<div class="gmail_quote">On Wed, Feb 8, 2012 at 18:53, Kenneth Graunke <span dir="ltr"><<a href="mailto:kenneth@whitecape.org">kenneth@whitecape.org</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
These fix many GPU hangs for Eugeni, though not on my machine for some<br>
reason.<br>
<br>
Oddly, the register writes to UCGCTL2 and SQ_CHICKEN_MBCUNIT_CONFIG stick,<br>
but the writes to L3_CHICKEN_MODE, L3CNTLREG1, and COMMON_SLICE_CHICKEN1<br>
don't seem to take effect. Currently no theories why.<br>
<br>
Manually writing these values with intel_reg_write /does/ fix the hangs<br>
for me.<br>
<br>
I'm fine with these going to -fixes. They seem to help some people, and<br>
I highly doubt they'll make anything worse. It'd be nice to understand<br>
why the register writes aren't sticking, though...<br></blockquote><div><br>Complementing Ken's mail, Li Bo from our QA team has did a full round of tests with these patches on IVB and all known issues were gone apparently.<br>
<br>Keith, Jesse - I think they are good -fixes candidates at this point.<br><br></div></div>-- <br>Eugeni Dodonov<a href="http://eugeni.dodonov.net/" target="_blank"><br></a><br>