We present a model of parallel computation, the parameterized task graph, which is a compact, problem size independent, representation of some frequently used directed acyclic task graphs.Expand

Parallel Algorithms and Architectures provides a thorough introduction to this technology, explaining the fundamentals of parallelism in a logical and readable way.Expand

Theorem [Komornik-Loretil. There exists a smallest q E (1, 2) for which there exists a unique expansion of 1 as 1 = ESn=j 8nq n with an E{, 11. Furthermore, for this smallest q, the coefficient 8n is… Expand

SummaryWe show that the greedy algorithm introduced in [1] and [5] to perform the parallel QR decomposition of a dense rectangular matrix of sizem×n is optimal. Then we assume thatm/n2 tends to zero… Expand

An optimal algorithm to perform the parallel QR decomposition of a dense matrix of size <N</italic>, when an unlimited number of processors is available.Expand

We present a scheduling algorithm for a parameterized task graph which first derives symbolic linear clusters and assigns task clusters to processors in a multi-threaded fashion.Expand

We propose a dynamic scheduling algorithm which finds good schedules for coarse-grain task graphs, has a low memory cost, and a low computational complexity.Expand