<table border="1" cellspacing="0" cellpadding="8">
    <tr>
        <th>Issue</th>
        <td>
            <a href=https://github.com/llvm/llvm-project/issues/95646>95646</a>
        </td>
    </tr>

    <tr>
        <th>Summary</th>
        <td>
            LLVM ERROR: Cannot select: intrinsic %llvm.nvvm.shfl.sync.bfly.i32 Aborted
        </td>
    </tr>

    <tr>
      <th>Labels</th>
      <td>
            new issue
      </td>
    </tr>

    <tr>
      <th>Assignees</th>
      <td>
      </td>
    </tr>

    <tr>
      <th>Reporter</th>
      <td>
          mathysferrato
      </td>
    </tr>
</table>

<pre>
    Hi I tried to train a quantized model fitting my VRAM as I have a GTX 1070ti, but I got this error that I did not have on a friend's computer who has an RTX 2070 (so same VRAM but more recent) :


I found that people were having a similar issue but the only real solution was to buy a new GPU, is it really the only way ?

Thanks for your help.
</pre>
<img width="1px" height="1px" alt="" src="http://email.email.llvm.org/o/eJx8Uk1r7DgQ_DXypRljy98HHybJOjuQsMuQDbnKVmusXVmaldoz-P36hzwPcntgsOhWdXWVSoSgLxaxZ9UTq14SsdLsfL8Imreg0HtBLhmd3Po_NZyAvEYJ5IC80BYE_L8KS_oHSlicRANKE2l7gWWDz_PxHUSAE8zihiDg9eML8qzJSDP-DONKcIKLI6BZB0DvnQeaRaxKLcE6egBd5FFeo5WMNwEmt1xXQg_32cEsAggL548v4FmTAeNtcBDEgg_-yLI4j-BxQkuMd8CKI8v2j-esetKLuCCrXhhvZ6JriG0-MD5cNM3rmE5uYXxYbTCOZqG_z4wPIgSkwPiQ5zWveZO3jA9F17WtnMbDyDk_lM0kDm3ddIesK0YsG1WJvGK8e-xwAuVWKx_Cr-iuBuGOHqP06KOAoBdthAcdwoq7HpqjKWYDj8JAcGYl7SzcRYgvM64bCLB4h9e__4lG6wCa9rtm-8bexQasGB5bfMzC_hdAOQ-bWz3MaK5pIvtCdkUnEuzzJm_LouV5k8x9VkhZT9NYjbkqugaLplOyKFVeyE6pJkt0zzNeZnVeZU1VV01adm1eVpVQmVKtapCVGS5Cm9SY25I6f0l2dX1X1WWdGDGiCXsiOY9C9ibjPAbU9xFzGNdLYGVmdKDwPYU0Gezf3j7f4Y_z-a8zK47wLGyMUkCDE8WCtuS1DXoCxqsdam-3JQ2zMmnY7JSOymypLjgcR-cJZbJ60_8mG3HGr9_h6t2_kYcP-9IxGw9Rt57_DAAA__9F2Bpx">