Computer Science – Mathematical Software
Scientific paper
2007-09-09
Computer Science
Mathematical Software
Scientific paper
As multicore systems continue to gain ground in the High Performance Computing world, linear algebra algorithms have to be reformulated or new algorithms have to be developed in order to take advantage of the architectural features on these new processors. Fine grain parallelism becomes a major requirement and introduces the necessity of loose synchronization in the parallel execution of an operation. This paper presents an algorithm for the Cholesky, LU and QR factorization where the operations can be represented as a sequence of small tasks that operate on square blocks of data. These tasks can be dynamically scheduled for execution based on the dependencies among them and on the availability of computational resources. This may result in an out of order execution of the tasks which will completely hide the presence of intrinsically sequential tasks in the factorization. Performance comparisons are presented with the LAPACK algorithms where parallelism can only be exploited at the level of the BLAS operations and vendor implementations.
Buttari Alfredo
Dongarra Jack
Kurzak Jakub
Langou Julien
No associations
LandOfFree
A Class of Parallel Tiled Linear Algebra Algorithms for Multicore Architectures does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with A Class of Parallel Tiled Linear Algebra Algorithms for Multicore Architectures, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Class of Parallel Tiled Linear Algebra Algorithms for Multicore Architectures will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-631762