<table border="1" cellspacing="0" cellpadding="8">
<tr>
<th>Issue</th>
<td>
<a href=https://github.com/llvm/llvm-project/issues/138336>138336</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>
Funnel shift is not lowered to an intrinsic in 64-bit
</td>
</tr>
<tr>
<th>Labels</th>
<td>
new issue
</td>
</tr>
<tr>
<th>Assignees</th>
<td>
</td>
</tr>
<tr>
<th>Reporter</th>
<td>
AZero13
</td>
</tr>
</table>
<pre>
Yes I know this has two cases of subpar optimization: One where the funnel shift is 64-bit based, and the other is left funnel shifts that can be converted to a right funnel shift. This one is about the latter. However, this was lifted from one of gcc's test suites.
https://godbolt.org/z/Yd63ed3sv
</pre>
<img width="1" height="1" alt="" src="http://email.email.llvm.org/o/eJxcUT-P3C4Q_TS4GZ3lhTW-LSj294uspEqT5tIBHhsSFlbMeK3cp49srRTdVRS8f_OeJYpLRjSi_0_0Xxq7cijVXH9iLSfVuDL9MW9I8A1-57IBh0gQLAFvBbwlJCgz0OrutkK5c7zFd8uxZKGu8D0jbAErAgeEec0ZE1CIM0Mk0OcXFxmcJZyE_B9sng5c4YB1BySc-QOLgINl8DaDQ_AlP7AyTsAFLNS4hI_wFn7saUvGXc26svJhkCwz1ha-lg0fWHfv46zNEqQ474pzLbeDWGZYvBdyIGAkBlojI7UguqvoroH5TkJdhRyFHJcyuZK4LXURcnwXcnybtMJJ0aOZjJou6mIbNKfhrOVJX7RqgrlIPU_61ble-q7vh27wqPyrH1x_Vlq7JhrZyb7rOym7k-5UO8-qP3k7OTUPergM4tzhzcbUpvS47d5NJFrRnNSrUrpJ1mGiY10pM25w_Aop97Gr2Ukvbl1InLsUiemfDEdOaMZPq-XCkMqG9dl7hpi5xkzRQ8zPUZu1JvOpnMhhda0vNyHH3eP5vNxr-YWehRyPZCTk-Iz-MPJvAAAA__-20d55">