Stream Scheduling: A Framework to Manage Bulk Operations in Memory Hierarchies

With the emergence of streaming and multi-core architectures, there is an increasing demand to map parallel algorithms efficiently across all architectures. This paper describes a platform-independent optimization framework called Stream Scheduling, that orchestrates parallel execution of bulk computations and data transfers, and allocates storage at multiple levels of a memory hierarchy. By adjusting block sizes, and applying software pipelining on bulk operations, it ensures computation-to-communication ratio is maximized on each level. We evaluate our framework on a diverse set of Sequoia applications, targeting systems with different memory hierarchies: a Cell blade, a distributed-memory cluster, and the Cell blade attached to a disk.