compile

Class: dlhdl.Workflow
Package: dlhdl

Compile workflow object

expand all in page

Syntax

compile
compile(Name,Value)

Description

example

compile compiles the dlhdl.Workflow object and generates the parameters for deploying the network on the target device.

compile(Name,Value) compiles the dlhdl.Workflow object and generates the parameters for deploying the network on the target device, with additional options specified by one or more Name,Value pair arguments.

The function returns two matrices. One matrix describes the layers of the network. The Conv Controller (Scheduling) and the FC Controller (Scheduling) modules in the deep learning processor IP use this matrix to schedule the convolution and fully connected layer operations. The second matrix contains the weights, biases, and inputs of the neural network. This information is loaded onto the DDR memory and used by the Generic Convolution Processor and the Generic FC Processor in the deep learning processor.

Examples

expand all

Compile the dlhdl.Workflow object, for deployment to the Intel® Arria® 10 SoC development kit that has single data types.

Create a dlhdl.Workflow object and then use the compile function to deploy the pretrained network to the target hardware.

snet = vgg19;
hT = dlhdl.Target('Intel');
hW = dlhdl.Workflow('network', snet, 'Bitstream', 'arria10soc_single','Target',hT);
hW.compile

Once the code is executed the result is:

  hW.compile
          offset_name          offset_address     allocated_space 
    _______________________    ______________    _________________

    "InputDataOffset"           "0x00000000"     "24.0 MB"        
    "OutputResultOffset"        "0x01800000"     "4.0 MB"         
    "SystemBufferOffset"        "0x01c00000"     "52.0 MB"        
    "InstructionDataOffset"     "0x05000000"     "20.0 MB"        
    "ConvWeightDataOffset"      "0x06400000"     "276.0 MB"       
    "FCWeightDataOffset"        "0x17800000"     "472.0 MB"       
    "EndOffset"                 "0x35000000"     "Total: 848.0 MB"


ans = 

  struct with fields:

       Operators: [1×1 struct]
    LayerConfigs: [1×1 struct]
      NetConfigs: [1×1 struct]

  1. Create a dlhdl.Workflow object and then use the compile function with optional argument of InputFrameNumberLimit to deploy the pretrained network to the target hardware.

    snet = alexnet;
hT = dlhdl.Target('Xilinx');
hW = dlhdl.Workflow('network', snet, 'Bitstream', 'zcu102_single','Target',hT);
hW.compile('InputFrameNumberLimit',30);

  2. The result of the code execution is:

             offset_name          offset_address     allocated_space 
    _______________________    ______________    _________________

    "InputDataOffset"           "0x00000000"     "24.0 MB"        
    "OutputResultOffset"        "0x01800000"     "4.0 MB"         
    "SystemBufferOffset"        "0x01c00000"     "28.0 MB"        
    "InstructionDataOffset"     "0x03800000"     "4.0 MB"         
    "ConvWeightDataOffset"      "0x03c00000"     "16.0 MB"        
    "FCWeightDataOffset"        "0x04c00000"     "224.0 MB"       
    "EndOffset"                 "0x12c00000"     "Total: 300.0 MB"

Input Arguments

Name-Value Pair Arguments

Specify optional comma-separated pairs of Name,Value arguments. Name is the argument name and Value is the corresponding value. Name must appear inside quotes. You can specify several name and value pair arguments in any order as Name1,Value1,...,NameN,ValueN.

Parameter to specify maximum input frame number limit to calculate DDR memory access allocation.

Example: 'InputFrameNumberLimit',30

See Also

| |

Topics

Introduced in R2020b

Deep Learning HDL Toolbox Documentation

Support