Hi,
I need to access to Aerial SDK for research purpose. I request you to please guide.
Thanks!
@sukh.sandhu
Welcome to our community.
Please sign up the member account for being able to access the SDK via this link Log in | NVIDIA Developer
Thanks
Hi @jixu thank you for your reply. I am already signed up for the membership, but I am not getting access to Aerial SDK. Its showing some key error. Can you please help me? I need access to Aerial SDK. Please help!
Hi @sukh.sandhu
Can you please logout of NGC and then follow the link from 6G Developer Program | NVIDIA Developer to get back into it?
Hi @jixu I logged in from the link provided by you and if you see the screenshots the access to Aerial SDK is not there. Usually Aerial SDK is visible separately. It should be visible where I have placed the question mark. We need to be given access to Aerial SDK. Also, I am getting and error that access denied. Please help!
Hi @jixu I logged in from the link provided by you and if you see the screenshots the access to Aerial SDK is not there. Usually Aerial SDK is visible separately. It should be visible where I have placed the question mark. We need to be given access to Aerial SDK. Also, I am getting and error that access denied. Please help!
Hi @sukh.sandhu
Please check if you can access by clicking “Get Aerial CUDA-Accelerated RAN” under Download Software. Then choose aerial-ran-and-ai-radio-framework located on top of your question mark.
Hi @jixu,
We followed the instructions given by you. On searching the containers for the Aerial SDK 25-1, we are not able to see all the containers available in the SDK. We are only able to pull the docker image for Cubb using the command:
sudo docker pull nvcr.io/nvidia/aerial/aerial-cuda-accelerated-ran:25-1-cubb
This command is able to pull the cubb image.
The tags are not visible to be and requires an active subscription although we are the active members.
Hi @sukh.sandhu
From NGC catalog, only available aerial SDK is version 25-1-cubb. what else containers are you looking for?
Hi @jixu and @nhashimoto
on running this command:
sudo docker pull nvcr.io/nvidia/aerial/aerial-cuda-accelerated-ran:25-1-cubb
output is:Error response from daemon: Head “https://nvcr.io/v2/nvidia/aerial/aerial-cuda-accelerated-ran/manifests/25-1-cubb”: unknown: {“errors”: [{“code”: “DENIED”, “message”: “Payment Required”}]}
Is there a requirement for a paid subscription to access Aerial SDK ?
Hi @sukh.sandhu
No, no need to pay for the subscription. Your subscription request has been approved. Would you please try it again and let us know the outcome.
Thanks!
Thank you @jixu, I am able to pull the image for
aerial-cuda-accelerated-ran:25-1-cubb. After installation, I followed the cuBB quickstart guide (Generating TV and Launch Pattern Files — Aerial CUDA-Accelerated RAN). While generating the test vectors using MATLAB (I have installed MATLAB inside the cubb container as per step 1)
[Aerial Python]aerial@ubuntu-S2600STB:/opt/nvidia/cuBB/5GModel/aerial_mcore/examples$ ../scripts/gen_e2e_ota_tvs.sh
/opt/nvidia/cuBB/5GModel/aerial_mcore/scripts/gen_e2e_ota_tvs.sh starting…
/opt/nvidia/cuBB/5GModel/aerial_mcore/examples /opt/nvidia/cuBB/5GModel/aerial_mcore
Traceback (most recent call last):
File “/opt/nvidia/cuBB/5GModel/aerial_mcore/examples/genCuPhyChEstCoeffs.py”, line 49, in
import aerial_mcore as NRSimulator
File “/usr/local/lib/python3.10/dist-packages/aerial_mcore/init.py”, line 290, in
_pir.get_paths_from_os()
File “/usr/local/lib/python3.10/dist-packages/aerial_mcore/init.py”, line 142, in get_paths_from_os
raise RuntimeError(msg)
RuntimeError: Could not find an appropriate directory for MATLAB or the MATLAB runtime in LD_LIBRARY_PATH. Details: file not found: libmwmclmcrrt.so.9.14; LD_LIBRARY_PATH: :/usr/local/MATLAB/MATLAB_Runtime/R2023a/runtime/glnxa64:/usr/local/MATLAB/MATLAB_Runtime/R2023a/bin/glnxa64:/usr/local/MATLAB/MATLAB_Runtime/R2023a/sys/os/glnxa64:/usr/local/MATLAB/MATLAB_Runtime/R2023a/extern/bin/glnxa64:/usr/local/MATLAB/MATLAB_Runtime/R2023a/sys/opengl/lib/glnxa64
Could you please help me to resolve this error
@sukh.sandhu
The testVectors can be generated on x86 only. Matlab runtime lib can’t run on ARM.
Hi @jixu,
My cpu architecture configuration is x86. Pulled the image from
nvcr.io/nvidia/aerial/aerial-cuda-accelerated-ran:25-1-cubb
I have installed MATLAB inside the aerial pod as given in the first part of step 1 in Generating TV and Launch Pattern Files — Aerial CUDA-Accelerated RAN
How can I generate the test vectors using the gen_e2e_ota_tvs.sh script? This will enable me in verifying my installation.
Hi @jixu,
Reminder to please reply to my previous comment:
My cpu architecture configuration is x86. Pulled the image from
nvcr.io/nvidia/aerial/aerial-cuda-accelerated-ran:25-1-cubb
I have installed MATLAB inside the aerial pod as given in the first part of step 1 in Generating TV and Launch Pattern Files — Aerial CUDA-Accelerated RAN
How can I generate the test vectors using the gen_e2e_ota_tvs.sh script? This will enable me in verifying my installation. Please help!
We are stuck, can anybody help @jixu @eobiodu @nhashimoto . Please help us with the above query!
-
Install MATLAB runtime and supporting apt packages in Aerial cuBB container
export cuBB_SDK=$(pwd)
wget https://ssd.mathworks.com/supportfiles/downloads/R2023a/Release/1/deployment_files/installer/complete/glnxa64/MATLAB_Runtime_R2023a_Update_1_glnxa64.zip
mkdir unzip && cd unzip
sudo ./install -mode silent -agreeToLicense yes
cd .. && rm -rf MATLAB_Runtime_R2023a_Update_1_glnxa64.zip unzip
sudo apt install -y libxcomposite1 libnss3 libxrandr-dev libatk1.0-0 libatk-bridge2.0-0 libx11-xcb-dev libxcb-dri3-0 libxcursor-dev libxdamage-dev libxi-dev libdrm-dev libgbm-dev libasound-dev libcups2-dev libxtst-dev -
Creating an Aerial Container with matlab runtime enabled (run two steps on the host bare metal)
- need to edit Dockerfile to have the image**
FROM nvcr.io/nvidia/aerial/aerial-cuda-accelerated-ran:25-1-cubb
docker build -t aerial-cuda-accelerated-ran:25-1-cubb-matlab-runtime-enabled .
- Generate cuPhyChEstCoeffs.h5
docker exec -it cubb-251 bash
export cuBB_SDK=$(pwd)
cd ${cuBB_SDK}/5GModel/aerial_mcore/examples
source ../scripts/setup.sh
[Aerial Python]aerial@e200-r750-10:/opt/nvidia/cuBB/5GModel/aerial_mcore$
../scripts/gen_e2e_ota_tvs.sh
Please capture the outputs of all steps if the failure still happen