<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 - [PGO] Consider enabling pre-cleanup passes before PGO instrumentation at -Os"
   href="https://bugs.llvm.org/show_bug.cgi?id=47631">47631</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>[PGO] Consider enabling pre-cleanup passes before PGO instrumentation at -Os
          </td>
        </tr>

        <tr>
          <th>Product</th>
          <td>libraries
          </td>
        </tr>

        <tr>
          <th>Version</th>
          <td>trunk
          </td>
        </tr>

        <tr>
          <th>Hardware</th>
          <td>PC
          </td>
        </tr>

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

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

        <tr>
          <th>Severity</th>
          <td>enhancement
          </td>
        </tr>

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

        <tr>
          <th>Component</th>
          <td>Interprocedural Optimizations
          </td>
        </tr>

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

        <tr>
          <th>Reporter</th>
          <td>rnk@google.com
          </td>
        </tr>

        <tr>
          <th>CC</th>
          <td>davidxl@google.com, llvm-bugs@lists.llvm.org, xur@google.com
          </td>
        </tr></table>
      <p>
        <div>
        <pre>Rong Xu added a series of cleanup passes that run before PGO in this 2016
change: 
<a href="https://reviews.llvm.org/D21405">https://reviews.llvm.org/D21405</a>

Chromium's build uses a mix of -O2 and -Os for different targets. We discovered
that with PGO, without the initial cleanup inliner pass, PGO-instrumented
object files are much, much larger than they should be. Switching from -Os to
-O2 everywhere reduced total object file inputs to link chrome.dll from ~20GB
to ~9GB, and greatly reduced linker memory usage.

If the inliner is not run before PGO instrumentation, every linkonce_odr
function ends up being retained. Consider this example:

$ cat t.cpp 
void foo();
void bar();
inline void inlineMe(int x) {
  if (x > 0)
    foo();
  else
    bar();
}
int getVal();
int main() { inlineMe(getVal()); }

Normally, -Os and -O2 will inline away inlineMe, and then delete it.

However, if we do PGO instrumentation before the inliner can delete inlineMe,
the __profd_ data ends up recording the function address of all linkonce_odr
functions. This command line shows that it is retained with Os but not O2:

$ clang -S -emit-llvm -O2 t.cpp  -o - -fprofile-generate |& grep
define.*inlineM
# nothing
$ clang -S -emit-llvm -Os t.cpp  -o - -fprofile-generate |& grep
define.*inlineM
define linkonce_odr dso_local void @_Z8inlineMei(i32 %x) local_unnamed_addr #1
comdat {

The retention of all linkonce_odr functions by PGO instrumentation is
controlled here:
<a href="https://github.com/llvm/llvm-project/blob/master/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp#L830">https://github.com/llvm/llvm-project/blob/master/llvm/lib/Transforms/Instrumentation/InstrProfiling.cpp#L830</a>
David Li added it in this change:
<a href="http://github.com/llvm/llvm-project/commit/7008ce3f9891">http://github.com/llvm/llvm-project/commit/7008ce3f9891</a>

Almost every inline function in C++ is linkonce_odr, so this code ends up
retaining practically everything. This results in a lot of extra duplicate
sections and symbols that wouldn't normally make it to the final link in an
optimized build. In our case, the linker would run out of memory:
<a href="https://crbug.com/1058040">https://crbug.com/1058040</a>

We fixed the problem by switching to O2, but this behavior at Os seems
undesirable, so I am reporting it.</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>