Microsoft have released a new instance powered by NVIDIA A10 GPUs and AMD EPYC 74F3V(Milan) CPU with a base frequency of 3.2 Ghz, all cores peak frequency of 4.0Ghz. With NVadsA10v5-series Azure is introducing virtual machines with partial NVIDIA GPUs. Pick the right sized virtual machine for GPU accelerated graphics applications and virtual desktops starting at 1/6th of a GPU with 4-GiB frame buffer to a full A10 GPU with 24-GiB frame buffer.
The preview is currenty availabe in Azure – US South Central and Azure – West Europe regions.
Prices are now GA (21th March 2022) for North Europe, US East 2, US West3
NVIDIA Ampere GPU (A10) is supporting GPU-P (SR-IOV) which is why its a big step for partitioning the GPU and making the price dramatically cheaper in Azure. *note there have not been released any prices yet of the instances (its unknown)
It’s time to plan updating your NVIDIA Enterprise GPUs. NVIDIA vGPU Software 13 is now GA since August 2021.
NVIDIA vGPU software includes vWS, vCS, vPC, and vApps.
If you got any of followin NVIDIA GPU’s: A10, A16, A30, A40, A100, M6, M10, M60, P4, P6, P40, P100, V100, T4, RTX A5000, RTX A6000, RTX6000, RTX8000 If you are interested in a quick overview of which NVIDIA enterprise GPU is supporting which hypervisor, Guest os and remoting technology, I highly recommend you check out this link from NVIDIA that provides the NVIDIA vGPU software product support matrix.NVIDIA vGPU software 13 is supported until August 2024. NVIDIA vGPU software 13 is a Long-Termin Support Branch.
I this article, I am also covering which Public Cloud instance is available with NVIDIA GPUs and which license is BYO or provided by the public cloud provider such as Azure, AWS, GCP, Alibaba.
Tracing and profiling through the CUDA Profiling Tools Interface (CUPTI)
Compatibility with the guest VM drivers from the previous long-term support branch (11)
Single-slice GPU instances with decoder support
Miscellaneous bug fixes
Hardware and Software Support Introduced in Release 13.0
Support for the following GPUs:
NVIDIA A100 PCIe 80GB
NVIDIA A30
NVIDIA A16
Support for Windows Server 2022 with Hyper-V role
Support for Windows Server 2022 as a guest OS
Support for Citrix Virtual Apps and Desktops version 7 2106
Support for VMware Horizon 2106 (8.3)
Feature Support Withdrawn in Release 13.0
The following GPUs are no longer supported on VMware vSphere:
NVIDIA A100 HGX 80GB
NVIDIA A100 PCIe 40GB
NVIDIA A100 HGX 40GB
Instead, these GPUs are supported on VMware vSphere with NVIDIA AI Enterprise.
NVIDIA Virtual Compute Server (vCS) is no longer supported on VMware vSphere and C-series vGPU types are no longer available. Instead, vCS is supported on VMware vSphere with NVIDIA AI Enterprise.
The base VMware vSphere 7.0 release and VMware vSphere 7.0 Update 1 are no longer supported.
Its time to plan updating your NVIDIA TESLA M6, M10, M60, P4, P6, P40, P100, V100, T4, RTX6000, RTX8000 with NVIDIA vGPU software 10.0. NVIDIA have released new drivers for vGPU 10.0.
I have in this article also included which Public Cloud instance is available with NVIDIA GPUs and which license is BYO or provided by the public cloud provider such as Alibaba, Azure, AWS, GCP, Alibaba.
NVIDIA vGPU 10.0 is only supported with Citrix Virtual Apps & Desktops 7.15, 7 1808, 7 1903, 7 1906, 7 1909, 7 1912 in HDX 3D Pro mode
If you are a customer using XenServer 7.2, 7.3, 7.4, 7.5 its no longer supported with NVIDIA vGPU 10.0 and should plan upgrading to Citrix Hypervisor 8.1
This release includes the following software:
NVIDIA vGPU Manager version 440.43 for the Citrix Hypervisor, VMware vSphere, RHEL KVM, Nutanix AHV
NVIDIA Windows driver version 441.66
NVIDIA Linux driver version 440.43
New Features in Release 10.0
Support for NVIDIA® GRID™ Virtual PC and GRID Virtual Applications on Quadro RTX 6000 and Quadro RTX 8000 GPUs
Increase in the maximum number of virtual display heads supported by -1Q, -2B, and -1B4 vGPUs:
All -1Q vGPUs now support 4 heads instead of 2 heads.
All -2B vGPUs now support 4 heads instead of 2 heads.
All -1B4 vGPUs now support 4 heads instead of 1 head.
Flexible virtual display resolutions
Instead of a fixed maximum resolution per head, vGPUs now support a maximum combined resolution based on their frame buffer size. This behavior allows the same number of lower resolution displays to be used as before, but alternatively allows a smaller number of higher resolution displays to be used.
Virtual display resolutions greater than 4096×2160
10-bit color
Changes to allow cross-branch driver support in future main release branches
Note: This feature cannot be used until the next NVIDIA vGPU software main release branch is available.
The purpose of this change is to allow a release of the Virtual GPU Manager from a later main release branch to be used with the NVIDIA vGPU software graphics drivers for the guest VMs from the previous branch.
Miscellaneous bug fixes
Hardware and Software Support Introduced in Release 10.0
Support for passively cooled Quadro RTX 6000 and Quadro RTX 8000 GPUs
Support for Tesla V100S PCIe 32GB GPUs
Support for Red Hat Enterprise Linux 8.1 as a guest OS
Support for Red Hat Enterprise Linux 8.0 and CentOS 8.0 as a guest OS
Support for Windows 10 November 2019 Update (1909) as a guest OS
Support for Citrix Virtual Apps and Desktops version 7 1912
Support for Citrix Hypervisor 8.1
Support for VMware Horizon 7.11
Features Deprecated in Release 10.0
The following table lists features that are deprecated in this release of NVIDIA vGPU software. Although the features remain available in this release, they might be withdrawn in a future release. In preparation for the possible removal of these features, use the preferred alternative listed in the table.
Its time to plan updating your NVIDIA TESLA M6, M10, M60, P4, P6, P40, P100, V100, T4, RTX6000, RTX8000 with NVIDIA vGPU software 9.0
NVIDIA have released new drivers for NVIDIA vGPU 9.0 for June 2019 This new-feature branch is supported until June 2020.
I have in this article also included which Public Cloud instance is available with NVIDIA GPUs and which license is BYO or provided by the public cloud provider such as Alibaba, Azure, AWS, GCP. One of the news is that Alibaba is supporting vGPU in their offerings which is pretty awesome.
Citrix XenServer 7.0, 7.1 is not supported with NVIDIA Tesla T4
NVIDIA vGPU 9.0 is supported with VMware Horizon 7.9 7.8, 7.7, 7.6, 7.5, 7.4, 7.3, 7.2, 7.1, 7.0, 6.2
NVIDIA vGPU 9.0 is only supported with Citrix Virtual Apps & Desktops 7.15, 7.18, 7 1903, 7 1906 in HDX 3D Pro mode
If you are a customer using XenServer 7.2, 7.3, 7.4, 7.5 its no longer supported with NVIDIA vGPU 9.0 and should plan upgrading to XenServer 7.6 or Citrix Hypervisor 8.0
This release includes the following software:
NVIDIA vGPU Manager version 430.27 for the Citrix Hypervisor, VMware vSphere, RHEL KVM, Nutanix AHV
NVIDIA Windows driver version 431.02
NVIDIA Linux driver version 430.30
New in this Release:
New Features in Release 9.0
NVIDIA vComputeServer vGPUs for artificial intelligence, deep learning, and high-performance computing workloads
Error correcting code (ECC) memory support
Page retirement support
Peer-to-peer CUDA transfers over NVLinksupport
Configurable times slices for equal share schedulers and fixed share schedulers
New configuration parameter to specify host ID of a licensed client
Hardware and Software Support Introduced in Release 9.0
Support for Windows 10 May 2019 Update (1903) as a guest OS
Support for Ubuntu 18.04 LTS as a guest OS on Citrix Hypervisor 7.1 cumulative update 2
Its time to plan updating your NVIDIA TESLA M6, M10, M60, P4, P6, P40, P100, V100, T4, RTX6000, RTX8000 with NVIDIA vGPU software 8.0
NVIDIA have released new drivers for NVIDIA vGPU 8.0 for April 2019
NVIDIA vGPU 8.0 is a MAJOR release with many new software features + support for the new RTX6000 and RTX8000 GPUs, which are NVIDIA flagship for Real Time Raytracing. The great thing is now they have vGPU capabilities, which is a BIG NEWS.
I have in this article also included which Public Cloud instance is available with NVIDIA GPUs and which license is BYO or provided by the public cloud provider such as Azure, AWS, GCP.
Citrix XenServer 7.5 is not supported with vGPU 8.0
Citrix XenServer 7.0, 7.1 is not supported with NVIDIA Tesla T4
NVIDIA vGPU 8.0 is supported with VMware Horizon 7.8, 7.7, 7.6, 7.5, 7.4, 7.3, 7.2, 7.1, 7.0, 6.2
NVIDIA vGPU 8.0 is only supported with Citrix Virtual Apps & Desktops (aka XenDesktop) 7.15, 7.17, 7.18, 7 1808, 7 1903 in HDX 3D Pro mode
VMware vSphere ESXi 5.5 is no longer supported with NVIDIA vGPU 8.0
If you are a customer using XenServer 7.2, 7.3, 7.4, 7.5 its no longer supported with NVIDIA vGPU 8.0 and should plan upgrading to XenServer 7.6 or upcoming Citrix Hypervisor 8.0
Customer using Citrix XenServer 7.2, 7.3 is supported with NVIDIA vGPU 6.0 & 6.1
Customer using Citrix XenServer 7.4 is supported with NVIDIA vGPU 6.0 & 6.1 & 6.2
Customers using Citrix XenServer 7.0, 7.1, 7.6 is supported with NVIDIA vGPU 8.0
Customers using Citrix XenServer 7.0, 7.1 isn’t supported with XenMotion with vGPU
This release includes the following software:
NVIDIA vGPU Manager version 418.66 for the Citrix XenServer, VMware vSphere, RHEL KVM, Nutanix AHV
NVIDIA Windows driver version 425.31
NVIDIA Linux driver version 418.70
New in this Release:
Support for the following GPUs:
Quadro RTX 6000
Quadro RTX 8000
Support for the following OS releases as a guest OS:
Windows 10 October 2018 Update (1809)
Windows Server 2019
Support for Windows Server 2019 with Hyper-V role
New -1B4 virtual GPU types (4K resolution/1monitor on 1GB FB)
Support for multiple vGPUs of the following types in a single VM:
RTX6000-24Q
RTX8000-48Q
Above is valid for hypervisor
Red Hat Enterprise Linux with KVM
Red Hat Virtualization RHV 4.2
vGPU migration with ESX & XenMotion support on the following GPUs:
