StarPU

StarPU: A unified platform for task scheduling on heterogeneous multicore architectures. Multicore machines equipped with accelerators are becoming increasingly popular. The TOP500-leading RoadRunner machine is probably the most famous example of a parallel computer mixing IBM Cell Broadband Engines and AMD opteron processors. Other architectures, featuring GPU accelerators, are expected to appear in the near future. To fully tap into the potential of these hybrid machines, pure offloading approaches, in which the main core of the application runs on regular processors and offloads specific parts on accelerators, are not sufficient. The real challenge is to build systems where the application would permanently spread across the entire machine, that is, where parallel tasks would be dynamically scheduled over the full set of available processing units. To face this challenge, we propose a new runtime system capable of scheduling tasks over heterogeneous, accelerator-based machines. Our system features a software virtual shared memory that provides a weak consistency model. The system keeps track of data copies within accelerator embedded-memories and features a data-prefetching engine. Such facilities, together with a database of self-tuned per-task performance models, can be used to greatly improve the quality of scheduling policies in this context. We demonstrate the relevance of our approach by benchmarking various parallel numerical kernel implementations over our runtime system. We obtain significant speedups and a very high efficiency on various typical workloads over multicore machines equipped with multiple accelerators.


References in zbMATH (referenced in 38 articles )

Showing results 1 to 20 of 38.
Sorted by year (citations)

1 2 next

  1. Duff, Iain; Hogg, Jonathan; Lopez, Florent: A new sparse (LDL^T) solver using a posteriori threshold pivoting (2020)
  2. Gratien, Jean-Marc: A robust and scalable multi-level domain decomposition preconditioner for multi-core architecture with large number of cores (2020)
  3. Henrio, Ludovic; Kessler, Christoph; Li, Lu: Leveraging access mode declarations in a model for memory consistency in heterogeneous systems (2020)
  4. Bremer, Maximilian; Kazhyken, Kazbek; Kaiser, Hartmut; Michoski, Craig; Dawson, Clint: Performance comparison of HPX versus traditional parallelization strategies for the discontinuous Galerkin method (2019)
  5. Coulette, David; Franck, Emmanuel; Helluy, Philippe; Mehrenberger, Michel; Navoret, Laurent: High-order implicit palindromic discontinuous Galerkin method for kinetic-relaxation approximation (2019)
  6. Sameh Abdulah, Yuxiao Li, Jian Cao, Hatem Ltaief, David E. Keyes, Marc G. Genton, Ying Sun: ExaGeoStatR: A Package for Large-Scale Geostatistics in R (2019) arXiv
  7. Badwaik, Jayesh; Boileau, Matthieu; Coulette, David; Franck, Emmanuel; Helluy, Philippe; Klingenberg, Christian; Mendoza, Laura; Oberlin, Herbert: Task-based parallelization of an implicit kinetic scheme (2018)
  8. Duff, Iain; Hogg, Jonathan; Lopez, Florent: Experiments with sparse Cholesky using a sequential task-flow implementation (2018)
  9. Duff, Iain; Lopez, Florent; Nakov, Stojce: Sparse direct solution on parallel computers (2018)
  10. Essadki, Mohamed; Jung, Jonathan; Larat, Adam; Pelletier, Milan; Perrier, Vincent: A task-driven implementation of a simple numerical solver for hyperbolic conservation laws (2018)
  11. Jeannot, Emmanuel; Fournier, Yvan; Lorendeau, Benjamin: Experimenting task-based runtimes on a legacy computational fluid dynamics code with unstructured meshes (2018)
  12. Kedad-Sidhoum, Safia; Monna, Florence; Mounié, Grégory; Trystram, Denis: A family of scheduling algorithms for hybrid parallel platforms (2018)
  13. Malik, Avinash; Walker, Cameron; O’Sullivan, Michael; Sinnen, Oliver: Satisfiability modulo theory (SMT) formulation for optimal scheduling of task graphs with communication delay (2018)
  14. Agullo, Emmanuel; Buttari, Alfredo; Guermouche, Abdou; Lopez, Florent: Implementing multifrontal sparse solvers for multicore architectures with sequential task flow runtime systems (2016)
  15. Ghysels, Pieter; Li, Xiaoye S.; Rouet, François-Henry; Williams, Samuel; Napov, Artem: An efficient multicore implementation of a novel HSS-structured multifrontal solver using randomized sampling (2016)
  16. Gonnet, Pedro: Efficient and scalable algorithms for smoothed particle hydrodynamics on hybrid shared/distributed-memory architectures (2015)
  17. Huismann, Immo; Stiller, Jörg; Fröhlich, Jochen: Two-level parallelization of a fluid mechanics algorithm exploiting hardware heterogeneity (2015)
  18. Tillenius, Martin: Superglue: a shared memory framework using data versioning for dependency-aware task-based parallelization (2015)
  19. Tillenius, Martin; Larsson, Elisabeth; Lehto, Erik; Flyer, Natasha: A scalable RBF-FD method for atmospheric flow (2015)
  20. Bigot, Julien; Hou, Zhengxiong; Pérez, Christian; Pichon, Vincent: A low level component model easing performance portability of HPC applications (2014) ioport

1 2 next


Further publications can be found at: http://starpu.gforge.inria.fr/#publications