Algorithms exist for compiling Fortran D for MIMD distributed-memory machines, but are significantly restricted in the presence of procedure calls. This paper presents interprocedural analysis, optimization, and code generation algorithms for Fortran D that limit compilation to only one pass over each procedure. This is accomplished by collecting summary information after edits, then compiling procedures in reverse topological order to propagate necessary information. Delaying instantiation of the computation partition, communication, and dynamic data decomposition is key to enabling interprocedural optimization. Recompilation analysis preserves the benefits of separate compilation. Empirical results show that interprocedural optimization is crucial in achieving acceptable performance for a common application.

In the past 20 years there has been treftlendous progress in developing and analyzing parallel algorithftls. Researchers have developed efficient parallel algorithms to solve most problems for which efficient sequential solutions are known. Although some ofthese algorithms are efficient only in a theoretical framework, many are quite efficient in practice or have key ideas that have been used in efficient implementations. This research on parallel algorithms has not only improved our general understanding ofparallelism but in several cases has led to improvements in sequential algorithms. Unf:ortunately there has been less success in developing good languages f:or prograftlftling parallel algorithftls, particularly languages that are well suited for teaching and prototyping algorithms. There has been a large gap between languages

We introduce the Split-C language, a parallel extension of C intended for high performance programming on distributed memory multiprocessors, and demonstrate the use of the language in optimizing parallel programs. Split-C provides a global address space with a clear concept of locality and unusual assignment operators. These are used as tools to reduce the frequency and cost of remote access. The language allows a mixture of shared memory, message passing, and data parallel programming styles while providing efficient access to the underlying machine. We demonstrate the basic language concepts using regular and irregular parallel programs and give performance results for various stages of program optimization. 1 Overview Split-C is a parallel extension of the C programming language that supports efficient access to a global address space on current distributed memory multiprocessors. It retains the "small language" character of C and supports careful engineering and optimization of ...

This report describes Nesl, a strongly-typed, applicative, data-parallel language. Nesl is intended to be used as a portable interface for programming a variety of parallel and vector supercomputers, and as a basis for teaching parallel algorithms. Parallelism is supplied through a simple set of data-parallel constructs based on vectors, including a mechanism for applying any function over the elements of a vector in parallel, and a broad set of parallel functions that manipulate vectors. Nesl fully supports nested vectors and nested parallelism---the ability to take a parallel function and then apply it over multiple instances in parallel. Nested parallelism is important for implementing algorithms with complex and dynamically changing data structures, such as required in many graph or sparse matrix algorithms. Nesl also provides a mechanism for calculating the asymptotic running time for a program on various parallel machine models, including the parallel random access machine (PRAM...

An important problem facing numerous research projects on parallelizing compilers for distributed memory machines is that of automatically determining a suitable data partitioning scheme for a program. Most of the current projects leave this tedious problem almost entirely to the user. In this paper, we present a novel approach to the problem of automatic data partitioning. We introduce the notion of constraints on data distribution, and show how, based on performance considerations, a compiler identifies constraints to be imposed on the distribution of various data structures. These constraints are then combined by the compiler to obtain a complete and consistent picture of the data distribution scheme, one that offers good performance in terms of the overall execution time.

The views and conclusions contained in this document are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of Wright Laboratory or the U. S. Government. Keywords: Data-parallel, parallel algorithms, supercomputers, nested parallelism, This report describes Nesl, a strongly-typed, applicative, data-parallel language. Nesl is intended to be used as a portable interface for programming a variety of parallel and vector computers, and as a basis for teaching parallel algorithms. Parallelism is supplied through a simple set of data-parallel constructs based on sequences, including a mechanism for applying any function over the elements of a sequence in parallel and a rich set of parallel functions that manipulate sequences. Nesl fully supports nested sequences and nested parallelism—the ability to take a parallel function and apply it over multiple instances in parallel. Nested parallelism is important for implementing algorithms with irregular nested loops (where the inner loop lengths depend on the outer iteration) and for divide-and-conquer algorithms. Nesl also provides a performance model for calculating the asymptotic performance of a program on

Because of the complexity and variety of parallel architectures, an efficient machine-independent parallel programming model is needed to make parallel computing truly usable for scientific programmers. We believe that Fortran D, a version of Fortran enhanced with data decomposition specifications, can provide such a programming model. This paper presents the design of a prototype Fortran D compiler for the iPSC/860, a MIMD distributed-memory machine. Issues addressed include data decomposition analysis, guard introduction, communications generation and optimization, program transformations, and storage assignment. A test suite of scientific programs will be used to evaluate the effectiveness of both the compiler technology and programming model for the Fortran D compiler.

The Fortran D compiler uses data decomposition specifications to automatically translate Fortran programs for execution on MIMD distributed-memory machines. This paper introduces and classifies a number of advanced optimizations needed to achieve acceptable performance; they are analyzed and empirically evaluated for stencil computations. Communication optimizations reduce communication overhead by decreasing the number of messages and hide communication overhead by overlapping the cost of remaining messages with local computation. Parallelism optimizations exploit parallel and pipelined computations, and may need to restructure the computation to increase parallelism. Profitability formulas are derived for each optimization. Empirical results show that exploiting parallelism for pipelined computations, reductions, and scans is vital. Message vectorization, collective communication, and efficient coarse-grain pipelining also significantly affect performance. Scalability of communicatio...

In this paper we prove time and space bounds for the implementation of the programming language NESL on various parallel machine models. NESL is a sugared typed J-calculus with a set of array primitives and an explicit parallel map over arrays. Our results extend previous work on provable implementation bounds for functional languages by considering space and by including arrays. For modeling the cost of NESL we augment a standard call-by-value operational semantics to return two cost measures: a DAG representing the sequential dependence in the computation, and a measure of the space taken by a sequential implementation. We show that a NESL program with w work (nodes in the DAG), d depth (levels in the DAG), and s sequential space can be implemented on a p processor butterfly network, hypercube, or CRCW PRAM usin O(w/p + d log p) time and 0(s + dp logp) reachable space. For programs with sufficient parallelism these bounds are optimal in that they give linew speedup and use space within a constant factor of the sequential space. 1

The process of writing large parallel programs is complicated by the need to specify both the parallel behaviour of the program and the algorithm that is to be used to compute its result. This paper introduces evaluation strategies, lazy higher-order functions that control the parallel evaluation of non-strict functional languages. Using evaluation strategies, it is possible to achieve a clean separation between algorithmic and behavioural code. The result is enhanced clarity and shorter parallel programs. Evaluation strategies are a very general concept: this paper shows how they can be used to model a wide range of commonly used programming paradigms, including divideand -conquer, pipeline parallelism, producer/consumer parallelism, and data-oriented parallelism. Because they are based on unrestricted higher-order functions, they can also capture irregular parallel structures. Evaluation strategies are not just of theoretical interest: they have evolved out of our experience in parallelising several large-scale applications, where they have proved invaluable in helping to manage the complexities of parallel behaviour. These applications are described in detail here. The largest application we have studied to date, Lolita, is a 60,000 line natural language parser. Initial results show that for these applications we can achieve acceptable parallel performance, while incurring minimal overhead for using evaluation strategies.