From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
To: "Christian König" <christian.koenig@amd.com>,
dri-devel@lists.freedesktop.org
Cc: Alex Deucher <alexander.deucher@amd.com>,
intel-gfx@lists.freedesktop.org, Xinhui Pan <Xinhui.Pan@amd.com>
Subject: Re: [Intel-gfx] [PATCH 0/3] drm/helpers: Make the suballocation manager drm generic.
Date: Thu, 24 Feb 2022 21:39:03 +0100 [thread overview]
Message-ID: <b2775a1f-0bf1-99ad-ba89-ea9fb4ebce4e@linux.intel.com> (raw)
In-Reply-To: <868b0d69-0620-95a6-ed47-7f89288afdc5@amd.com>
Op 23-02-2022 om 16:11 schreef Christian König:
> Am 23.02.22 um 14:51 schrieb Maarten Lankhorst:
>> Second version of the patch. I didn't fix the copyright (which ame up
>> in the previous version), as I feel the original author should send a
>> patch for that.
>>
>> I've made the suballocator into its own module, and did a cleanup pass on it.
>> The suballocator is generic enough to be useful for any resource that can be
>> subdivided and is guarded by a completion fence.
>
> Well the main issue is still that you removed the per allocation alignment.
>
> For amdgpu that is not much of a problem, but for radeon that could cause massive issues with UVD semaphore synchronization.
Hey,
Is this really a problem? I made the per allocation alignment fixed and set it to the higher of the 2 places it's used in by radeon. This just means that slightly more memory might be allocated to each suballocation. This shouldn't cause any problem. It would reserve 256 bytes for a semaphore allocation, instead of 8.
~Maarten
next prev parent reply other threads:[~2022-02-24 20:39 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-23 13:51 [Intel-gfx] [PATCH 0/3] drm/helpers: Make the suballocation manager drm generic Maarten Lankhorst
2022-02-23 13:51 ` [Intel-gfx] [PATCH 1/3] drm: Extract amdgpu_sa.c as a generic suballocation helper Maarten Lankhorst
2022-02-23 13:51 ` [Intel-gfx] [PATCH 2/3] drm/amd: Convert amdgpu to use " Maarten Lankhorst
2022-02-23 13:51 ` [Intel-gfx] [PATCH 3/3] drm/radeon: Use the drm suballocation manager implementation Maarten Lankhorst
2022-02-23 15:11 ` [Intel-gfx] [PATCH 0/3] drm/helpers: Make the suballocation manager drm generic Christian König
2022-02-24 20:39 ` Maarten Lankhorst [this message]
2022-02-24 7:55 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for drm/helpers: Make the suballocation manager drm generic. (rev2) Patchwork
2022-02-24 7:56 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2022-02-24 8:26 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2022-02-24 20:28 ` [Intel-gfx] ✓ Fi.CI.IGT: " Patchwork
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=b2775a1f-0bf1-99ad-ba89-ea9fb4ebce4e@linux.intel.com \
--to=maarten.lankhorst@linux.intel.com \
--cc=Xinhui.Pan@amd.com \
--cc=alexander.deucher@amd.com \
--cc=christian.koenig@amd.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-gfx@lists.freedesktop.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox