<table border="1" cellspacing="0" cellpadding="8">
<tr>
<th>Issue</th>
<td>
<a href=https://github.com/llvm/llvm-project/issues/69671>69671</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>
[adrp] Is there a way to use adrp instructions for accessing data in very large structs?
</td>
</tr>
<tr>
<th>Labels</th>
<td>
new issue
</td>
</tr>
<tr>
<th>Assignees</th>
<td>
</td>
</tr>
<tr>
<th>Reporter</th>
<td>
erickq
</td>
</tr>
</table>
<pre>
In my recent research work, I found that versions above gcc12 tend to generate adrp, improved address rematerialization, for very large memory accesses, which improves performance.
Is there any way clang can achieve a similar effect?
</pre>
<img width="1px" height="1px" alt="" src="http://email.email.llvm.org/o/eJxMkc-OpDwMxJ8mXKxpQfjTw4HDfN8IqR_DJAayE5JeO3SLffpV6F3NXpKDyyXXr1DELYFoUO1_qv0scE9r5IHYma-fxRTtMdwCbAcwGQoJmISQzQrPyF9K_w83mOMeLKQVEzyIxcUggFN8ECzGVBoS5XGEhQIxJgK0fM-rbrtzfJAFtJZJBJg2TMQOvfuFycWQVXPk7HuAR14INtoiH4DGkAhJVjxXZ9a_bgJ34jnyhsHQRZWfqvx4vTeBtBITYDjgiQcYj2EBgwHQrI4eBAjiNueRgeaZTFL1WNihtn3dY0FD1fXXa9e1_XuxDn2J8zy1uunbCduJqkpPbW30tZuvVdOYwg261HVV6rKsmr59vzTvta111RJ1dtZNp5qSNnT-4v1ju0ReCiey09D13bUqPE7k5exF60BPOIdK61wTD3nnbdoXUU3pnST5dkku-bPQE3T7Cd_Jz9wpwi6vGsAFSbybdLaWUb_AurCAxYTgwr_wX1rJWHb2w5rSXVT9ofSo9Li4tO7TxcRN6TEf8-d7u3P8kWHq8YwgSo9nxN8BAAD__0ni1Yw">