Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
To: Francois Dugast <francois.dugast@intel.com>
Cc: <intel-xe@lists.freedesktop.org>,
	Matthew Brost <matthew.brost@intel.com>
Subject: Re: [PATCH] drm/xe/migrate: Configure migration queue as low latency
Date: Tue, 23 Dec 2025 10:07:56 -0500	[thread overview]
Message-ID: <aUqwTJaZfR5ly2CU@intel.com> (raw)
In-Reply-To: <20251223115327.49555-1-francois.dugast@intel.com>

On Tue, Dec 23, 2025 at 12:53:27PM +0100, Francois Dugast wrote:
> Commit 5488bec96bcc ("drm/xe/uapi: Use hint for guc to set GT frequency")
> introduced low latency hint for use by user space when creating an exec
> queue. This instructs SLPC to ramp the GT frequency aggressively.
> 
> SVM relies on an internal exec queue to migrate memory upon page faults.
> This change creates this exec queue with the low latency hint to speed up
> migration.
> 
> This should not impact systems where GT frequency is set over sysfs, or
> with long running workloads which give enough time for the frequency to
> ramp up. An example of memory access pattern that shows an improvement of
> SVM performance is running hundreds of times IGT eu-fault-2m-once-device
> in xe_exec_system_allocator. The copy duration provided by GT stats in
> svm_2M_device_copy_us shows per GPU page fault:
>     ~ 165 μs without low latency hint
>     ~ 130 μs with low latency hint
> 
> Suggested-by: Matthew Brost <matthew.brost@intel.com>
> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Signed-off-by: Francois Dugast <francois.dugast@intel.com>

pushed to drm-xe-next.

> ---
>  drivers/gpu/drm/xe/xe_migrate.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
> index 3de8ce2516e2..00eef41a9e36 100644
> --- a/drivers/gpu/drm/xe/xe_migrate.c
> +++ b/drivers/gpu/drm/xe/xe_migrate.c
> @@ -472,7 +472,8 @@ int xe_migrate_init(struct xe_migrate *m)
>  					    EXEC_QUEUE_FLAG_KERNEL |
>  					    EXEC_QUEUE_FLAG_PERMANENT |
>  					    EXEC_QUEUE_FLAG_HIGH_PRIORITY |
> -					    EXEC_QUEUE_FLAG_MIGRATE, 0);
> +					    EXEC_QUEUE_FLAG_MIGRATE |
> +					    EXEC_QUEUE_FLAG_LOW_LATENCY, 0);
>  	} else {
>  		m->q = xe_exec_queue_create_class(xe, primary_gt, vm,
>  						  XE_ENGINE_CLASS_COPY,
> -- 
> 2.43.0
> 

  parent reply	other threads:[~2025-12-23 15:08 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-23 11:53 [PATCH] drm/xe/migrate: Configure migration queue as low latency Francois Dugast
2025-12-23 12:25 ` ✓ CI.KUnit: success for drm/xe/migrate: Configure migration queue as low latency (rev2) Patchwork
2025-12-23 13:01 ` ✓ Xe.CI.BAT: " Patchwork
2025-12-23 15:07 ` Rodrigo Vivi [this message]
2025-12-23 23:48 ` ✗ Xe.CI.Full: failure " 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=aUqwTJaZfR5ly2CU@intel.com \
    --to=rodrigo.vivi@intel.com \
    --cc=francois.dugast@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.brost@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