Bare-Metal RISC-V + NVDLA SoC for Efficient Deep Learning Inference
By Vineet Kumar 1, Ajay Kumar M 1, Yike Li 1, Shreejith Shanker 2, Deepu John 1
1 School of Electrical and Electronic Engineering, University College Dublin, Ireland,
2 Department of Electronic and Electrical Engineering, Trinity College Dublin, Ireland
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 µRISC_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.
Index Terms — System-on-chip, RISC-V, NVDLA, Hardware accelerators, Deep learning, FPGA
To read the full article, click here
Related Semiconductor IP
- 64 bit RISC-V Multicore Processor with 2048-bit VLEN and AMM
- RISC-V AI Acceleration Platform - Scalable, standards-aligned soft chiplet IP
- 32 bit RISC-V Multicore Processor with 256-bit VLEN and AMM
- All-In-One RISC-V NPU
- ISO26262 ASIL-B/D Compliant 32-bit RISC-V Core
Related White Papers
- A RISC-V Multicore and GPU SoC Platform with a Qualifiable Software Stack for Safety Critical Systems
- Boosting RISC-V SoC performance for AI and ML applications
- Efficient Hardware-Assisted Heap Memory Safety for Embedded RISC-V Systems
- Accelerating SoC Evolution With NoC Innovations Using NoC Tiling for AI and Machine Learning
Latest White Papers
- Redefining Speed: How FPGAs are shaping the future of high-frequency trading
- Bare-Metal RISC-V + NVDLA SoC for Efficient Deep Learning Inference
- Akida Exploits Sparsity For Low Power in Neural Networks
- A new era of chip-level DRC debug: Fast, scalable and AI-driven
- Physical Design Exploration of a Wire-Friendly Domain-Specific Processor for Angstrom-Era Nodes