Please reference to Dataset in table 1.
For representing the resource utilization in each benchmark, we separate the overall utilization into 2 parts, where P stands for the resource usage in platform, that is those instantiated in static region of the FPGA card, as well as K represents those used in kernels (dynamic region). The target device is set to Alveo U280.
|Naive Bayes (U200)||999 samples with 10 features||0.519||266MHz||185.9K/70.1K||345/114||0/256||10/467|
|Support Vector Machine (U250)||999 samples with 66 features||0.23||300MHz||178.5K/367.0K||403/276||0/132||13/1232|
|Log Analyzer Demo (U200)||1.2G access log||990||251MHz||282.6K/226.8K||835/332||0/208||16/22|
|Duplicate Record Match (U50)||Randomly generate 10,000,000 lines (about 1GB)||8215560||270MHz||135.8K/272.0K||180/50||0/260||4/506|
These are details for benchmark result and usage steps.
Here are benchmarks of the Vitis Data Analytics Library using the Vitis environment.
Vitis Data Analytics Library¶
- Download code
These data analytics benchmarks can be downloaded from vitis libraries
git clone https://github.com/Xilinx/Vitis_Libraries.git cd Vitis_Libraries git checkout master cd data_analytics
- Setup environment
Specifying the corresponding Vitis, XRT, and path to the platform repository by running following commands.
source <intstall_path>/installs/lin64/Vitis/2021.1_released/settings64.sh source /opt/xilinx/xrt/setup.sh export PLATFORM_REPO_PATHS=/opt/xilinx/platforms