Use parallel_sort in the LayoutPass.

Time to link lld using lld improved from 5.7s to 5.4s on Windows.
It's not a significant improvement but not bad for one-line change.

This patch includes a bug fix for Parallel.h as the original code
uses operator< instead of a compare function there.

llvm-svn: 227132

lld/include/lld/Core/Parallel.h

@@ -221,8 +221,8 @@ void parallel_quick_sort(RandomAccessIterator start, RandomAccessIterator end,
   auto pivot = medianOf3(start, end, comp);
   // Move pivot to end.
   std::swap(*(end - 1), *pivot);
-  pivot = std::partition(start, end - 1, [end](decltype(*start) v) {
-    return v < *(end - 1);
+  pivot = std::partition(start, end - 1, [&comp, end](decltype(*start) v) {
+    return comp(v, *(end - 1));
   });
   // Move pivot to middle of partition.
   std::swap(*pivot, *(end - 1));

lld/lib/Passes/LayoutPass.cpp

@@ -9,6 +9,7 @@
 
 #include "lld/Passes/LayoutPass.h"
 #include "lld/Core/Instrumentation.h"
+#include "lld/Core/Parallel.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/Support/Debug.h"
 #include <algorithm>
@@ -534,7 +535,7 @@ void LayoutPass::perform(std::unique_ptr<MutableFile> &mergedFile) {
   });
 
   std::vector<LayoutPass::SortKey> vec = decorate(atomRange);
-  std::sort(vec.begin(), vec.end(),
+  parallel_sort(vec.begin(), vec.end(),
       [&](const LayoutPass::SortKey &l, const LayoutPass::SortKey &r) -> bool {
         return compareAtoms(l, r, _customSorter);
       });