<table border="1" cellspacing="0" cellpadding="8">
    <tr>
        <th>Issue</th>
        <td>
            <a href=https://github.com/llvm/llvm-project/issues/63853>63853</a>
        </td>
    </tr>

    <tr>
        <th>Summary</th>
        <td>
            libc GPU not compiled with -fconvergent-functions
        </td>
    </tr>

    <tr>
      <th>Labels</th>
      <td>
            backend:AMDGPU,
            libc,
            backend:NVPTX
      </td>
    </tr>

    <tr>
      <th>Assignees</th>
      <td>
            jhuber6
      </td>
    </tr>

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

<pre>
    The conservatively correct thing to do is assume all functions are convergent by default. I don't know if the libc build should add -fconvergent-functions, or if it should be implied by targets with divergence rather than just implied by the language in clang
</pre>
<img width="1px" height="1px" alt="" src="http://email.email.llvm.org/o/eJxskc1u2zAQhJ-GuixsSKRlWwce0gQOemiRQ1L0yp-VSIciDXLpwG9fyHFjFOiJWGDnW86MKsVPEVGy_hvj_OiqxrxlnLP-qVGVXMpS5YJxbnSyF_nqEEyKBfNZkT9juIBJOaMhIOfjBJTAJvAFVCl1RlAhwFijIZ9iAZWv8jPmCSOBvoDFUdVAa_gONkXGdwTvMX2AH4EcQvDagK4-WCgu1WBBWQur8Q5ZfdEZf4SUF6Wnv9sawc-n4NEux0jlCanAhycH1n8SDEJW5DADORXhWAv9o1l-oeJU1YTgI5hlaKwUdhCDalB22_3A97tO9I2TvdLj1qDq227c625EPfTD0O-7TWd2G6MaL3nLRbvrBOe8F_1ab3a8FW1nTTsO7TCyTYuz8mEdwnlepzw1vpSKciv2vWiC0hjKrS2tzDtGy8TDw4-n55e3pTb-yDhfUvsa7ls_f728_r51m-XCX-k6FbZpgy9U7hfJU0B5zf755Q1iIjBpPvmA9jO7_xfQ1BykIzoVJh4YPzB-mDy5qtcmzYwfFv7tWZ1yOqIhxg9Xe4Xxw9XhnwAAAP__8NzcYQ">