paper-with-me

홈 › Papers

HYDRA: Hybrid Data Multiplexing and Run-time Layer Configurable DNN Accelerator

2024-09-08 · Sonu Kumar, Komal Gupta, Gopal Raut, Mukul Lokhande, Santosh Kumar Vishvakarma

Deep neural networks (DNNs) offer plenty of challenges in executing efficient computation at edge nodes, primarily due to the huge hardware resource demands. The article proposes HYDRA, hybrid data multiplexing, and runtime layer configurable DNN accelerators to overcome the drawbacks. The work proposes a layer-multiplexed approach, which further reuses a single activation function within the execution of a single layer with improved Fused-Multiply-Accumulate (FMA). The proposed approach works in iterative mode to reuse the same hardware and execute different layers in a configurable fashion. The proposed architectures achieve reductions over 90% of power consumption and resource utilization improvements of state-of-the-art works, with 35.21 TOPSW. The proposed architecture reduces the area overhead (N-1) times required in bandwidth, AF and layer architecture. This work shows HYDRA architecture supports optimal DNN computations while improving performance on resource-constrained edge devices.

📄 PDF Abstract BibTeX arXiv:2409.04976

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Hydra 설명 없음

Similar Papers 제목 키워드 기반

HydraWave: Multi-Group Multicast Hybrid Precoding and Low-Latency Scheduling for Ubiquitous Industry 4.0 mmWave Communication

2020-02-03 · Luis F. Abanto-Leon, Matthias Hollick, Gek Hong Sim

Industry 4.0 anticipates massive interconnectivity of industrial devices (e.g., sensors, actuators) to support factory automation and production. Due to the rigidity of wired connections to harmonize with automation, wir…

Robust DesignScheduling

HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization

2026-06-18 · Zhentao Tan, Wei Chen, Jingyi Shen, Yao Liu 외 arxiv

The quadratic complexity of attention poses a critical bottleneck for long-context processing, spurring interest in hybrid attention designs. Most open-source hybrid models adopt a layer-wise strategy. Yet, prior work ha…

Tydra: An Efficient Hybrid Model for Tabular Data

2026-08-21 · Mieszko Komisarczyk, Saurabh Mathur, Maurice Kraus, Sriraam Natarajan 외 arxiv

Transformer-based tabular foundation models such as TabPFN achieve strong predictive performance but incur quadratic computational cost with context length. On the other hand, subquadratic SSM-based alternatives such as …

Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation

2024-09-16 · Minghan Chen, Guikun Chen, Wenguan Wang, Yi Yang

DETR introduces a simplified one-stage framework for scene graph generation (SGG). However, DETR-based SGG models face two challenges: i) Sparse supervision, as each image typically contains fewer than 10 relation annota…

Graph GenerationRelationScene Graph Generation

HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning

2024-09-30 · Momin Ahmad Khan, Yasra Chandio, Fatima Muhammad Anwar

Data heterogeneity among Federated Learning (FL) users poses a significant challenge, resulting in reduced global model performance. The community has designed various techniques to tackle this issue, among which Knowled…

Federated LearningKnowledge DistillationModel Poisoning