@article{gajjar_kashyap_aysu_franzon_dey_cheng_2022, title={FAXID: FPGA-Accelerated XGBoost Inference for Data Centers using HLS}, ISSN={["2576-2621"]}, url={http://dx.doi.org/10.1109/fccm53951.2022.9786085}, DOI={10.1109/FCCM53951.2022.9786085}, abstractNote={Advanced ensemble trees have proven quite effective in providing real-time predictions against ransomware detection, medical diagnosis, recommendation engines, fraud detection, failure predictions, crime risk, to name a few. Especially, XGBoost, one of the most prominent and widely used decision trees, has gained popularity due to various optimizations on gradient boosting framework that provides increased accuracy for classification and regression problems. XGBoost’s ability to train relatively faster, handling missing values, flexibility and parallel processing make it a better candidate to handle data center workload. Today’s data centers with enormous Input/Output Operations per Second (IOPS) demand a real-time accelerated inference with low latency and high throughput because of significant data processing due to applications such as ransomware detection or fraud detection.This paper showcases an FPGA-based XGBoost accelerator designed with High-Level Synthesis (HLS) tools and design flow accelerating binary classification inference. We employ Alveo U50 and U200 to demonstrate the performance of the proposed design and compare it with existing state-of-the-art CPU (Intel Xeon E5-2686 v4) and GPU (Nvidia Tensor Core T4) implementations with relevant datasets. We show a latency speedup of our proposed design over state-of-art CPU and GPU implementations, including energy efficiency and cost-effectiveness. The proposed accelerator is up to 65.8x and 5.3x faster, in terms of latency than CPU and GPU, respectively. The Alveo U50 is a more cost-effective device, and the Alveo U200 stands out as more energy-efficient.}, journal={2022 IEEE 30TH INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE CUSTOM COMPUTING MACHINES (FCCM 2022)}, publisher={IEEE}, author={Gajjar, Archit and Kashyap, Priyank and Aysu, Aydin and Franzon, Paul and Dey, Sumon and Cheng, Chris}, year={2022}, pages={113–121} }
 @article{kashyap_gajjar_choi_wong_baron_wu_cheng_franzon_2022, title={RxGAN: Modeling High-Speed Receiver through Generative Adversarial Networks}, url={http://dx.doi.org/10.1145/3551901.3556480}, DOI={10.1145/3551901.3556480}, abstractNote={Creating models for modern high-speed receivers using circuit-level simulations is costly, as it requires computationally expensive simulations and upwards of months to finalize a model. Added to this is that many models do not necessarily agree with the final hardware they are supposed to emulate. Further, these models are complex due to the presence of various filters, such as a decision feedback equalizer (DFE) and continuous-time linear equalizer (CTLE), which enable the correct operation of the receiver. Other data-driven approaches tackle receiver modeling through multiple models to account for as many configurations as possible. This work proposes a data-driven approach using generative adversarial training to model a real-world receiver with varying DFE and CTLE configurations while handling different channel conditions and bitstreams. The approach is highly accurate as the eye height and width are within 1.59% and 1.12% of the ground truth. The horizontal and vertical bathtub curves match the ground truth and correlate to the ground truth bathtub curves.}, journal={MLCAD '22: PROCEEDINGS OF THE 2022 ACM/IEEE 4TH WORKSHOP ON MACHINE LEARNING FOR CAD (MLCAD)}, publisher={ACM}, author={Kashyap, Priyank and Gajjar, Archit and Choi, Yongjin and Wong, Chau-Wai and Baron, Dror and Wu, Tianfu and Cheng, Chris and Franzon, Paul}, year={2022}, pages={167–172} }