Use Case Attributes
New Blueprint for VR/AR on the Network Edge
Integrated Edge Cloud (IEC)
Deployment of generic edge end and cloud environment for VR/AR cloud streaming
Blueprint proposed Name
IEC Type 4: AR/VR oriented Internet Edge Stack for Integrated Edge Cloud (IEC) Blueprint Family
Initial POD Cost (capex)
NVIDIA RTX GPUs
Chelsio T580-CR NICs
Scale & Type
Generic blueprint PoC:
Large scale deployment:
Generic blueprint POD: Small scale cloud AR/VR rendering farm with generic SO.
Power and memory restrictions
Docker 118.1309.1 4 or above (19.03 may be needed to run windows container with nVidia GUP support) and K8s 1.1014.2 1 or above- Container Orchestration, VMWare VM
OS - Ubuntu 1618.x04.2, windows server 2019
Under Cloud Orchestration - Airship v1.0 (TBD)
Calico and K8s, Memcached load balancer (optional)
VR and AR applications with split rendering runtime running inside Containers or VM
The test configuration consists of 2 3 machines connected back-to-back using single portusing ethernet switch: a master and 2 worker nodenodes, each with TBD processor clocked at TBD GHz, with TBD GB of RAM and Ubuntu operating system for master, windows server 2019 or later for worker. MTU of 1450B is configured (to compensate for GTP tunnel header). One Chelsio T580-CR and TBD GPU adapter is installed in each system with Chelsio GPUDirect RDMA driver v188.8.131.52, CUDA v6.5, OpenMPI v1.8.4 (with CUDA support), OSU micro benchmarking tools v4.4.1 and nVIDIA peer memory driver.
Each windows server preconfigures with 2-3 VMs with fixed GPU allocation per VM.
View file name 5GXRSIG UC3- v5 submitted to Akraino for IEC Type 4 review-v2.pdf height 250