Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Belgaumkar, Vinay" <vinay.belgaumkar@intel.com>
To: Rodrigo Vivi <rodrigo.vivi@intel.com>, <intel-xe@lists.freedesktop.org>
Subject: Re: [PATCH 2/3] drm/xe/lnl: Enable GuC SLPC DCC task
Date: Tue, 22 Oct 2024 17:00:46 -0700	[thread overview]
Message-ID: <da1914c6-40f8-4dd2-b9c9-009a41487a3e@intel.com> (raw)
In-Reply-To: <20241009183648.36948-2-rodrigo.vivi@intel.com>


On 10/9/2024 11:36 AM, Rodrigo Vivi wrote:
> Enable DCC (Duty Cycle Control) in Lunar Lake.
>
> DCC is the SLPC task that tries to keep
> the GT from operating inefficiently when thermally constrained.
>
> Although the recommendation is to enable it, LNL GuC is leaving
> it disabled by default on LNL.
>
> It would minimize the GT frequency oscilation on throttled
> scenarios, what could potentially reduce latencies.
>
> Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_guc_pc.c | 14 ++++++++++++++
>   1 file changed, 14 insertions(+)
>
> diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
> index 4b38523c49e9..d141165e016b 100644
> --- a/drivers/gpu/drm/xe/xe_guc_pc.c
> +++ b/drivers/gpu/drm/xe/xe_guc_pc.c
> @@ -948,6 +948,16 @@ static int pc_init_freqs(struct xe_guc_pc *pc)
>   	return ret;
>   }
>   
> +static int slpc_set_policies(struct xe_guc_pc *pc)
> +{
> +	struct xe_device *xe = pc_to_xe(pc);
> +
> +	if (xe->info.platform == XE_LUNARLAKE)
> +		return pc_action_set_param(pc, SLPC_PARAM_TASK_ENABLE_DCC, 1);
> +
> +	return 0;
> +}
> +
>   /**
>    * xe_guc_pc_start - Start GuC's Power Conservation component
>    * @pc: Xe_GuC_PC instance
> @@ -983,6 +993,10 @@ int xe_guc_pc_start(struct xe_guc_pc *pc)
>   	if (ret)
>   		goto out;
>   
> +	ret = slpc_set_policies(pc);
> +	if (ret)
> +		goto out;
> +

Might be better to call set_policies after the wait_for_pc_state below? 
Since we just did a reset. Although, pc_action_set_param() also does a 
wait for running state, so we have some redundancy here.

Thanks,

Vinay,

>   	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING)) {
>   		xe_gt_err(gt, "GuC PC Start failed\n");
>   		ret = -EIO;

  reply	other threads:[~2024-10-23  0:00 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-09 18:36 [PATCH 1/3] drm/xe: Introduce GuC PC debugfs Rodrigo Vivi
2024-10-09 18:36 ` [PATCH 2/3] drm/xe/lnl: Enable GuC SLPC DCC task Rodrigo Vivi
2024-10-23  0:00   ` Belgaumkar, Vinay [this message]
2024-10-09 18:36 ` [PATCH 3/3] drm/xe: Introduce the RPa information Rodrigo Vivi
2024-10-09 20:46 ` ✓ CI.Patch_applied: success for series starting with [1/3] drm/xe: Introduce GuC PC debugfs Patchwork
2024-10-09 20:46 ` ✓ CI.checkpatch: " Patchwork
2024-10-09 20:47 ` ✓ CI.KUnit: " Patchwork
2024-10-09 21:06 ` ✓ CI.Build: " Patchwork
2024-10-09 21:09 ` ✓ CI.Hooks: " Patchwork
2024-10-09 21:10 ` ✗ CI.checksparse: warning " Patchwork
2024-10-09 21:42 ` ✓ CI.BAT: success " Patchwork
2024-10-10 10:50 ` ✗ CI.FULL: failure " Patchwork
2024-10-22 23:55 ` [PATCH 1/3] " Belgaumkar, Vinay

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=da1914c6-40f8-4dd2-b9c9-009a41487a3e@intel.com \
    --to=vinay.belgaumkar@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=rodrigo.vivi@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