hls4ml
clash-ghc
hls4ml | clash-ghc | |
---|---|---|
11 | 33 | |
1,110 | 1,375 | |
3.5% | 1.2% | |
9.2 | 9.1 | |
9 days ago | 5 days ago | |
C++ | Haskell | |
Apache License 2.0 | BSD 2-clause "Simplified" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
hls4ml
- How to participate in open-source FPGA projects?
- Looking for HLS frameworks to start deploying DL algorithms on FPGAs
-
Hi, What could be the best HLS tool for implementing neural networks on FPGA
I see that someone has already suggested hls4ml. I second that opinion. From my experience, it is extremely well documented. They have published papers which explain the scientific background. They have a really nice git page where they explain all the features of their tool. Additionally they also have an easy to follow tutorial of doing it from scratch using tensorflow networks. You can find all the information herehls4ml.
-
5 layered CNN implementation on arduino/FPGAs [P]
Open source project that originated at Fermilab https://github.com/fastmachinelearning/hls4ml (based on Xilinx Vivado which has been replaced by Vitis)
-
Help needed to build a Hardware accelerator for CNN's
You may check the hls4ml framework: it's a "translator" from the ML model (Keras, PyTorch) to a synthesizable High-Level Synthesis (HLS) IP Core.
-
Sub ms - 3ms Latency Vision task on FPGA
It really depends on the type of data you are using. There may (or may not) be some trade offs and sacrifices. There are frameworks which can basically translate your neural network information from a high level python code into equivalent HLS code which is optimized for low latency when inferred on FPGAs. Some frameworks which might be useful for you to explore are hls4ml and finn. These are some frameworks which can achieve low latency inference of neural networks on FPGAs using Xilinx Vitis HLS. These are what I found when I did a similar experiment but with much lower latency target (a few hundred ns) and a very simple MLP with 1D signal as input which was a year ago. Not sure if there are better alternatives available as of 2023. But conceptually all these work on the primary principle of having a supporting framework/methodology to first quantize the network and limit the precision of data to fixed point. The HLS then produced will also be a result of the framework applying dataflow techniques such that the resulting HLS code will produce an RTL which has the best overall latency.
-
looking for resources to design a basic deep learning feed forward accelerator
Check hls4ml. Developed by CERN for fast classification in FPGA for high-energy physics experiments.
-
How to build FPGA-based ML accelerator?
I would check out hls4ml. It's an open source project made by/for people at CERN to convert neural networks created in Python using QKeras (a quantization extension of Keras) into HLS, with Vivado HLS being the most well supported. There are some caveats though, and a fellow student and I have had trouble getting the generated HLS to match the Keras model and be feasible to synthesize, but it seems to work well for smaller neural networks.
-
How are TensorFlow Models implemented on PYNQ's PS & PL
Since you're looking for PL-only implementation, HLS4ML may fit your needs. It was developed to port TensorFlow models directly to FPGAs in particle physics experiments. Current development allows for implementation on SoC and MPSoC, though.
- Open source projects?
clash-ghc
- Clash: A Functional Hardware Description Language
- Clash (Haskell) for ASIC design
-
Building a Networked Key-Value-Store on an FPGA
> You'd be better off with a higher-level or more modern HDL that compiles to Verilog/VHDL. "Chisel" is one such.
As is Clash :) https://clash-lang.org/
-
Need project idea
You can take a look at https://clash-lang.org/. There is also a book for it. https://gergo.erdi.hu/retroclash/
-
5 layered CNN implementation on arduino/FPGAs [P]
I don't know much about FPGAs, but Clash lang compiles to VHDL, and might do the trick: https://clash-lang.org
- An addressable little explored language gap: HDL - Hardware Description Languages, any language used for electronic circuit design, description, and specs
- Pedagogical Downsides of Haskell
- Ask HN: Choice of HDL for an FPGA Project
-
Baud rate 1.5% lower than expected, is this normal?
if you need inspiration there is a full UART core available in clash: https://github.com/clash-lang/clash-compiler/blob/master/clash-cores/src/Clash/Cores/UART.hs
-
A circuit simulator that doesn't look like it was made in 2003
Perhaps peripheral (the original site has been hugged to death).
Both clashlang: https://clash-lang.org/
And Hardcaml: https://github.com/janestreet/hardcaml
have personally fueled my interest in hardware.
Dan Luu speaks eloquently and at length about how better options are needed for logic design. I would recommend both of the above to the enthusiastic novice.
What are some alternatives?
qkeras - QKeras: a quantization deep learning library for Tensorflow Keras
wiringPi - A Haskell binding to the wiringPi library, for using GPIO on the Raspberry Pi.
Silice - Silice is an easy-to-learn, powerful hardware description language, that simplifies designing hardware algorithms with parallelism and pipelines.
clash-prelude
v4l2rtspserver - RTSP Server for V4L2 device capture supporting HEVC/H264/JPEG/VP8/VP9
mercury-api - Haskell binding to Mercury API for ThingMagic RFID readers
srs - SRS is a simple, high-efficiency, real-time video server supporting RTMP, WebRTC, HLS, HTTP-FLV, SRT, MPEG-DASH, and GB28181.
ICFP2020_Bluespec_Tutorial - Tutorial on hardware design using Bluespec BH (Bluespec Classic) for Haskell programmers at ACM ICFP 2020 conference
PipelineC - A C-like hardware description language (HDL) adding high level synthesis(HLS)-like automatic pipelining as a language construct/compiler feature.
riscv-cores-list - RISC-V Cores, SoC platforms and SoCs
fastocloud_com - Self-hosted IPTV/NVR/CCTV/Video service (Community version) [Moved to: https://github.com/fastogt/fastocloud]
amaranth - A modern hardware definition language and toolchain based on Python