A consideration of several different examples sheds new light on the problem of ereat-ing reliable, well-structured programs that behave efficiently. This study focuses largely on two issues: (a) improved syntax for iterations and error exits, making it possible to write a larger class of programs clearly and efficiently without go to state-

A trampolined program is organized as a single loop in which computations are scheduled and their execution allowed to proceed in discrete steps. Writing programs in trampolined style supports primitives for multithreading without language support for continuations. Various forms of trampolining allow for different degrees of interaction between threads. We present two architectures based on an only mildly intrusive trampolined style. Concurrency can be supported at multiple levels of granularity by performing the trampolining transformation multiple times.

this paper is to refine this definition somewhat, adapting it to the purposes of the research community in computer science. Accordingly, we shall attempt to provide a reasonable definition of or, rather, criteria for folk theorems, followed by a detailed example illustrating the ideas. The latter endeavor might take one of two possible forms. We could take a piece of folklore and show that it is a theorem, or take a theorem and show that it is folklore. As an example of the first form we could have shown that the statement P NP, which is folklore, is also a theorem. However, since we have resolved to introduce no new technical material in this paper, and moreover, since researchers in our community seem to be less familiar with folklore than with theorems, Permission to copy without fee all or part of this material is granted provided that the copies are not made or distributed for direct commercial advantage, the ACM copyright notice and the title of the publication and its date appear, and notice is given that copying is by permission of the Association for Computing Machinery. To copy otherwise, or to republish, requires a fee and/or specific permission

Abstract. We perceive programs as single-pass instruction sequences. A single-pass instruction sequence under execution is considered to produce a behaviour to be controlled by some execution environment. Threads as considered in basic thread algebra model such behaviours. We show that all regular threads, i.e. threads that can only be in a finite number of states, can be produced by single-pass instruction sequences without jump instructions if use can be made of Boolean registers. We also show that, in the case where goto instructions are used instead of jump instructions, a bound to the number of labels restricts the expressiveness.

Abstract. Heterogeneous multi-core and streaming architectures such as the GPU, Cell, ClearSpeed, and Imagine processors have better power/ performance ratios and memory bandwidth than traditional architectures. These types of processors are increasingly being used to accelerate compute-intensive applications. Their performance advantage is achieved by using multiple SIMD processor cores but limiting the complexity of each core, and by combining this with a simplified memory system. In particular, these processors generally avoid the use of cache coherency protocols and may even omit general-purpose caches, opting for restricted caches or explictly managed local memory. We show how control flow can be emulated on such tiled SIMD architectures and how memory access can be organized to avoid the need for a general-purpose cache and to tolerate long memory latencies. Our technique uses streaming execution and multipass partitioning. Our prototype targets GPUs. On GPUs the memory system is deeply pipelined and caches for read and write are not coherent, so reads and writes may not use the same memory locations simultaneously. This requires the use of double-buffered streaming. We emulate general control flow in a way that is transparent to the programmer and include specific optimizations in our approach that can deal with double-buffering. 1

Branch-coverage testability transformation for unstructured programs