Skip to content

🖥️ A small, customizable and extensible MCU-class 32-bit RISC-V soft-core CPU and microcontroller-like SoC written in platform-independent VHDL.

License

Notifications You must be signed in to change notification settings

stnolting/neorv32

NEORV32

The NEORV32 RISC-V Processor

datasheet (pdf) datasheet (html) userguide (pdf) userguide (html) doxygen

  1. Overview
  2. Features
  3. FPGA Implementation Results
  4. Performance
  5. Getting Started 🚀

1. Overview

neorv32 Overview

The NEORV32 Processor is a customizable microcontroller-like system on chip (SoC) built around the NEORV32 RISC-V CPU that is written in platform-independent VHDL. The processor is intended as auxiliary controller in larger SoC designs or as tiny and customized microcontroller that even fits into a Lattice iCE40 UltraPlus low-power & low-density FPGA. The project is intended to work out of the box and targets FPGA / RISC-V beginners as well as advanced users.

Special focus is paid on execution safety to provide defined and predictable behavior at any time. For example, the CPU ensures all memory accesses are properly acknowledged and all invalid/malformed instructions are always detected as such. Whenever an unexpected state occurs the application software is informed via precise and resumable hardware exceptions.

Feel free to open a new issue or start a new discussion if you have questions, comments, ideas, feedback or if something is not working as expected. See how to contribute.

Key Features

  • all-in-one package: CPU SoC Software Framework & Tooling
  • completely described in behavioral, platform-independent VHDL - no platform-specific primitives, macros, attributes, etc.; an all-Verilog "version" is also available
  • extensive configuration options for adapting the processor to the requirements of the application (on CPU, processor and system level)
  • aims to be as small as possible while being as RISC-V-compliant as possible - with a reasonable area-vs-performance trade-off
  • FPGA friendly (e.g. all internal memories can be mapped to block RAM - including the CPU's register file)
  • optimized for high clock frequencies to ease integration / timing closure
  • from zero to "hello world!" - completely open source and documented (on software and hardware side)
  • easy to use even for FPGA / RISC-V starters – intended to work out of the box

Project Status

release commits-since-latest-release

Task / Subproject Repository CI Status
GitHub pages (docs) neorv32 GitHub Pages
Build documentation neorv32 Documentation
Processor verification neorv32 Processor
RISCOF core verification neorv32-riscof neorv32-riscof
FPGA implementations neorv32-setups Implementation
All-Verilog version neorv32-verilog neorv32-verilog
FreeRTOS port neorv32-freertos neorv32-freertos
Prebuilt GCC toolchains riscv-gcc-prebuilt Prebuilt_Toolchains

The processor passes the official RISC-V architecture tests to ensure compatibility with the RISC-V ISA specs., which is checked by the neorv32-riscof repository. It can successfully run any C program (for example from the sw/example folder) including CoreMark and FreeRTOS and can be synthesized for any target technology - tested on Intel, AMD, Cologne Chip and Lattice FPGAs. The conversion into a single, plain-Verilog module file is automatically checked by the neorv32-verilog repository.

2. Features

The NEORV32 Processor provides a full-featured microcontroller-like SoC build around the NEORV32 CPU. By using generics the design is highly configurable and allows a flexible customization to tailor the setup according to your needs. Note that all of the following SoC modules are entirely optional.

CPU Core

Memories

  • processor-internal data and instruction memories (DMEM / IMEM) & caches (iCACHE and dCACHE)
  • pre-installed bootloader (BOOTLDROM) with serial user interface; allows booting application code via UART or from external SPI flash

Timers and Counters

  • 64-bit machine timer (MTIME), RISC-V spec. compatible
  • 32-bit general purpose timer (GPTMR)
  • watchdog timer (WDT)

Input / Output

  • standard serial interfaces (UART, SPI (SPI host), SDI (SPI device), TWI (I²C host), TWD (I²C device), ONEWIRE/1-Wire)
  • general purpose IOs (GPIO) and PWM
  • smart LED interface (NEOLED) to directly control NeoPixel(TM) LEDs

SoC Connectivity

  • 32-bit external bus interface - Wishbone b4 compatible (XBUS) with optional cache (XCACHE); wrappers for AXI4-Lite and Avalon-MM host interfaces
  • stream link interface with independent RX and TX channels - AXI4-Stream compatible (SLINK)
  • external interrupts controller with up to 32 channels (XIRQ)

Advanced

  • true-random number generator (TRNG) based on the neoTRNG
  • execute-in-place module (XIP) to execute code right out of a SPI flash
  • custom functions subsystem (CFS) for custom tightly-coupled co-processors, accelerators or interfaces
  • direct memory access controller (DMA) for CPU-independent data transfers and conversions
  • cyclic redundancy check unit (CRC) to test data integrity (CRC8/16/32)

Debugging

  • on-chip debugger (OCD) accessible via standard JTAG interface
  • compatible to the "Minimal RISC-V Debug Specification Version 1.0"
  • compatible with OpenOCD, GDB and Segger Embedded Studio
  • RISC-V trigger module for hardware-assisted breakpoints
  • optional authentication module to implement custom security mechanisms

3. FPGA Implementation Results

Implementation results for exemplary CPU configurations generated for an Intel Cyclone IV EP4CE22F17C6 FPGA using Intel Quartus Prime Lite 21.1 (no timing constrains, balanced optimization, f_max from Slow 1200mV 0C Model).

CPU Configuration (version 1.7.8.5) LEs FFs Memory bits DSPs f_max
rv32i_Zicsr 1223 607 1024 0 130 MHz
rv32i_Zicsr_Zicntr 1578 773 1024 0 130 MHz
rv32imc_Zicsr_Zicntr 2338 992 1024 0 130 MHz

An incremental list of CPU extensions and processor modules can be found in the Data Sheet: FPGA Implementation Results.

4. Performance

The NEORV32 CPU is based on a two-stages pipelined/multi-cycle architecture (fetch and execute). The following table shows the performance results (scores and average CPI) for exemplary CPU configurations (no caches) executing 2000 iterations of the CoreMark CPU benchmark (using plain GCC10 rv32i built-in libraries only!).

CPU Configuration (version 1.5.7.10) CoreMark Score
small (rv32i_Zicsr_Zifencei) 33.89
medium (rv32imc_Zicsr_Zifencei) 62.50
performance (rv32imc_Zicsr_Zifencei perf. options) 95.23

More information regarding the CPU performance can be found in the Data Sheet: CPU Performance. The CPU & SoC provide further "tuning" options to optimize the design for maximum performance, maximum clock speed, minimal area or minimal power consumption: User Guide: Application-Specific Processor Configuration

5. Getting Started

This overview provides some quick links to the most important sections of the online Data Sheet and the online User Guide.

🔍 NEORV32 Project - An Introduction

🖥️ NEORV32 Processor - The SoC

🧮 NEORV32 CPU - The Core

💾 Software Framework - The Software Ecosystem

🚀 User Guide - Let's Get It Started

©️ Legal

license DOI

  • Overview - license, disclaimer, limitation of liability for external links, proprietary notice, etc.
  • Citing - citing information

This is an open-source project that is free of charge. Use this project in any way you like (as long as it complies to the permissive license). Please cite it appropriately. 👍


❤️ A big shout-out to the community and all the contributors - this project would not be where it is without them!