Re: Enabling peer to peer device transactions for PCIe devices

From	Alex Deucher <alexdeucher@gmail.com>
Newsgroups	linux.kernel
Subject	Re: Enabling peer to peer device transactions for PCIe devices
Date	2016-11-26 00:50 +0100
Message-ID	<sHypH-7cW-3@gated-at.bofh.it> (permalink)
References	(6 earlier) <sGR1o-44N-13@gated-at.bofh.it> <sH5nH-5hZ-7@gated-at.bofh.it> <sHuvL-4HW-7@gated-at.bofh.it> <sHuvL-4HW-9@gated-at.bofh.it> <sHuvL-4HW-5@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Fri, Nov 25, 2016 at 2:34 PM, Jason Gunthorpe
<jgunthorpe@obsidianresearch.com> wrote:
> On Fri, Nov 25, 2016 at 12:16:30PM -0500, Serguei Sagalovitch wrote:
>
>> b) Allocation may not  have CPU address  at all - only GPU one.
>
> But you don't expect RDMA to work in the case, right?
>
> GPU people need to stop doing this windowed memory stuff :)
>

Blame 32 bit systems and GPUs with tons of vram :)

I think resizable bars are finally coming in a useful way so this
should go away soon.

Alex

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

Re: Enabling peer to peer device transactions for PCIe devices Jason Gunthorpe <jgunthorpe@obsidianresearch.com> - 2016-11-25 20:40 +0100
  Re: Enabling peer to peer device transactions for PCIe devices Jason Gunthorpe <jgunthorpe@obsidianresearch.com> - 2016-11-25 21:30 +0100
  Re: Enabling peer to peer device transactions for PCIe devices Alex Deucher <alexdeucher@gmail.com> - 2016-11-26 00:50 +0100

csiph-web