<table border="1" cellspacing="0" cellpadding="8">
    <tr>
        <th>Issue</th>
        <td>
            <a href=https://github.com/llvm/llvm-project/issues/60301>60301</a>
        </td>
    </tr>

    <tr>
        <th>Summary</th>
        <td>
            [NVPTX] No output from `ptxas` when compiling with `--target=nvptx64-nvidia-cuda`
        </td>
    </tr>

    <tr>
      <th>Labels</th>
      <td>
      </td>
    </tr>

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

    <tr>
      <th>Reporter</th>
      <td>
          jhuber6
      </td>
    </tr>
</table>

<pre>
    Recently we added support for directly targeting the `nvptx` architecture via cross-compilation. There's a bug that causes the output from `clang foo.c -c --target=nvptx64-nvidia-cuda` to be removed as a temp file. This is because of erroneous comparison of `const char *` values instead of string comparisons.
</pre>
<img width="1px" height="1px" alt="" src="http://email.email.llvm.org/o/eJyEkktr3DAQxz-NfBlsvPJjvQcfUpY9hlJC6VWPWVtBloxmtEm-fZETCPTSk2Ae_9_8Z6SI3BIQZzH8EFK-rlljGoWUYrhWKvMa0_wVrHS0H_MvNBjYf8AbgrIWLVDe95gY7jGBdQlNybJKC7ILC_CKIMY2PHZ-F2MLKpnVMRrOCeHhFJgUiWoTt915xS6GBl5WTCjkmUCBzkVDMRiVCenQi5n3zHBPcSvaxquwwD3GxkBtoK4_6aK7HtSxr8PDWadqk60qM3AEjZBwiw-0oAqGcdvh7jwWuiNwBBoPJMQ7YEoxYMwEZU6VHMVQ4gUeAzGYVSUQ8qmoP5TPSOACMSpbyohTWcV3LzWVnTt76S6qwvk0nvtxGrqpr9b5rPpW9xP28mT1dDnbSdpO60m19qw7nCo3y1Z27UkOUsqu7ZvzfdSDthc7XczlpFvRt7gp5xvvH1sT01I5oozz2HbtqfJKo6fj3sO1SnMpqnVeSPStd8T03caO_fEznn__fPkjhis8x393v_O7ouL6bcUAn1csXt8cryX_32NUOfl5Zd5JdE9C3oS8LY7XrBsTNyFvZZqvp95TfEXDQt4ORyTk7TD1NwAA__-iLu1H">