SIParCS 2015- Ramakrishnaiah


Vinay Ramakrishnaiah, University of Wyoming

Accelerating ‘fields’ by revamping the Cholesky Decomposition

(Slides) (Recorded Talk)

The Geophysical Statistics project group within the Institute for Mathematics Applied to Geosciences (IMAGe) has been making use of Matrix Algebra on GPU and Multicore Architectures (MAGMA) to accelerate the Cholesky decomposition (CD). The acceleration of the CD is motivated by a) Its frequent use in key computations in the spatial statistics R ‘fields’ package, b) Major bottleneck in ‘fields’ package execution and c) Operations involving big matrices make it suitable for parallelization.  The CD was accelerated last summer using the MAGMA library. However, the performance of the accelerated CD on multiple GPUs was observed to be unconventional - a) Execution time of CD on multiple GPUs was higher in comparison to single GPU execution of CD and b) Deep copy and in-place CD algorithms had opposite impacts on performance when executed on one and multiple GPUs. Our CPU and GPU profiling, conducted this summer, explains the unconventional behavior observed in the multi-GPU executions. The profiling provided insight to further accelerate the CD hierarchically– a) accelerate the underlying C function, b) reduce function call overhead in R and c) optimize the R environment.

Mentors: Dorit Hammerling, CISL IMAGe