| Gslice: controlled spatial sharing of gpus for a scalable inference platform A Dhakal, SG Kulkarni, KK Ramakrishnan Proceedings of the 11th ACM Symposium on Cloud Computing, 492-506, 2020 | 83 | 2020 |
| Machine learning at the network edge for automated home intrusion monitoring A Dhakal, KK Ramakrishnan 2017 IEEE 25th International Conference on Network Protocols (ICNP), 1-6, 2017 | 18 | 2017 |
| Machine learning at the edge: Efficient utilization of limited cpu/gpu resources by multiplexing A Dhakal, SG Kulkarni, KK Ramakrishnan 2020 IEEE 28th International Conference on Network Protocols (ICNP), 1-6, 2020 | 15 | 2020 |
| Netml: An nfv platform with efficient support for machine learning applications A Dhakal, KK Ramakrishnan 2019 IEEE Conference on Network Softwarization (NetSoft), 396-404, 2019 | 15 | 2019 |
| SLAM-share: visual simultaneous localization and mapping for real-time multi-user augmented reality A Dhakal, X Ran, Y Wang, J Chen, KK Ramakrishnan Proceedings of the 18th International Conference on emerging Networking …, 2022 | 13 | 2022 |
| ECML: Improving efficiency of machine learning in edge clouds A Dhakal, SG Kulkarni, KK Ramakrishnan 2020 IEEE 9th International Conference on Cloud Networking (CloudNet), 1-6, 2020 | 9 | 2020 |
| Spatial Sharing of GPU for Autotuning DNN models A Dhakal, J Cho, SG Kulkarni, KK Ramakrishnan, P Sharma arXiv preprint arXiv:2008.03602, 2020 | 6 | 2020 |
| Primitives enhancing gpu runtime support for improved dnn performance A Dhakal, SG Kulkarni, KK Ramakrishnan 2021 IEEE 14th International Conference on Cloud Computing (CLOUD), 53-64, 2021 | 3 | 2021 |
| Kernel-as-a-Service: A serverless programming model for heterogeneous hardware accelerators T Pfandzelter, A Dhakal, E Frachtenberg, SR Chalamalasetti, D Emmot, ... Proceedings of the 24th International Middleware Conference, 192-206, 2023 | 2 | 2023 |
| Fine-grained heterogeneous execution framework with energy aware scheduling G Rattihalli, N Hogade, A Dhakal, E Frachtenberg, RPH Enriquez, P Bruel, ... 2023 IEEE 16th International Conference on Cloud Computing (CLOUD), 35-44, 2023 | 2 | 2023 |
| D-STACK: High Throughput DNN Inference by Effective Multiplexing and Spatio-Temporal Scheduling of GPUs A Dhakal, SG Kulkarni, KK Ramakrishnan arXiv preprint arXiv:2304.13541, 2023 | 2 | 2023 |
| Slice-tune: A system for high performance dnn autotuning A Dhakal, KK Ramakrishnan, SG Kulkarni, P Sharma, J Cho Proceedings of the 23rd ACM/IFIP International Middleware Conference, 228-240, 2022 | 2 | 2022 |
| Predicting Heterogeneity and Serverless Principles of Converged High-Performance Computing, Artificial Intelligence, and Workflows P Bruel, SR Chalamalasetti, A Dhakal, E Frachtenberg, N Hogade, ... Computer 57 (1), 136-144, 2024 | 1 | 2024 |
| Fine-grained accelerator partitioning for Machine Learning and Scientific Computing in Function as a Service Platform A Dhakal, P Raith, L Ward, RP Hong Enriquez, G Rattihalli, K Chard, ... Proceedings of the SC'23 Workshops of The International Conference on High …, 2023 | 1 | 2023 |
| Estimating energy-efficiency in quantum optimization algorithms RPH Enriquez, RM Badia, B Chapman, K Bresniker, A Dhakal, ... Cray User Group Conference Proceedings, 2023 | 1 | 2023 |
| Quantum optimization algorithms: Energetic implications RP Hong Enriquez, RM Badia, B Chapman, K Bresniker, S Pakin, ... Concurrency and Computation: Practice and Experience, e8121, 2024 | | 2024 |
| Cooperative Design of Machine Learning and GPU-Based Systems for Inference A Dhakal University of California, Riverside, 2022 | | 2022 |
K. K. RamakrishnanDistinguished Professor of Computer Science and Engineering, University of California, RiversideVerified email at cs.ucr.edu
