Search NASA⌕ Search

SEARCH · Search NASA

Results for “Floating-point”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
NASA NTRS2004

A Discussion of Using a Reconfigurable Processor to Implement the Discrete Fourier Transform

This paper presents the design and implementation of the Discrete Fourier Transform (DFT) algorithm on a reconfigurable processor system. While highly applicable to many engineering problems, the DFT is an extremely computationally intensive algorithm. Consequently, the eventual goal of this work is to enhance the execution of a floating-point precision DFT algorithm by off loading the algorithm from the computing system. This computing system, within the context of this research, is a typical high performance desktop computer with an may of field programmable gate arrays (FPGAs). FPGAs are hardware devices that are configured by software to execute an algorithm. If it is desired to change the algorithm, the software is changed to reflect the modification, then download to the FPGA, which is then itself modified. This paper will discuss methodology for developing the DFT algorithm to be implemented on the FPGA. We will discuss the algorithm, the FPGA code effort, and the results to date.

White, Michael J.↗
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 NTRS2001

Computationally efficient control allocation

A computationally efficient method for calculating near-optimal solutions to the three-objective, linear control allocation problem is disclosed. The control allocation problem is that of distributing the effort of redundant control effectors to achieve some desired set of objectives. The problem is deemed linear if control effectiveness is affine with respect to the individual control effectors. The optimal solution is that which exploits the collective maximum capability of the effectors within their individual physical limits. Computational efficiency is measured by the number of floating-point operations required for solution. The method presented returned optimal solutions in more than 90% of the cases examined; non-optimal solutions returned by the method were typically much less than 1% different from optimal and the errors tended to become smaller than 0.01% as the number of controls was increased. The magnitude of the errors returned by the present method was much smaller than those that resulted from either pseudo inverse or cascaded generalized inverse solutions. The computational complexity of the method presented varied linearly with increasing numbers of controls; the number of required floating point operations increased from 5.5 i, to seven times faster than did the minimum-norm solution (the pseudoinverse), and at about the same rate as did the cascaded generalized inverse solution. The computational requirements of the method presented were much better than that of previously described facet-searching methods which increase in proportion to the square of the number of controls.

Durham, Wayne↗
NASA NTRS2008

Injecting Artificial Memory Errors Into a Running Computer Program

Single-event upsets (SEUs) or bitflips are computer memory errors caused by radiation. BITFLIPS (Basic Instrumentation Tool for Fault Localized Injection of Probabilistic SEUs) is a computer program that deliberately injects SEUs into another computer program, while the latter is running, for the purpose of evaluating the fault tolerance of that program. BITFLIPS was written as a plug-in extension of the open-source Valgrind debugging and profiling software. BITFLIPS can inject SEUs into any program that can be run on the Linux operating system, without needing to modify the program s source code. Further, if access to the original program source code is available, BITFLIPS offers fine-grained control over exactly when and which areas of memory (as specified via program variables) will be subjected to SEUs. The rate of injection of SEUs is controlled by specifying either a fault probability or a fault rate based on memory size and radiation exposure time, in units of SEUs per byte per second. BITFLIPS can also log each SEU that it injects and, if program source code is available, report the magnitude of effect of the SEU on a floating-point value or other program variable.

Bornstein, Benjamin J.↗
NASA NTRS2008

Support for Diagnosis of Custom Computer Hardware

The Coldfire SDN Diagnostics software is a flexible means of exercising, testing, and debugging custom computer hardware. The software is a set of routines that, collectively, serve as a common software interface through which one can gain access to various parts of the hardware under test and/or cause the hardware to perform various functions. The routines can be used to construct tests to exercise, and verify the operation of, various processors and hardware interfaces. More specifically, the software can be used to gain access to memory, to execute timer delays, to configure interrupts, and configure processor cache, floating-point, and direct-memory-access units. The software is designed to be used on diverse NASA projects, and can be customized for use with different processors and interfaces. The routines are supported, regardless of the architecture of a processor that one seeks to diagnose. The present version of the software is configured for Coldfire processors on the Subsystem Data Node processor boards of the Solar Dynamics Observatory. There is also support for the software with respect to Mongoose V, RAD750, and PPC405 processors or their equivalents.

Molock, Dwaine S.↗
NASA NTRS2010

Hardware-Independent Proofs of Numerical Programs

On recent architectures, a numerical program may give different answers depending on the execution hardware and the compilation. Our goal is to formally prove properties about numerical programs that are true for multiple architectures and compilers. We propose an approach that states the rounding error of each floating-point computation whatever the environment. This approach is implemented in the Frama-C platform for static analysis of C code. Small case studies using this approach are entirely and automatically proved

Boldo, Sylvie↗
NASA NTRS2009

Theorem Proving in Intel Hardware Design

For the past decade, a framework combining model checking (symbolic trajectory evaluation) and higher-order logic theorem proving has been in production use at Intel. Our tools and methodology have been used to formally verify execution cluster functionality (including floating-point operations) for a number of Intel products, including the Pentium(Registered TradeMark)4 and Core(TradeMark)i7 processors. Hardware verification in 2009 is much more challenging than it was in 1999 - today s CPU chip designs contain many processor cores and significant firmware content. This talk will attempt to distill the lessons learned over the past ten years, discuss how they apply to today s problems, outline some future directions.

O'Leary, John↗
NASA NTRS2009

A Comparative Study of Randomized Constraint Solvers for Random-Symbolic Testing

The complexity of constraints is a major obstacle for constraint-based software verification. Automatic constraint solvers are fundamentally incomplete: input constraints often build on some undecidable theory or some theory the solver does not support. This paper proposes and evaluates several randomized solvers to address this issue. We compare the effectiveness of a symbolic solver (CVC3), a random solver, three hybrid solvers (i.e., mix of random and symbolic), and two heuristic search solvers. We evaluate the solvers on two benchmarks: one consisting of manually generated constraints and another generated with a concolic execution of 8 subjects. In addition to fully decidable constraints, the benchmarks include constraints with non-linear integer arithmetic, integer modulo and division, bitwise arithmetic, and floating-point arithmetic. As expected symbolic solving (in particular, CVC3) subsumes the other solvers for the concolic execution of subjects that only generate decidable constraints. For the remaining subjects the solvers are complementary.

Takaki, Mitsuo↗
NASA NTRS2011

Single-Frame Terrain Mapping Software for Robotic Vehicles

This software is a component in an unmanned ground vehicle (UGV) perception system that builds compact, single-frame terrain maps for distribution to other systems, such as a world model or an operator control unit, over a local area network (LAN). Each cell in the map encodes an elevation value, terrain classification, object classification, terrain traversability, terrain roughness, and a confidence value into four bytes of memory. The input to this software component is a range image (from a lidar or stereo vision system), and optionally a terrain classification image and an object classification image, both registered to the range image. The single-frame terrain map generates estimates of the support surface elevation, ground cover elevation, and minimum canopy elevation; generates terrain traversability cost; detects low overhangs and high-density obstacles; and can perform geometry-based terrain classification (ground, ground cover, unknown). A new origin is automatically selected for each single-frame terrain map in global coordinates such that it coincides with the corner of a world map cell. That way, single-frame terrain maps correctly line up with the world map, facilitating the merging of map data into the world map. Instead of using 32 bits to store the floating-point elevation for a map cell, the vehicle elevation is assigned to the map origin elevation and reports the change in elevation (from the origin elevation) in terms of the number of discrete steps. The single-frame terrain map elevation resolution is 2 cm. At that resolution, terrain elevation from 20.5 to 20.5 m (with respect to the vehicle's elevation) is encoded into 11 bits. For each four-byte map cell, bits are assigned to encode elevation, terrain roughness, terrain classification, object classification, terrain traversability cost, and a confidence value. The vehicle s current position and orientation, the map origin, and the map cell resolution are all included in a header for each map. The map is compressed into a vector prior to delivery to another system.

Rankin, Arturo L.↗
NASA NTRS2004

Partitioning a Gridded Rectangle into Smaller Rectangles

A relatively simple algorithm, devised for use in an image-data-compression application, partitions a rectangular pixelated image (or any other rectangle on which a regular rectangular grid has already been superimposed) into a specified number of smaller rectangles, hereafter denoted segments. The algorithm has the following properties: No floating-point operations are needed. The segments tend to be nearly square (in the sense that their widths and heights in pixel units tend to be nearly equal). The segments tend to have nearly equal areas. The algorithm yields valid results (no zero-width or zero-height segments) as long as the specified number of segments, s, does not exceed the number of pixels (equivalently, the number of grid cells). The inputs to the algorithm are the positive integer s plus the positive integers h and w, denoting the height and width, respectively, of the rectangle in pixel units. The limit on s for a valid result is given by s less than or equal to wh.

Klimesh, Matthew↗
NASA NTRS2011

Fast Image Texture Classification Using Decision Trees

Texture analysis would permit improved autonomous, onboard science data interpretation for adaptive navigation, sampling, and downlink decisions. These analyses would assist with terrain analysis and instrument placement in both macroscopic and microscopic image data products. Unfortunately, most state-of-the-art texture analysis demands computationally expensive convolutions of filters involving many floating-point operations. This makes them infeasible for radiation- hardened computers and spaceflight hardware. A new method approximates traditional texture classification of each image pixel with a fast decision-tree classifier. The classifier uses image features derived from simple filtering operations involving integer arithmetic. The texture analysis method is therefore amenable to implementation on FPGA (field-programmable gate array) hardware. Image features based on the "integral image" transform produce descriptive and efficient texture descriptors. Training the decision tree on a set of training data yields a classification scheme that produces reasonable approximations of optimal "texton" analysis at a fraction of the computational cost. A decision-tree learning algorithm employing the traditional k-means criterion of inter-cluster variance is used to learn tree structure from training data. The result is an efficient and accurate summary of surface morphology in images. This work is an evolutionary advance that unites several previous algorithms (k-means clustering, integral images, decision trees) and applies them to a new problem domain (morphology analysis for autonomous science during remote exploration). Advantages include order-of-magnitude improvements in runtime, feasibility for FPGA hardware, and significant improvements in texture classification accuracy.

Thompson, David R.↗
NASA NTRS2014

Automated Testcase Generation for Numerical Support Functions in Embedded Systems

We present a tool for the automatic generation of test stimuli for small numerical support functions, e.g., code for trigonometric functions, quaternions, filters, or table lookup. Our tool is based on KLEE to produce a set of test stimuli for full path coverage. We use a method of iterative deepening over abstractions to deal with floating-point values. During actual testing the stimuli exercise the code against a reference implementation. We illustrate our approach with results of experiments with low-level trigonometric functions, interpolation routines, and mathematical support functions from an open source UAS autopilot.

Metrics↗
NASA NTRS2014

Compositional Solution Space Quantification for Probabilistic Software Analysis

Probabilistic software analysis aims at quantifying how likely a target event is to occur during program execution. Current approaches rely on symbolic execution to identify the conditions to reach the target event and try to quantify the fraction of the input domain satisfying these conditions. Precise quantification is usually limited to linear constraints, while only approximate solutions can be provided in general through statistical approaches. However, statistical approaches may fail to converge to an acceptable accuracy within a reasonable time. We present a compositional statistical approach for the efficient quantification of solution spaces for arbitrarily complex constraints over bounded floating-point domains. The approach leverages interval constraint propagation to improve the accuracy of the estimation by focusing the sampling on the regions of the input domain containing the sought solutions. Preliminary experiments show significant improvement on previous approaches both in results accuracy and analysis time.

Monte Carlo Methods↗
NASA NTRS2015

Discrete Fourier Transform in a Complex Vector Space

An image-based phase retrieval technique has been developed that can be used on board a space based iterative transformation system. Image-based wavefront sensing is computationally demanding due to the floating-point nature of the process. The discrete Fourier transform (DFT) calculation is presented in "diagonal" form. By diagonal we mean that a transformation of basis is introduced by an application of the similarity transform of linear algebra. The current method exploits the diagonal structure of the DFT in a special way, particularly when parts of the calculation do not have to be repeated at each iteration to converge to an acceptable solution in order to focus an image.

Dean, Bruce H.↗
NASA NTRS2017

Hierarchical Data Formats (HDF) Update

In this presentation, we will talk about the latest releases of HDF4 and HDF5 software and tools, new features available in HDF5, and roadmap for the HDF software. We will also solicit feedback from the users of HDF data and HDF application developers on new features and new tools. The talk will cover: Difference between 1.8 and 1.10 releases and how and when to move to the latest release Features of the recent HDF5 1.8.19, 1.10.1 and HDF 4.2.13 Overview of HDF View 3.0 and other enhancements to tools Supported compilers and systems Open discussion of new requirements and wish list of the HDF features Compression library for interoperability with h5py and Pandas and better floating-point data compression.

HDFView↗
NASA NTRS2021

Integration of an Arm Kinematics Hot Patch onboard the Curiosity Rover

NASA's Mars Science Laboratory (MSL) mission has updated the Curiosity rover's flight software multiple times since landing on Mars on August 6, 2012. The most common patching method has been a hot patch, in which running flight software is modified after being copied into RAM from its persistent storage. The latest hot patch to be installed on Curiosity fixed an issue in the robotic arm software that computes generalized inverse kinematics. Additional unit testing performed since the start of the surface mission revealed that this software can sometimes produce erroneous solutions.The cause was identified as numerical instability in a quartic root finder. When the inputs to that solver are not well conditioned, floating-point numerical issuescan cause erroneous roots to be reported. In theory, this could result in the robotic arm turret instruments being commanded to unintended positions, for example, below the terrain surface. Out of approximately 3.7 million unit test cases, 97.2\% of the position errors were below 5 mm. However, there were 16 test cases where theposition error was greater than 20 cm, and the maximum position error was 1.2 meters.The patch was uploaded to Curiosity on sol 2642 (January 11, 2020) after the solution was developed, re-implemented as a hot patch, and validated and verified using Earth-based Curiosity testbeds. A checkout test of the patch was performed on Curiosity on sol 2657, and nominal use of the patch began on sol 2658. In this paper, we describe the steps that led to integrating the arm kinematic hot patch into Curiosity's flight software, from the discovery of the bug to the nominal use of the patch in flight.

Maimone, Mark↗
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↗
DOE OSTI2025

ComPort: Rigorous Testing Methods to Safeguard Software Porting (Final Technical Report)

This is a technical report from the lead institution – University of Utah, Kahlert School of Computing – funded under the Department of Energy, Office of Science, Office of Advanced Scientific Computing Research under award number DE-SC0022252. We summarize our work done over the three years of funding received. The relevant papers and software have already been uploaded at the DOE site.

97 MATHEMATICS AND COMPUTING↗