Bare-Metal RISC-V + NVDLA SoC for Efficient Deep Learning Inference

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kumar, Vineet, M, Ajay Kumar, Li, Yike, Shanker, Shreejith, John, Deepu
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917087833751552
author Kumar, Vineet
M, Ajay Kumar
Li, Yike
Shanker, Shreejith
John, Deepu
author_facet Kumar, Vineet
M, Ajay Kumar
Li, Yike
Shanker, Shreejith
John, Deepu
contents This paper presents a novel System-on-Chip (SoC) architecture for accelerating complex deep learning models for edge computing applications through a combination of hardware and software optimisations. The hardware architecture tightly couples the open-source NVIDIA Deep Learning Accelerator (NVDLA) to a 32-bit, 4-stage pipelined RISC-V core from Codasip called uRISC_V. To offload the model acceleration in software, our toolflow generates bare-metal application code (in assembly), overcoming complex OS overheads of previous works that have explored similar architectures. This tightly coupled architecture and bare-metal flow leads to improvements in execution speed and storage efficiency, making it suitable for edge computing solutions. We evaluate the architecture on AMD's ZCU102 FPGA board using NVDLA-small configuration and test the flow using LeNet-5, ResNet-18 and ResNet-50 models. Our results show that these models can perform inference in 4.8 ms, 16.2 ms and 1.1 s respectively, at a system clock frequency of 100 MHz.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16095
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bare-Metal RISC-V + NVDLA SoC for Efficient Deep Learning Inference
Kumar, Vineet
M, Ajay Kumar
Li, Yike
Shanker, Shreejith
John, Deepu
Hardware Architecture
This paper presents a novel System-on-Chip (SoC) architecture for accelerating complex deep learning models for edge computing applications through a combination of hardware and software optimisations. The hardware architecture tightly couples the open-source NVIDIA Deep Learning Accelerator (NVDLA) to a 32-bit, 4-stage pipelined RISC-V core from Codasip called uRISC_V. To offload the model acceleration in software, our toolflow generates bare-metal application code (in assembly), overcoming complex OS overheads of previous works that have explored similar architectures. This tightly coupled architecture and bare-metal flow leads to improvements in execution speed and storage efficiency, making it suitable for edge computing solutions. We evaluate the architecture on AMD's ZCU102 FPGA board using NVDLA-small configuration and test the flow using LeNet-5, ResNet-18 and ResNet-50 models. Our results show that these models can perform inference in 4.8 ms, 16.2 ms and 1.1 s respectively, at a system clock frequency of 100 MHz.
title Bare-Metal RISC-V + NVDLA SoC for Efficient Deep Learning Inference
topic Hardware Architecture
url https://arxiv.org/abs/2508.16095