From: "Welty, Brian" <brian.welty@intel.com>
To: "Christian König" <christian.koenig@amd.com>,
"Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
dri-devel@lists.freedesktop.org,
"Matthew Brost" <matthew.brost@intel.com>,
intel-xe@lists.freedesktop.org
Cc: Dave Airlie <airlied@gmail.com>, Daniel Vetter <daniel@ffwll.ch>
Subject: [Intel-xe] ttm_bo and multiple backing store segments
Date: Thu, 29 Jun 2023 14:10:58 -0700 [thread overview]
Message-ID: <c886cd42-2a78-fe3e-405b-e531d54449fb@intel.com> (raw)
Hi Christian / Thomas,
Wanted to ask if you have explored or thought about adding support in
TTM such that a ttm_bo could have more than one underlying backing store
segment (that is, to have a tree of ttm_resources)?
We are considering to support such BOs for Intel Xe driver.
Some of the benefits:
* devices with page fault support can fault (and migrate) backing store
at finer granularity than the entire BO
* BOs can support having multiple backing store segments, which can be
in different memory domains/regions
* BO eviction could operate on smaller granularity than entire BO
Or is the thinking that workloads should use SVM/HMM instead of
GEM_CREATE if they want above benefits?
Is this something you are open to seeing an RFC series that starts
perhaps with just extending ttm_bo_validate() to see how this might
shape up?
-Brian
WARNING: multiple messages have this Message-ID (diff)
From: "Welty, Brian" <brian.welty@intel.com>
To: "Christian König" <christian.koenig@amd.com>,
"Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
dri-devel@lists.freedesktop.org,
"Matthew Brost" <matthew.brost@intel.com>,
intel-xe@lists.freedesktop.org
Subject: ttm_bo and multiple backing store segments
Date: Thu, 29 Jun 2023 14:10:58 -0700 [thread overview]
Message-ID: <c886cd42-2a78-fe3e-405b-e531d54449fb@intel.com> (raw)
Hi Christian / Thomas,
Wanted to ask if you have explored or thought about adding support in
TTM such that a ttm_bo could have more than one underlying backing store
segment (that is, to have a tree of ttm_resources)?
We are considering to support such BOs for Intel Xe driver.
Some of the benefits:
* devices with page fault support can fault (and migrate) backing store
at finer granularity than the entire BO
* BOs can support having multiple backing store segments, which can be
in different memory domains/regions
* BO eviction could operate on smaller granularity than entire BO
Or is the thinking that workloads should use SVM/HMM instead of
GEM_CREATE if they want above benefits?
Is this something you are open to seeing an RFC series that starts
perhaps with just extending ttm_bo_validate() to see how this might
shape up?
-Brian
next reply other threads:[~2023-06-29 21:11 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-29 21:10 Welty, Brian [this message]
2023-06-29 21:10 ` ttm_bo and multiple backing store segments Welty, Brian
2023-07-17 17:24 ` [Intel-xe] " Rodrigo Vivi
2023-07-17 17:24 ` Rodrigo Vivi
2023-07-19 9:02 ` Christian König
2023-07-19 9:02 ` Christian König
2023-08-04 0:19 ` Welty, Brian
2023-08-04 0:19 ` Welty, Brian
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=c886cd42-2a78-fe3e-405b-e531d54449fb@intel.com \
--to=brian.welty@intel.com \
--cc=airlied@gmail.com \
--cc=christian.koenig@amd.com \
--cc=daniel@ffwll.ch \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-xe@lists.freedesktop.org \
--cc=matthew.brost@intel.com \
--cc=thomas.hellstrom@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.