This report describes Processor Coupling, a mechanism for controlling multiple ALUs on a single integrated circuit to exploit both instruction-level and inter-thread parallelism. A compiler statically schedules individual threads to discover available intra-thread instruction-level parallelism. The runtime scheduling mechanism interleaves threads, exploiting inter-thread parallelism to maintain high ALU utilization. ALUs are assigned to threads on a cycle byscycle basis, and several threads can be active concurrently. Simulation results show that Processor Coupling performs well both on single threaded and multi-threaded applications. The experiments address the effects of memory latencies, function unit latencies, and communication bandwidth between function units.

The present work studies methods of scheduling in heterogeneous distributed systems. First there are introduced some theoretical basics which contain not only the scheduling theory itself but also the graph theory and the computational complexity theory. After that, compile-time scheduling methods and some well-known algorithms solving the problem are presented, followed by real-time scheduling basics and by classification of used methods. In the main part of the work there are proposed algorithms which respect additional restrictions. These algorithms are tested via the enclosed application and compared either to each other or to another algorithms which mostly don't respect additional restrictions. The mentioned application and the documentation for this application are a part of this work as well.