We propose a novel framework that utilizes both virtual machines (VMs) and software containers to create a workflow system that establishes a uniform build and execution environment (BEE) beyond the capabilities of current systems. In this environment, applications will run reliably and repeatably across heterogeneous hardware and software. Containers, both commercial (Docker and Rocket) and open-source (LXC and LXD), define a runtime that isolates all software dependencies from the machine operating system. Workflows may contain multiple containers that run different operating systems, different software, and even different versions of the same software. We will run containers in open-source virtual machines (KVM) and emulators (QEMU) so that workflows run on any machine entirely in user-space. On this platform of containers and virtual machines, we will deliver workflow software that provides services, including repeatable execution, provenance, checkpointing, and future proofing. We will capture provenance about how containers were launched and how they interact to annotate workflows for repeatable and partial re-execution. We will coordinate the physical snapshots of virtual machines with parallel programming constructs, such as barriers, to automate checkpoint and restart. We will also integrate with HPC-specific container runtimes to gain access to accelerators and other specialized hardware to preserve native performance. Containers will link development to continuous integration. When application developers check code in, it will automatically be tested on a suite of different software and hardware architectures.

Guan, Qiang↗

LBNL DDoS Detection on Science Networks v0.1

This software contains a set of analysis tools to identify certain types of DDoS attacks and disambiguate those attacks from large scientific data transfers over networks as well as ordinary Internet network traffic. It also contains a piece of "driver" code that allows individual scripts that detect certain types of attacks to selectively be run.

Peisert, SeanP.↗

Concurrent Relaxation through Accelerated Deep Learning

CRADL captures performance metrics of machine learning algorithms operating on mesh data from multiphysics codes This proxy application is a tool to explore scalability of inference on HPC platforms, and also gather performance metrics for inference on new machine learning specific hardware. CRADL is designed to give users as fine a control as possible over an inference simulation. Users may select the number of cycles, amount of data, and batch size to pass to the accelerator of choice. Additionally the user may select a number of performance optimization libraries and flags. CRADL comes packaged with a repository of anonymized multi-physics simulation data, as well as a pretrained model for inference. The code allows a user to load their own pre-trained model and data if they wish. The code can operate in multiple parallelization schemes, with performance enhancing options such as half-precision libraries, PyTorch benchmarking, and pinned memory with non-blocking data transfers.

Zieb, KristoferJ.↗

ESnet Secure Copy (EScp) v0.6

EScp is a high speed transfer tool with a similar command line syntax to scp. Unlike SCP it is designed to transfer files at high speed, thus far we have been able to show 100gbit/s transfers, although I expect that the throughput should scale in proportion to the network interface, i.e. I expect 400gbit/s performance on our 400gbit/s test bed. EScp achieves good performance through an innovative design (multithreaded, zero copy transfers), along with pluggable filters and I/O engines. As an example, you can switch from POSIX i/O to UIO by checking a different engine. It also natively supports encryption, and cheksums for file verification and transport security. AAA is through standard SSH (same as SCP). By taking advantage of filters, EScp supports transferring unstructured data and/or I/O to non-posix data sources. Examples include streaming data (i.e. from equipment), transferring data to the cloud, and/or supporting non-posix file systems (like HPSS).

Shiflett, Charles↗

HPXML Version Translator

HPXML is a consensus data transfer standard for residential buildings. Over several years, multiple versions of the standard have been released. This tool accepts an HPXML file in an older version and translates it to a newer version.

Merket, Noel↗

TEE-ACM2

TEE-ACM2 is a library that computes matrix chain multiplication efficiently on GPUs, using a blocking strategy to load data. The library will provide an energy efficient algorithm for chain Matrix Multiplication, by minimizing both computations and off chip data transfers on the GPUs.

Lim, Hyun↗

artdaq

The artdaq toolkit is a data-acquisition framework designed for high-energy physics experiments. It provides a flexible, reliable backbone for data transfers and has several locations where users can perform custom analysis tasks using the art framework.

Flumerfelt, EricL. [Fermi National Accelerator Lab↗

DDCP framework

DDCP protocol software 1.0 This repository contains the C++ implementation of version 1.x of the Distributed Data Communications Protocol (DDCP). DDCP provides request/reply, feature discovery, data transfer, control, interrupt, and transaction support for communicating with accelerator instrumentation over UDP. The standard server port is 65000. The framework is a source dependency for services that communicate directly with DDCP hardware. It is not a deployable service by itself.

Joshi, Shreya [Fermi National Accelerator Laborato↗

Scaling soft matter physics to thousands of graphics processing units in parallel

We describe a multi-graphics processing unit (GPU) implementation of the Ludwig application, which specialises in simulating a variety of complex fluids via lattice Boltzmann fluid dynamics coupled to additional physics describing complex fluid constituents. We describe our methodology in augmenting the original central processing unit (CPU) version with GPU functionality in a maintainable fashion. We present several optimisations that maximise performance on the GPU architecture through tuning for the GPU memory hierarchy. We describe how we implement particles within the fluid in such a way to avoid a major diversion of the CPU and GPU codebases, whilst minimising data transfer at each time step. We detail our halo-exchange communication phase for the code, which exploits overlapping to allow efficient parallel scaling to many GPUs. We present results showing that the application demonstrates excellent scaling to at least 8192 GPUs in parallel, the largest system tested at the time of writing. The GPU version (on NVIDIA K20X GPUs) is around 3.5–5 times faster that the CPU version (on fully utilised AMD Opteron 6274 16-core CPUs), comparing equal numbers of CPUs and GPUs.

Computer Science↗

Unprecedented cloud resolution in a GPU-enabled full-physics atmospheric climate simulation on OLCF’s summit supercomputer

Clouds represent a key uncertainty in future climate projection. While explicit cloud resolution remains beyond our computational grasp for global climate, we can incorporate important cloud effects through a computational middle ground called the Multi-scale Modeling Framework (MMF), also known as Super Parameterization. This algorithmic approach embeds high-resolution Cloud Resolving Models (CRMs) to represent moist convective processes within each grid column in a Global Climate Model (GCM). The MMF code requires no parallel data transfers and provides a self-contained target for acceleration. This study investigates the performance of the Energy Exascale Earth System Model-MMF (E3SM-MMF) code on the OLCF Summit supercomputer at an unprecedented scale of simulation. Hundreds of kernels in the roughly 10K lines of code in the E3SM-MMF CRM were ported to GPUs with OpenACC directives. A high-resolution benchmark using 4600 nodes on Summit demonstrates the computational capability of the GPU-enabled E3SM-MMF code in a full physics climate simulation.

58 GEOSCIENCES↗