publications
2024
-
GMorph: Accelerating Multi-DNN Inference via Model FusionIn Proceedings of the 19th ACM European Conference on Computer Systems (Eurosys), 2024
-
-
Graph Neural Network Training Systems: A Performance Comparison of Full-Graph and Mini-BatcharXiv preprint arXiv:2406.00552, 2024
2023
-
GSplit: Scaling Graph Neural Network Training on Large Graphs via Split-ParallelismarXiv preprint arXiv:2303.13775, 2023
2022
-
Tuning the Tail Latency of Distributed Queries Using ReplicationarXiv preprint arXiv:2212.10387, 2022
2021
-
Scalable Graph Neural Network Training: The Case for SamplingACM SIGOPS Operating Systems Review (OSR), 2021
-
FlexPushdownDB: Hybrid Pushdown and Caching in a Cloud DBMSProceedings of the VLDB Endowment, 2021
2020
-
-
PushdownDB: Accelerating a DBMS using S3 computationIn Proceedings of the IEEE 36th International Conference on Data Engineering (ICDE), 2020
-
Do the Best Cloud Configurations Grow on Trees? An Experimental Evaluation of Black Box Algorithms for Optimizing Cloud WorkloadsProceedings of the VLDB Endowment, 2020
2019
-
-
Gyro: A Modular Scale-Out Layer for Single-Server DBMSsIn Proceedings of the 38th IEEE Symposium on Reliable Distributed Systems (SRDS), 2019
2018
-
P-store: An Elastic Database System with Predictive ProvisioningIn Proceedings of the 2018 ACM International Conference on Management of Data (SIGMOD), 2018
2017
-
Graph Data Mining with ArabesqueIn Proceedings of the 2017 ACM International Conference on Management of Data (SIGMOD demo), 2017
-
Load Balancing for Skewed Streams on Heterogeneous ClusterarXiv preprint arXiv:1705.09073, 2017
-
Qfrag: Distributed Graph Search via Subgraph IsomorphismIn Proceedings of the 2017 ACM Symposium on Cloud Computing (SoCC), 2017
2016
-
When Two Choices are not Enough: Balancing at Scale in Distributed Stream ProcessingIn Proceedings of the 32nd IEEE International Conference on Data Engineering (ICDE), 2016
-
Clay: Fine-Grained Adaptive Partitioning for General Database SchemasProceedings of the VLDB Endowment, 2016
2015
-
Scalable Error Isolation for Distributed SystemsIn Proceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI), 2015
-
The Power of Both Choices: Practical Load Balancing for Distributed Stream Processing EnginesIn Proceedings of the 31st IEEE International Conference on Data Engineering (ICDE), 2015
2014
-
Accordion: Elastic Scalability for Database Systems Supporting Distributed TransactionsProceedings of the VLDB Endowment, 2014
-
E-store: Fine-Grained Elastic Partitioning for Distributed Transaction Processing SystemsProceedings of the VLDB Endowment, 2014
2013
-
-
Efficient Verification of Distributed Protocols Using Stateful Model CheckingIn Proceedings of the VLDB Endowment, 2013
-
On Barriers and the Gap Between Active and Passive ReplicationIn Proceedings of the 2013 International Symposium on Distributed Computing (DISC), 2013
2012
-
Practical Hardening of Crash-Tolerant SystemsIn Proceedings of the 2012 USENIX Annual Technical Conference (USENIX ATC), 2012
2011
-
To crash or not to crash: Efficient modeling of fail-stop faultsIn Invited paper, Proceedings of the Workshop on Logical Aspects of Fault-Tolerance (LAFT, in assoc. with LICS), 2011
-
Leader election for replicated services using application scoresIn Proceedings of the ACM/IFIP/USENIX 12th International Middleware Conference (Middleware), 2011
-
Application-level diagnostic and membership protocols for generic time-triggered systemsIEEE Transactions on Dependable and Secure Computing, 2011
-
Zab: High-Performance Broadcast for Primary-Backup SystemsIn Proceedings of the 41st IEEE/IFIP International Conference on Dependable Systems & Networks (DSN), 2011
-
Efficient model checking of fault-tolerant distributed protocolsIn Proceedings of the 41st IEEE/IFIP International Conference on Dependable Systems & Networks (DSN), 2011
-
Supporting domain-specific state space reductions through local partial-order reductionIn Proceedings of the 26th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2011
2010
-
HP: Hybrid paxos for WANsIn Proceedings of the 9th IEEE European Dependable Computing Conference (EDCC), 2010
-
On efficient models for model checking message-passing distributed protocolsIn Proceedings of the International Conference on Formal Techniques for Networked and Distributed Systems (FORTE), 2010
-
Scrooge: Reducing the costs of fast Byzantine replication in presence of unresponsive replicasIn Proceedings of the 40th IEEE/IFIP International Conference on Dependable Systems & Networks (DSN), 2010
-
Eventually linearizable shared objectsIn Proceedings of the 29th ACM SIGACT-SIGOPS Symposium on Principles of Distributed Computing (PODC), 2010
-
Weak consistency as a last resortIn Proceedings of the 4th International Workshop on Large Scale Distributed Systems and Middleware (LADIS), 2010
2009
-
Abortable fork-linearizable storageIn Proceedings of the 13th International Conference on the Principles of Distributed Systems (OPODIS), 2009
-
Efficient robust storage using secret tokensIn Proceedings of the 11th International Symposium on Stabilization, Safety, and Security of Distributed Systems (SSS), 2009
-
Role-based symmetry reduction of fault-tolerant distributed protocols with language supportIn Proceedings of the International Conference on Formal Engineering Methods (ICFEM), 2009
2008
-
Malicious Fault Characterization Exploiting Honeypot DataIn Proceedings of the 7th IEEE European Dependable Computing Conference (EDCC), 2008
-
Dependable and cost-effective architecture for X-by-wire systems with membership middlewareIn Proceedings of the 32nd FISITA World Automotive Congress 2008, 2008
-
Reducing the costs of large-scale BFT replicationIn Proceedings of the 2nd Workshop on Large-Scale Distributed Systems and Middleware (LADIS), 2008
2007
-
A tunable add-on diagnostic protocol for time-triggered systemsIn Proceedings of the 37th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2007
-
The fail-heterogeneous architectural modelIn Proceedings of the 26th IEEE International Symposium on Reliable Distributed Systems (SRDS), 2007
-
On-line diagnosis and recovery: On the choice and impact of tuning parametersIEEE Transactions on Dependable and Secure Computing, 2007
-
Sustaining Property Verification of Synchronous Dependable Protocols over ImplementationIn Proceedings of the 10th IEEE High Assurance Systems Engineering Symposium (HASE), 2007