CIMFlow Framework
An integrated framework for digital CIM accelerator design and simulation
CIMFlow provides an end-to-end solution for designing and evaluating SRAM-based Compute-in-Memory accelerators. The framework integrates an MLIR-based compiler with a cycle-accurate SystemC simulator, enabling researchers and engineers to explore CIM architectures from neural network models to detailed performance analysis.
Documentation
What is CIMFlow?
Architecture overview and design philosophy
Features
Compiler and simulator capabilities
Installation
Setup guide for Linux systems
Quickstart
End-to-end pipeline tutorial
CLI Reference
Complete command-line interface documentation
Configuration
Configuration files and parameters
Framework Components
Who Is This For?
To get started, see Installation and Quickstart.
Prerequisites
Familiarity with the following is helpful:
- CIM fundamentals: See Literatures on SRAM-based CIM for background
- ONNX format: CIMFlow accepts neural network models in ONNX format
- Command-line usage: Terminal navigation and shell commands
No prior experience with MLIR or SystemC is required.
Last updated on