Difference between revisions of "GPGPU-FedCloud"
Jump to navigation
Jump to search
Line 1: | Line 1: | ||
= Status of accelerated computing in Clouds = | = Status of accelerated computing in Clouds = | ||
<div>Need modification/support at all levels</div> | <div>Need modification/support at all levels</div> | ||
<br> | <br> | ||
*Chipset : HW virtualization support (otherwise some limitation) | |||
*OS level: correct kernel configuration for the accelerators | *OS level: correct kernel configuration for the accelerators | ||
*Hypervisor: configuration pass-through, vGPU | *Hypervisor: configuration pass-through, vGPU | ||
*CMFs: VM start, scheduler | *CMFs: VM start, scheduler | ||
*FedCloud facilities: accounting, information discovery | *FedCloud facilities: accounting, information discovery | ||
*Application: VM images with correct drivers for specific chipsets | *Application: VM images with correct drivers for specific chipsets<br> | ||
= Accelerators = | |||
== GPGPU (General-Purpose computing on Graphical Processing Units) == | |||
<div>NVIDIA GPU/Tesla/GRID, AMD Radeon/FirePro, Intel HD Graphics,...</div><div>Virtualization using VGA pass-through, vGPU (GPU partitioning) - NVIDIA GRID accelerators</div><div><br></div> |
Revision as of 14:33, 30 April 2015
Status of accelerated computing in Clouds
Need modification/support at all levels
- Chipset : HW virtualization support (otherwise some limitation)
- OS level: correct kernel configuration for the accelerators
- Hypervisor: configuration pass-through, vGPU
- CMFs: VM start, scheduler
- FedCloud facilities: accounting, information discovery
- Application: VM images with correct drivers for specific chipsets
Accelerators
GPGPU (General-Purpose computing on Graphical Processing Units)
NVIDIA GPU/Tesla/GRID, AMD Radeon/FirePro, Intel HD Graphics,...
Virtualization using VGA pass-through, vGPU (GPU partitioning) - NVIDIA GRID accelerators