No project description provided
Project description
Design Philosophy
This is an much more efficient implementation of canal. It is rewritten from scratch to utilize kratos’ efficient hardware generator framework.
Original canal description copied below:
In canal, the hardware is represented as a directed graph (DiGraph). In principle each node in the graph will be turn into a hardware component based on the property of the node. The edge will be transformed into a wire.
One thing to notice is that staged generation happens on the graph level. That is, passes have to be operated on the DiGraph, rather than the hardware generator itself. This allows better analysis and reduce the computation overhead since magma is slow when constructing large hardware. In canal, different bit width routing network will have different DiGraph by design. This allows us to share the common passes on different DiGraph while constructing on the same interconnect
How to install
pip install kcanal
Relationship with CGRA_PNR (Thunder/Cyclone)
The internal DiGraph representation is identical to Cyclone. Due to the requirement of pure-Python implementation, canal re-implemented the graph representation with more utility functions. The PnR information is interchangeable with Thunder and Cyclone and thus can be used in place route directly.
There is a python utility package called archipelago, that can take Interconnect object in canal and perform place and route directly. To install archipelago, you can use
pip install archipelago
It will use pre-built Python native wheels to speed up place and route.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distribution
File details
Details for the file kcanal-0.0.1-py3-none-any.whl
.
File metadata
- Download URL: kcanal-0.0.1-py3-none-any.whl
- Upload date:
- Size: 31.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.9.13
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | aed27858544770d5829d15ae8b1a93f70f02846be39a9c8a81eef6cc2ae58c65 |
|
MD5 | fdb7c1d403eb8c4280bda2b8f81ea0e4 |
|
BLAKE2b-256 | b667e614cebc38c49c2496dd40b4fa22920f37416196e299b9a58e34c7dc4f1b |