Low Precision Networks for Efficient Inference on FPGAs White Paper - Shows how quantizing neural network parameters with Block Floating Point can lead to savings in cost, time, power, and FPGA resource usage for your neural network. - 2026-05-13

Version

1.1

Product Type

Device Families > Stratix Families > Stratix 10

Device Families > Arria Families > Arria 10

Device Families > Agilex Families > Agilex 5 > D-Series

Device Families > Agilex Families > Agilex 5 > E-Series

Device Families > Cyclone Families > Cyclone 10 > Cyclone 10 GX

Development Software and Tools > AI Development Tools > FPGA AI Suite

Device Families > Agilex Families > Agilex 7 > F-Series

Device Families > Agilex Families > Agilex 3 > C-Series

Device Families > Agilex Families > Agilex 7 > I-Series

Device Families > Agilex Families > Agilex 7 > M-Series

Resource Type

Documentation > White Papers

Source Name

UD