<html>
    <head>
      <base href="https://bugs.llvm.org/">
    </head>
    <body><table border="1" cellspacing="0" cellpadding="8">
        <tr>
          <th>Bug ID</th>
          <td><a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - clang -flto doesn't respect -fno-unroll-loops option"
   href="https://bugs.llvm.org/show_bug.cgi?id=35139">35139</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>clang -flto doesn't respect -fno-unroll-loops option
          </td>
        </tr>

        <tr>
          <th>Product</th>
          <td>clang
          </td>
        </tr>

        <tr>
          <th>Version</th>
          <td>unspecified
          </td>
        </tr>

        <tr>
          <th>Hardware</th>
          <td>All
          </td>
        </tr>

        <tr>
          <th>OS</th>
          <td>All
          </td>
        </tr>

        <tr>
          <th>Status</th>
          <td>NEW
          </td>
        </tr>

        <tr>
          <th>Severity</th>
          <td>normal
          </td>
        </tr>

        <tr>
          <th>Priority</th>
          <td>P
          </td>
        </tr>

        <tr>
          <th>Component</th>
          <td>Driver
          </td>
        </tr>

        <tr>
          <th>Assignee</th>
          <td>unassignedclangbugs@nondot.org
          </td>
        </tr>

        <tr>
          <th>Reporter</th>
          <td>st@quanttec.com
          </td>
        </tr>

        <tr>
          <th>CC</th>
          <td>llvm-bugs@lists.llvm.org
          </td>
        </tr></table>
      <p>
        <div>
        <pre>When I let clang link together object files that I produced with -flto -Os, the
link time optimization seems to respect the -Os option. When I let it link
files produced with -flto -O2 -fno-unroll-loops the -fno-unroll-loops flag
seems to be ignored.

Test case:

The following 3 commands produce an executable with an unrolled loop (using
clang 5.0 and the files pasted below; verified by disassembling the
executable):

<span class="quote">> clang -flto -O2 -fno-unroll-loops -c loop.c -o loop.o
> clang -O2 -fno-unroll-loops -c main.c -o main.o
> clang -flto -O2 -fno-unroll-loops loop.o main.o -o main</span >

I'd expect this to produce an executable without an unrolled loop, even when
the last command only reads `clang -flto loop.o main.o -o main`, as is the case
when using -Os instead of -O2 when compiling loop.c and main.c. 

Adding `-Xlinker -mllvm -Xlinker -unroll-count=0` to the last command actually
does stop LLVM from unrolling the loop.

-- loop.c --
__attribute__((noinline))
int loop(float *array, int count) {
  float i1 = 1;
  for (int i = 0; i < count; ++i, i1 += 1) {
    array[i] += i1;
  }
  return count;
}

-- loop.h --
int loop(float *array, int count);

-- main.c --
#include "loop.h"

int main() {
  volatile int zero = 0;
  return loop(0, zero);
}</pre>
        </div>
      </p>


      <hr>
      <span>You are receiving this mail because:</span>

      <ul>
          <li>You are on the CC list for the bug.</li>
      </ul>
    </body>
</html>