The problems involved in developing efficient parallel programs have proved harder than those in developing efficient sequential ones, both for programmers and for compilers. Although program calculation has been found to be a promising way to solve these problems in the sequential world, we believe that it needs much more effort to study its effective use in the parallel world. In this paper, we propose a calculational framework for the derivation of efficient parallel programs with two main innovations: - We propose a novel inductive synthesis lemma based on which an elementary but powerful parallelization theorem is developed. - We make the first attempt to construct a calculational algorithm for parallelization, deriving associative operators from data type definition and making full use of existing fusion and tupling calculations. Being more constructive, our method is not only helpful in the design of efficient parallel programs in general but also promising in the construc...

Abstract program schemes, such as scan or homomorphism, can capture a wide range of data parallel programs. While versatile, these schemes are of limited practical use on their own. A key problem is that the more natural sequential specifications may not have associative combine operators required by these schemes. As a result, they often fail to be immediately identified. To resolve this problem, we propose a method to systematically derive parallel programs from sequential definitions. This method is special in that it can automatically invent auxiliary functions needed by associative combine operators. Apart from a formalisation, we also provide new theorems, based on the notion of context preservation, to guarantee parallelization for a precise class of sequential programs. 1 Introduction It is well-recognised that a key problem of parallel computing remains the development of efficient and correct parallel software. This task is further complicated by the variety of parallel arc...

this paper, we study functions called list homomorphisms, which represent a particular pattern of parallelism.

Parallel skeletons intend to encourage programmers to build...

Parallel primitives (skeletons) intend to encourage programmers to build a parallel program from ready-made components for which efficient implementations are known to exist, making the parallelization process easier. However, programmers often suffer from the difficulty to choose a combination of proper parallel primitives so as to construct efficient parallel programs. To overcome this difficulty, we shall propose a new transformation, called diffusion, which can efficiently decompose a recursive definition into several functions such that each function can be described by some parallel primitive. This allows programmers to describe algorithms in a more natural recursive form. We demonstrate our idea with several interesting examples. Our diffusion transformation should be significant not only in development of new parallel algorithms, but also in construction of parallelizing compilers.

. Systematic parallelization of sequential programs remains a major challenge in parallel computing. Traditional approaches using program schemes tend to be narrower in scope, as the properties which enable parallelism are difficult to capture via ad-hoc schemes. In [CTH98], a systematic approach to parallelization based on the notion of preserving the context of recursive sub-terms has been proposed. This approach can be used to derive a class of divide-and-conquer algorithms. In this paper, we enhance the methodology by using invariants to guide the parallelization process. The enhancement enables the parallelization of a class of recursive functions with conditional and tupled constructs, which were not possible previously. We further show how such invariants can be discovered and verified systematically, and demonstrate the power of our methodology by deriving a parallel code for maximum segment product. To the best of our knowledge, this is the first systematic parall...

ion and Performance in the Design of Parallel Programs Der Fakultat fur Mathematik und Informatik der Universitat Passau vorgelegte Zusammenfassung der Veroffentlichungen zur Erlangung der venia legendi von Dr. Sergei Gorlatch Passau, Juli 1997 Contents 1 Introduction 2 2 Outline of the SAT Approach 6 2.1 Performance View . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.2 Abstraction View . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.3 Design in SAT: Stages and Transformations . . . . . . . . . . 9 2.4 SAT and Homomorphisms . . . . . . . . . . . . . . . . . . . . 11 3 List Homomorphisms 12 4 Extraction and Adjustment 14 4.1 The CS-Method . . . . . . . . . . . . . . . . . . . . . . . . . . 14 4.2 Mechanizing the CS-Method . . . . . . . . . . . . . . . . . . . 17 4.3 Almost-Homomorphisms: the MSS Problem . . . . . . . . . . 19 5 Composition of Homomorphisms 21 5.1 Rules of Composition . . . . . . . . . . . . . . . . . . . . . . . 21 5.2 Derivation by Transformation...

Data parallelism is currently one of the most successful models for programming massively parallel computers. The central idea is to evaluate a uniform collection of data in parallel by simultaneously manipulating each data element in the collection. Despite many of its promising features, the current approach suffers from two problems. First, the main parallel data structures that most data parallel languages currently support are restricted to simple collection data types like lists, arrays or similar structures. But other useful data structures like trees have not been well addressed. Second, parallel programming relies on a set of parallel primitives that capture parallel skeletons of interest. However, these primitives are not well structured, and efficient parallel programming with these primitives is difficult. In this paper, we propose a polytypic framework for developing efficient parallel programs on most data structures. We showhow a set of polytypic parallel primitives can be formally defined for manipulating most data structures, how these primitives can be successfully structured into a uniform recursive definition, and how an efficient combination of primitives can be derived from a naive specification program. Our framework should be significant not only in development of new parallel algorithms, but also in construction of parallelizing compilers.

Parallel programming is becoming an important cornerstone of general computing. In addition, type systems have significant impact on program analysis. In this paper, we demonstrate an automated typebased system that soundly detects parallelizability of sequential functional programs. Our type inference system discovers the parallelizability property of a sequential program in a modular fashion, by exploring a ring structure among the program’s operators. It handles self-recursive functions with accumulating parameters, as well as a class of non-linear mutual-recursive functions. Programs whose types are inferred to be parallelizable can be automatically transformed to parallel code in a mutumorphic form – a succint model for parallel computation. Transforming into such a form is an important step towards constructing efficient data parallel programs.

Parallel programs can be synthesized from sequential functional programs via a technique known as context preservation [6]. This technique has significantly broadened the set of sequential programs eligible for parallelization. However, the ability to automatically detect functions which admit context-preservation property has not been investigated. In this paper, we propose a type-based approach to automatically detect a class of functions with context-preservation property. In essence, our type system aims to detect an extended-ring property of the subject program, from which context preservation is guaranteed. Through this type system, a sequential program can be automatically transformed to fit into a skeletal form, which can then be parallelized.