This chapter describes the performance of the Vitis AI Library on the following different evaluation boards and data center accelerator cards.
- ZCU102 Evaluation Kit
- ZCU104 Evaluation Board
- KV260 Vision AI Starter Kit
- VCK190 Evaluation Board
- VCK5000 Versal Development Card for AI Inference
- Alveo U50LV Data Center Accelerator Card
- Alveo U55C High Performance Compute Card
For the one thread performance test, the performance is calculated using the
formula: (1000 ms / E2E_mean
time)*batch_number. Taking VCK190 as an example, if the
batch_number is 3, the E2E_mean and DPU_mean are as shown in the following
figure.
Figure 1. One Thread Performance Test Example for Batch num
3
