- AI Engine
- Each AI Engine is a very long
instruction word (VLIW) processor containing the following components.
- A scalar unit
- A vector unit
- Two load units
- A single store unit
- AI Engine Tile
- An AI Engine tile contains the
following components.
- An AI Engine
- A local memory module together with several communication paths to support data exchange between tiles.
- AI Engine Array
- The AI Engine array consists of a 2D
array of AI Engine tiles, where each
AI Engine tile contains the following
components.
- An AI Engine
- Memory module
- A tile interconnect module
- AI Engine Program
- Consists of a data flow graph specification, written as a C++ class. A top-level program instantiates one or more graph classes and is compiled and executed using the AI Engine tool chain.
- AI Engine Kernels
- AI Engine vector data types and intrinsic functions are used to write kernels in C/C++. These are the computation functions running on an AI Engine. The kernels form the fundamental building blocks of a data flow graph specification.
- ADF Graph
- An ADF graph is a network with a single AI Engine kernel or multiple AI Engine kernels connected by data streams. The ADF graph
interacts with the programmable logic, global memory, and processing system
with specific constructs such as RTP and the following.
- PLIO
- The port attribute in the graph that makes stream connections to or from the programmable logic.
- GMIO
- The port attribute in the graph that is makes external memory-mapped connections to or from the global memory.
- RTP
- The Runtime Parameters (RTP) are communication channels between the processing system (PS) and the AI Engine. RTPs are suitable for low-throughput and low-latency signals.
You can embed graphs into other graphs as sub-graphs, allowing you to structure the design into logical subsystems.