Index: lib/Target/AArch64/AArch64Subtarget.h
===================================================================
--- lib/Target/AArch64/AArch64Subtarget.h
+++ lib/Target/AArch64/AArch64Subtarget.h
@@ -86,6 +86,9 @@
     return &getInstrInfo()->getRegisterInfo();
   }
   bool enableMachineScheduler() const override { return true; }
+  bool enablePostMachineScheduler() const override {
+    return isCortexA53() || isCortexA57();
+  }
 
   bool hasZeroCycleRegMove() const { return HasZeroCycleRegMove; }
 
Index: lib/Target/AArch64/AArch64TargetMachine.cpp
===================================================================
--- lib/Target/AArch64/AArch64TargetMachine.cpp
+++ lib/Target/AArch64/AArch64TargetMachine.cpp
@@ -117,7 +117,9 @@
 class AArch64PassConfig : public TargetPassConfig {
 public:
   AArch64PassConfig(AArch64TargetMachine *TM, PassManagerBase &PM)
-      : TargetPassConfig(TM, PM) {}
+      : TargetPassConfig(TM, PM) {
+    substitutePass(&PostRASchedulerID, &PostMachineSchedulerID);
+  }
 
   AArch64TargetMachine &getAArch64TargetMachine() const {
     return getTM<AArch64TargetMachine>();
Index: test/CodeGen/AArch64/arm64-postra-mi-sched.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AArch64/arm64-postra-mi-sched.ll
@@ -0,0 +1,39 @@
+; RUN: llc < %s -O3 -march=arm64 -mcpu=cortex-a53 | FileCheck %s
+; With cortex-a53, each of fmul and fcvt have latency of 6 cycles.  After the
+; pre-RA MI scheduler, fmul, fcvt and fdiv will be consecutive.  The top-down
+; post-RA MI scheduler will clean this up.
+@d1 = common global double 0.000000e+00, align 8
+
+; Function Attrs: nounwind
+define i32 @f(float %s2, float %s3, double %d, i32 %i2, i32 %i3) #0 {
+entry:
+; CHECK: fmul
+; CHECK-NEXT: add
+; CHECK: fcvt
+; CHECK-NEXT: mul
+  %mul = fmul float %s2, %s3
+  %conv = fpext float %mul to double
+  %div = fdiv double %d, %conv
+  store double %div, double* @d1, align 8, !tbaa !1
+  %factor = shl i32 %i3, 1
+  %add1 = add i32 %i2, 4
+  %add2 = add i32 %add1, %factor
+  %add3 = add nsw i32 %add2, %i2
+  %add4 = add nsw i32 %add3, %add2
+  %mul5 = mul i32 %add3, %add3
+  %mul6 = mul i32 %mul5, %add4
+  %mul7 = shl i32 %add4, 1
+  %factor18 = mul i32 %mul7, %mul6
+  %add9 = add i32 %factor18, %mul6
+  ret i32 %add9
+}
+
+attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!llvm.ident = !{!0}
+
+!0 = metadata !{metadata !"clang version 3.6.0 "}
+!1 = metadata !{metadata !2, metadata !2, i64 0}
+!2 = metadata !{metadata !"double", metadata !3, i64 0}
+!3 = metadata !{metadata !"omnipotent char", metadata !4, i64 0}
+!4 = metadata !{metadata !"Simple C/C++ TBAA"}