Home Publications edited volumes Awards Research Teaching Miscellaneous Full CV [pdf] BLOG
Events
Past Events

Publications of Torsten Hoefler
Grzegorz Kwasniewski and Marko Kabić and Maciej Besta and Joost VandeVondele and Raffaele Solcà and Torsten Hoefler:
  RedBlue Pebbling Revisited: Near Optimal Parallel MatrixMatrix Multiplication
(In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC19), Nov. 2019) Best Paper Finalist, SC19 Best Student Paper (1/87)
Publisher Reference
AbstractWe propose COSMA: a parallel matrixmatrix multiplication algorithm that is near communicationoptimal for all combinations of matrix dimensions, processor counts, and memory sizes. The key idea behind COSMA is to derive an optimal (up to a factor of 0.03% for 10MB of fast memory) sequential schedule and then parallelize it, preserving I/O optimality. To achieve this, we use the redblue pebble game to precisely model MMM dependencies and derive a constructive and tight sequential and parallel I/O lower bound proofs. Compared to 2D or 3D algorithms, which fix processor decomposition upfront and then map it to the matrix dimensions, it reduces communication volume by up to 3 times. COSMA outperforms the established ScaLAPACK, CARMA, and CTF algorithms in all scenarios up to 12.8x (2.2x on average), achieving up to 88% of Piz Daint’s peak performance. Our work does not require any hand tuning and is maintained as an open source implementation.
DocumentsPublisher URL: http://doi.acm.org/10.1145/3295500.3356181download article:
  BibTeX  @inproceedings{, author={Grzegorz Kwasniewski and Marko Kabić and Maciej Besta and Joost VandeVondele and Raffaele Solcà and Torsten Hoefler}, title={{RedBlue Pebbling Revisited: Near Optimal Parallel MatrixMatrix Multiplication}}, year={2019}, month={Nov.}, booktitle={Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC19)}, source={http://www.unixer.de/~htor/publications/}, } 

