Dana Diaconu

Dana Diaconu

Auto-generated profile, based on publicly available information

Dana Diaconu

Northeastern University, Boston, MA, USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 January 2025
Verified
Conference Paper
Open access
YXYanyue Xie
Yanyue Xie
ZLZhengang Li
Zhengang Li
DDDana Diaconu
Dana Diaconu
SHSuranga Handagala
Suranga Handagala
MLMiriam Leeser
Miriam Leeser
XLXue Lin
Xue Lin
For FPGA-based neural network accelerators, digital signal processing (DSP) blocks have traditionally been the cornerstone for handling multiplications. This paper introduces LUTMUL, which harnesses the potential of look-up tables (LUTs) for performing multiplications. The availability of LUTs typically outnumbers that of DSPs by a factor of 100, offering a significant computational advantage. By exploiting this advantage of LUTs, our method demonstrates a potential boost in the performance of FPGA-based neural network accelerators with a reconfigurable dataflow architecture. Our approach challenges the conventional peak performance on DSP-based accelerators and sets a new benchmark for efficient neural network inference on FPGAs. Experimental results demonstrate that our design achieves the best inference speed among all FPGA-based accelerators, achieving a throughput of 1627 images per second and maintaining a top-1 accuracy of 70.95% on the ImageNet dataset.

8 December 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
DDDana Diaconu
Dana Diaconu
XLXue Lin
Xue Lin
MBMichaela Blott
Michaela Blott
MLMiriam Leeser
Miriam Leeser
3D Convolutional Neural Networks (3D CNNs) can outperform 2D CNNs on several tasks, including action recognition, video captioning, abnormal event detection, and medical image interpretation. Compared to 2D CNNs, 3D CNNs have a larger number of parameters and higher computational complexity. For this reason, researchers have focused on designing efficient 3D CNN architectures and hardware accelerators. The purpose of this survey is to serve as a guide to recent work on 3D CNNs for action recognition with a focus on FPGA-based accelerators and hardware-aware algorithmic optimizations. We provide an overview of the state-of-the-art in 3D CNN architectures as well as the action recognition datasets used for training and testing the architectures. A performance comparison of 2D versus 3D CNNs on two datasets (Sports-1M and UCF101) is included. We explore the designs of FPGA-based accelerators and compare them in terms of achieved throughput, resource utilization, and power. We survey current methods of optimization for 3D CNN architectures, which are meant to reduce the number of parameters and the memory requirements and to facilitate their deployment on FPGAs. Finally, we highlight current challenges and potential areas of improvement in acceleration of 3D CNNs on FPGA platforms.

25 December 2024 in Computing in Science & Engineering
Verified
Journal Article
Open access
MLMiriam Leeser
Miriam Leeser
SHSuranga Handagala
Suranga Handagala
DDDana Diaconu
Dana Diaconu
ZHZhaoyang Han
Zhaoyang Han
MZMichael Zink
Michael Zink
The Open Cloud Testbed (OCT) has the goal to provide bare-metal resources to the systems research community. In contrast to other infrastructures that offer such resources, the field-programmable gate arrays (FPGAs) in OCT expose their network interface directly to the experimenter, unlocking new possibilities for researchers focusing on cloud application acceleration and data center disaggregation. OCT provides two models for programming network-attached FPGAs. The first grants users direct access to the network interface. The features of this approach are demonstrated with examples that make use of User Datagram Protocol (UDP) and Transmission Control Protocol stacks. An example involving UDP is highlighted that facilitates a distributed machine learning (ML) application. The second model allows FPGA network interface programming via Programming Protocol-Independent Packet Processors, thus providing the FPGA with smart network interface card capabilities. In addition, this article outlines future research directions into network-attached FPGAs, including the security of such systems.