Application Acceleration With FPGAs
Programmable Acceleration Cards (PACs), DCP, FPGA AI Suite, Software Stack, and Reference Designs
477 Discussions

Error Code: 78 when dla_compile

RubenPadial
New Contributor I
955 Views

Hello

I'm starting with OpenVino and Intel FPGA AI suite. I have a pretrained model imported from TF and working with OpenVino. I have the .bin and the .xml files. However, when I try to copile the model for Arria 10 SOC FPGA I get the following error:

"

Starting compilation
Error Code: 78
Error Description: Error: Filter cache is too small. Maximum filter channels is too small to be bumped down to a multiple of sb_c_banks. Must be multiple of 32 that does not exceed 20
File: ../compiler/core/src/dla_pass_slice_analysis.cpp
Function: computeChannelSliceFactor
Line #: 2053
Error occurred.
../compiler/aot_plugin/src/dla_executable_network.cpp:60 DLA has thrown an exception: Error: Filter cache is too small. Maximum filter channels is too small to be bumped down to a multiple of sb_c_banks. Must be multiple of 32 that does not exceed 20

"

 

I have used the given A10_Performance.arch file. Could you help me?

Thank you in advance

0 Kudos
7 Replies
JohnT_Intel
Employee
918 Views

Hi,

 

May I know which AI Suite version are you using? May I know how do you create the Neural Network configuration file?

0 Kudos
RubenPadial
New Contributor I
912 Views

Hello @JohnT_Intel ,

NN was trainded with TF 2.6.0 and it was experted as SavedModel format (.pb). The NN is working properly as IR model once it is imported.

0 Kudos
JohnT_Intel
Employee
908 Views

Hi,

How about the file needed to compile the FPGA design? Can you guide me on what is the changes made? 

0 Kudos
JohnT_Intel
Employee
874 Views

Hi,


Can you provide the guide to duplicate the issue?


0 Kudos
RubenPadial
New Contributor I
859 Views

Hello @JohnT_Intel ,

 

In the file attached yo will find the following files:

  • SavedModel: Model exported from TF
  • IR: Model converted from TF to Intermediate  Representation (IR) with model optimizer function:
mo
--saved_model_dir "{path_savedModelPath}"
--input_shape "{lst_inputShape}"
--model_name "{str_modelName}"
--data_type FP16
--output_dir "{path_irTargetPath}"
 

where

  • input_shape = [1,28,28,1]
  • path_savedModelPath: Path to SaveModel files
  • str_modelName = "CustomModel"
  • path_irTargetPath: Target path to save .xml and .bin files

 

  • A10_Generic.arch: IP configuration

 

After getting the .bin and .xml files I checked that IR model works properly and I tried to compile using the following dlaCommand command:

dla_compiler
--march "{path_archPath}"
--network-file "{path_xmlPath}"
--foutput-format=open_vino_hetero
--o "{path_binPath}"
--batch-size=1
--fanalyze-performance
 

where

  • path_archPath: Path to "A10_Generic.arch" file
  • path_xmlPath: Path to IR .xml file from previous step
  • path_binPath: Path to IR .bin file from previous step

Thank you for your help

0 Kudos
JohnT_Intel
Employee
785 Views

Hi,


I have feedback this issue to engineering to look into this issue


0 Kudos
JohnT_Intel
Employee
731 Views

Hi,


I have check with engineering and based on their feedback, the error you observed is due to the model not able to be implemented into AI Suite on FPGA. The reason is that not all model are able to be supported.


0 Kudos
Reply