Search NASA⌕ Search

SEARCH · Search NASA

Results for “Memory Bandwidth”

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 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS1995

Exploring the use of I/O nodes for computation in a MIMD multiprocessor

As parallel systems move into the production scientific-computing world, the emphasis will be on cost-effective solutions that provide high throughput for a mix of applications. Cost effective solutions demand that a system make effective use of all of its resources. Many MIMD multiprocessors today, however, distinguish between 'compute' and 'I/O' nodes, the latter having attached disks and being dedicated to running the file-system server. This static division of responsibilities simplifies system management but does not necessarily lead to the best performance in workloads that need a different balance of computation and I/O. Of course, computational processes sharing a node with a file-system service may receive less CPU time, network bandwidth, and memory bandwidth than they would on a computation-only node. In this paper we begin to examine this issue experimentally. We found that high performance I/O does not necessarily require substantial CPU time, leaving plenty of time for application computation. There were some complex file-system requests, however, which left little CPU time available to the application. (The impact on network and memory bandwidth still needs to be determined.) For applications (or users) that cannot tolerate an occasional interruption, we recommend that they continue to use only compute nodes. For tolerant applications needing more cycles than those provided by the compute nodes, we recommend that they take full advantage of both compute and I/O nodes for computation, and that operating systems should make this possible.

Kotz, David↗
NASA NTRSDate not supplied

Memory Optimizations for Sparse Linear Algebra on GPU Hardware

An effort to maximize memory bandwidth utilization for a sparse linear algebra kernel executing on NVIDIA® Tesla V100 and A100 Graphics Processing Units (GPUs) is described. The kernel consists of a block-sparse matrix-vector product and a series of forward/backward triangular solves. The computation is memory-bound and exhibits low arithmetic intensity. Along with a relatively small block size, the data layout poses a challenge to effectively utilize the available memory bandwidth on common GPU architectures. An earlier implementation using a warp to process a single row of the matrix was found to yield good memory performance on the V100 architecture. However, anew approach, which assigns a warp to six rows of the matrix, is proposed for the A100. In addition, two new features offered by the A100 architecture are explored.L2residency control enables a portion of theL2cache to be used for persistent data access, and the asynchronous copy instruction allows data to be loaded directly from main memory into shared memory. Demonstrations show that the new implementation improves memory bandwidth utilization from 71.5% to 81.2% of the peak available on theA100 architecture.

GPU↗
NASA NTRS2000

Method and device for maximizing memory system bandwidth by accessing data in a dynamically determined order

A data processing system is disclosed which comprises a data processor and memory control device for controlling the access of information from the memory. The memory control device includes temporary storage and decision ability for determining what order to execute the memory accesses. The compiler detects the requirements of the data processor and selects the data to stream to the memory control device which determines a memory access order. The order in which to access said information is selected based on the location of information stored in the memory. The information is repeatedly accessed from memory and stored in the temporary storage until all streamed information is accessed. The information is stored until required by the data processor. The selection of the order in which to access information maximizes bandwidth and decreases the retrieval time.

Wulf, William A.↗
NASA NTRS1997

On the Floating Point Performance of the i860 Microprocessor

The i860 microprocessor is a pipelined processor that can deliver two double precision floating point results every clock. It is being used in the Touchstone project to develop a teraflop computer by the year 2000. With such high computational capabilities it was expected that memory bandwidth would limit performance on many kernels. Measured performance of three kernels showed performance is less than what memory bandwidth limitations would predict. This paper develops a model that explains the discrepancy in terms of memory latencies and points to some problems involved in moving data from memory to the arithmetic pipelines.

Lee, King↗
NASA NTRSDate not supplied

Performance and Portability of a Linear Solver Across Emerging Architectures

A linear solver algorithm used by a large-scale unstructured-grid computational fluid dynamics application is examined for a broad range of familiar and emerging architectures. Efficient implementation of a linear solver is challenging on recent CPUs offering vector architectures. Vector loads and stores are essential to effectively utilize available memory bandwidth on CPUs, and maintaining performance across different CPUs can be difficult in the face of varying vector lengths offered by each. A similar challenge occurs on GPU architectures, where it is essential to have coalesced memory accesses to utilize memory bandwidth effectively. In this work, we demonstrate that restructuring a computation, and possibly data layout, with regard to architecture is essential to achieve optimal performance by establishing a performance benchmark for each target architecture in a low level language such as vector intrinsics or CUDA. In doing so, we demonstrate how a linear solver kernel can be mapped to Intel® Xeon™ and Xeon Phi™, Marvell® ThunderX2®, NEC® SX-Aurora™ TSUBASA Vector Engine, and NVIDIA® and AMD® GPUs. We further demonstrate that the required code restructuring can be achieved in higher level programming environments such as OpenACC, OCCA, and Intel® OneAPI™/SYCL, and that each generally results in optimal performance on the target architecture. Relative performance metrics for all implementations are shown, and subjective ratings for ease of implementation and optimization are suggested.

Programming models↗
NASA NTRS1974

A multiprocessor computer simulation model employing a feedback scheduler/allocator for memory space and bandwidth matching and TMR processing

A computer simulation model for a multiprocessor computer is developed that is useful for studying the problem of matching multiprocessor's memory space, memory bandwidth and numbers and speeds of processors with aggregate job set characteristics. The model assumes an input work load of a set of recurrent jobs. The model includes a feedback scheduler/allocator which attempts to improve system performance through higher memory bandwidth utilization by matching individual job requirements for space and bandwidth with space availability and estimates of bandwidth availability at the times of memory allocation. The simulation model includes provisions for specifying precedence relations among the jobs in a job set, and provisions for specifying precedence execution of TMR (Triple Modular Redundant and SIMPLEX (non redundant) jobs.

Bradley, D. B.↗
NASA NTRS2008

Initial Performance Results on IBM POWER6

The POWER5+ processor has a faster memory bus than that of the previous generation POWER5 processor (533 MHz vs. 400 MHz), but the measured per-core memory bandwidth of the latter is better than that of the former (5.7 GB/s vs. 4.3 GB/s). The reason for this is that in the POWER5+, the two cores on the chip share the L2 cache, L3 cache and memory bus. The memory controller is also on the chip and is shared by the two cores. This serializes the path to memory. For consistently good performance on a wide range of applications, the performance of the processor, the memory subsystem, and the interconnects (both latency and bandwidth) should be balanced. Recognizing this, IBM has designed the Power6 processor so as to avoid the bottlenecks due to the L2 cache, memory controller and buffer chips of the POWER5+. Unlike the POWER5+, each core in the POWER6 has its own L2 cache (4 MB - double that of the Power5+), memory controller and buffer chips. Each core in the POWER6 runs at 4.7 GHz instead of 1.9 GHz in POWER5+. In this paper, we evaluate the performance of a dual-core Power6 based IBM p6-570 system, and we compare its performance with that of a dual-core Power5+ based IBM p575+ system. In this evaluation, we have used the High- Performance Computing Challenge (HPCC) benchmarks, NAS Parallel Benchmarks (NPB), and four real-world applications--three from computational fluid dynamics and one from climate modeling.

Saini, Subbash↗
NASA NTRSDate not supplied

Performance Optimization Methods for a Memory-Bound, Unstructured-Grid CFD Application on Massively Parallel GPU Platforms

Computational performance of the FUN3D unstructured-grid computational fluid dynamics (CFD) application on massively parallel GPU environments is memory-bound and highly dependent upon efficient reads from and atomic updates to the irregular cell-, edge-, and node-based data structures. In this talk, we present recent efforts into optimizing select performance-critical kernels on NVIDIA Tesla V100 and A100 GPUs and AMD CDNA MI100 GPUs. A novel use of L2 cache residency controls and asynchronous loads into on-chip shared memory are explored on the A100 GPU for the sparse iterative solver, which is dominated by mixed-precision, sparse matrix vector multiplication. Demonstrations show that these methods improve global memory bandwidth utilization by 13.5% on the A100 GPU. Several techniques are also presented that use registers and/or shared memory to facilitate array transposition and aggregation which combine to reduce the frequency and increase the cache efficiency of floating-point atomic updates to the irregular data structures. These methods are demonstrated to improve the kernel throughput by nearly 500% on select kernels on the AMD MI100 over atomic updates directly to global memory. Overall, both V100 and A100 GPUs outperformed the MI100 GPU on kernels dominated by double-precision atomic updates; however, the techniques demonstrated here reduced the performance gap and improved the MI100 performance.

GPU CPU unstructured CFD memory↗
NASA NTRS1992

Using a Cray Y-MP as an array processor for a RISC Workstation

As microprocessors increase in power, the economics of centralized computing has changed dramatically. At the beginning of the 1980's, mainframes and super computers were often considered to be cost-effective machines for scalar computing. Today, microprocessor-based RISC (reduced-instruction-set computer) systems have displaced many uses of mainframes and supercomputers. Supercomputers are still cost competitive when processing jobs that require both large memory size and high memory bandwidth. One such application is array processing. Certain numerical operations are appropriate to use in a Remote Procedure Call (RPC)-based environment. Matrix multiplication is an example of an operation that can have a sufficient number of arithmetic operations to amortize the cost of an RPC call. An experiment which demonstrates that matrix multiplication can be executed remotely on a large system to speed the execution over that experienced on a workstation is described.

Lamaster, Hugh↗
NASA NTRS1995

Improved reduced-resolution satellite imagery

The resolution of satellite imagery is often traded-off to satisfy transmission time and bandwidth, memory, and display limitations. Although there are many ways to achieve the same reduction in resolution, algorithms vary in their ability to preserve the visual quality of the original imagery. These issues are investigated in the context of the Landsat browse system, which permits the user to preview a reduced resolution version of a Landsat image. Wavelets-based techniques for resolution reduction are proposed as alternatives to subsampling used in the current system. Experts judged imagery generated by the wavelets-based methods visually superior, confirming initial quantitative results. In particular, compared to subsampling, the wavelets-based techniques were much less likely to obscure roads, transmission lines, and other linear features present in the original image, introduce artifacts and noise, and otherwise reduce the usefulness of the image. The wavelets-based techniques afford multiple levels of resolution reduction and computational speed. This study is applicable to a wide range of reduced resolution applications in satellite imaging systems, including low resolution display, spaceborne browse, emergency image transmission, and real-time video downlinking.

Ellison, James↗
NASA NTRS1996

An Evaluation of Architectural Platforms for Parallel Navier-Stokes Computations

We study the computational, communication, and scalability characteristics of a computational fluid dynamics application, which solves the time accurate flow field of a jet using the compressible Navier-Stokes equations, on a variety of parallel architecture platforms. The platforms chosen for this study are a cluster of workstations (the LACE experimental testbed at NASA Lewis), a shared memory multiprocessor (the Cray YMP), and distributed memory multiprocessors with different topologies - the IBM SP and the Cray T3D. We investigate the impact of various networks connecting the cluster of workstations on the performance of the application and the overheads induced by popular message passing libraries used for parallelization. The work also highlights the importance of matching the memory bandwidth to the processor speed for good single processor performance. By studying the performance of an application on a variety of architectures, we are able to point out the strengths and weaknesses of each of the example computing platforms.

Jayasimha, D. N.↗
NASA NTRS1997

Parallelizing Navier-Stokes Computations on a Variety of Architectural Platforms

We study the computational, communication, and scalability characteristics of a Computational Fluid Dynamics application, which solves the time accurate flow field of a jet using the compressible Navier-Stokes equations, on a variety of parallel architectural platforms. The platforms chosen for this study are a cluster of workstations (the LACE experimental testbed at NASA Lewis), a shared memory multiprocessor (the Cray YMP), distributed memory multiprocessors with different topologies-the IBM SP and the Cray T3D. We investigate the impact of various networks, connecting the cluster of workstations, on the performance of the application and the overheads induced by popular message passing libraries used for parallelization. The work also highlights the importance of matching the memory bandwidth to the processor speed for good single processor performance. By studying the performance of an application on a variety of architectures, we are able to point out the strengths and weaknesses of each of the example computing platforms.

Jayasimha, D. N.↗
NASA NTRS1994

Applications Performance on NAS Intel Paragon XP/S - 15#

The Numerical Aerodynamic Simulation (NAS) Systems Division received an Intel Touchstone Sigma prototype model Paragon XP/S- 15 in February, 1993. The i860 XP microprocessor with an integrated floating point unit and operating in dual -instruction mode gives peak performance of 75 million floating point operations (NIFLOPS) per second for 64 bit floating point arithmetic. It is used in the Paragon XP/S-15 which has been installed at NAS, NASA Ames Research Center. The NAS Paragon has 208 nodes and its peak performance is 15.6 GFLOPS. Here, we will report on early experience using the Paragon XP/S- 15. We have tested its performance using both kernels and applications of interest to NAS. We have measured the performance of BLAS 1, 2 and 3 both assembly-coded and Fortran coded on NAS Paragon XP/S- 15. Furthermore, we have investigated the performance of a single node one-dimensional FFT, a distributed two-dimensional FFT and a distributed three-dimensional FFT Finally, we measured the performance of NAS Parallel Benchmarks (NPB) on the Paragon and compare it with the performance obtained on other highly parallel machines, such as CM-5, CRAY T3D, IBM SP I, etc. In particular, we investigated the following issues, which can strongly affect the performance of the Paragon: a. Impact of the operating system: Intel currently uses as a default an operating system OSF/1 AD from the Open Software Foundation. The paging of Open Software Foundation (OSF) server at 22 MB to make more memory available for the application degrades the performance. We found that when the limit of 26 NIB per node out of 32 MB available is reached, the application is paged out of main memory using virtual memory. When the application starts paging, the performance is considerably reduced. We found that dynamic memory allocation can help applications performance under certain circumstances. b. Impact of data cache on the i860/XP: We measured the performance of the BLAS both assembly coded and Fortran coded. We found that the measured performance of assembly-coded BLAS is much less than what memory bandwidth limitation would predict. The influence of data cache on different sizes of vectors is also investigated using one-dimensional FFTs. c. Impact of processor layout: There are several different ways processors can be laid out within the two-dimensional grid of processors on the Paragon. We have used the FFT example to investigate performance differences based on processors layout.

Saini, Subhash↗
NASA NTRS2005

An Application-Based Performance Characterization of the Columbia Supercluster

Columbia is a 10,240-processor supercluster consisting of 20 Altix nodes with 512 processors each, and currently ranked as the second-fastest computer in the world. In this paper, we present the performance characteristics of Columbia obtained on up to four computing nodes interconnected via the InfiniBand and/or NUMAlink4 communication fabrics. We evaluate floating-point performance, memory bandwidth, message passing communication speeds, and compilers using a subset of the HPC Challenge benchmarks, and some of the NAS Parallel Benchmarks including the multi-zone versions. We present detailed performance results for three scientific applications of interest to NASA, one from molecular dynamics, and two from computational fluid dynamics. Our results show that both the NUMAlink4 and the InfiniBand hold promise for application scaling to a large number of processors.

Biswas, Rupak↗
NASA NTRS2015

High-Speed On-Board Data Processing for Science Instruments: HOPS

The project called High-Speed On-Board Data Processing for Science Instruments (HOPS) has been funded by NASA Earth Science Technology Office (ESTO) Advanced Information Systems Technology (AIST) program during April, 2012 â€" April, 2015. HOPS is an enabler for science missions with extremely high data processing rates. In this three-year effort of HOPS, Active Sensing of CO2 Emissions over Nights, Days, and Seasons (ASCENDS) and 3-D Winds were of interest in particular. As for ASCENDS, HOPS replaces time domain data processing with frequency domain processing while making the real-time on-board data processing possible. As for 3-D Winds, HOPS offers real-time high-resolution wind profiling with 4,096-point fast Fourier transform (FFT). HOPS is adaptable with quick turn-around time. Since HOPS offers reusable user-friendly computational elements, its FPGA IP Core can be modified for a shorter development period if the algorithm changes. The FPGA and memory bandwidth of HOPS is 20 GB/sec while the typical maximum processor-to-SDRAM bandwidth of the commercial radiation tolerant high-end processors is about 130-150 MB/sec. The inter-board communication bandwidth of HOPS is 4 GB/sec while the effective processor-to-cPCI bandwidth of commercial radiation tolerant high-end boards is about 50-75 MB/sec. Also, HOPS offers VHDL cores for the easy and efficient implementation of ASCENDS and 3-D Winds, and other similar algorithms. A general overview of the 3-year development of HOPS is the goal of this presentation.

Beyon, Jeffrey↗
NASA NTRS2019

Application of Machine Learning Techniques to Delay Tolerant Network Routing

This dissertation discusses several machine learning techniques to improve routing in delay tolerant networks (DTNs). These are networks in which there may be long one-way trip times, asymmetric links, high error rates, and deterministic as well as non-deterministic loss of contact between network nodes, such as interplanetary satellite networks, mobile ad hoc networks and wireless sensor networks. This work uses historical network statistics to train a multi-label classifier to predict reliable paths through the network. In addition, a clustering technique is used to predict future mobile node locations. Both of these techniques are used to reduce the consumption of resources such as network bandwidth, memory and data storage that is required by replication routing methods often used in opportunistic DTN environments. Thesis contributions include: an emulation tool chain developed to create a DTN test bed for machine learning, the network and software architecture for a machine learning based routing method, the development and implementation of classification and clustering techniques and performance evaluation in terms of machine learning and routing metrics.

Dudukovich, Rachel M.↗
NASA NTRSDate not supplied

NASA and Blue Origin Collaborative Assessment of Precision Landing Algorithms and Computing

NASA’s Safe and Precise Landing Integrated Capabilities Evolution (SPLICE) project is developing sensor, algorithm, and compute technologies for precision landing and hazard avoidance. These technologies are being tested as an integrated Precision Landing and Hazard Avoidance (PL&HA) system on Blue Origin’s New Shephard suborbital vehicle. A key goal for the computing element of this technology development is to characterize the performance of the SPLICE software workloads on the project’s Descent and Landing Computer (DLC). The DLC is a multi-core processor designed as a surrogate for NASA’s High-Performance Space Computer (HPSC). Measurements of the SPLICE workload performance on the DLC provides NASA insight on how PL&HA capabilities will perform on the HPSC, and guidance on how the SPLICE algorithms can be implemented to best utilize the DLC platform. This insight can also be used to derive requirements to guide trade studies on candidate computing architectures, for use on platforms like Blue Moon. NASA and Blue Origin are collaborating under an agreement to pursue this mutual benefit. Performance metrics collected are based on measurement of common compute resources such as percentage used of memory bandwidth, I/O utilization, interrupt latency, and kernel vs. user space code residency. Where possible existing performance counters and metrics that are part of the operating system kernel are used. As the design has a significant FPGA component, performance counters are identified and instantiated in the fabric to measure DMA performance and interface metrics. Collection of metrics is performed on the DLC with a representative workload that simulates a full landing cycle of the Blue Origin New Shepard vehicle. Consideration is given to the other compute implementations and whether they can run SPLICE algorithms at the same rate and with the same latency as the DLC. One option being considered is the use of a RISC-V soft core instantiated in a radiation resilient FPGA fabric such as the Xilinx KU60. Select algorithms from the SPLICE code will be run for comparison with the DLC. This paper describes how the DLC is instrumented to collect performance measurements of the SPLICE workloads, preliminary results from these measurements, and their implications on SPLICE algorithm implementation. The results of experimentation to derive candidate requirements for architecture trades on a PL&HA computing system are also presented.

computer performance↗
NASA NTRSDate not supplied

Improvements to a Batch Pentadiagonal Solver on NVIDIA GPUs

This poster presents the recent work in OVERFLOW to port the batched pentadiagonal solver to NVIDIA GPUs. There are five pentadiagonal systems for each pencil in the grid but three of these systems share the same LHS. Our first simple approach for porting the pentadiagonal solver to the GPUs was to take advantage of the shared LHS by assigning three threads to the three LHS of each pencil. We demonstrated that this custom solver was 92% faster than the NVIDIA batched pentadiagonal library implementation on a V100 GPU due to the lower memory bandwidth requirements. The second approach treated each pentadiagonal system as a 2x2 block tridiagonal system and used a variant of the parallel cyclic reduction algorithm to solve the problem. One benefit of this approach is that it does not require interleaving the data between each system. We demonstrated that this algorithm is 2.18x faster than the NVIDIA library implementation for the same amount of work. If we take advantage of our shared LHS, this approach is 2.58x faster than the library implementation on a V100 GPU.

GPU Programming↗