SEARCH · Engineering Papers

Results for “Parallel communication”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

All sources NASA NTRS DOE OSTI

NASA NTRS1985

Efficient implementation of real-time programs under the VAX/VMS operating system

Techniques for writing efficient real-time programs under the VAX/VMS oprating system are presented. Basic operations are presented for executing at real-time priority and for avoiding needlless processing delays. A highly efficient technique for accessing physical devices by mapping to the input/output space and accessing the device registrs directly is described. To illustrate the application of the technique, examples are included of different uses of the technique on three devices in the Langley Avionics Integration Research Lab (AIRLAB): the KW11-K dual programmable real-time clock, the Parallel Communications Link (PCL11-B) communication system, and the Datacom Synchronization Network. Timing data are included to demonstrate the performance improvements realized with these applications of the technique.

Johnson, S. C.↗

NASA NTRS1990

Optimal expression evaluation for data parallel architectures

A data parallel machine represents an array or other composite data structure by allocating one processor per data item. A pointwise operation can be performed between two such arrays in unit time, provided their corresponding elements are allocated in the same processors. If the arrays are not aligned in this fashion, the cost of moving one or both of them is part of the cost of operation. The choice of where to perform the operation then affects this cost. If an expression with several operands is to be evaluated, there may be many choices of where to perform the intermediate operations. An efficient algorithm is given to find the minimum cost way to evaluate an expression, for several different data parallel architectures. The algorithm applies to any architecture in which the metric describing the cost of moving an array has a property called robustness. This encompasses most of the common data parallel communication architectures, including meshes of arbitrary dimension and hypercubes.

Gilbert, J. R.↗

NASA NTRS1991

Optimal expression evaluation for data parallel architectures

A data parallel machine represents an array or other composits data structure by allocating one processor per data item. A pointwise operation can be performed between two such arrays in unit time, provided their corresponding elements are allocated in the same processors. If the arrays are not aligned in this fashion, the cost of moving one or both of them is part of the cost of operation. The choice of where to perform the operation then affects this cost. If an expression with several operands is to be evaluated, there may be many choices of where to perform the intermediate operations. An efficient algorithm is given to find the minimum cost way to evaluate an expression, for several different data parallel architectures. The algorithm applies to any architecture in which the metric describing the cost of moving an array has a property called robustness. This encompasses most of the common data parallel communication architectures, including meshes of arbitrary dimension and hypercubes.

Gilbert, John R.↗

NASA NTRS1990

Optimal expression evaluation for data parallel architectures

A data parallel machine represents an array or other composite data structure by allocating one processor (at least conceptually) per data item. A pointwise operation can be performed between two such arrays in unit time, provided their corresponding elements are allocated in the same processors. If the arrays are not aligned in this fashion, the cost of moving one or both of them is part of the cost of the operation. The choice of where to perform the operation then affects this cost. If an expression with several operands is to be evaluated, there may be many choices of where to perform the intermediate operations. An efficient algorithm is given to find the minimum-cost way to evaluate an expression, for several different data parallel architectures. This algorithm applies to any architecture in which the metric describing the cost of moving an array is robust. This encompasses most of the common data parallel communication architectures, including meshes of arbitrary dimension and hypercubes. Remarks are made on several variations of the problem, some of which are solved and some of which remain open.

Gilbert, John R.↗

NASA NTRS1991

High resolution ultrasonic spectroscopy system for nondestructive evaluation

With increased demand for high resolution ultrasonic evaluation, computer based systems or work stations become essential. The ultrasonic spectroscopy method of nondestructive evaluation (NDE) was used to develop a high resolution ultrasonic inspection system supported by modern signal processing, pattern recognition, and neural network technologies. The basic system which was completed consists of a 386/20 MHz PC (IBM AT compatible), a pulser/receiver, a digital oscilloscope with serial and parallel communications to the computer, an immersion tank with motor control of X-Y axis movement, and the supporting software package, IUNDE, for interactive ultrasonic evaluation. Although the hardware components are commercially available, the software development is entirely original. By integrating signal processing, pattern recognition, maximum entropy spectral analysis, and artificial neural network functions into the system, many NDE tasks can be performed. The high resolution graphics capability provides visualization of complex NDE problems. The phase 3 efforts involve intensive marketing of the software package and collaborative work with industrial sectors.

Chen, C. H.↗

NASA NTRS1995

Performance Comparison of a Matrix Solver on a Heterogeneous Network Using Two Implementations of MPI: MPICH and LAM

Two of the current and most popular implementations of the Message-Passing Standard, Message Passing Interface (MPI), were contrasted: MPICH by Argonne National Laboratory, and LAM by the Ohio Supercomputer Center at Ohio State University. A parallel skyline matrix solver was adapted to be run in a heterogeneous environment using MPI. The Message-Passing Interface Forum was held in May 1994 which lead to a specification of library functions that implement the message-passing model of parallel communication. LAM, which creates it's own environment, is more robust in a highly heterogeneous network. MPICH uses the environment native to the machine architecture. While neither of these free-ware implementations provides the performance of native message-passing or vendor's implementations, MPICH begins to approach that performance on the SP-2. The machines used in this study were: IBM RS6000, 3 Sun4, SGI, and the IBM SP-2. Each machine is unique and a few machines required specific modifications during the installation. When installed correctly, both implementations worked well with only minor problems.

Phillips, Jennifer K.↗

NASA NTRS2002

Software Engineering Support of the Third Round of Scientific Grand Challenge Investigations: An Earth Modeling System Software Framework Strawman Design that Integrates Cactus and UCLA/UCB Distributed Data Broker

One of the most significant challenges in large-scale climate modeling, as well as in high-performance computing in other scientific fields, is that of effectively integrating many software models from multiple contributors. A software framework facilitates the integration task. both in the development and runtime stages of the simulation. Effective software frameworks reduce the programming burden for the investigators, freeing them to focus more on the science and less on the parallel communication implementation, while maintaining high performance across numerous supercomputer and workstation architectures. This document proposes a strawman framework design for the climate community based on the integration of Cactus, from the relativistic physics community, and UCLA/UCB Distributed Data Broker (DDB) from the climate community. This design is the result of an extensive survey of climate models and frameworks in the climate community as well as frameworks from many other scientific communities. The design addresses fundamental development and runtime needs using Cactus, a framework with interfaces for FORTRAN and C-based languages, and high-performance model communication needs using DDB. This document also specifically explores object-oriented design issues in the context of climate modeling as well as climate modeling issues in terms of object-oriented design.

Talbot, Bryan↗

DOE OSTI2022

Accelerating Collective Communication in Data Parallel Training across Deep Learning Frameworks

This work develops new techniques within Horovod, a generic communication library supporting data parallel training across deep learning frameworks. In particular, we improve the Horovod control plane by implementing a new coordination scheme that takes advantage of the characteristics of the typical data parallel training paradigm, namely the repeated execution of collectives on the gradients of a fixed set of tensors. Using a caching strategy, we execute Horovod’s existing coordinator-worker logic only once during a typical training run, replacing it with a more efficient decentralized orchestration strategy using the cached data and a global intersection of a bitvector for the remaining training duration. Next, we introduce a feature for end users to explicitly group collective operations, enabling finer grained control over the communication buffer sizes. To evaluate our proposed strategies, we conduct experiments on a world-class supercomputer — Summit. We compare our proposals to Horovod’s original design and observe 2x performance improvement at a scale of 6000 GPUs; we also compare them against tf.distribute and torch.DDP and achieve 12% better and comparable performance, respectively, using up to 1536 GPUs; we compare our solution against BytePS in typical HPC settings and achieve about 20% better performance on a scale of 768 GPUs. Finally, we test our strategies on a scientific application (STEMDL) using up to 27,600 GPUs (the entire Summit) and show that we achieve a near-linear scaling of 0.93 with a sustained performance of 1.54 exaflops (with standard error +- 0.02) in FP16 precision.

Romero, Joshua↗

NASA NTRS1998

Parallel processing spacecraft communication system

An uplink controlling assembly speeds data processing using a special parallel codeblock technique. A correct start sequence initiates processing of a frame. Two possible start sequences can be used; and the one which is used determines whether data polarity is inverted or non-inverted. Processing continues until uncorrectable errors are found. The frame ends by intentionally sending a block with an uncorrectable error. Each of the codeblocks in the frame has a channel ID. Each channel ID can be separately processed in parallel. This obviates the problem of waiting for error correction processing. If that channel number is zero, however, it indicates that the frame of data represents a critical command only. That data is handled in a special way, independent of the software. Otherwise, the processed data further handled using special double buffering techniques to avoid problems from overrun. When overrun does occur, the system takes action to lose only the oldest data.

Bolotin, Gary S.↗

NASA NTRS2005

Parallel Estimators and Communication in Spacecraft Formations

This paper investigates the closed-loop dynamics of systems controlled via parallel estimators. This structure arises in formation flying problems when each spacecraft bases its control action on an internal estimate of the complete formation state. For LTI systems a separation principle shows that the necessary and sufficient conditions for overall system stability are more stringent than the single controller case; the controllers' open-loop dynamics necessarily appear in the closed-loop dynamics. Communication amongst the spacecraft can be used to specify the complete system dynamics and a framework for integrating the design of the communication links into the formation flying control design problem is presented.

communications↗

NASA NTRS1993

Dynamic overset grid communication on distributed memory parallel processors

A parallel distributed memory implementation of intergrid communication for dynamic overset grids is presented. Included are discussions of various options considered during development. Results are presented comparing an Intel iPSC/860 to a single processor Cray Y-MP. Results for grids in relative motion show the iPSC/860 implementation to be faster than the Cray implementation.

Barszcz, Eric↗

NASA NTRS1993

Generating local addresses and communication sets for data-parallel programs

Generating local addresses and communication sets is an important issue in distributed-memory implementations of data-parallel languages such as High Performance Fortran. We show that for an array A affinely aligned to a template that is distributed across p processors with a cyclic(k) distribution, and a computation involving the regular section A, the local memory access sequence for any processor is characterized by a finite state machine of at most k states. We present fast algorithms for computing the essential information about these state machines, and extend the framework to handle multidimensional arrays. We also show how to generate communication sets using the state machine approach. Performance results show that this solution requires very little runtime overhead and acceptable preprocessing time.

Chatterjee, Siddhartha↗

NASA NTRS1993

Generating local addresses and communication sets for data-parallel programs

Generating local addresses and communication sets is an important issue in distributed-memory implementations of data-parallel languages such as High Performance FORTRAN. We show that, for an array A affinely aligned to a template that is distributed across p processors with a cyclic(k) distribution and a computation involving the regular section A(l:h:s), the local memory access sequence for any processor is characterized by a finite state machine of at most k states. We present fast algorithms for computing the essential information about these state machines, and extend the framework to handle multidimensional arrays. We also show how to generate communication sets using the state machine approach. Performance results show that this solution requires very little run-time overhead and acceptable preprocessing time.

Chatterjee, Siddhartha↗

NASA NTRS1986

Communications oriented programming of parallel iterative solutions of sparse linear systems

Parallel algorithms are developed for a class of scientific computational problems by partitioning the problems into smaller problems which may be solved concurrently. The effectiveness of the resulting parallel solutions is determined by the amount and frequency of communication and synchronization and the extent to which communication can be overlapped with computation. Three different parallel algorithms for solving the same class of problems are presented, and their effectiveness is analyzed from this point of view. The algorithms are programmed using a new programming environment. Run-time statistics and experience obtained from the execution of these programs assist in measuring the effectiveness of these algorithms.

Patrick, M. L.↗

NASA NTRS1991

Performance effects of irregular communications patterns on massively parallel multiprocessors

A detailed study of the performance effects of irregular communications patterns on the CM-2 was conducted. The communications capabilities of the CM-2 were characterized under a variety of controlled conditions. In the process of carrying out the performance evaluation, extensive use was made of a parameterized synthetic mesh. In addition, timings with unstructured meshes generated for aerodynamic codes and a set of sparse matrices with banded patterns on non-zeroes were performed. This benchmarking suite stresses the communications capabilities of the CM-2 in a range of different ways. Benchmark results demonstrate that it is possible to make effective use of much of the massive concurrency available in the communications network.

Saltz, Joel↗

NASA NTRS1991

Performance effects of irregular communications patterns on massively parallel multiprocessors

Saltz, Joel↗

NASA NTRS1999

The Feasibility of Adaptive Unstructured Computations On Petaflops Systems

This viewgraph presentation covers the advantages of mesh adaptation, unstructured grids, and dynamic load balancing. It illustrates parallel adaptive communications, and explains PLUM (Parallel dynamic load balancing for adaptive unstructured meshes), and PSAW (Proper Self Avoiding Walks).

Biswas, Rupak↗

NASA NTRS1994

Efficient massively parallel simulation of dynamic channel assignment schemes for wireless cellular communications

Fast, efficient parallel algorithms are presented for discrete event simulations of dynamic channel assignment schemes for wireless cellular communication networks. The driving events are call arrivals and departures, in continuous time, to cells geographically distributed across the service area. A dynamic channel assignment scheme decides which call arrivals to accept, and which channels to allocate to the accepted calls, attempting to minimize call blocking while ensuring co-channel interference is tolerably low. Specifically, the scheme ensures that the same channel is used concurrently at different cells only if the pairwise distances between those cells are sufficiently large. Much of the complexity of the system comes from ensuring this separation. The network is modeled as a system of interacting continuous time automata, each corresponding to a cell. To simulate the model, conservative methods are used; i.e., methods in which no errors occur in the course of the simulation and so no rollback or relaxation is needed. Implemented on a 16K processor MasPar MP-1, an elegant and simple technique provides speedups of about 15 times over an optimized serial simulation running on a high speed workstation. A drawback of this technique, typical of conservative methods, is that processor utilization is rather low. To overcome this, new methods were developed that exploit slackness in event dependencies over short intervals of time, thereby raising the utilization to above 50 percent and the speedup over the optimized serial code to about 120 times.

Greenberg, Albert G.↗