How to use NVIDIA/cuda_samples code?

I want to use sampleIPC.cu , link is below.

so i downloaded “cuda-samples-master” folder which is 593.6MB. and put the command “make” on terminal.

and i got some error like below

HP-ZCentral-4R-Workstation:~/Desktop/User/docker/cuda-samples-master/Samples/0_Introduction/simpleIPC$ make
/usr/local/cuda/bin/nvcc -ccbin g++ -I…/…/…/Common -m64 --threads 0 --std=c++11 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=sm_75 -gencode arch=compute_80,code=sm_80 -gencode arch=compute_86,code=sm_86 -gencode arch=compute_89,code=sm_89 -gencode arch=compute_90,code=sm_90 -gencode arch=compute_90,code=compute_90 -o helper_multiprocess.o -c …/…/…/Common/helper_multiprocess.cpp
nvcc fatal : Unsupported gpu architecture ‘compute_89’
make: *** [Makefile:352: helper_multiprocess.o] Error 1

how can i solve this?

You could remove all references to compute_89 and sm_89. That is actually a valid computation level so this probably means you need a newer version of the CUDA SDK to support them.

The RTX 4000 series cards are at computation level 8.9 and the RTX Ada series of cards at level 9.0 so those really are valid.