| Systems and methods for reducing data movement during convolution operations in artificial neural networks EKA Zadeh, M Schatz, KN Nair, Y Hao, AU Diril, R Komuravelli US Patent 11,699,081, 2023 | | 2023 |
| Mtia: First generation silicon targeting meta's recommendation systems A Firoozshahian, J Coburn, R Levenstein, R Nattoji, A Kamath, O Wu, ... Proceedings of the 50th Annual International Symposium on Computer …, 2023 | 13 | 2023 |
| Systems and methods for reducing power consumption of convolution operations of artificial neural networks KN Nair, AU Diril, Y Hao, TM Ulrich, R Komuravelli, EKA Zadeh, M Schatz US Patent 11,599,181, 2023 | 4 | 2023 |
| Grouped convolution using point-to-point connected channel convolution engines R Komuravelli, KN Nair, AU Diril, EKA Zadeh, Y Hao, M Schatz, TM Ulrich, ... US Patent 11,580,192, 2023 | 1 | 2023 |
| High throughput matrix processor with support for concurrently processing multiple matrices KN Nair, O Wu, EKA Zadeh, AU Diril, TM Ulrich, Y Hao, R Komuravelli, ... US Patent App. 17/855,391, 2023 | | 2023 |
| Mapping convolution to a channel convolution engine KN Nair, R Komuravelli, AU Diril, EKA Zadeh, Y Hao, M Schatz, TM Ulrich, ... US Patent 11,537,865, 2022 | 4 | 2022 |
| Mapping convolution to a partition channel convolution engine KN Nair, R Komuravelli, AU Diril, EKA Zadeh, Y Hao, M Schatz, TM Ulrich, ... US Patent 11,520,853, 2022 | 7 | 2022 |
| Support for different matrix multiplications by selecting adder tree intermediate results Y Hao, KN Nair, EKA Zadeh, R Komuravelli, AU Diril, TM Ulrich US Patent 11,520,854, 2022 | 2 | 2022 |
| Systems and methods for handling padding regions in convolution operations KN Nair, EK Ardestani, M Schatz, Y Hao, AU Diril, R Komuravelli US Patent 11,501,147, 2022 | | 2022 |
| Pipelined pointwise convolution using per-channel convolution operations R Komuravelli, KN Nair, AU Diril, EKA Zadeh, Y Hao, M Schatz, TM Ulrich, ... US Patent 11,443,013, 2022 | 1 | 2022 |
| High throughput matrix processor with support for concurrently processing multiple matrices KN Nair, O Wu, EKA Zadeh, AU Diril, TM Ulrich, Y Hao, R Komuravelli, ... US Patent 11,409,838, 2022 | 9 | 2022 |
| Understanding data storage and ingestion for large-scale deep recommendation model training: Industrial product M Zhao, N Agarwal, A Basant, B Gedik, S Pan, M Ozdal, R Komuravelli, ... Proceedings of the 49th annual international symposium on computer …, 2022 | 63 | 2022 |
| Software-hardware co-design for fast and scalable training of deep learning recommendation models D Mudigere, Y Hao, J Huang, Z Jia, A Tulloch, S Sridharan, X Liu, ... Proceedings of the 49th Annual International Symposium on Computer …, 2022 | 89 | 2022 |
| Floating point multiply hardware using decomposed component numbers KN Nair, AR Kadkol, EKA Zadeh, O Wu, Y Hao, TM Ulrich, R Komuravelli US Patent App. 17/506,506, 2022 | | 2022 |
| Learning to collide: Recommendation system model compression with learned hash functions B Ghaemmaghami, M Ozdal, R Komuravelli, D Korchev, D Mudigere, ... arXiv preprint arXiv:2203.15837, 2022 | 6 | 2022 |
| Hardware for floating-point arithmetic in multiple formats TM Ulrich, AU Diril, KN Nair, Z Wang, R Komuravelli US Patent 11,275,560, 2022 | 3 | 2022 |
| Floating point multiply hardware using decomposed component numbers KN Nair, AR Kadkol, EKA Zadeh, O Wu, Y Hao, TM Ulrich, R Komuravelli US Patent 11,188,303, 2021 | 4 | 2021 |
| Mapping convolution to connected processing elements using distributed pipelined separable convolution operations R Komuravelli, KN Nair, AU Diril, EKA Zadeh, Y Hao, M Schatz, TM Ulrich, ... US Patent App. 16/855,927, 2021 | | 2021 |
| High-performance, distributed training of large-scale deep learning recommendation models D Mudigere, Y Hao, J Huang, A Tulloch, S Sridharan, X Liu, M Ozdal, ... arXiv preprint arXiv:2104.05158, 2021 | 33 | 2021 |
| M. khorashadi, P D Mudigere, Y Hao, J Huang, Z Jia, A Tulloch, S Sridharan, X Liu, ... Bhattacharya, P. Lapukhov, M. Naumov, L. Qiao, M. Smelyanskiy, B. Jia, and V …, 2021 | 42 | 2021 |
