From: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
To: Chris Wilson <chris@chris-wilson.co.uk>, intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH 2/2] drm/i915/hsw/bdw: Enable resource streamer bits on MI_BATCH_BUFFER_START
Date: Fri, 15 May 2015 12:16:06 +0300 [thread overview]
Message-ID: <5555B956.10908@linux.intel.com> (raw)
In-Reply-To: <20150513102240.GB6652@nuc-i3427.alporthouse.com>
Hi,
On 05/13/2015 01:22 PM, Chris Wilson wrote:
> On Wed, May 13, 2015 at 11:13:24AM +0300, Abdiel Janulgue wrote:
>> Adds support for executing the resource streamer on BDW and HSW
>>
>> v2: Add support for Execlists (Minu Mathai <minu.mathai@intel.com>)
>>
>> Signed-off-by: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
>
> I would have liked to have seen the comments for HSW_CTX_TOTAL_SIZE
> updated to include the resource streamer requirements.
Comment block mention HSW_CTX_TOTAL_SIZE as 70720 bytes which already
implicitly include RS dwords.
I can add "70720 bytes include resource streamer dwords" to the comments
or do you want me to break this down further still?
>
> Also
>
> /* These flags are for resource streamer on HSW+ */
> if (!IS_HASWELL(ring->dev) && INTEL_INFO(ring->dev)->gen < 8)
> flags |= (MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN);
>
> implies to me that we should be setting something for hsw to
> save/restore RS that we do not currently. So either the comment needs
> fixing, or we have a lack of code.
I checked, the current code does disable context save and restore for RS
in HSW (commit e80f14b6d36e3e07111cf2ab084ef8dd5d015ce2)
But I've now modified this to:
if (IS_HASWELL(ring->dev))
flags |= (MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN);
so that MI_SET_CONTEXT includes RS context on HSW.
Anyway, this seems to work perfectly fine in HSW as well. I'll include
that in the next version.
>
> Note that intel_lrc.c has duplicate functions for gen8. :|
> -Chris
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2015-05-15 9:16 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-13 8:13 drm/i915/hsw/bdw: Enable resource streamer v2 Abdiel Janulgue
2015-05-13 8:13 ` [PATCH 1/2] drm/i915/hsw/bdw: Expose I915_EXEC_RESOURCE_STREAMER flag Abdiel Janulgue
2015-05-13 8:13 ` [PATCH 2/2] drm/i915/hsw/bdw: Enable resource streamer bits on MI_BATCH_BUFFER_START Abdiel Janulgue
2015-05-13 10:22 ` Chris Wilson
2015-05-15 9:16 ` Abdiel Janulgue [this message]
2015-05-15 11:39 ` Chris Wilson
-- strict thread matches above, loose matches on Subject: below --
2015-05-11 9:01 drm/i915/hsw/bdw: Enable resource streamer Abdiel Janulgue
2015-05-11 9:01 ` [PATCH 2/2] drm/i915/hsw/bdw: Enable resource streamer bits on MI_BATCH_BUFFER_START Abdiel Janulgue
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=5555B956.10908@linux.intel.com \
--to=abdiel.janulgue@linux.intel.com \
--cc=chris@chris-wilson.co.uk \
--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 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.