With a stream-based access model, the kernels receive an input stream or an output stream of typed data as an argument. Each access to these streams is synchronized. That is, reads stall if the data is not available in the stream and writes stall if the stream is unable to accept new data.
An AI Engine supports two 32-bit input
stream ports with
id=0 or 1 and two 32-bit output stream ports with id=0 or 1. This ID is supplied as an
argument to the stream object constructors. The AI Engine compiler automatically allocates the input and output stream
port IDs from left to right in the argument list of a kernel. Multiple kernels mapped to
the same AI Engine are not allowed to share stream
ports unless the streams are packet switched (see Explicit Packet Switching).public:
input_plio din;
output_plio dout;
adf::kernel k0,k1;
...
connect <stream> (din.out[0], k1.in[0]);
connect <stream> (k1.out[0], k2.in[0]);
connect <stream> (k2.out[0], dout.in[0]);There is also a direct stream communication channel between the accumulator
register of one AI Engine and the physically adjacent
core, called a cascade. The cascade stream connects within the AI Engine array in a snake-like linear fashion from AI Engine processor to
processor.
connect <cascade> (k1.out[1], k2.in[1]);The AI Engine compiler automatically infers stream data structures from data flow graph connections. The structures are automatically declared in the wrapper code implementing the graph control. Kernel functions operate on pointers to stream data structures. These pointers are passed to the functions as arguments. There is no need to declare these stream data structures in data flow graph or kernel program.
Stream Connection for Multi-Rate Processing
Multi-rate analysis is not an easy task when it comes to streams and
packet-streams connections if there is no user specification. Use constraints to
specify how many samples the kernel reads from the input stream or pktstream input.
Also specify how many samples the kernel writes to the stream or
pktstream output, as shown
below:// constraint to specify samples per iteration for stream/pktstream ports to support multirate connections
constraint<uint32_t> samples_per_iteration(adf::port<adf::input>& p);
constraint<uint32_t> samples_per_iteration(adf::port<adf::output>& p);constraint keyword needs the sample datatype as
a template value. The function samples_per_iteration is applied to the input or the output of the
kernel. You can connect the related stream to another stream of a buffer.Note: The multi-rate analysis pass calculates
the rate for only those stream/pktstream ports for which
adf::samples_per_iteration (>0) is specified.