FPGA AI Suite: IP Reference Manual

ID 768974
Date 3/29/2024
Public
Document Table of Contents

B. FPGA AI Suite IP Reference Manual Document Revision History

Document Version FPGA AI SuiteVersion Changes
2024.03.29 2024.1
  • Rebranded from "Intel FPGA AI Suite" to "FPGA AI Suite".
  • Added updates to support new dedicated layout transform module.
  • Updated "FPGA AI Suite Layer / Primitive Ranges" as follows:
    • Updated description of Softmax.
    • Added Sigmoid.
    • Added Swish.
  • Updated "FPGA AI Suite IP Block Configuration" as follows:
    • Expanded the ranges of the c_vector, pool k_vector, and activation k_vector parameters.
    • Added the enable_sigmoid parameter.
    • Expanded the range of the arch_precision parameter.
  • Updated "Parameter Group: Global Parameters" with additional information about Agilex™ 5 device family support.
  • Added activation/enable_sigmoid to "Parameter Group: activation ".
  • Added softmax/max_num_channels parameter description to "Module: softmax ".
2023.12.01 2023.3
  • Updated "Model Performance" with Version 2023.3 values
  • Updated arch_precision parameter description in "Parameter group: Global Parameters".
  • Added "Performance Registers".
  • Added "Debug Network Registers".
  • Added "PE scale precision" to " FPGA AI Suite IP Block Configuration".
  • Updated "Parameter Group: Global Parameters" for Agilex™ 5 support.
  • Updated "Parameter Group: pe_array " for Agilex™ 5 support.
2023.09.08 2023.2.1
  • Added Multilayer Perceptrons (MLPs) to supported models.
2023.07.03 2023.2
  • Updated "Model Performance" with Version 2023.2 values and the enabling of non-default Quartus® Prime options (register merging).
  • Added additional information about modifying the internal precision of a graph for performance improvement in "Architecture Description File Format for Instance Parameterization".
2023.04.05 2023.1
  • Added ChannelToSpace, DepthToSpace, and PixelShuffle to " FPGA AI Suite Layer / Primitive Ranges".
  • Added enable_debug to " FPGA AI Suite IP Block Configuration and Interfaces".
  • Added description of enable_round_clamp activation parameter where needed.
  • Added "Input Transform Mapping".
  • Added output transform mapping information to "Output Tensor In-Memory Format".
  • Renamed thedlac command. The FPGA AI Suite compiler command is now dla_compiler.
  • Updated "Model Performance" with Version 2023.1 values.
  • Updated the Intel® Agilex™ product family name to "Intel Agilex® 7."
2023.02.03 2022.2
  • Correct the description of the -bgr option of the AOT splitter utility.
2022.12.23 2022.2
  • Added SqueezeNet to the list of supported models.
  • Added the family architecture description file global parameter.
  • Removed the --family IP generation utility command option.

2022.04.27

2022.1

  • Removed references to HLS generation.
  • Updated descriptions of parameters in the .arch file.
  • Added a Model Performance section.

2021.09.10

2021.2

  • Added information for Intel® Agilex™device support.
  • Added information for MobileNet v3 support.

2021.04.30

2021.1

  • Various corrections and updates.

2020.12.04

2020.2

  • Renamed Intel® FPGA AI Suite IP Core to Intel® FPGA AI Suite IP".

2020.10.30

2020.1

  • Initial release.