Article SMARTS: exploiting temporal locality and parallelism through vertical execution Share on Authors: Suvas Vajracharya Los Alamos National Laboratory, Los Alamos, NM Los Alamos National Laboratory, Los Alamos, NMView Profile , Steve Karmesin Los Alamos National Laboratory, Los Alamos, NM Los Alamos National Laboratory, Los Alamos, NMView Profile , Peter Beckman Los Alamos National Laboratory, Los Alamos, NM Los Alamos National Laboratory, Los Alamos, NMView Profile , James Crotinger Los Alamos National Laboratory, Los Alamos, NM Los Alamos National Laboratory, Los Alamos, NMView Profile , Allen Malony Dept. of Computer and Information Science, University of Oregon and Los Alamos National Laboratory, Los Alamos, NM Dept. of Computer and Information Science, University of Oregon and Los Alamos National Laboratory, Los Alamos, NMView Profile , Sameer Shende Dept. of Computer and Information Science, University of Oregon and Los Alamos National Laboratory, Los Alamos, NM Dept. of Computer and Information Science, University of Oregon and Los Alamos National Laboratory, Los Alamos, NMView Profile , Rod Oldehoeft Los Alamos National Laboratory, Los Alamos, NM Los Alamos National Laboratory, Los Alamos, NMView Profile , Stephen Smith Los Alamos National Laboratory, Los Alamos, NM Los Alamos National Laboratory, Los Alamos, NMView Profile Authors Info & Claims ICS '99: Proceedings of the 13th international conference on SupercomputingJune 1999 Pages 302–310https://doi.org/10.1145/305138.305207Online:01 May 1999Publication History 16citation354DownloadsMetricsTotal Citations16Total Downloads354Last 12 Months4Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

In this article, we discuss two programming language features that have value for expressibility and efficiency: nonstrictness and nondeterminism. Our work arose while assessing ways to enhance a currently successful language, SISAL [McGraw et al. 1985]. The questions of how best to include these features, if at all, has led not to conclusions but to an impetus to explore the answers in an objective way. We will retain strictness for efficiency reasons and explore the limits it may impose, and we will experiment with a carefully controlled form of nondeterminism to assess its expressive power.

In this minisymposium speakers address architectural principles and issues of multithreaded computer systems, examine approaches to providing implicitly parallel software for these machines, and give an industrial perspective that includes the potential wider influence of multithreaded computers. Multithreaded computer systems are parallel machines in which threads are sequentially executed code segments. Each processor has hardware support for quickly switching contexts among runnable threads. Other features include some form of data matching, split-phase memory accesses, and a dataflow-like regime for thread instantiation. They combine features of conventional von Neumann systems with those of fine-grained dataflow architectures.>

The DI interpreter is both a debugger and interpreter of SISAL programs. Its use as a program interpreter is only a small part of its role; it is designed to be a tool for studying compilation techniques for applicative languages. DI interprets dataflow graphs expressed in the IF1 and IF2 languages, and is heavily instrumented to report the activity of dynamic storage activity, reference counting, copying and updating of structured data values. It also aids the SISAL language evaluation by providing an interim execution vehicle for SISAL programs. DI provides determinate, sequential interpretation of graph nodes for sequential and parallel operations in a canonical order. As a debugging aid, DI allows tracing, breakpointing, and interactive display of program data values. DI handles creation of SISAL and IF1 error values for each data type and propagates them according to a well-defined algebra. We have begun to implement IF1 optimizers and have measured the improvements with DI.

This paper describes a technique for predicting the execution behavior of a source program or a software design specification. As a by-product of syntactic analysis, a program graph is constructed which can subsequently be treated as the graph of a finite automaton. The expression for execution behavior is the regular expression of the graph. Several simplification techniques for these expressions are discussed and exemplified. In particular, the substitution of known values for program segments followed by constant folding cannot be done indiscriminately; the allowable situations are characterized. Applications include the prediction of execution time for a program or a software design, other forms of language analysis, and program restructuring.

Abstract An interactive facility for development and maintenance of Pascal programs is described. Features include interactive addition, deletion and modification of modules, independentcompilation of groups of procedures, and automatic recompilation of an entire program only if global declarations are modified. The implementation required modification of a Pascal compiler to process an arbitrary number of programs in a single run and to compile correctly if the main program is missing. Overall processing is managed by a parameterized control statement procedure that invokes several system utilities. The facility has been used successfully in instructional and research computing situations. Significant remaining problems are errors caused by mismatched parameters between independently compiled procedures, and interpretation by users of error messages generated by system utilities.

Two disciplines have been developed during the past few years for the study of computer software. Software physics has as its purpose the analysis of execution characteristics of programs. Basic measures of software work, time, and shortage occupancy are used to derive measures such as power, capacity usage, and storage work, with applications to the choice of processor and device speeds. Software science is related to information theory. Occurrences of operators and operands in the text of programs are counted to provide measures for a number of relationships; among them are estimates for program length, program and language level, and programming time.

In the last few years it has been generally recognized that teaching programming involves more than describing a new FORTRAN statement each day and providing programming problems to be coded. The concepts of disciplined programming and the accompanying interest in the problem solving process, coupled with the increasing economic desirability of constructing correct and maintainable software has resulted in significant attention being focused on what should be taught, and, to a lesser extent, on how this is best accomplished.

Abstract The NAPSS (Numerical Analysis Problem Solving System) project was an attempt to develop an interactive system, with a high‐level language resembling conventional mathematics, for solving problems in numerical analysis. This report uses NAPSS as an example to discuss some aspects of the design and implementation of the programming languages and software which comprise problem solving systems. Successful features as well as failures (with alternative proposals) are detailed in the areas of general language management, specific language features and the operating system interface. In general, a massive, coherent implementation of theoretical work being done at the frontiers of research has abundant opportunity for failure.

Software science techniques have been used to provide a framework for evaluation of problem solving systems. In that effort, two methods for calculating the level of a language (L and L̂) were used, it was suspected that L̂, while adequate in that application, might be inferior to L. By using a set of hypothetical languagesj each with different intrinsic data structures and operators, it is shown here that when an inappropriate language is applied to some problems, L̂ may reflect an inaccurately large value for language level, and can sometimes be made to yield an arbitrary value. Since L is often as easily applied as L, and does not exhibit this anomalous behavior, it is suggested that its general use is to be preferred.

Considerable effort has been expanded in attempts to combine the power found in algorithmic languages with the power found in program libraries. However, most of these attempts to construct problem-solving systems for a particular class of users have failed to achieve their objective of providing the user with the potential benefits inherent in such systems. This paper attempts to define and place problem-solving systems in a general context, and thereby shows when the potential for failure or success is high.