<table border="1" cellspacing="0" cellpadding="8">
    <tr>
        <th>Issue</th>
        <td>
            <a href=https://github.com/llvm/llvm-project/issues/68768>68768</a>
        </td>
    </tr>

    <tr>
        <th>Summary</th>
        <td>
            [ARM][LV] SVE vs Advanced SIMD
        </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>
    I ran into a problem while reading this recently. [https://community.arm.com/arm-community-blogs/b/tools-software-ides-blog/posts/gcc-12]

![image](https://github.com/llvm/llvm-project/assets/12108571/269af467-7b2a-4fcf-bdac-88cef5843ced)

 I have a question. As mentioned in the sve vs advanced simd section, the test cases provided can generate neon mian loop followed by an SVE epilogue.. Do you need to add any special compilation options? I used gcc12 to compile the use case and did not generate the situation described in the article.
</pre>
<img width="1px" height="1px" alt="" src="http://email.email.llvm.org/o/eJyUk0_PpDYMxj9NuFggCP8PHGY6RRqpe-lKezeJB9KGhI3DjObbV7D79m2Pe8EIP9i_2E-Q2cyOaBD1VdS3BPe4-DBQMOrv78nk9Xu4Q0AHxkUPCFvwk6UVXouxBIFQGzdDXAxDIEUu2ncGor4uMW4syouQo5Cj8uu6OxPfGYY1U34VcsSwpv9-TyfrZxZynIQco_eWU_aP-MJAqdHEZ17IcfMcD9msVFpIUd9EfhP55edTFqK-mhVnOjKy-z_EbOKyTz-7W_v8COkW_F-k4sHETGf9QhZ5V7eFkKNsenxUTZu2k8S0eqhHOmlUadcpetRdVSrSQvb_BYE7LPgkQPi-E0fjXQYXhpXc8U4ajIO4EPCT4MmA-olOkQY2qwYmdaiE_O3UROIICpn4mP3TaNKg0MFMjgJGAkfewWrQgfV-g4e31r9Iw_QGdPD12-9Am7F-3inL4Obh7XdwRBqOfWoN6N7AGymDFpRfN2Px6A9-OwKLcoQ77EwaZqUKefz2Q0Yn38504gE6DdpocD5-wp2nNHH_UVITq2CmzwFgiEZZyhI9lLove0xoKJq-zfOulHWyDNSglNT0VV2VhFiqSRc9VVNDbVX0OSVmkLksi7wo8raQeZ1hQVWtK1Xi1HaPohNVTisamx2rznyYE8O809B0bdMlFieyfJpfSkcvOJNCHtZKwnDaY9pnFlVuDUf-rBJNtOetufz55XBbff3jm6hv58CfDJePnX69f7kle7DDL5vxRDnMeKL-EwAA__-wnTMs">