<html>
    <head>
      <base href="https://llvm.org/bugs/" />
    </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 --- - Improve NEON autovectorization?"
   href="https://llvm.org/bugs/show_bug.cgi?id=27103">27103</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>Improve NEON autovectorization?
          </td>
        </tr>

        <tr>
          <th>Product</th>
          <td>libraries
          </td>
        </tr>

        <tr>
          <th>Version</th>
          <td>3.8
          </td>
        </tr>

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

        <tr>
          <th>OS</th>
          <td>Linux
          </td>
        </tr>

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

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

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

        <tr>
          <th>Component</th>
          <td>Backend: ARM
          </td>
        </tr>

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

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

        <tr>
          <th>CC</th>
          <td>llvm-bugs@lists.llvm.org
          </td>
        </tr>

        <tr>
          <th>Classification</th>
          <td>Unclassified
          </td>
        </tr></table>
      <p>
        <div>
        <pre>Created <span class=""><a href="attachment.cgi?id=16107" name="attach_16107" title="VFP assembly">attachment 16107</a> <a href="attachment.cgi?id=16107&action=edit" title="VFP assembly">[details]</a></span>
VFP assembly

Benchmarking matrix multiplication Rust code
(<a href="https://github.com/bluss/matrixmultiply/">https://github.com/bluss/matrixmultiply/</a>), we find that on Cortex-A5:


Using VFP:

test mat_mul_f32::m004 ... bench:       1,632 ns/iter (+/- 51)
test mat_mul_f32::m007 ... bench:       3,767 ns/iter (+/- 56)
test mat_mul_f32::m008 ... bench:       4,151 ns/iter (+/- 96)
test mat_mul_f32::m012 ... bench:       8,712 ns/iter (+/- 408)

Using NEON:

test mat_mul_f32::m004 ... bench:       1,588 ns/iter (+/- 89)
test mat_mul_f32::m007 ... bench:       3,307 ns/iter (+/- 94)
test mat_mul_f32::m008 ... bench:       3,056 ns/iter (+/- 62)
test mat_mul_f32::m012 ... bench:       6,197 ns/iter (+/- 181)


Starting with m>=16 the speedup finally reaches 2x. Is there room for
improvement here?</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>