HP ProLiant WS460c HP Hardware Accelerated Graphics for Desktop Virtualization - Page 10
XenServer Multi-GPU pass-through considerations, Citrix XenServer NVIDIA GRID vGPU considerations - g6 workstation
View all HP ProLiant WS460c manuals
Add to My Manuals
Save this manual to your list of manuals |
Page 10 highlights
Technical white paper | HP Hardware Accelerated Graphics for Desktop Virtualization Table 3b. Client OS Support Matrix for WS460c XP XP 32 64 Vista Vista Win7 Win7 Win8 Win8 Server Server RHEL RHEL 32 64 32 64 32 64 2008 R2 2012 5 6 WS460c G6 Bare Metal Yes Yes Yes Yes Yes Yes No No Yes** Yes** Yes Yes WS460c Gen8 Bare Metal No No No No No Yes No No Yes** Yes** Yes Yes VMware vSGA VM No No No No Yes Yes Yes Yes No No No No VMware vDGA VM No No No No Yes Yes Yes Yes No No Yes*** Yes*** Citrix GPU pass-through VM Yes Yes Yes Yes Yes Yes Yes Yes Yes* Yes* No*** No*** True virtual GPU VM No No No No Yes Yes Yes Yes TBD TBD TBD TBD * GPU supported referenced in this table refers to Microsoft Hyper-V and Citrix XenApp. ** Server 2012 only supported on WS460c Gen8 when using NVIDIA GRID cards. Windows 2008/2012 Server OS only supported on WS460c as Hyper-V server. *** Concerning Linux pass-through GPU support • VMware only supports vDGA on Linux for DirectPath I/O (GPU compute) • Citrix does not formally support GPU pass-through on Linux • Neither VMware View nor Citrix XenDesktop support brokering Linux desktop at this time XenServer Multi-GPU pass-through considerations • GPU pass-through technology allows for maximum graphical performance (Workstation grade) as each VM has a dedicated GPU attached • XenServer only supports passing through only 1 GPU per VM • When creating a VM with workstation class graphics performance, you will also need to give it workstation class resources with at least 2 vCPU and 2-4 Gb memory • GPU to VM density determined by number of GPUs, this model uses one GPU per VM, no sharing Citrix XenServer NVIDIA GRID vGPU considerations • Each physical GPU can be split into 2 or 4 vGPUs • NVIDIA GRID K1 and K2 cards have multiple GPUs per card: GRID K1 has 4 K600 level GPUs with 16 GB of vRAM and GRID K2 has 2 K5000 level GPUs with 8 GB of vRAM • At time of this writing, the predefined GRID vGPU are as follows, only same type vGPUs can be used on the same physical GPUs (table 4) Table 4. GRID vGPU types Card Physical GPUs Virtual GPU Use case Frame buffer Virtual display Maximum (MB) heads resolution Maximum vGPUs per GPU per Board GRID K2 2 GRID K260Q Typical Designer 2048 4 2560 x 1600 2 4 GRID K2 2 GRID K240Q Entry-Level Designer 1024 2 2560 x 1600 4 8 GRID K2 2 GRID K200 Knowledge Worker 256 2 1920 x 1200 8 16 GRID K1 4 GRID K140Q Basic Designer 1024 2 2560 x 1600 4 16 GRID K1 4 GRID K100 Knowledge Worker 256 2 1920 x 1200 8 32 • When creating a VM with workstation class graphics performance, you will also need to give it workstation class resources with at least 2 vCPU and 2-4 Gb Memory 10