dri-devel.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: bugzilla-daemon@freedesktop.org
To: dri-devel@lists.freedesktop.org
Subject: [Bug 34377] New: Radeon driver PCIe throughput not up to PCIe2.0 levels
Date: Thu, 17 Feb 2011 01:12:43 -0800 (PST)	[thread overview]
Message-ID: <bug-34377-502@http.bugs.freedesktop.org/> (raw)

https://bugs.freedesktop.org/show_bug.cgi?id=34377

           Summary: Radeon driver PCIe throughput not up to PCIe2.0 levels
           Product: Mesa
           Version: git
          Platform: x86 (IA32)
        OS/Version: Linux (All)
            Status: NEW
          Severity: normal
          Priority: medium
         Component: Drivers/DRI/R600
        AssignedTo: dri-devel@lists.freedesktop.org
        ReportedBy: lucvermoesen@gmail.com


Created an attachment (id=43476)
 --> (https://bugs.freedesktop.org/attachment.cgi?id=43476)
test data and test program for PCIe gen2 issue

On an HD5450 card, when I load the latest gallium3D driver with kernel
2.6.38-rc4 and firmware I got from
http://people.freedesktop.org/~agd5f/radeon_ucode/ , this together with the
latest git checkouts for X and modules (and thus also xf86-video-ati) and
latest mesa git checkout that has been built with –enable-gallium-r600

installing the radeon kernel module with 
modprobe radeon modeset=1 pcie_gen2=1


Then I get 0.5GB/s CPU->GPU 
From GPU -> CPU, I get about the same 0.5GB/s.

When I load the fglrx ati proprietary driver (11.1) for the 5450 card, then I
get throughputs of about 2GB/s in both directions. 

Running the same test in same environment on the HD5970 
with the gallium drivers and kernel mode setting and pcie_gen2 activation, i
get about the same figures as above.
With fglrx for 5970, then 5970 only performs well in CPU->GPU with about 2GB/s
and only 0.5GB/s in GPU->CPU direction 

I have included the test and configuration output for both cases (fglrx and
radeon) and also code for the testprogram might you want to reproduce this
case.

-- 
Configure bugmail: https://bugs.freedesktop.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

             reply	other threads:[~2011-02-17  9:12 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-02-17  9:12 bugzilla-daemon [this message]
2012-11-02 16:37 ` [Bug 34377] Radeon driver PCIe throughput not up to PCIe2.0 levels bugzilla-daemon
2013-05-12  7:38 ` bugzilla-daemon
2013-05-12  7:42 ` bugzilla-daemon
2013-05-12 14:03 ` bugzilla-daemon
2014-07-07 16:04 ` bugzilla-daemon

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=bug-34377-502@http.bugs.freedesktop.org/ \
    --to=bugzilla-daemon@freedesktop.org \
    --cc=dri-devel@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).