Neutrino-Pub

This page is read only. You can view the source, but not change it. Ask your administrator if you think this is wrong.

====== hls4ml tutorial ======
hls4ml is a package for translating neural networks to FPGA firmware for inferance with extremely low latency on FPGAs
  * https://github.com/hls-fpga-machine-learning/hls4ml 
  * https://fastmachinelearning.org/hls4ml/
  * pip install hls4ml


===== Demonstration =====

===== Hardware =====
https://github.com/mlcommons/tiny_results_v0.7/tree/main/open/hls4ml-finn
  * The first board is a TUL PYNQ-Z2 based on Xilinx Zynq SoC (See https://www.tul.com.tw/productspynq-z2.html for more information).
  * The second board is a Digilent Arty A7-100T based on Xilinx Artix-7 SoC (See https://digilent.com/shop/arty-a7-artix-7-fpga-development-board/ for more information).


===== Terminology =====
FPGA: (Field Programmable Gate Arrays)    \\
ASIC (Application-Specific Integrated Circuit).    \\
CPU (Central Processing Unit).  \\
GPU (Graphics Processing Unit). \\

HDL Hardware Description Languages. \\
HLS High Level Synthesis \\
LUT Look Up Table. \\ 
FF Flip Flops  \\
DSP Digital Signal Processor \\
BRAM Block RAM. \\