Overview
The LatticeMico32™ is a 32-bit Harvard, RISC architecture "soft" microprocessor, available for free with an open IP core licensing agreement. The LatticeMico32 provides the visibility, flexibility and portability that you expect in an open source hardware design. Everything you need is provided, including software development tools (via LatticeMico™ System) and evaluation boards to try out your designs in hardware.
By combining a 32-bit wide instruction set with 32 general purpose registers, the LatticeMico32 provides the performance and flexibility suitable for a wide variety of markets. Using a RISC architecture, the core consumes minimal device resources, while maintaining the performance required for a broad application set. To accelerate the development of microprocessor systems, several optional WISHBONE compatible peripheral components may be integrated with the LatticeMico32.
WISHBONE Compatible Peripheral Components
To accelerate the development of microprocessor systems, several optional WISHBONE compatible peripheral components may be integrated with the LatticeMico32.
* Memory controllers * DDR, DDR2 & DDR3 SDRAM
* Asynchronous SRAM
* On-chip Block Memory
* SDRAM controller
* On-chip dual port memory
* SPI Flash
* Parallel Flash
* I/O * 32-bit Timer
* DMA Controller
* GPIO
* I2C Master Controller
* SPI
* Tri-Speed Ethernet MAC
* UART
* PCI Target
Three Configurations to Optimize Area and Performance
* Basic * No Multiplier
* Multicycle Shifter
* No Cache
* Standard * Multiplier
* Pipelined Shifter
* 8K I-Cache, No D-Cache
* Full * Multiplier
* Pipelined Shifter
* 8K I-Cache, 8K D-Cache
Development Tools
LatticeMico System is to be used to implement a LatticeMico32 system with attached peripheral components. It is based on the Eclipse C/C++ Development Tools Environment, which is an industry open-source development and application framework for building software.
Supported Development Boards
Lattice has pre-defined a number of its development boards as platforms within the LatticeMico System Software. This allows you to rapidly start developing LatticeMico32 based systems on these boards. The following boards have been developed:
* LatticeMico32 Development Board for LatticeECP2
* LatticeMico32 Development Board for LatticeECP
Learn more about CPU IP core
For the first time in our more than 35-year history, Arm is delivering its own silicon products – extending the Arm Neoverse platform beyond IP and Arm Compute Subsystems (CSS) to give customers greater choice in how they deploy Arm compute – from building custom silicon to integrating platform-level solutions or deploying Arm-designed processors.
The ChiPy DSL is Quadric's Python framework for building complete on-chip pipelines. Using YOLOX-M as a case study, we show how backbone inference, box decoding, and NMS run entirely on the Chimera GPNPU — no host CPU intervention, no DDR round-trips, just Python compiled to silicon.
As part of the new Arm Lumex compute subsystem (CSS) platform, the Arm C1 CPU cluster – the first built on the Armv9.3 architecture – is the next evolution of our highest performing CPU cluster for consumer devices, designed to unleash the full potential of on-device AI and elevate the user experience.
Hardware fuzzing has recently gained momentum with many discovered bugs in open-source RISC-V CPU designs. Comparing the effectiveness of different hardware fuzzers, however, remains a challenge: each fuzzer optimizes for a different metric and is demonstrated on different CPU designs.
Unlock ultra-efficient performance, advanced AI processing, and robust security with the Cortex-A320—designed to power the future of IoT and edge AI innovation.
Pie maintains low computation latency, high throughput, and high elasticity. Our experimental evaluation demonstrates that Pie achieves optimal swapping policy during cache warmup and effectively balances increased memory capacity with negligible impact on computation. With its extended capacity, Pie outperforms vLLM by up to 1.9X in throughput and 2X in latency. Additionally, Pie can reduce GPU memory usage by up to 1.67X while maintaining the same performance. Compared to FlexGen, an offline profiling-based swapping solution, Pie achieves magnitudes lower latency and 9.4X higher throughput.
