This project demonstrates a simple matrix addition application using NVIDIA Holoscan with CUDA.
- Create a build folder and navigate inside:
mkdir build
cd build- Configure the project using CMake (make sure to set the Holoscan path):
cmake ../src -DCMAKE_PREFIX_PATH=/opt/nvidia/holoscan- Build the project:
make -jOnce, makefile is generated run the following code
nsys profile --trace=cuda,nvtx,osrt --gpu-metrics-devices=all --sample=cpu --output=profile_report3 ./cudaTestOpen Nsight systems UI and locate the file
nsys-uiOnce, makefile is generated run the following code
ncu --replay-mode application -o compute_report ./cudaTestOpen Nsight compute directly with the file name as an argument
ncu-ui compute_report.ncu-rep