OF DISSERTATION CODE GENERATIONS, EVALUATIONS, AND OPTIMIZATIONS IN MULTITHREADED EXECUTIONS Efficient large-scale parallel processing can result only from proper handling of latency. Latency arises either from remote memory accesses or synchronizations. Multithreading is an execution model that can effectively deal with latency by switching among a set of ready threads. This model has been proposed in a variety of forms: a unit of storage can be based on either a collection of threads or a single thread, threads can be either blocking or non-blocking, and synchronization can be either implicit or explicit. This dissertation describes research in the evaluation and optimization of various issues in multithreading. Issues of particular interest are the development of a multithreaded execution model to be used as a test-bed and a hybrid code generation scheme where threads are generated in a top-down manner and then optimized in a bottom-up fashion. Various forms of locality are also ide...

OF DISSERTATION THE SPECTRUM OF THREAD IMPLEMENTATIONS ON HYBRID MULTITHREADED ARCHITECTURES The proliferation of multithreaded architectures indicates a desire to combine the best of the dataflow and von Neumann models. These architectures have the capability of masking memory latencies using the dataflow model as well as the capability of exploiting locality, both temporal and spatial, a la von Neumann. This is accomplished by increasing granularity from instruction level to thread level. Increased granularity results in reducing the synchronization required per instruction and introduces locality where none was present. Applicative and functional languages expose parallelism with no intervention by the programmer and without expensive data dependence analysis, apart from array analysis. With the combination of applicative languages, hybrid multithreaded architectures and capable compilers, a possible platform for scalable high performance computing is created. The challenge is to de...