<html>
    <head>
      <base href="https://bugs.llvm.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 - [Matrix] Allow specifying the width of the accumulator for matrix multiplication"
   href="https://bugs.llvm.org/show_bug.cgi?id=47764">47764</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>[Matrix] Allow specifying the width of the accumulator for matrix multiplication
          </td>
        </tr>

        <tr>
          <th>Product</th>
          <td>clang
          </td>
        </tr>

        <tr>
          <th>Version</th>
          <td>trunk
          </td>
        </tr>

        <tr>
          <th>Hardware</th>
          <td>PC
          </td>
        </tr>

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

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

        <tr>
          <th>Severity</th>
          <td>enhancement
          </td>
        </tr>

        <tr>
          <th>Priority</th>
          <td>P
          </td>
        </tr>

        <tr>
          <th>Component</th>
          <td>-New Bugs
          </td>
        </tr>

        <tr>
          <th>Assignee</th>
          <td>unassignedclangbugs@nondot.org
          </td>
        </tr>

        <tr>
          <th>Reporter</th>
          <td>florian_hahn@apple.com
          </td>
        </tr>

        <tr>
          <th>CC</th>
          <td>htmldeveloper@gmail.com, llvm-bugs@lists.llvm.org, neeilans@live.com, richard-llvm@metafoo.co.uk
          </td>
        </tr></table>
      <p>
        <div>
        <pre>Sometimes it is desirable to perform matrix multiplications where the results
are accumulated in a wider type than the inputs, for example because this
allows to use of specialized instructions, e.g. AArch64's udot instruction.

We would need a way to express this using the C/C++ extension and for
@llvm.matrix.multiply.

We could allow different element types for the return type of
@llvm.matrix.multiply and have the width of the result type indicate the width
of the accumulator to be used. If users want to truncate/extend the result of
the multiplication, this can be done using zext/trunc already.

On the C/C++ side, I am not sure we can get away with this, because the
extension allows conversions between matrixes with different element types, so
we probably would need a way to specify the accumulator width explicitly,
perhaps using a specialized multiply builtin.

This was discussed on cfe-dev
(<a href="http://lists.llvm.org/pipermail/cfe-dev/2020-August/066489.html">http://lists.llvm.org/pipermail/cfe-dev/2020-August/066489.html</a>) and also
raised during the Q&A of the "Matrix Support in Clang and LLVM" talk.</pre>
        </div>
      </p>


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

      <ul>
          <li>You are on the CC list for the bug.</li>
      </ul>
    </body>
</html>