Index: include/llvm/Analysis/TargetTransformInfo.h
===================================================================
--- include/llvm/Analysis/TargetTransformInfo.h
+++ include/llvm/Analysis/TargetTransformInfo.h
@@ -363,6 +363,9 @@
   /// \brief Return true if this type is legal.
   bool isTypeLegal(Type *Ty) const;
 
+  /// \brief Return true if this instruction is related with prefetch.
+  bool isPrefetchInlineAsm(CallInst *CI) const;
+
   /// \brief Returns the target's jmp_buf alignment in bytes.
   unsigned getJumpBufAlignment() const;
 
@@ -662,6 +665,7 @@
   virtual bool isTruncateFree(Type *Ty1, Type *Ty2) = 0;
   virtual bool isProfitableToHoist(Instruction *I) = 0;
   virtual bool isTypeLegal(Type *Ty) = 0;
+  virtual bool isPrefetchInlineAsm(CallInst *CI) = 0;
   virtual unsigned getJumpBufAlignment() = 0;
   virtual unsigned getJumpBufSize() = 0;
   virtual bool shouldBuildLookupTables() = 0;
@@ -827,6 +831,9 @@
     return Impl.isProfitableToHoist(I);
   }
   bool isTypeLegal(Type *Ty) override { return Impl.isTypeLegal(Ty); }
+  bool isPrefetchInlineAsm(CallInst *CI) override {
+    return Impl.isPrefetchInlineAsm(CI);
+  }
   unsigned getJumpBufAlignment() override { return Impl.getJumpBufAlignment(); }
   unsigned getJumpBufSize() override { return Impl.getJumpBufSize(); }
   bool shouldBuildLookupTables() override {
Index: include/llvm/Analysis/TargetTransformInfoImpl.h
===================================================================
--- include/llvm/Analysis/TargetTransformInfoImpl.h
+++ include/llvm/Analysis/TargetTransformInfoImpl.h
@@ -232,6 +232,8 @@
 
   bool isTypeLegal(Type *Ty) { return false; }
 
+  bool isPrefetchInlineAsm(CallInst *CI) { return false; }
+
   unsigned getJumpBufAlignment() { return 0; }
 
   unsigned getJumpBufSize() { return 0; }
Index: lib/Analysis/TargetTransformInfo.cpp
===================================================================
--- lib/Analysis/TargetTransformInfo.cpp
+++ lib/Analysis/TargetTransformInfo.cpp
@@ -139,6 +139,10 @@
   return TTIImpl->isLegalMaskedGather(DataType);
 }
 
+bool TargetTransformInfo::isPrefetchInlineAsm(CallInst *CI) const {
+  return TTIImpl->isPrefetchInlineAsm(CI);
+}
+
 int TargetTransformInfo::getScalingFactorCost(Type *Ty, GlobalValue *BaseGV,
                                               int64_t BaseOffset,
                                               bool HasBaseReg,
Index: lib/Target/AArch64/AArch64TargetTransformInfo.h
===================================================================
--- lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -138,6 +138,8 @@
   unsigned getMinPrefetchStride();
 
   unsigned getMaxPrefetchIterationsAhead();
+
+  bool isPrefetchInlineAsm(CallInst *CI);
   /// @}
 };
 
Index: lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -20,6 +20,15 @@
 
 #define DEBUG_TYPE "aarch64tti"
 
+/// \brief Return true if this instruction is related with prefetch.
+bool AArch64TTIImpl::isPrefetchInlineAsm(CallInst *CI) {
+  if (const InlineAsm *IA = dyn_cast<InlineAsm>(CI->getCalledValue())) {
+    if (StringRef(IA->getAsmString()).find("prfm") != StringRef::npos)
+      return true;
+  }
+  return false;
+}
+
 /// \brief Calculate the cost of materializing a 64-bit value. This helper
 /// method might only calculate a fraction of a larger immediate. Therefore it
 /// is valid to return a cost of ZERO.
Index: lib/Transforms/Scalar/LoopDataPrefetch.cpp
===================================================================
--- lib/Transforms/Scalar/LoopDataPrefetch.cpp
+++ lib/Transforms/Scalar/LoopDataPrefetch.cpp
@@ -192,10 +192,14 @@
     // what they are doing and don't add any more.
     for (BasicBlock::iterator J = (*I)->begin(), JE = (*I)->end();
          J != JE; ++J)
-      if (CallInst *CI = dyn_cast<CallInst>(J))
-        if (Function *F = CI->getCalledFunction())
+      if (CallInst *CI = dyn_cast<CallInst>(J)) {
+        if (TTI->isPrefetchInlineAsm(CI))
+          return MadeChange;
+        if (Function *F = CI->getCalledFunction()) {
           if (F->getIntrinsicID() == Intrinsic::prefetch)
             return MadeChange;
+        }
+      }
 
     Metrics.analyzeBasicBlock(*I, *TTI, EphValues);
   }
Index: test/Transforms/LoopDataPrefetch/AArch64/check-asm.ll
===================================================================
--- /dev/null
+++ test/Transforms/LoopDataPrefetch/AArch64/check-asm.ll
@@ -0,0 +1,26 @@
+; RUN: opt -mcpu=cyclone -mtriple=arm64-apple-ios -loop-data-prefetch -max-prefetch-iters-ahead=1000 -min-prefetch-stride=1 -S < %s | FileCheck %s
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-n32:64-S128"
+
+define void @no_prefetch(double* nocapture %a, double* nocapture readonly %b) {
+entry:
+  br label %for.body
+
+; ALL: for.body:
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds double, double* %b, i64 %indvars.iv
+; CHECK-NOT: call void @llvm.prefetch
+  tail call void asm sideeffect "prfm PLDL1KEEP, [$0, $1]", "r,n"(double* %arrayidx, i32 0)
+  %0 = load double, double* %arrayidx, align 8
+  %add = fadd double %0, 1.000000e+00
+  %arrayidx2 = getelementptr inbounds double, double* %a, i64 %indvars.iv
+  store double %add, double* %arrayidx2, align 8
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1600
+  br i1 %exitcond, label %for.end, label %for.body
+
+; ALL: for.end:
+for.end:                                          ; preds = %for.body
+  ret void
+}
+