2025

Haris, Jude and Cano, Jose ORCID: https://orcid.org/0000-0002-2243-389X (2025) Accelerating Transposed Convolutions on FPGA-based Edge Devices. 35th International Conference on Field-Programmable Logic and Applications (FPL) 2025, Leiden, The Netherlands, 1-5 Sept 2025. (Accepted for Publication)

Haris, Jude and Cano, Jose ORCID: https://orcid.org/0000-0002-2243-389X (2025) SECDA Design Suite: Efficient Hardware-Software Co-Design of DNN Accelerator. 4th Workshop on Open-Source Computer Architecture Research (OSCAR) at ISCA 2025, Tokyo, Japan, 21 June 2025. (Accepted for Publication)

Haris, Jude and Cano, Jose ORCID: https://orcid.org/0000-0002-2243-389X (2025) F-BFQ: Flexible Block Floating-Point Quantization Accelerator for LLMs. New Approaches for Addressing the Computing Requirements of LLMs and GNSs LG-ARC’2025 Workshop @ ISCA 2025, Tokyo, Japan, 22 June 2025. (Accepted for Publication)

2024

Saha, Rappy ORCID: https://orcid.org/0000-0001-9581-0193, Haris, Jude and Cano, José ORCID: https://orcid.org/0000-0002-2243-389X (2024) Accelerating PoT Quantization on Edge Devices. In: 31st IEEE International Conference on Electronics, Circuits and Systems, Nancy, France, 18-20 Nov 2024, ISBN 9798350377200 (doi: 10.1109/ICECS61496.2024.10849093)

Haris, Jude, Saha, Rappy ORCID: https://orcid.org/0000-0001-9581-0193, Hu, Wenhao and Cano, José ORCID: https://orcid.org/0000-0002-2243-389X (2024) Designing Efficient LLM Accelerators for Edge Devices. ARC-LG: New Approaches for Addressing the Computing Requirements of LLMs and GNNs, Buenos Aires, Argentina, 30 Jun 2024.

Haris, Jude, Agostini, Nicolas Bohm, Tumeo, Antonino, Kaeli, David and Cano, Jose ORCID: https://orcid.org/0000-0002-2243-389X (2024) Data Transfer Optimizations for Host-CPU and Accelerators in AXI4MLIR. 5th Compilers for Machine Learning Workshop (C4ML), at CGO 2024, Edinburgh, UK, 03 March 2024. (doi: 10.48550/arXiv.2402.19184)

2023

Haris, Jude, Gibson, Perry, Cano, José ORCID: https://orcid.org/0000-0002-2243-389X, Bohm Agostini, Nicolas and Kaeli, David (2023) SECDA-TFLite: a toolkit for efficient development of FPGA-based DNN accelerators for edge inference. Journal of Parallel and Distributed Computing, 173, pp. 140-151. (doi: 10.1016/j.jpdc.2022.11.005)

Articles

Haris, Jude, Gibson, Perry, Cano, José ORCID: https://orcid.org/0000-0002-2243-389X, Bohm Agostini, Nicolas and Kaeli, David (2023) SECDA-TFLite: a toolkit for efficient development of FPGA-based DNN accelerators for edge inference. Journal of Parallel and Distributed Computing, 173, pp. 140-151. (doi: 10.1016/j.jpdc.2022.11.005)

Conference or Workshop Item

Haris, Jude and Cano, Jose ORCID: https://orcid.org/0000-0002-2243-389X (2025) Accelerating Transposed Convolutions on FPGA-based Edge Devices. 35th International Conference on Field-Programmable Logic and Applications (FPL) 2025, Leiden, The Netherlands, 1-5 Sept 2025. (Accepted for Publication)

Haris, Jude and Cano, Jose ORCID: https://orcid.org/0000-0002-2243-389X (2025) SECDA Design Suite: Efficient Hardware-Software Co-Design of DNN Accelerator. 4th Workshop on Open-Source Computer Architecture Research (OSCAR) at ISCA 2025, Tokyo, Japan, 21 June 2025. (Accepted for Publication)

Haris, Jude and Cano, Jose ORCID: https://orcid.org/0000-0002-2243-389X (2025) F-BFQ: Flexible Block Floating-Point Quantization Accelerator for LLMs. New Approaches for Addressing the Computing Requirements of LLMs and GNSs LG-ARC’2025 Workshop @ ISCA 2025, Tokyo, Japan, 22 June 2025. (Accepted for Publication)

Haris, Jude, Saha, Rappy ORCID: https://orcid.org/0000-0001-9581-0193, Hu, Wenhao and Cano, José ORCID: https://orcid.org/0000-0002-2243-389X (2024) Designing Efficient LLM Accelerators for Edge Devices. ARC-LG: New Approaches for Addressing the Computing Requirements of LLMs and GNNs, Buenos Aires, Argentina, 30 Jun 2024.

Haris, Jude, Agostini, Nicolas Bohm, Tumeo, Antonino, Kaeli, David and Cano, Jose ORCID: https://orcid.org/0000-0002-2243-389X (2024) Data Transfer Optimizations for Host-CPU and Accelerators in AXI4MLIR. 5th Compilers for Machine Learning Workshop (C4ML), at CGO 2024, Edinburgh, UK, 03 March 2024. (doi: 10.48550/arXiv.2402.19184)

Conference Proceedings

Saha, Rappy ORCID: https://orcid.org/0000-0001-9581-0193, Haris, Jude and Cano, José ORCID: https://orcid.org/0000-0002-2243-389X (2024) Accelerating PoT Quantization on Edge Devices. In: 31st IEEE International Conference on Electronics, Circuits and Systems, Nancy, France, 18-20 Nov 2024, ISBN 9798350377200 (doi: 10.1109/ICECS61496.2024.10849093)