AN 307: Intel® FPGA Design Flow for AMD* Xilinx* Users

ID 683562
Date 9/08/2023
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents

3.3.15.4. Fractal Synthesis

Fractal Synthesis optimizations can be used for deep-learning accelerators and other high-throughput, arithmetic-intensive designs that exceed all available DSP resources. For such designs, fractal synthesis optimization can achieve 20-45% area reduction.

Fractal synthesis uses techniques such as multiplier regularization and retiming which are ideal for operations like calculating dot-products, and continuous arithmetic packing to pack adder trees, multipliers into logic blocks optimally sized to fit Intel FPGA LABs.