The HLS Kernel to AIE block reformats a signal driven by a port of an HLS kernel block,
so that 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. Default size is '1'.