Thomas P. Parnell

65 papers A* 6A 1B 6C 3Journal 34Unranked 15

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	GPU Performance Portability needs Autotuning. CoRR Burkhard Ringlein, Thomas P. Parnell, Radu Stoica
2025	J	`jnl`	The Anatomy of a Triton Attention Kernel. CoRR Burkhard Ringlein, Jan van Lunteren, Radu Stoica, Thomas P. Parnell
2024	J	`jnl`	Accelerating Production LLMs with Combined Token/Embedding Speculators. CoRR Davis Wertheimer, Joshua Rosenkranz, Thomas P. Parnell, Sahil Suneja, Pavithra Ranganathan, Raghu K. Ganti, Mudhakar Srivatsa
2024	A	`conf`	LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services. SC Malgorzata Lazuka, Andreea Anghel, Thomas P. Parnell
2024	J	`jnl`	LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services. CoRR Malgorzata Lazuka, Andreea Anghel, Thomas P. Parnell
2023	C	`conf`	Acceleration of Decision-Tree Ensemble Models on the IBM Telum Processor. ISCAS Nikolaos Papandreou, Jan van Lunteren, Andreea Anghel, Thomas P. Parnell, Martin Petermann, Milos Stanisavljevic, Cédric Lichtenau, Andrew Sica, Dominic Röhm, Elpida Tzortzatos, Haralampos Pozidis
2023	B	`conf`	xCloudServing: Automated ML Serving Across Clouds. CLOUD Malgorzata Lazuka, Andreea Anghel, Parikshit Ram, Haralampos Pozidis, Thomas P. Parnell
2022	B	`conf`	Search-based Methods for Multi-Cloud Configuration. CLOUD Malgorzata Lazuka, Thomas P. Parnell, Andreea Anghel, Haralampos Pozidis
2022	J	`jnl`	Search-based Methods for Multi-Cloud Configuration. CoRR Malgorzata Lazuka, Thomas P. Parnell, Andreea Anghel, Haralampos Pozidis
2021	A*	`conf`	Differentially Private Stochastic Coordinate Descent. AAAI Georgios Damaskinos, Celestine Mendler-Dünner, Rachid Guerraoui, Nikolaos Papandreou, Thomas P. Parnell
2021	J	`jnl`	Efficient Pipelined Execution of CNNs Based on In-Memory Computing and Graph Homomorphism Verification. IEEE Trans. Computers Martino Dazzi, Abu Sebastian, Thomas P. Parnell, Pier Andrea Francese, Luca Benini, Evangelos Eleftheriou
2021	—	`conf`	Towards a General Framework for ML-based Self-tuning Databases. EuroMLSys@EuroSys Thomas Schmied, Diego Didona, Andreas C. Döring, Thomas P. Parnell, Nikolas Ioannou
2020	J	`jnl`	Differentially Private Stochastic Coordinate Descent. CoRR Georgios Damaskinos, Celestine Mendler-Dünner, Rachid Guerraoui, Nikolaos Papandreou, Thomas P. Parnell
2020	J	`jnl`	MixBoost: A Heterogeneous Boosting Machine. CoRR Thomas P. Parnell, Andreea Anghel, Malgorzata Lazuka, Nikolas Ioannou, Sebastian Kurella, Peshal Agarwal, Nikolaos Papandreou, Haralampos Pozidis
2020	—	`conf`	Open Block Characterization and Read Voltage Calibration of 3D QLC NAND Flash. IRPS Nikolaos Papandreou, Haralampos Pozidis, Nikolas Ioannou, Thomas P. Parnell, Roman A. Pletka, Milos Stanisavljevic, Radu Stoica, Sasa Tomic, Patrick Breen, Gary A. Tressler, Aaron Fry, Timothy Fisher, Andrew Walls
2020	A*	`conf`	SnapBoost: A Heterogeneous Boosting Machine. NeurIPS Thomas P. Parnell, Andreea Anghel, Malgorzata Lazuka, Nikolas Ioannou, Sebastian Kurella, Peshal Agarwal, Nikolaos Papandreou, Haralampos Pozidis
2020	J	`jnl`	Tera-scale coordinate descent on GPUs. Future Gener. Comput. Syst. Thomas P. Parnell, Celestine Dünner, Kubilay Atasu, Manolis Sifalakis, Haralampos Pozidis
2020	J	`jnl`	Towards a General Framework for ML-based Self-tuning Databases. CoRR Thomas Schmied, Diego Didona, Andreas C. Döring, Thomas P. Parnell, Nikolas Ioannou
2020	A*	`conf`	Weighted Sampling for Combined Model Selection and Hyperparameter Tuning. AAAI Dimitrios Sarigiannis, Thomas P. Parnell, Haralampos Pozidis
2019	J	`jnl`	5 Parallel Prism: A topology for pipelined implementations of convolutional neural networks using computational memory. CoRR Martino Dazzi, Abu Sebastian, Pier Andrea Francese, Thomas P. Parnell, Luca Benini, Evangelos Eleftheriou
2019	J	`jnl`	Addressing Algorithmic Bottlenecks in Elastic Machine Learning with Chicle. CoRR Michael Kaufmann, Kornilios Kourtis, Celestine Mendler-Dünner, Adrian Schüpbach, Thomas P. Parnell
2019	J	`jnl`	Addressing Interpretability and Cold-Start in Matrix Factorization for Recommender Systems. IEEE Trans. Knowl. Data Eng. Michail Vlachos, Celestine Dünner, Reinhard Heckel, Vassilios G. Vassiliadis, Thomas P. Parnell, Kubilay Atasu
2019	J	`jnl`	Breadth-first, Depth-next Training of Random Forests. CoRR Andreea Anghel, Nikolas Ioannou, Thomas P. Parnell, Nikolaos Papandreou, Celestine Mendler-Dünner, Haris Pozidis
2019	—	`conf`	Characterization and Analysis of Bit Errors in 3D TLC NAND Flash Memory. IRPS Nikolaos Papandreou, Haralampos Pozidis, Thomas P. Parnell, Nikolas Ioannou, Roman A. Pletka, Sasa Tomic, Patrick Breen, Gary A. Tressler, Aaron Fry, Timothy Fisher
2019	J	`jnl`	Learning to Tune XGBoost with XGBoost. CoRR Johanna Sommer, Dimitrios Sarigiannis, Thomas P. Parnell
2019	—	`conf`	Reliability of 3D NAND flash memory with a focus on read voltage calibration from a system aspect. NVMTS Nikolaos Papandreou, Nikolas Ioannou, Thomas P. Parnell, Roman A. Pletka, Milos Stanisavljevic, Radu Stoica, Sasa Tomic, Haralampos Pozidis
2019	J	`jnl`	Sampling Acquisition Functions for Batch Bayesian Optimization. CoRR Alessandro De Palma, Celestine Mendler-Dünner, Thomas P. Parnell, Andreea Anghel, Haralampos Pozidis
2019	A*	`conf`	SySCD: A System-Aware Parallel Coordinate Descent Algorithm. NeurIPS Nikolas Ioannou, Celestine Mendler-Dünner, Thomas P. Parnell
2019	J	`jnl`	SySCD: A System-Aware Parallel Coordinate Descent Algorithm. CoRR Nikolas Ioannou, Celestine Mendler-Dünner, Thomas P. Parnell
2019	J	`jnl`	Weighted Sampling for Combined Model Selection and Hyperparameter Tuning. CoRR Dimitrios Sarigiannis, Thomas P. Parnell, Haris Pozidis
2018	J	`jnl`	Benchmarking and Optimization of Gradient Boosted Decision Tree Algorithms. CoRR Andreea Anghel, Nikolaos Papandreou, Thomas P. Parnell, Alessandro De Palma, Haralampos Pozidis
2018	C	`conf`	Drift-Invariant Detection for Multilevel Phase-Change Memory. ISCAS Milos Stanisavljevic, Thomas Mittelholzer, Nikolaos Papandreou, Thomas P. Parnell, Haralampos Pozidis
2018	J	`jnl`	Elastic CoCoA: Scaling In to Improve Convergence. CoRR Michael Kaufmann, Thomas P. Parnell, Kornilios Kourtis
2018	J	`jnl`	Enabling 3D-TLC NAND Flash in Enterprise Storage Systems. ERCIM News Roman A. Pletka, Nikolas Ioannou, Nikolaos Papandreou, Thomas P. Parnell, Sasa Tomic
2018	—	`conf`	Introduction to ParLearning 2018. IPDPS Workshops Henri E. Bal, Arindam Pal, Azalia Mirhoseini, Thomas P. Parnell
2018	J	`jnl`	Management of Next-Generation NAND Flash to Achieve Enterprise-Level Endurance and Latency Targets. ACM Trans. Storage Roman A. Pletka, Ioannis Koltsidas, Nikolas Ioannou, Sasa Tomic, Nikolaos Papandreou, Thomas P. Parnell, Haralampos Pozidis, Aaron Fry, Tim Fisher
2018	—	`conf`	ParLearning 2018 Invited Talk 3. IPDPS Workshops Thomas P. Parnell
2018	J	`jnl`	Parallel training of linear models without compromising convergence. CoRR Nikolas Ioannou, Celestine Dünner, Kornilios Kourtis, Thomas P. Parnell
2018	A*	`conf`	Snap ML: A Hierarchical Framework for Machine Learning. NeurIPS Celestine Dünner, Thomas P. Parnell, Dimitrios Sarigiannis, Nikolas Ioannou, Andreea Anghel, Gummadi Ravi, Madhusudanan Kandasamy, Haralampos Pozidis
2018	J	`jnl`	Snap ML: A Hierarchical Framework for Machine Learning. CoRR Celestine Dünner, Thomas P. Parnell, Dimitrios Sarigiannis, Nikolas Ioannou, Andreea Anghel, Haralampos Pozidis
2017	—	`conf`	Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems. NIPS Celestine Dünner, Thomas P. Parnell, Martin Jaggi
2017	J	`jnl`	Efficient Use of Limited-Memory Resources to Accelerate Linear Learning. CoRR Celestine Dünner, Thomas P. Parnell, Martin Jaggi
2017	—	`conf`	From random block corruption to privilege escalation: A filesystem attack vector for rowhammer-like attacks. WOOT Anil Kurmus, Nikolas Ioannou, Nikolaos Papandreou, Thomas P. Parnell
2017	B	`conf`	High-Performance Recommender System Training Using Co-Clustering on CPU/GPU Clusters. ICPP Kubilay Atasu, Thomas P. Parnell, Celestine Dünner, Michail Vlachos, Haralampos Pozidis
2017	—	`conf`	Large-Scale Stochastic Learning Using GPUs. IPDPS Workshops Thomas P. Parnell, Celestine Dünner, Kubilay Atasu, Manolis Sifalakis, Haris Pozidis
2017	J	`jnl`	Large-Scale Stochastic Learning using GPUs. CoRR Thomas P. Parnell, Celestine Dünner, Kubilay Atasu, Manolis Sifalakis, Haris Pozidis
2017	J	`jnl`	Linear-Complexity Relaxed Word Mover's Distance with GPU Acceleration. CoRR Kubilay Atasu, Thomas P. Parnell, Celestine Dünner, Manolis Sifalakis, Haralampos Pozidis, Vasileios Vasileiadis, Michail Vlachos, Cesar Berrospi, Abdel Labbi
2017	—	`conf`	Linear-complexity relaxed word Mover's distance with GPU acceleration. IEEE BigData Kubilay Atasu, Thomas P. Parnell, Celestine Dünner, Manolis Sifalakis, Haralampos Pozidis, Vasileios Vasileiadis, Michail Vlachos, Cesar Berrospi, Abdel Labbi
2017	J	`jnl`	Neuromorphic computing with multi-memristive synapses. CoRR Irem Boybat, Manuel Le Gallo, S. R. Nandakumar, Timoleon Moraitis, Thomas P. Parnell, Tomas Tuma, Bipin Rajendran, Yusuf Leblebici, Abu Sebastian, Evangelos Eleftheriou
2017	A*	`conf`	Scalable and Interpretable Product Recommendations via Overlapping Co-Clustering. ICDE Reinhard Heckel, Michail Vlachos, Thomas P. Parnell, Celestine Dünner
2017	J	`jnl`	Temporal correlation detection using computational phase-change memory. CoRR Abu Sebastian, Tomas Tuma, Nikolaos Papandreou, Manuel Le Gallo, Lukas Kull, Thomas P. Parnell, Evangelos Eleftheriou
2017	—	`conf`	Understanding and optimizing the performance of distributed machine learning applications on apache spark. IEEE BigData Celestine Dünner, Thomas P. Parnell, Kubilay Atasu, Manolis Sifalakis, Haralampos Pozidis
2016	J	`jnl`	Capacity of the MLC NAND Flash Channel. IEEE J. Sel. Areas Commun. Thomas P. Parnell, Celestine Dünner, Thomas Mittelholzer, Nikolaos Papandreou
2016	J	`jnl`	High-Performance Distributed Machine Learning using Apache SPARK. CoRR Celestine Dünner, Thomas P. Parnell, Kubilay Atasu, Manolis Sifalakis, Haralampos Pozidis
2016	C	`conf`	Improving the error-floor performance of binary half-product codes. ISITA Thomas Mittelholzer, Thomas P. Parnell, Nikolaos Papandreou, Haralampos Pozidis
2015	—	`conf`	Endurance limits of MLC NAND flash. ICC Thomas P. Parnell, Celestine Dünner, Thomas Mittelholzer, Nikolaos Papandreou, Haralampos Pozidis
2015	J	`jnl`	Enhancing the Reliability of MLC NAND Flash Memory Systems by Read Channel Optimization. ACM Trans. Design Autom. Electr. Syst. Nikolaos Papandreou, Thomas P. Parnell, Haralampos Pozidis, Thomas Mittelholzer, Evangelos Eleftheriou, Charles Camp, Thomas Griffin, Gary A. Tressler, Andrew Walls
2015	—	`conf`	Performance of cell-to-cell interference mitigation in 1y-nm MLC flash memory. NVMTS Thomas P. Parnell, Nikolaos Papandreou, Thomas Mittelholzer, Haralampos Pozidis
2015	B	`conf`	Symmetry-based subproduct codes. ISIT Thomas Mittelholzer, Thomas P. Parnell, Nikolaos Papandreou, Haralampos Pozidis
2014	B	`conf`	Modelling of the threshold voltage distributions of sub-20nm NAND flash memory. GLOBECOM Thomas P. Parnell, Nikolaos Papandreou, Thomas Mittelholzer, Haralampos Pozidis
2014	—	`conf`	Using adaptive read voltage thresholds to enhance the reliability of MLC NAND flash memory systems. ACM Great Lakes Symposium on VLSI Nikolaos Papandreou, Thomas P. Parnell, Haralampos Pozidis, Thomas Mittelholzer, Evangelos Eleftheriou, Charles Camp, Thomas Griffin, Gary A. Tressler, Andrew Walls
2011	J	`jnl`	Information Storage and Retrieval for Probe Storage using Optical Diffraction Patterns CoRR Joost Van Honschoten, Henri de Jong, Wabe W. Koelmans, Thomas P. Parnell, Oleg V. Zaboronski
2011	J	`jnl`	Information theory of massively parallel probe storage channels CoRR Oliver Hambrey, Thomas P. Parnell, Oleg V. Zaboronski
2009	B	`conf`	Performance Evaluation of the Probe Storage Channel. GLOBECOM Thomas P. Parnell, Haralampos Pozidis, Oleg V. Zaboronski
2008	—	`conf`	Forward Message Passing Detector for Probe Storage. ICC Thomas P. Parnell, Haralampos Pozidis, Oleg V. Zaboronski