Index: lib/Transforms/Scalar/LoopDataPrefetch.cpp
===================================================================
--- lib/Transforms/Scalar/LoopDataPrefetch.cpp
+++ lib/Transforms/Scalar/LoopDataPrefetch.cpp
@@ -30,6 +30,7 @@
 #include "llvm/IR/Dominators.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/IntrinsicInst.h"
+#include "llvm/IR/InlineAsm.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
@@ -192,10 +193,16 @@
     // 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 (const InlineAsm *IA = dyn_cast<InlineAsm>(CI->getCalledValue())) {
+          // TODO: Need to check other architectures.
+          if (StringRef(IA->getAsmString()).startswith_lower("prfm"))
+            return MadeChange;
+        } else 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
+}
+