Index: include/llvm/Analysis/ValueTracking.h
===================================================================
--- include/llvm/Analysis/ValueTracking.h
+++ include/llvm/Analysis/ValueTracking.h
@@ -160,7 +160,8 @@
   /// Map a call instruction to an intrinsic ID.  Libcalls which have equivalent
   /// intrinsics are treated as-if they were intrinsics.
   Intrinsic::ID getIntrinsicForCallSite(ImmutableCallSite ICS,
-                                        const TargetLibraryInfo *TLI);
+                                        const TargetLibraryInfo *TLI,
+                                        bool forVector = false);
 
   /// Return true if we can prove that the specified FP value is never equal to
   /// -0.0.
Index: lib/Analysis/ValueTracking.cpp
===================================================================
--- lib/Analysis/ValueTracking.cpp
+++ lib/Analysis/ValueTracking.cpp
@@ -2422,7 +2422,8 @@
 }
 
 Intrinsic::ID llvm::getIntrinsicForCallSite(ImmutableCallSite ICS,
-                                            const TargetLibraryInfo *TLI) {
+                                            const TargetLibraryInfo *TLI,
+                                            bool forVector) {
   const Function *F = ICS.getCalledFunction();
   if (!F)
     return Intrinsic::not_intrinsic;
@@ -2523,7 +2524,7 @@
   case LibFunc::sqrt:
   case LibFunc::sqrtf:
   case LibFunc::sqrtl:
-    if (ICS->hasNoNaNs())
+    if (ICS->hasNoNaNs() || forVector)
       return Intrinsic::sqrt;
     return Intrinsic::not_intrinsic;
   }
Index: lib/Analysis/VectorUtils.cpp
===================================================================
--- lib/Analysis/VectorUtils.cpp
+++ lib/Analysis/VectorUtils.cpp
@@ -85,7 +85,7 @@
 /// its ID, in case it does not found it return not_intrinsic.
 Intrinsic::ID llvm::getVectorIntrinsicIDForCall(const CallInst *CI,
                                                 const TargetLibraryInfo *TLI) {
-  Intrinsic::ID ID = getIntrinsicForCallSite(CI, TLI);
+  Intrinsic::ID ID = getIntrinsicForCallSite(CI, TLI, /*forVector*/ true);
   if (ID == Intrinsic::not_intrinsic)
     return Intrinsic::not_intrinsic;
 
Index: test/CodeGen/X86/vector-sqrt.ll
===================================================================
--- test/CodeGen/X86/vector-sqrt.ll
+++ test/CodeGen/X86/vector-sqrt.ll
@@ -1,60 +1,33 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx  | FileCheck %s --check-prefix=CHECK
 
-; Function Attrs: nounwind readonly uwtable
 define <2 x double> @sqrtd2(double* nocapture readonly %v) local_unnamed_addr #0 {
 ; CHECK-LABEL: sqrtd2:
-; CHECK:       vsqrtsd (%rdi), %xmm0, %xmm0
-; CHECK-NEXT:  vsqrtsd 8(%rdi), %xmm1, %xmm1
-; CHECK-NEXT:  vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
-; CHECK-NEXT:  retq
+; CHECK:       # BB#0: # %entry
+; CHECK-NEXT:    vsqrtpd (%rdi), %xmm0
+; CHECK-NEXT:    retq
 entry:
-  %0 = load double, double* %v, align 8
-  %call = tail call double @sqrt(double %0) #2
-  %arrayidx1 = getelementptr inbounds double, double* %v, i64 1
-  %1 = load double, double* %arrayidx1, align 8
-  %call2 = tail call double @sqrt(double %1) #2
-  %vecinit.i = insertelement <2 x double> undef, double %call, i32 0
-  %vecinit1.i = insertelement <2 x double> %vecinit.i, double %call2, i32 1
-  ret <2 x double> %vecinit1.i
+  %0 = bitcast double* %v to <2 x double>*
+  %1 = load <2 x double>, <2 x double>* %0, align 8
+  %2 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> %1)
+  ret <2 x double> %2
 }
 
-; Function Attrs: nounwind readnone
-declare double @sqrt(double) local_unnamed_addr #1
-
-; Function Attrs: nounwind readonly uwtable
 define <4 x float> @sqrtf4(float* nocapture readonly %v) local_unnamed_addr #0 {
 ; CHECK-LABEL: sqrtf4:
-; CHECK:       vsqrtss (%rdi), %xmm0, %xmm0
-; CHECK-NEXT:  vsqrtss 4(%rdi), %xmm1, %xmm1
-; CHECK-NEXT:  vsqrtss 8(%rdi), %xmm2, %xmm2
-; CHECK-NEXT:  vsqrtss 12(%rdi), %xmm3, %xmm3
-; CHECK-NEXT:  vinsertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3]
-; CHECK-NEXT:  vinsertps {{.*#+}} xmm0 = xmm0[0,1],xmm2[0],xmm0[3]
-; CHECK-NEXT:  vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm3[0]
-; CHECK-NEXT:  retq
+; CHECK:       # BB#0: # %entry
+; CHECK-NEXT:    vsqrtps (%rdi), %xmm0
+; CHECK-NEXT:    retq
 entry:
-  %0 = load float, float* %v, align 4
-  %call = tail call float @sqrtf(float %0) #2
-  %arrayidx1 = getelementptr inbounds float, float* %v, i64 1
-  %1 = load float, float* %arrayidx1, align 4
-  %call2 = tail call float @sqrtf(float %1) #2
-  %arrayidx3 = getelementptr inbounds float, float* %v, i64 2
-  %2 = load float, float* %arrayidx3, align 4
-  %call4 = tail call float @sqrtf(float %2) #2
-  %arrayidx5 = getelementptr inbounds float, float* %v, i64 3
-  %3 = load float, float* %arrayidx5, align 4
-  %call6 = tail call float @sqrtf(float %3) #2
-  %vecinit.i = insertelement <4 x float> undef, float %call, i32 0
-  %vecinit1.i = insertelement <4 x float> %vecinit.i, float %call2, i32 1
-  %vecinit2.i = insertelement <4 x float> %vecinit1.i, float %call4, i32 2
-  %vecinit3.i = insertelement <4 x float> %vecinit2.i, float %call6, i32 3
-  ret <4 x float> %vecinit3.i
+  %0 = bitcast float* %v to <4 x float>*
+  %1 = load <4 x float>, <4 x float>* %0, align 4
+  %2 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> %1)
+  ret <4 x float> %2
 }
 
-; Function Attrs: nounwind readnone
-declare float @sqrtf(float) local_unnamed_addr #1
+declare <2 x double> @llvm.sqrt.v2f64(<2 x double>) #1
+declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) #1
+
+attributes #0 = { nounwind readonly uwtable  "target-features"="+avx2" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { nounwind readnone }
 
-attributes #0 = { nounwind readonly uwtable "target-features"="+avx" "unsafe-fp-math"="false" "use-soft-float"="false" }
-attributes #1 = { nounwind readnone  "target-features"="+avx2" "unsafe-fp-math"="false" "use-soft-float"="false" }
-attributes #2 = { nounwind readnone }