In this paper we introduce a new algorithm for computing near optimal schedules for task graph problems. In contrast to conventional approaches for solving those scheduling proble...
This paper presents a new modulo scheduling algorithm for clustered microarchitectures. The main feature of the proposed scheme is that the assignment of instructions to clusters ...
In order to achieve practical efficient execution on a parallel architecture, a knowledge of the data dependencies related to the application appears as the key point for building...
We give tight bounds on the parallel complexity of some problems involving random graphs. Speci cally, we show that a Hamiltonian cycle, a breadth rst spanning tree, and a maximal...
Applications structured as parallel task graphs exhibit both data and task parallelism, and arise in many domains. Scheduling these applications on parallel platforms has been a lo...