The HLS Kernel to AIE block reformats a signal driven by a port of an HLS
kernel block. The resulting signal matches the data type and complexity required by an
AI Engine kernel or an input of a AI Engine graph block. For example, if the data type of
port of the HLS kernel block is axiu<128> and the
data type of the port of the AI Engine is uint32, the HLS Kernel to AIE block reformats the input
samples by unpacking each axisu<128> sample into
four uint32 samples. The output port of this block is a
variable-size signal.
Figure 1. HLS Kernel to AIE Block
Double-click the block symbol to see the parameters of the HLS Kernel to AIE block.
Figure 2. Block Parameters: HLS Kernel to AIE
- Output Data Type
- Possible values are: int8, int16, int32, int64, uint8, uint16, uint32, uint64, cint16, cint32, float, cfloat, bfloat16, cbfloat16.
- Output Size
- The size of the output port. The output port is a variable-sized
signal whose maximum size is specified by the Output Size parameter. The Output Size
parameter has a lower bound, calculated based on the input data type, input
size, and output data type. For example, if the input data type is
cint16, the input size is 8, and if the output data type isint32, the Output Size parameter must be at least 4. To use a smaller Output Size, enable theAllow Multiple-Rate Processingparameter. - Allow Multiple-Rate Processing
- When this property is enabled, the Output Size parameter has no lower bound. If the Output Size parameter is set to a value less than the original lower bound, the output sample rate is greater than the input sample rate.
- Input Data Type
- Possible values are: cint16, int32, uint32, cint32, int64, uint64, sfix128, ufix128, float, cfloat.