Search NASA⌕ Search

SEARCH · Search NASA

Results for “PROCESSORS”

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 1,621 records · Page 90

Petascale Computing Enabling Technologies Project Final Report

The Petascale Computing Enabling Technologies (PCET) project addressed challenges arising from current trends in computer architecture that will lead to large-scale systems with many more nodes, each of which uses multicore chips. These factors will soon lead to systems that have over one million processors. Also, the use of multicore chips will lead to less memory and less memory bandwidth per core. We need fundamentally new algorithmic approaches to cope with these memory constraints and the huge number of processors. Further, correct, efficient code development is difficult even with the number of processors in current systems; more processors will only make it harder. The goal of PCET was to overcome these challenges by developing the computer science and mathematical underpinnings needed to realize the full potential of our future large-scale systems. Our research results will significantly increase the scientific output obtained from LLNL large-scale computing resources by improving application scientist productivity and system utilization. Our successes include scalable mathematical algorithms that adapt to these emerging architecture trends and through code correctness and performance methodologies that automate critical aspects of application development as well as the foundations for application-level fault tolerance techniques. PCET's scope encompassed several research thrusts in computer science and mathematics: code correctness and performance methodologies, scalable mathematics algorithms appropriate for multicore systems, and application-level fault tolerance techniques. Due to funding limitations, we focused primarily on the first three thrusts although our work also lays the foundation for the needed advances in fault tolerance. In the area of scalable mathematics algorithms, our preliminary work established that OpenMP performance of the AMG linear solver benchmark and important individual kernels on Atlas did not match the predictions of our simple initial model. Our investigations demonstrated that a poor default memory allocation mechanism degraded performance. We developed a prototype NUMA library to provide generic mechanisms to overcome these issues, resulting in significantly improved OpenMP performance. After additional testing, we will make this library available to all users, providing a simple means to improve threading on LLNL's production Linux platforms. We also made progress on developing new scalable algorithms that target multicore nodes. We designed and implemented a new AMG interpolation operator with improved convergence properties for very low complexity coarsening schemes. This implementation will also soon be available to LLNL's application teams as part of the hypre library. We presented results for both topics in an invited plenary talk entitled 'Efficient Sparse Linear Solvers for Multi-Core Architectures' at the 2009 HPCMP Institutes Annual Meeting/CREATE Annual All-Hands Meeting. The interpolation work was summarized in a talk entitled 'Improving Interpolation for Aggressive Coarsening' at the 14th Copper Mountain Conference on Multigrid Methods and in a research paper that will appear in Numerical Linear Algebra with Applications. In the area of code correctness, we significantly extended our behavior equivalence class identification mechanism. Specifically, we not only demonstrated it works well at very large scales but we also added the ability to classify MPI tasks not only by function call traces, but also by specific call sites (source code line numbers) being executed by tasks. More importantly, we developed a new technique to determine relative logical execution progress of tasks in the equivalence classes by combining static analysis with our original dynamic approach. We applied this technique to a correctness issue that arose at 4096 tasks during the development of the new AMG interpolation operator discussed above. This scale isat the limit of effectiveness of production tools, but our technique quickly located the erroneous source code, demonstrating the power of understanding relationships between behavioral equivalence classes. This work is the subject of a paper recently accepted to SC09, as well as a presentation entitled 'Providing Order to Extreme Scale Debugging Chaos' given at the ParaDyn Week annual conference in College Park, MD. In addition to this theoretical extension, we have made significant progress in developing a front end for this tool set, and the front-end is now available on several of LLNL's largescale computing resources. In addition, we explored mechanisms to identify exact locations of erroneous MPI usage in application source code. In this work, we developed a new model that led to a highly efficient algorithm for detecting deadlock during dynamic software testing. This work was the subject of a well-received paper at ICS 2009 [4].

99 GENERAL AND MISCELLANEOUS↗

Final report and documentation for the security enabled programmable switch for protection of distributed internetworked computers LDRD.

An increasing number of corporate security policies make it desirable to push security closer to the desktop. It is not practical or feasible to place security and monitoring software on all computing devices (e.g. printers, personal digital assistants, copy machines, legacy hardware). We have begun to prototype a hardware and software architecture that will enforce security policies by pushing security functions closer to the end user, whether in the office or home, without interfering with users' desktop environments. We are developing a specialized programmable Ethernet network switch to achieve this. Embodied in this device is the ability to detect and mitigate network attacks that would otherwise disable or compromise the end user's computing nodes. We call this device a 'Secure Programmable Switch' (SPS). The SPS is designed with the ability to be securely reprogrammed in real time to counter rapidly evolving threats such as fast moving worms, etc. This ability to remotely update the functionality of the SPS protection device is cryptographically protected from subversion. With this concept, the user cannot turn off or fail to update virus scanning and personal firewall filtering in the SPS device as he/she could if implemented on the end host. The SPS concept also provides protection to simple/dumb devices such as printers, scanners, legacy hardware, etc. This report also describes the development of a cryptographically protected processor and its internal architecture in which the SPS device is implemented. This processor executes code correctly even if an adversary holds the processor. The processor guarantees both the integrity and the confidentiality of the code: the adversary cannot determine the sequence of instructions, nor can the adversary change the instruction sequence in a goal-oriented way.

99 GENERAL AND MISCELLANEOUS↗

Variable word length encoder reduces TV bandwith requirements

Adaptive variable resolution encoding technique provides an adaptive compression pseudo-random noise signal processor for reducing television bandwidth requirements. Complementary processors are required in both the transmitting and receiving systems. The pretransmission processor is analog-to-digital, while the postreception processor is digital-to-analog.

Sivertson, W. E., Jr.↗

A fault-tolerant information processing concept for space vehicles.

A distributed fault-tolerant information processing system is proposed, comprising a central multiprocessor, dedicated local processors, and multiplexed input-output buses connecting them together. The processors in the multiprocessor are duplicated for error detection, which is felt to be less expensive than using coded redundancy of comparable effectiveness. Error recovery is made possible by a triplicated scratchpad memory in each processor. The main multiprocessor memory uses replicated memory for error detection and correction. Local processors use any of three conventional redundancy techniques: voting, duplex pairs with backup, and duplex pairs in independent subsystems.

Hopkins, A. L., Jr.↗

A programmable computer interface for CAMAC

An interface has been developed for CAMAC instrumentation systems that implements data transfers controlled either by the computer CPU or by an autonomous (data-channel) processor in the interface unit. The data channel processor executes programs stored in the computer memory. These programs consist of standard CAMAC module commands plus special control characters and commands for the processor itself. The interface was built for the PDP-15 computer, which has an 18-bit word structure, but both 18- and 24-bit data transfers can be made. A software system has been written that exploits the many features of the processor.

Bercaw, R. W.↗

Set processing in a network environment

A combination of a local network, a mass storage system, and an autonomous set processor serving as a data/storage management machine is described. Its characteristics include: content-accessible data bases usable from all connected devices; efficient storage/access of large data bases; simple and direct programming with data manipulation and storage management handled by the set processor; simple data base design and entry from source representation to set processor representation with no predefinition necessary; capability available for user sort/order specification; significant reduction in tape/disk pack storage and mounts; flexible environment that allows upgrading hardware/software configuration without causing major interruptions in service; minimal traffic on data communications network; and improved central memory usage on large processors.

Hardgrave, W. T.↗

Dispersion analysis techniques within the space vehicle dynamics simulation program

The Space Vehicle Dynamics Simulation (SVDS) program was evaluated as a dispersion analysis tool. The Linear Error Analysis (LEA) post processor was examined in detail and simulation techniques relative to conducting a dispersion analysis using the SVDS were considered. The LEA processor is a tool for correlating trajectory dispersion data developed by simulating 3 sigma uncertainties as single error source cases. The processor combines trajectory and performance deviations by a root-sum-square (RSS process) and develops a covariance matrix for the deviations. Results are used in dispersion analyses for the baseline reference and orbiter flight test missions. As a part of this study, LEA results were verified as follows: (A) Hand calculating the RSS data and the elements of the covariance matrix for comparison with the LEA processor computed data. (B) Comparing results with previous error analyses. The LEA comparisons and verification are made at main engine cutoff (MECO).

Snow, L. S.↗

Applications and limitations of very large-scale integration in SAR azimuth processing

The major limitation of a convolution processor designed with CCD memory chips is the inability to operate in real time except for slow aircraft speeds or coarse resolutions. Two methods of summing the products were evaluated with respect to speed, power, and space requirements. A convolution processor was designed, and the number of chips as well as the power and volume requirements were determined using 4, 6, and 8 bit data words. The processor is flexible because range samples may be traded for additional azimuth samples by altering the control signals. The processor is also modular, and additional range or azimuth may be processed by adding more cards.

Kuhler, D. G.↗

NASF transposition network: A computing network for unscrambling p-ordered vectors

The viewpoints of design, programming, and application of the transportation network (TN) is presented. The TN is a programmable combinational logic network that connects 521 memory modules to 512 processors. The unscrambling of p-ordered vectors to 1-ordered vectors in one cycle is described. The TN design is based upon the concept of cyclic groups from abstract algebra and primitive roots and indices from number theory. The programming of the TN is very simple, requiring only 20 bits: 10 bits for offset control and 10 bits for barrel switch shift control. This simple control is executed by the control unit (CU), not the processors. Any memory access by a processor must be coordinated with the CU and wait for all other processors to come to a synchronization point. These wait and synchronization events can be a degradation in performance to a computation. The TN application is for multidimensional data manipulation, matrix processing, and data sorting, and can also perform a perfect shuffle. Unlike other more complicated and powerful permutation networks, the TN cannot, if possible at all, unscramble non-p-ordered vectors in one cycle.

Lim, R. S.↗

A microprocessor based high speed packet switch for satellite communications

The architectures of a single processor, a three processor, and a multiple processor system are described. The hardware circuits, and software routines required for implementing the three and multiple processor designs are presented. A bit-slice microprocessor was designed and microprogrammed. Maximum throughput was calculated for all three designs. Queue theoretic models for these three designs were developed and utilized to obtain analytical expressions for the average waiting times, overall average response times and average queue sizes. From these expressions, graphs were obtained showing the effect on the system performance of a number of design parameters.

Arozullah, M.↗

Mark 3 correlator hardware and software

The Mark 3 correlator system is described in some detail. The correlator system is based on a modular philosophy. Each correlator module independently processes the data from one track pair. Therefore, 28 modules are necessary to complete a full one baseline processor and 84 modules for a full 3 baseline processor. Each correlator module has two interfaces: (1) data and clock from each of the two tracks to be correlated and (2) Computer Automated Measurement and Control (CAMAC) dataway interface to the computer. The processor is organized around the IEEE CAMAC standard architecture, housing 15 correlator modules in each of 6 crates. This allows one pass processing of a full 3 baseline 28 track observation or a 6 baseline (4 station) 14 track observation. The correlator architecture allows easy expansion for up to 8 stations. The computer system is an HP 1000 system utilizing a 16 bit minicomputer with disc and tape peripherals. The processing software is also organized in a modular fashion with many independent but cooperative programs controlling the operation of the Mark 3 processor. Processing time through the correlator is normally real time or faster, with graphics displays providing real time monitor and control of the processing operation.

Whitney, A. R.↗

Methodology for measurement of fault latency in a digital avionic miniprocessor

Investigations regarding the synthesis of a reliability assessment capability for fault-tolerant computer-based systems have been conducted for several years. In 1978 a pilot study was conducted to test the feasibility of measuring detection coverage and investigating the dynamics of fault propagation in a digital computer. A description is presented of an investigation concerned with the applicability of previous results to a real avionics processor. The obtained results show that emulation is a practicable approach to failure modes and effects analysis of a digital processor. The run time of the emulated processor on a PDP-10 host computer is only 20,000 to 25,000 times slower than the actual processor. As a consequence large numbers of faults can be studied at relatively little cost and in a timely manner.

Mcgough, J. G.↗

Finite element computation with parallel VLSI

This paper describes a parallel processing computer consisting of a 16-bit microcomputer as a master processor which controls and coordinates the activities of 8086/8087 VLSI chip set slave processors working in parallel. The hardware is inexpensive and can be flexibly configured and programmed to perform various functions. This makes it a useful research tool for the development of, and experimentation with parallel mathematical algorithms. Application of the hardware to computational tasks involved in the finite element analysis method is demonstrated by the generation and assembly of beam finite element stiffness matrices. A number of possible schemes for the implementation of N-elements on N- or n-processors (N is greater than n) are described, and the speedup factors of their time consumption are determined as a function of the number of available parallel processors.

Mcgregor, J.↗

Singular value decomposition with systolic arrays

Systolic arrays for determining the singular value decomposition of a mxn, m n, matrix A of bandwidth w are presented. After A has been reduced to bidiagonal form B by means of Givens plane rotations, the singular values of B are computed by the Golub-Reinsch iteration. The products of plane rotations form the matrices of left and right singular vectors. Assuming each processor can compute or supply a plane rotation, O(wn) processors accomplish the reduction to bidiagonal form in O(np) steps, where p is the number of superdiagonals. A constant number of processors then determines each singular value in about 6n steps. The singular vectors are computed by rerouting the rotations through the arrays used for the reduction to bidiagonal form, or else along the way by employing another rectangular array of O(wm) processors.

Ipsen, I. C. F.↗

Landsat image registration for agricultural applications

An image registration system has been developed at the NASA Johnson Space Center (JSC) to spatially align multi-temporal Landsat acquisitions for use in agriculture and forestry research. Working in conjunction with the Master Data Processor (MDP) at the Goddard Space Flight Center, it functionally replaces the long-standing LACIE Registration Processor as JSC's data supplier. The system represents an expansion of the techniques developed for the MDP and LACIE Registration Processor, and it utilizes the experience gained in an IBM/JSC effort evaluating the performance of the latter. These techniques are discussed in detail. Several tests were developed to evaluate the registration performance of the system. The results indicate that 1/15-pixel accuracy (about 4m for Landsat MSS) is achievable in ideal circumstances, sub-pixel accuracy (often to 0.2 pixel or better) was attained on a representative set of U.S. acquisitions, and a success rate commensurate with the LACIE Registration Processor was realized. The system has been employed in a production mode on U.S. and foreign data, and a performance similar to the earlier tests has been noted.

Wolfe, R. H., Jr.↗

Modular, Fast, Two-Dimensional Cyclic Convolver

Proposed high-throughput, real-time synthetic-aperture-radar (SAR) processor built using new, modular, two-dimensional cyclic convolver architecture based on polynomial factorization and designed for very-large-scale integrated (VLSI) circuitry. New architecture reduces cost, size, and power dissipation of SAR processor in comparison to high-speed array-processor approach. Processor also used for other image-and data-processing applications involving two-dimensional Fourier transforms.

Liu, K. Y.↗

Automatic Dynamic Aircraft Modeler (ADAM) for the Computer Program NASTRAN

Large general purpose finite element programs require users to develop large quantities of input data. General purpose pre-processors are used to decrease the effort required to develop structural models. Further reduction of effort can be achieved by specific application pre-processors. Automatic Dynamic Aircraft Modeler (ADAM) is one such application specific pre-processor. General purpose pre-processors use points, lines and surfaces to describe geometric shapes. Specifying that ADAM is used only for aircraft structures allows generic structural sections, wing boxes and bodies, to be pre-defined. Hence with only gross dimensions, thicknesses, material properties and pre-defined boundary conditions a complete model of an aircraft can be created.

Griffis, H.↗

Approximate algorithms for partitioning and assignment problems

The problem of optimally assigning the modules of a parallel/pipelined program over the processors of a multiple computer system under certain restrictions on the interconnection structure of the program as well as the multiple computer system was considered. For a variety of such programs it is possible to find linear time if a partition of the program exists in which the load on any processor is within a certain bound. This method, when combined with a binary search over a finite range, provides an approximate solution to the partitioning problem. The specific problems considered were: a chain structured parallel program over a chain-like computer system, multiple chain-like programs over a host-satellite system, and a tree structured parallel program over a host-satellite system. For a problem with m modules and n processors, the complexity of the algorithm is no worse than O(mnlog(W sub T/epsilon)), where W sub T is the cost of assigning all modules to one processor and epsilon the desired accuracy.

Iqbal, M. A.↗