From: "Hajda, Andrzej" <andrzej.hajda@intel.com>
To: "Zbigniew Kempczyński" <zbigniew.kempczynski@intel.com>,
igt-dev@lists.freedesktop.org
Cc: Priyanka Dandamudi <priyanka.dandamudi@intel.com>
Subject: Re: [PATCH i-g-t v2 1/2] lib/gpgpu_fill: Add support for xe3p gpgpu fill
Date: Wed, 6 May 2026 13:08:16 +0200 [thread overview]
Message-ID: <48a445f0-bd77-4b1f-a58b-a0484d15214d@intel.com> (raw)
In-Reply-To: <20260506065500.162563-5-zbigniew.kempczynski@intel.com>
W dniu 6.05.2026 o 08:55, Zbigniew KempczyÅski pisze:
> XE3P uses in non-legacy mode COMPUTE_WALKER_2 so adopt pipeline and
> shader in gpgpu library to properly handle gpgpu fill.
>
> Difference between previous platforms shaders is no surface state
> is used so all geometry must be handled by the pipeline / shader
> (accesses to memory are via untyped global [ugm]). Threads spawned
> here are still SIMD16, but due to conditional writing to ugm memory
> with 4B vector using 4x1 sizes and positions become possible.
>
> Signed-off-by: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com>
> Cc: Priyanka Dandamudi <priyanka.dandamudi@intel.com>
> Cc: Andrzej Hajda <andrzej.hajda@intel.com>
> ---
> v2: drop buffer patching and pass its offset via inline (Andrzej)
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Regards
Andrzej
next prev parent reply other threads:[~2026-05-06 11:08 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-06 6:55 [PATCH i-g-t v2 0/2] Extend gpgpu fill support to XE3P Zbigniew Kempczyński
2026-05-06 6:55 ` [PATCH i-g-t v2 1/2] lib/gpgpu_fill: Add support for xe3p gpgpu fill Zbigniew Kempczyński
2026-05-06 11:08 ` Hajda, Andrzej [this message]
2026-05-06 6:55 ` [PATCH i-g-t v2 2/2] tests/xe_gpgpu_fill: Add subtest with 4x4 position for XE3P Zbigniew Kempczyński
2026-05-06 7:38 ` ✗ i915.CI.BAT: failure for Extend gpgpu fill support to XE3P (rev2) Patchwork
2026-05-06 7:58 ` ✓ Xe.CI.BAT: success " Patchwork
2026-05-06 8:59 ` ✗ Xe.CI.FULL: failure " Patchwork
2026-05-06 13:09 ` Zbigniew Kempczyński
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=48a445f0-bd77-4b1f-a58b-a0484d15214d@intel.com \
--to=andrzej.hajda@intel.com \
--cc=igt-dev@lists.freedesktop.org \
--cc=priyanka.dandamudi@intel.com \
--cc=zbigniew.kempczynski@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox