<html>
    <head>
      <base href="https://bugs.freedesktop.org/">
    </head>
    <body><table border="1" cellspacing="0" cellpadding="8">
        <tr>
          <th>Bug ID</th>
          <td><a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - dEQP-VK tests running very long time"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=110432">110432</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>dEQP-VK tests running very long time
          </td>
        </tr>

        <tr>
          <th>Product</th>
          <td>Mesa
          </td>
        </tr>

        <tr>
          <th>Version</th>
          <td>git
          </td>
        </tr>

        <tr>
          <th>Hardware</th>
          <td>Other
          </td>
        </tr>

        <tr>
          <th>OS</th>
          <td>All
          </td>
        </tr>

        <tr>
          <th>Status</th>
          <td>NEW
          </td>
        </tr>

        <tr>
          <th>Severity</th>
          <td>normal
          </td>
        </tr>

        <tr>
          <th>Priority</th>
          <td>medium
          </td>
        </tr>

        <tr>
          <th>Component</th>
          <td>Drivers/DRI/i965
          </td>
        </tr>

        <tr>
          <th>Assignee</th>
          <td>intel-3d-bugs@lists.freedesktop.org
          </td>
        </tr>

        <tr>
          <th>Reporter</th>
          <td>lemody@gmail.com
          </td>
        </tr>

        <tr>
          <th>QA Contact</th>
          <td>intel-3d-bugs@lists.freedesktop.org
          </td>
        </tr></table>
      <p>
        <div>
        <pre>Some of the dEQP-VK tests spend a lot of time in compiler. In particular these
2 ones are heavily affected:

dEQP-VK.spirv_assembly.instruction.graphics.8bit_storage.32struct_to_8struct.storage_buffer_sint_geom
dEQP-VK.spirv_assembly.instruction.graphics.8bit_storage.32struct_to_8struct.storage_buffer_uint_geom

Normally with old Mesa take take 2-3 secs to complete but with current git I
measured today 38 minutes 43 seconds (!)


I've bisected this to following commit:

-------------- 8< -----------------------------
commit b031c643491a92a5574c7a4bd659df33f2d89bb6
Author: Ian Romanick <<a href="mailto:ian.d.romanick@intel.com">ian.d.romanick@intel.com</a>>
Date:   Thu Jan 17 17:53:40 2019 -0800

    nir: Convert a bcsel with only phi node sources to a phi node

    v2: Remove the original ALU instruciton after all of its readers are
    modified to read the new ALU instruction.

    v3: Fix an issue where a bcsel that may not be executed on a loop
    iteration due to a break statement is converted to a phi (and therefore
    incorrectly "executed").  Noticed by Tim.

    Bugzilla: <a class="bz_bug_link 
          bz_status_VERIFIED  bz_closed"
   title="VERIFIED FIXED - 4-27% performance drop in Vulkan benchmarks"
   href="show_bug.cgi?id=109216">https://bugs.freedesktop.org/show_bug.cgi?id=109216</a>
    Fixes: 8fb8ebfbb05 ("intel/compiler: More peephole select")
    Reviewed-by: Timothy Arceri <<a href="mailto:tarceri@itsqueeze.com">tarceri@itsqueeze.com</a>></pre>
        </div>
      </p>


      <hr>
      <span>You are receiving this mail because:</span>

      <ul>
          <li>You are the QA Contact for the bug.</li>
          <li>You are the assignee for the bug.</li>
      </ul>
    </body>
</html>