FPGA-Accelerated RISC-V ISA Extensions for Efficient Neural Network Inference on Edge Devices
By Arya Parameshwara, Santosh Hanamappa Mokashi
Department of Electronics and Communication, PES University, Bangalore, India

Abstract
Edge AI deployment faces critical challenges balanc ing computational performance, energy efficiency, and resource constraints. This paper presents FPGA-accelerated RISC-V instruction set architecture (ISA) extensions for efficient neural network inference on resource-constrained edge devices. We introduce a custom RISC-V core with four novel ISA extensions (FPGA.VCONV, FPGA.GEMM, FPGA.RELU, FPGA.CUSTOM) and integrated neural network accelerators, implemented and validated on the Xilinx PYNQ-Z2 platform.
The complete system achieves 2.14× average latency speedup and 49.1% energy reduction versus an ARM Cortex-A9 software baseline across four benchmark models (MobileNet V2, ResNet 18, EfficientNet Lite, YOLO Tiny). Hardware implementation closes timing with +12.793ns worst negative slack at 50MHz while using 0.43% LUTs and 11.4% BRAM for the base core and 38.8% DSPs when accelerators are active. Hardware verification confirms successful FPGA deployment with verified 64KB BRAM memory interface and AXI interconnect functionality.
All performance metrics are obtained from physical hardware measurements. This work establishes a reproducible framework for ISA-guided FPGA acceleration that complements fixed function ASICs by trading peak performance for programmability.
Index Terms — RISC-V, ISA extensions, FPGA acceleration, neural networks, edge computing, energy efficiency, hardware software co-design
To read the full article, click here
Related Semiconductor IP
- 64-Bit 8-stage superscalar RISC-V processor
- Multi-core capable RISC-V processor with vector extensions
- 32 Bit - Embedded RISC-V Processor Core
- ARC-V RHX-100 dual-issue, 32-bit single-core RISC-V processor for real-time applications
- ARC-V RMX-100 ultra-low power 32-bit RISC-V processor for embedded applications
Related Articles
- VitaLLM: A Versatile and Tiny Accelerator for Mixed-Precision LLM Inference on Edge Devices
- A Framework for Accelerating Transformer Inference on RISC-V for Edge AI
- MultiVic: A Time-Predictable RISC-V Multi-Core Processor Optimized for Neural Network Inference
- VMXDOTP: A RISC-V Vector ISA Extension for Efficient Microscaling (MX) Format Acceleration
Latest Articles
- An Agentic Python Framework for LLM-Driven UVM Testbench Synthesis with Closed-Loop Compiler Feedback
- Reconfiguring System-Level Protection Through Bounded Delegation in RISC-V MCUs
- SkipLane: Write-Once, Conflict-Free Accumulation for Zero-Skipping CNN Engines on FPGAs
- Priority-Aware Deficit Round Robin for AXI4 Bandwidth Fairness in ASAP-7nm Process
- Atik: A Shared-Mesh Transformer Accelerator for RISC-V