Intel-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Ben Widawsky <ben@bwidawsk.net>
To: "Zhang, Xiong Y" <xiong.y.zhang@intel.com>
Cc: "intel-gfx@lists.freedesktop.org" <intel-gfx@lists.freedesktop.org>
Subject: Re: gfx context switch
Date: Wed, 12 Dec 2012 12:34:59 -0800	[thread overview]
Message-ID: <20121212203459.GA3288@lundgren> (raw)
In-Reply-To: <8082FF9BCB2B054996454E47167FF4ECC699DD@SHSMSX102.ccr.corp.intel.com>

On Wed, Dec 12, 2012 at 03:55:46PM +0000, Zhang, Xiong Y wrote:
> Hi, all:
> 
> When gfx executes batch buffer in render ring buffer, it will do
> context switch .
> 
> Since only when the previous batch buffer has finished, the next batch
> buffer can start. the batch buffer is executed in order. So I think
> there is no need to do context switch.
> 
> Why i915 driver introduce context switch ?  If context switch is
> disabled, what error will occur ?

No GPU state is preserved in between execution unless you use contexts.
Before contexts, it was required that the client upload any and all
state required to perform operations. While most state is still uploaded
anyway, some of it is not.

If you use a mesa expecting HW contexts, and a kernel which doesn't do
contexts switches, the results are undefined.

> 
> Why gfx need context switch, can somebody give me a example to use
> context switch ?

Transform feedback.

> 
> Thanks in advance.  _______________________________________________

-- 
Ben Widawsky, Intel Open Source Technology Center

      reply	other threads:[~2012-12-12 20:34 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-12-12 14:15 [PATCH] tests/gem_seqno_wrap: dont sync when crossing half of seqno space Mika Kuoppala
2012-12-12 15:55 ` gfx context switch Zhang, Xiong Y
2012-12-12 20:34   ` Ben Widawsky [this message]

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=20121212203459.GA3288@lundgren \
    --to=ben@bwidawsk.net \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=xiong.y.zhang@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