diff --git a/lld/MachO/Writer.cpp b/lld/MachO/Writer.cpp
--- a/lld/MachO/Writer.cpp
+++ b/lld/MachO/Writer.cpp
@@ -20,6 +20,7 @@
 #include "SyntheticSections.h"
 #include "Target.h"
 #include "UnwindInfoSection.h"
+#include "llvm/Support/Parallel.h"
 
 #include "lld/Common/Arrays.h"
 #include "lld/Common/CommonLinkerContext.h"
@@ -1081,9 +1082,15 @@
 
 void Writer::writeSections() {
   uint8_t *buf = buffer->getBufferStart();
-  for (const OutputSegment *seg : outputSegments)
-    for (const OutputSection *osec : seg->getSections())
-      osec->writeTo(buf + osec->fileOff);
+  std::vector<const OutputSection *> osecs;
+  for (const OutputSegment *seg : outputSegments) {
+    const std::vector<OutputSection *> &sections = seg->getSections();
+    osecs.insert(osecs.end(), sections.begin(), sections.end());
+  }
+
+  parallelForEach(osecs.begin(), osecs.end(), [&](const OutputSection *osec) {
+    osec->writeTo(buf + osec->fileOff);
+  });
 }
 
 // In order to utilize multiple cores, we first split the buffer into chunks,