Target workloads compiled by the accelerator compiler into executable form, used to run real models on the emulation platform before silicon.
Test Work product in the AI accelerator lifecycle
Running real compiled workloads before silicon checks the compiler, the hardware interface and the design together and gives early performance data, so compiler and hardware mismatches are found long before silicon.
The full lifecycle detail, with its charts, flows, tables and every section, is for registered members. Registration is free and takes a minute. You come back to this page afterwards.