On 15/02/2019 16:30, David Gibson wrote:
> On Fri, Feb 15, 2019 at 03:42:56PM +1100, Alexey Kardashevskiy wrote:
>>
>>
>> On 15/02/2019 14:22, David Gibson wrote:
>>> On Thu, Feb 14, 2019 at 04:21:44PM +1100, Alexey Kardashevskiy wrote:
NVIDIA V100 GPUs have on-board RAM which is mapped int
On Fri, Feb 15, 2019 at 03:42:56PM +1100, Alexey Kardashevskiy wrote:
>
>
> On 15/02/2019 14:22, David Gibson wrote:
> > On Thu, Feb 14, 2019 at 04:21:44PM +1100, Alexey Kardashevskiy wrote:
> >> NVIDIA V100 GPUs have on-board RAM which is mapped into the host memory
> >> space and accessible as
On 15/02/2019 14:22, David Gibson wrote:
> On Thu, Feb 14, 2019 at 04:21:44PM +1100, Alexey Kardashevskiy wrote:
>> NVIDIA V100 GPUs have on-board RAM which is mapped into the host memory
>> space and accessible as normal RAM via an NVLink bus. The VFIO-PCI driver
>> implements special regions f
On Thu, Feb 14, 2019 at 04:21:44PM +1100, Alexey Kardashevskiy wrote:
> NVIDIA V100 GPUs have on-board RAM which is mapped into the host memory
> space and accessible as normal RAM via an NVLink bus. The VFIO-PCI driver
> implements special regions for such GPUs and emulates an NVLink bridge.
> NVL
NVIDIA V100 GPUs have on-board RAM which is mapped into the host memory
space and accessible as normal RAM via an NVLink bus. The VFIO-PCI driver
implements special regions for such GPUs and emulates an NVLink bridge.
NVLink2-enabled POWER9 CPUs also provide address translation services
which inclu
