Workload placement on heterogeneous CPU-GPU environments

A review and a comparison of state-of-the-art strategies for workload placement on heterogeneous CPU-GPU architectures, along with runtime prediction techniques and methods to support multi-device code.

Tutorial presented at VLDB 2024.

• A copy of the paper and the slides presented
• The list of papers considered in the tutorial

License

The project is licensed under the GPL-3.0 license.

Full citation:

Marcos N. L. Carvalho, Alkis Simitsis, Anna Queralt, and Oscar Romero. Workload Placement on Heterogeneous CPU-GPU Systems . PVLDB, 17(12): 4241 - 4244, 2024. doi:10.14778/3685800.3685845

BibTex Citation

@article{CSQR24,
  author       = {Marcos N. L. Carvalho and
                  Alkis Simitsis and
                  Anna Queralt and
                  Oscar Romero},
  title        = {Workload Placement on Heterogeneous {CPU-GPU} Systems},
  journal      = {Proc. {VLDB} Endow.},
  volume       = {17},
  number       = {12},
  pages        = {4241--4244},
  year         = {2024},
  url          = {https://www.vldb.org/pvldb/vol17/p4241-carvalho.pdf}
}