Profiling - 2023.2 English

Vitis Libraries

Release Date
2023-12-20
Version
2023.2 English

The naive bayes design is validated on Alveo U200 board at 266 MHz frequency. The hardware resource utilizations are listed in the following table.

Table 39 Table 1 Hardware resources for naive bayes
Name LUT BRAM URAM DSP
Platform 185929 345 0 10
naiveBayesTrain_kernel 70058 114 256 467
User Budget 996311 1815 960 6830
Percentage 7.03% 6.28% 26.67% 6.84%
The performance is shown below.
This benchmark takes 0.519421ms to train 999 samples with 10 features, so it throughput is 73.37MB/s.