This topic describes the features of GPU-accelerated virtualization instance families and lists the instance types of each family.

vgn6i, lightweight GPU-accelerated compute optimized instance family

Features
  • If you want your vgn6i instance to support graphics features such as Open Graphics Library (OpenGL), you must purchase a GRID license from NVIDIA. Then, you must create an instance and manually install a GRID driver and activate the license after the instance is created.
  • Compute:
    • Uses NVIDIA T4 GPU computing accelerators.
    • Contains virtual GPUs generated from GPU slice virtualization.
      • Supports the 1/4 and 1/2 computing capacity of NVIDIA Tesla T4 GPUs.
      • Supports 4 GB and 8 GB of GPU video memory.
    • Offers a CPU-to-memory ratio of 1:5.
    • Uses 2.5 GHz Intel® Xeon® Platinum 8163 (Skylake) processors.
  • Storage:
    • Is an instance family in which all instances are I/O optimized.
    • Supports standard SSDs and ultra disks only.
  • Network:
    • Supports IPv6 addresses.
    • Provides high network performance based on large computing capacity.
  • Suits the following scenarios:
    • Real-time rendering for cloud games
    • Real-time rendering for AR and VR applications
    • AI (deep learning and machine learning) inference for elastic Internet service deployment
    • Educational environment of deep learning
    • Modeling experiment environment of deep learning
Instance types
Instance type vCPU Memory (GiB) GPU GPU memory Bandwidth (Gbit/s) Packet forwarding rate (Kpps) NIC queues ENIs Private IP addresses per ENI
ecs.vgn6i-m4.xlarge 4 23.0 NVIDIA T4 * 1/4 16GB * 1/4 3.0 500 2 4 10
ecs.vgn6i-m8.2xlarge 10 46.0 NVIDIA T4 * 1/2 16GB * 1/2 4.0 800 4 5 20
Note

vgn5i, lightweight GPU-accelerated compute optimized instance family

Features
  • If you want your vgn5i instance to support graphics features such as Open Graphics Library (OpenGL), you must purchase a GRID license from NVIDIA. Then, you must create an instance and manually install a GRID driver and activate the license after the instance is created.
  • Compute:
    • Uses NVIDIA P4 GPU computing accelerators.
    • Contains virtual GPUs generated from GPU slice virtualization.
      • Supports the 1/8, 1/4, 1/2, and 1/1 computing capacity of NVIDIA Tesla P4 GPUs.
      • Supports 1 GB, 2 GB, 4 GB, and 8 GB of GPU memory.
    • Offers a CPU-to-memory ratio of 1:3.
    • Uses 2.5 GHz Intel ® Xeon ® E5-2682 v4 (Broadwell) processors.
  • Storage:
    • Is an instance family in which all instances are I/O optimized.
    • Supports standard SSDs and ultra disks only.
  • Network:
    • Supports IPv6 addresses.
    • Provides high network performance based on large computing capacity.
  • Suits the following scenarios:
    • Real-time rendering for cloud games
    • Real-time rendering for AR and VR applications
    • AI (deep learning and machine learning) inference for elastic Internet service deployment
    • Educational environment of deep learning
    • Modeling experiment environment of deep learning
Instance types
Instance type vCPU Memory (GiB) GPU GPU memory Bandwidth (Gbit/s) Packet forwarding rate (Kpps) NIC queues ENIs Private IP addresses per ENI
ecs.vgn5i-m1.large 2 6.0 NVIDIA P4 * 1/8 8GB * 1/8 1.0 300 2 2 6
ecs.vgn5i-m2.xlarge 4 12.0 NVIDIA P4 * 1/4 8GB * 1/4 2.0 500 2 3 10
ecs.vgn5i-m4.2xlarge 8 24.0 NVIDIA P4 * 1/2 8GB * 1/2 3.0 800 2 4 10
ecs.vgn5i-m8.4xlarge 16 48.0 NVIDIA P4 * 1 8GB * 1 5.0 1,000 4 5 20
Note