×

hmglib

swMATH ID: 32904
Software Authors: Zaspel, P.
Description: hmglib - Hierarchical matrices on GPU(s) library. This library provides an entirely GPU-based implementation of the hierarchical (H) matrix approach. H matrices approximate specific dense matrices, e.g., from discretized integral equations or kernel ridge regression, leading to log-linear time complexity in dense matrix-vector products. The library specifically allows to construct and apply an H matrix on GPU(s). To get high performance on GPU(s), techniques like parallel tree traversal, space filling curves and batched operations are applied.
Homepage: https://github.com/zaspel/hmglib
Source Code:  https://github.com/zaspel/hmglib
Related Software: ArrayFire; Thrust; GitHub; H2Lib; Matlab; MPLA; ScalFMM; AHMED; STRUMPACK; ASKIT; PetRBF; CUDA
Cited in: 1 Document

Cited by 1 Author

1 Zaspel, Peter

Citations by Year