A system-level view of program execution can be helpful in identifying problems during program execution including functional correctness and performance related challenges. While system level hardware and software emulation help during the development phase of the system, AMD offers flows around functional and performance debug in hardware as well. The AI Engine architecture has support for generation, collection, and streaming of profile related data, and events as trace data during hardware execution.
Tip: To facilitate the testing of AI Engine graphs on VCK190, AMD provides a
ready-to-use test harness. This test harness is designed to provide a very simple and
natural transition from the AI Engine
simulation environment to testing on hardware. With the test harness, AI Engine graphs running in simulation can be
taken to hardware in just a few minutes and with only a few minor modifications. More
details about the AI Engine test harness
can be found here: https://xilinx.github.io/AI-Engine-Test-Harness/