Publications

2026

A Tale of Scale: Enabling Scalable and Holistic Storage QoS for Exascale HPC SystemsMiranda, M., Tanimura, Y., Haga, J., Ruhela, A., Harrell, S., Cazes, J., Pereira, J., Macedo, R., & Paulo, J.In 27th ACM International Middleware Conference (Middleware) (Just accepted). 2026.

@inproceedings{mmiranda2026taleofscale,
  title = {A Tale of Scale: Enabling Scalable and Holistic Storage QoS for Exascale HPC Systems},
  author = {Miranda, M. and Tanimura, Y. and Haga, J. and Ruhela, A. and Harrell, S. and Cazes, J. and Pereira, J. and Macedo, R. and Paulo, J.},
  booktitle = {27th ACM International Middleware Conference (Middleware) (Just accepted)},
  year = {2026},
  organization = {ACM}
}

Phoning Home: Repatriating output from cloud jobs with a user-level, provider-agnostic data transfer toolSouza, F., Sodré, D., Paulo, J., Macedo, R., Boeres, C., Rebello, V., Portella, F., Estrela, P., & Malini, R.In 38th IEEE/SBC International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD). 2026.

@inproceedings{fsouza2026phoninghome,
  title = {Phoning Home: Repatriating output from cloud jobs with a user-level, provider-agnostic data transfer tool},
  author = {Souza, F. and Sodr{\'e}, D. and Paulo, J. and Macedo, R. and Boeres, C. and Rebello, V. and Portella, F. and Estrela, P. and Malini, R.},
  booktitle = {38th IEEE/SBC International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)},
  year = {2026},
  organization = {IEEE}
}

Enabling easy-to-use and high-performance user-space storage I/O for applicationsOliveira, R. P., & Paulo, J.SOSP Doctoral Workshop (SysDW’26). 2026.

@article{roliveira2026sysdw,
  author = {Oliveira, Rui P. and Paulo, João},
  title = {Enabling easy-to-use and high-performance user-space storage I/O for applications},
  year = {2026},
  journal = {SOSP Doctoral Workshop (SysDW'26)}
}

2025

Polylayer: the Next 700 Storage ConfigurationsLopes, J., Pereira, B., Pereira, F., Muñoz, V., Gomes, T., Ribeiro, R., … Maia, F.In Workshop on Reliable Large-scale Data Management (RLDM’25), colocated with SRDS. 2025.

@inproceedings{11360379,
  title = {Polylayer: the Next 700 Storage Configurations},
  author = {Lopes, João and Pereira, Bruno and Pereira, Filipe and Muñoz, Vicente and Gomes, Tiago and Ribeiro, Rui and Costa, Filipe and Bonjardim, Marta and Cruz, Francisco and Paulo, João and Maia, Francisco},
  booktitle = {Workshop on Reliable Large-scale Data Management (RLDM'25), colocated with SRDS},
  year = {2025},
  pages = {422-427},
  url = {https://doi.org/10.1109/SRDS69199.2025.00052}
}

Speed Kills: Revisiting Data Deduplication for Modern Storage DevicesOliveira, R. P., Esteves, T., & Paulo, J.In Workshop on Reliable Large-scale Data Management (RLDM’25), colocated with SRDS. 2025.

@inproceedings{rpoliveira2025speedkills,
  title = {Speed Kills: Revisiting Data Deduplication for Modern Storage Devices},
  author = {Oliveira, R. P. and Esteves, T. and Paulo, J.},
  booktitle = {Workshop on Reliable Large-scale Data Management (RLDM'25), colocated with SRDS},
  year = {2025},
  url = {https://rldm.invisiblelab.dev/papers/speed-kills-revisiting-data-deduplication-for-modern-storage-devices.pdf}
}

Exploiting Trusted Execution Environments And Distributed Computation for Genomic Association TestsBrito, C. V., Ferreira, P. G., & Paulo, J.IEEE Journal of Biomedical and Health Informatics. 2025.

@article{brito2025exploiting,
  title = {Exploiting Trusted Execution Environments And Distributed Computation for Genomic Association Tests},
  author = {Brito, Cl{\'a}udia V and Ferreira, Pedro G and Paulo, Jo{\~a}o},
  journal = {IEEE Journal of Biomedical and Health Informatics},
  year = {2025},
  publisher = {IEEE},
  url = {https://10.1109/JBHI.2025.3562364}
}

2024

Can Current SDS Controllers Scale To Modern HPC Infrastructures?Miranda, M., Tanimura, Y., Haga, J., Ruhela, A., Harrell, S. L., Cazes, J., Macedo, R., Pereira, J., & Paulo, J.In Workshop of Intel Extreme Performance Users Group (IXPUG), colocated with SC. 2024.

@inproceedings{miranda2024can,
  title = {Can Current SDS Controllers Scale To Modern HPC Infrastructures?},
  author = {Miranda, Mariana and Tanimura, Yusuke and Haga, Jason and Ruhela, Amit and Harrell, Stephen Lien and Cazes, John and Macedo, Ricardo and Pereira, Jos{\'e} and Paulo, Jo{\~a}o},
  booktitle = {Workshop of Intel Extreme Performance Users Group (IXPUG), colocated with SC},
  pages = {861--868},
  year = {2024},
  organization = {IEEE},
  url = {https://doi.org/10.1109/SCW63240.2024.00123}
}

2023

Privacy-Preserving Machine Learning on Apache SparkBrito, C. V., Ferreira, P. G., Portela, B. L., Oliveira, R. C., & Paulo, J.IEEE Access. 2023.

@article{brito2023privacy,
  title = {Privacy-Preserving Machine Learning on Apache Spark},
  author = {Brito, Cl{\'a}udia V and Ferreira, Pedro G and Portela, Bernardo L and Oliveira, Rui C and Paulo, Jo{\~a}o},
  journal = {IEEE Access},
  volume = {11},
  pages = {127907--127930},
  year = {2023},
  publisher = {IEEE},
  url = {https://ieeexplore.ieee.org/abstract/document/10314994}
}

Taming Metadata-Intensive HPC Jobs Through Dynamic, Application-Agnostic QoS ControlMacedo, R., Miranda, M., Tanimura, Y., Haga, J., Ruhela, A., Harrell, S. L., Evans, R. T., Pereira, J., & Paulo, J.In IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid). 2023.

@inproceedings{macedo2023taming,
  title = {Taming Metadata-Intensive HPC Jobs Through Dynamic, Application-Agnostic QoS Control},
  author = {Macedo, Ricardo and Miranda, Mariana and Tanimura, Yusuke and Haga, Jason and Ruhela, Amit and Harrell, Stephen Lien and Evans, Richard Todd and Pereira, Jos{\'e} and Paulo, Joao},
  booktitle = {IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid)},
  pages = {47--61},
  year = {2023},
  organization = {IEEE},
  url = {https://doi.org/10.1109/CCGrid57682.2023.00015}
}

SOTERIA: Preserving Privacy in Distributed Machine LearningBrito, C., Ferreira, P., Portela, B., Oliveira, R., & Paulo, J.In Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing (SAC). 2023.

@inproceedings{brito2023soteria,
  title = {SOTERIA: Preserving Privacy in Distributed Machine Learning},
  author = {Brito, Cl{\'a}udia and Ferreira, Pedro and Portela, Bernardo and Oliveira, Rui and Paulo, Jo{\~a}o},
  booktitle = {Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing (SAC)},
  pages = {135--142},
  year = {2023},
  organization = {ACM},
  url = {https://dl.acm.org/doi/abs/10.1145/3555776.3578591}
}

2022

Protecting Metadata Servers From Harm Through Application-level I/O ControlMacedo, R., Miranda, M., Tanimura, Y., Haga, J., Ruhela, A., Harrell, S. L., Evans, R. T., & Paulo, J.In Workshop on Re-envisioning Extreme-Scale I/O for Emerging Hybrid HPC Workloads (REX-IO), colocated with CLUSTER. 2022.

@inproceedings{macedo2022protecting,
  title = {Protecting Metadata Servers From Harm Through Application-level I/O Control},
  author = {Macedo, Ricardo and Miranda, Mariana and Tanimura, Yusuke and Haga, Jason and Ruhela, Amit and Harrell, Stephen Lien and Evans, Richard Todd and Paulo, Jo{\~a}o},
  booktitle = {Workshop on Re-envisioning Extreme-Scale I/O for Emerging Hybrid HPC Workloads (REX-IO), colocated with CLUSTER},
  pages = {573--580},
  year = {2022},
  organization = {IEEE},
  url = {https://doi.org/10.1109/CLUSTER51413.2022.00075}
}

PAIO: General, Portable I/O Optimizations With Minor Application ModificationsMacedo, R., Tanimura, Y., Haga, J., Chidambaram, V., Pereira, J., & Paulo, J.In 20th USENIX Conference on File and Storage Technologies (FAST). 2022.

@inproceedings{macedo2022paio,
  title = {PAIO: General, Portable I/O Optimizations With Minor Application Modifications},
  author = {Macedo, Ricardo and Tanimura, Yusuke and Haga, Jason and Chidambaram, Vijay and Pereira, Jos{\'e} and Paulo, Jo{\~a}o},
  booktitle = {20th USENIX Conference on File and Storage Technologies (FAST)},
  pages = {413--428},
  year = {2022},
  organization = {USENIX},
  url = {https://www.usenix.org/conference/fast22/presentation/macedo}
}

2021

Pods-as-Volumes: Effortlessly Integrating Storage Systems and Middleware into KubernetesFaria, A., Macedo, R., & Paulo, J.In 7th International Workshop on Container Technologies and Container Clouds (WoC), colocated with Middleware. 2021.

@inproceedings{faria2021pods,
  title = {Pods-as-Volumes: Effortlessly Integrating Storage Systems and Middleware into Kubernetes},
  author = {Faria, Alberto and Macedo, Ricardo and Paulo, Jo{\~a}o},
  booktitle = {7th International Workshop on Container Technologies and Container Clouds (WoC), colocated with Middleware},
  pages = {1--6},
  year = {2021},
  url = {https://doi.org/10.1145/3493649.3493653}
}

PAIO: A Software-Defined Storage Data Plane FrameworkMacedo, R., Tanimura, Y., Haga, J., Chidambaram, V., Pereira, J., & Paulo, J.ArXiv - Computing Research Repository (CoRR). 2021.

@article{macedo2021paio,
  title = {PAIO: A Software-Defined Storage Data Plane Framework},
  author = {Macedo, Ricardo and Tanimura, Yusuke and Haga, Jason and Chidambaram, Vijay and Pereira, Jos{\'e} and Paulo, Jo{\~a}o},
  journal = {ArXiv - Computing Research Repository (CoRR)},
  year = {2021},
  url = {https://doi.org/10.48550/arXiv.2106.03617}
}

BDUS: Implementing Block Devices In User SpaceFaria, A., Macedo, R., Pereira, J., & Paulo, J.In 14th ACM International Conference on Systems and Storage (SYSTOR). 2021.

@inproceedings{faria2021bdus,
  title = {BDUS: Implementing Block Devices In User Space},
  author = {Faria, Alberto and Macedo, Ricardo and Pereira, Jos{\'e} and Paulo, Jo{\~a}o},
  booktitle = {14th ACM International Conference on Systems and Storage (SYSTOR)},
  pages = {1--11},
  year = {2021},
  organization = {ACM},
  url = {https://doi.org/10.1145/3456727.3463768}
}

S2Dedup: SGX-enabled Secure DeduplicationMiranda, M., Esteves, T., Portela, B., & Paulo, J.In 14th ACM International Conference on Systems and Storage (SYSTOR). 2021.

@inproceedings{miranda2021s2dedup,
  title = {S2Dedup: SGX-enabled Secure Deduplication},
  author = {Miranda, Mariana and Esteves, T{\^a}nia and Portela, Bernardo and Paulo, Jo{\~a}o},
  booktitle = {14th ACM International Conference on Systems and Storage (SYSTOR)},
  pages = {1--12},
  year = {2021},
  organization = {ACM},
  url = {https://doi.org/10.1145/3456727.3463773}
}

2020

Genodedup: Similarity-Based Deduplication And Delta-encoding For Genome Sequencing DataCogo, V., Paulo, J., & Bessani, A.IEEE Transactions on Computers. 2020.

@article{cogo2020genodedup,
  title = {Genodedup: Similarity-Based Deduplication And Delta-encoding For Genome Sequencing Data},
  author = {Cogo, Vinicius and Paulo, Joao and Bessani, Alysson},
  journal = {IEEE Transactions on Computers},
  volume = {70},
  number = {5},
  pages = {669--681},
  year = {2020},
  publisher = {IEEE},
  url = {https://doi.org/10.1109/TC.2020.2994774}
}

A Survey And Classification Of Software-Defined Storage SystemsMacedo, R., Paulo, J., Pereira, J., & Bessani, A.ACM Computing Surveys (CSUR). 2020.

@article{macedo2020survey,
  title = {A Survey And Classification Of Software-Defined Storage Systems},
  author = {Macedo, Ricardo and Paulo, Jo{\~a}o and Pereira, Jos{\'e} and Bessani, Alysson},
  journal = {ACM Computing Surveys (CSUR)},
  volume = {53},
  number = {3},
  pages = {1--38},
  year = {2020},
  publisher = {ACM New York, NY, USA},
  url = {https://doi.org/10.1145/3385896}
}

2019

A Case For Dynamically Programmable Storage Background TasksMacedo, R., Faria, A., Paulo, J., & Pereira, J.In Workshop on Distributed and Reliable Storage Systems (DRSS), colocated with SRDS. 2019.

@inproceedings{macedo2019case,
  title = {A Case For Dynamically Programmable Storage Background Tasks},
  author = {Macedo, Ricardo and Faria, Alberto and Paulo, Jo{\~a}o and Pereira, Jos{\'e}},
  booktitle = {Workshop on Distributed and Reliable Storage Systems (DRSS), colocated with SRDS},
  pages = {7--12},
  year = {2019},
  organization = {IEEE},
  url = {https://doi.org/10.1109/SRDSW49218.2019.00009}
}

TrustFS: An SGX-Enabled Stackable File System FrameworkEsteves, T., Macedo, R., Faria, A., Portela, B., Paulo, J., Pereira, J., & Harnik, D.In Workshop on Distributed and Reliable Storage Systems (DRSS), colocated with SRDS. 2019.

@inproceedings{esteves2019trustfs,
  title = {TrustFS: An SGX-Enabled Stackable File System Framework},
  author = {Esteves, T{\^a}nia and Macedo, Ricardo and Faria, Alberto and Portela, Bernardo and Paulo, Joao and Pereira, Jos{\'e} and Harnik, Danny},
  booktitle = {Workshop on Distributed and Reliable Storage Systems (DRSS), colocated with SRDS},
  pages = {25--30},
  year = {2019},
  organization = {IEEE},
  url = {https://doi.org/10.1109/SRDSW49218.2019.00012}
}

2017

DDFLASKS: Deduplicated Very Large Scale Data StoreMaia, F., Paulo, J., Coelho, F., Neves, F., Pereira, J., & Oliveira, R.In Distributed Applications and Interoperable Systems (DAIS). 2017.

@inproceedings{maia2017ddflasks,
  title = {DDFLASKS: Deduplicated Very Large Scale Data Store},
  author = {Maia, Francisco and Paulo, Jo{\~a}o and Coelho, F{\'a}bio and Neves, Francisco and Pereira, Jos{\'e} and Oliveira, Rui},
  booktitle = {Distributed Applications and Interoperable Systems (DAIS)},
  pages = {51--66},
  year = {2017},
  organization = {Springer},
  url = {https://link.springer.com/chapter/10.1007/978-3-319-59665-5_4}
}

SafeFS: A Modular Architecture For Secure User-space File Systems: One Fuse To Rule Them All Best Student Paper AwardPontes, R., Burihabwa, D., Maia, F., Paulo, J., Schiavoni, V., Felber, P., Mercier, H., & Oliveira, R.In 10th ACM International Systems and Storage Conference (SYSTOR). 2017.

@inproceedings{pontes2017safefs,
  title = {SafeFS: A Modular Architecture For Secure User-space File Systems: One Fuse To Rule Them All},
  author = {Pontes, Rog{\'e}rio and Burihabwa, Dorian and Maia, Francisco and Paulo, Jo{\~a}o and Schiavoni, Valerio and Felber, Pascal and Mercier, Hugues and Oliveira, Rui},
  booktitle = {10th ACM International Systems and Storage Conference (SYSTOR)},
  pages = {1--12},
  year = {2017},
  organization = {ACM},
  url = {https://doi.org/10.1145/3078468.3078480}
}

2016

Efficient Deduplication In A Distributed Primary Storage InfrastructurePaulo, J., & Pereira, J.ACM Transactions on Storage (TOS). 2016.

@article{paulo2016efficient,
  title = {Efficient Deduplication In A Distributed Primary Storage Infrastructure},
  author = {Paulo, Jo{\~a}o and Pereira, Jos{\'e}},
  journal = {ACM Transactions on Storage (TOS)},
  volume = {12},
  number = {4},
  pages = {1--35},
  year = {2016},
  publisher = {ACM New York, NY, USA},
  url = {https://doi.org/10.1145/2876509}
}

On The Cost Of Safe Storage For Public Clouds: An Experimental EvaluationBurihabwa, D., Pontes, R., Felber, P., Maia, F., Mercier, H., Oliveira, R., Paulo, J., & Schiavoni, V.In 35th Symposium on Reliable Distributed Systems (SRDS). 2016.

@inproceedings{burihabwa2016cost,
  title = {On The Cost Of Safe Storage For Public Clouds: An Experimental Evaluation},
  author = {Burihabwa, Dorian and Pontes, Rog{\'e}rio and Felber, Pascal and Maia, Francisco and Mercier, Hugues and Oliveira, Rui and Paulo, Jo{\~a}o and Schiavoni, Valerio},
  booktitle = {35th Symposium on Reliable Distributed Systems (SRDS)},
  pages = {157--166},
  year = {2016},
  organization = {IEEE},
  url = {https://doi.org/10.1109/SRDS.2016.028}
}

2014

A Survey And Classification Of Storage Deduplication SystemsPaulo, J., & Pereira, J.ACM Computing Surveys (CSUR). 2014.

@article{paulo2014survey,
  title = {A Survey And Classification Of Storage Deduplication Systems},
  author = {Paulo, Jo{\~a}o and Pereira, Jos{\'e}},
  journal = {ACM Computing Surveys (CSUR)},
  volume = {47},
  number = {1},
  pages = {1--30},
  year = {2014},
  publisher = {ACM},
  url = {https://doi.org/10.1145/2611778}
}

Distributed Exact Deduplication For Primary Storage InfrastructuresPaulo, J., & Pereira, J.In Distributed Applications and Interoperable Systems (DAIS). 2014.

@inproceedings{paulo2014distributed,
  title = {Distributed Exact Deduplication For Primary Storage Infrastructures},
  author = {Paulo, Joao and Pereira, Jos{\'e}},
  booktitle = {Distributed Applications and Interoperable Systems (DAIS)},
  pages = {52--66},
  year = {2014},
  organization = {Springer},
  url = {https://link.springer.com/chapter/10.1007/978-3-662-43352-2_5}
}