| Bit-tactical: A software/hardware approach to exploiting value and bit sparsity in neural networks A Delmas Lascorz, P Judd, DM Stuart, Z Poulos, M Mahmoud, S Sharify, ... Proceedings of the Twenty-Fourth International Conference on Architectural …, 2019 | 187* | 2019 |
| Laconic deep learning inference acceleration S Sharify, AD Lascorz, M Mahmoud, M Nikolic, K Siu, DM Stuart, Z Poulos, ... Proceedings of the 46th International Symposium on Computer Architecture …, 2019 | 157 | 2019 |
| Shapeshifter: Enabling fine-grain data width adaptation in deep learning AD Lascorz, S Sharify, I Edo, DM Stuart, OM Awad, P Judd, M Mahmoud, ... Proceedings of the 52nd Annual IEEE/ACM International Symposium on …, 2019 | 51 | 2019 |
| Bitpruning: Learning bitlengths for aggressive and accurate quantization M Nikolić, GB Hacene, C Bannon, AD Lascorz, M Courbariaux, OM Awad, ... 2024 IEEE International Symposium on Circuits and Systems (ISCAS), 1-5, 2024 | 41 | 2024 |
| Characterizing sources of ineffectual computations in deep learning networks M Nikolić, M Mahmoud, A Moshovos, Y Zhao, R Mullins 2019 IEEE International Symposium on Performance Analysis of Systems and …, 2019 | 32 | 2019 |
| Neural network accelerator A Moshovos, AD Lascorz, Z Poulos, DM Stuart, P Judd, S Sharify, ... US Patent App. 16/968,678, 2021 | 29 | 2021 |
| DPRed: Making typical activation and weight values matter in deep learning computing A Delmas, S Sharify, P Judd, K Siu, M Nikolic, A Moshovos arXiv preprint arXiv:1804.06732, 2018 | 26* | 2018 |
| Boveda: Building an on-chip deep learning memory hierarchy brick by brick I Edo Vivancos, S Sharify, D Ly-Ma, A Abdelhadi, C Bannon, M Nikolic, ... Proceedings of Machine Learning and Systems 3, 1-20, 2021 | 12 | 2021 |
| Atalanta: A bit is worth a “thousand” tensor values AD Lascorz, M Mahmoud, AH Zadeh, M Nikolic, K Ibrahim, C Giannoula, ... Proceedings of the 29th ACM International Conference on Architectural …, 2024 | 11 | 2024 |
| Schrödinger's FP: Dynamic Adaptation of Floating-Point Containers for Deep Learning Training M Nikolić, ET Sanchez, J Wang, AH Zadeh, M Mahmoud, A Abdelhadi, ... arXiv preprint arXiv:2204.13666, 2022 | 6* | 2022 |
| Accelerating Image-Sensor-Based Deep Learning Applications M Mahmoud, DM Stuart, Z Poulos, AD Lascorz, P Judd, S Sharify, ... IEEE Micro 39 (5), 26-35, 2019 | 2 | 2019 |
| Identifying and Exploiting Ineffectual Computations to Enable Hardware Acceleration of Deep Learning A Moshovos, J Albericio, P Judd, A Delmas, S Sharify, M Mahmoud, ... 2018 16th IEEE International New Circuits and Systems Conference (NEWCAS …, 2018 | 2 | 2018 |
| Evaluating training acceleration through selective workload skipping: Methods and benchmarks K Ibrahim, M Nikolic, N Giamblanco, AH Zadeh, ET Sanchez, A Moshovos 13th International Conference on Human Interaction and Emerging Technologies …, 2025 | 1 | 2025 |
| Every Bit Matters: A Hardware/Software Approach for Enabling More Powerful Machine Learning Models ET Sanchez, M Nikolić, K Ibrahim, AD Lascorz, AH Zadeh, J Wang, ... 2024 58th Asilomar Conference on Signals, Systems, and Computers, 1235-1240, 2024 | 1 | 2024 |
| Building an on-chip deep learning memory hierarchy brick by brick: late breaking results IE Vivancos, S Sharify, M Nikolic, C Bannon, M Mahmoud, AD Lascorz, ... Proceedings of the 57th ACM/EDAC/IEEE Design Automation Conference, 1-2, 2020 | 1 | 2020 |
| Late Breaking Results: Building an On-Chip Deep Learning Memory Hierarchy Brick by Brick IE Vivancos, S Sharify, M Nikolic, C Bannon, M Mahmoud, AD Lascorz, ... 2020 57th ACM/IEEE Design Automation Conference (DAC), 1-2, 2020 | 1 | 2020 |
| Learning Efficient Datatypes for Deep Neural Network Training and Inference M Nikolić University of Toronto (Canada), 2025 | | 2025 |
Andreas MoshovosProfessor, Electrical and Computer Engineering, University of TorontoVerified email at utoronto.ca
