Parallel Programming in Split - CDavid

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 eecient 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 eecient access to a global address space on current distributed memory multipro-cessors. It retains the \small language" character of C and supports careful engineering and optimization of programs by providing a simple, predictable cost model. This is in stark contrast to languages that rely on extensive program transformation at compile time to obtain performance on parallel machines. Split-C programs do what the programmer speciies; the compiler takes care of addressing and communication, as well as code generation. Thus, the ability to exploit parallelism or locality is not limited by the com-piler's recognition capability, nor is there need to second guess the compiler transformations while optimizing the program. The language provides a small set of global access primitives and simple parallel storage layout declarations. These seem to capture most of the useful elements of shared memory, message passing, and data parallel programming in a common, familiar context. Split-C is currently implemented on the Thinking Machines Corp. CM-5, building from GCC Send e-mail to: [email protected] and Active Messagess17] and implementations are underway for architectures with more aggressive support for global access. It has been used extensively as a teaching tool in parallel computing courses and hosts a wide variety of applications. Split-C may also be viewed as a compilation target for higher level parallel languages. This paper describes the central concepts in Split-C and illustrates how these are used in the process of optimizing parallel programs. We begin with a brief overview of the language as a whole and examine each concept individually in the following sections. The presentation interweaves the example use, the optimization techniques, and the language deenition concept by concept. Control Model: Split-C follows an SPMD (single program, multiple data) …