diff --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -1687,7 +1687,7 @@
         isHomogeneousAggregate(Ty, Base, NumElts)) {
       if (State.FreeSSERegs >= NumElts) {
         State.FreeSSERegs -= NumElts;
-        Args[I].info = ABIArgInfo::getDirect();
+        Args[I].info = ABIArgInfo::getDirectInReg();
         State.IsPreassigned.set(I);
       }
     }
diff --git a/clang/test/CodeGen/vectorcall.c b/clang/test/CodeGen/vectorcall.c
--- a/clang/test/CodeGen/vectorcall.c
+++ b/clang/test/CodeGen/vectorcall.c
@@ -31,13 +31,13 @@
 // indirectly. Additional vector arguments can consume the rest of the SSE
 // registers.
 void __vectorcall hfa2(struct HFA4 a, struct HFA4 b, double c) {}
-// X32: define dso_local x86_vectorcallcc void @"\01hfa2@@72"(%struct.HFA4 inreg %a.coerce, %struct.HFA4* inreg %b, double %c)
+// X32: define dso_local x86_vectorcallcc void @"\01hfa2@@72"(%struct.HFA4 inreg %a.coerce, %struct.HFA4* inreg %b, double inreg %c)
 // X64: define dso_local x86_vectorcallcc void @"\01hfa2@@72"(%struct.HFA4 inreg %a.coerce, %struct.HFA4* %b, double %c)
 
 // Ensure that we pass builtin types directly while counting them against the
 // SSE register usage.
 void __vectorcall hfa3(double a, double b, double c, double d, double e, struct HFA2 f) {}
-// X32: define dso_local x86_vectorcallcc void @"\01hfa3@@56"(double %a, double %b, double %c, double %d, double %e, %struct.HFA2* inreg %f)
+// X32: define dso_local x86_vectorcallcc void @"\01hfa3@@56"(double inreg %a, double inreg %b, double inreg %c, double inreg %d, double inreg %e, %struct.HFA2* inreg %f)
 // X64: define dso_local x86_vectorcallcc void @"\01hfa3@@56"(double %a, double %b, double %c, double %d, double %e, %struct.HFA2* %f)
 
 // Aggregates with more than four elements are not HFAs and are passed byval.
@@ -64,21 +64,21 @@
 // X64: define dso_local x86_vectorcallcc <4 x float> @"\01hva1@@80"(i32 %a, %struct.HVA4 inreg %b.coerce, i32 %c)
 
 v4f32 __vectorcall hva2(struct HVA4 a, struct HVA4 b, v4f32 c) {return c;}
-// X32: define dso_local x86_vectorcallcc <4 x float> @"\01hva2@@144"(%struct.HVA4 inreg %a.coerce, %struct.HVA4* inreg %b, <4 x float> %c)
+// X32: define dso_local x86_vectorcallcc <4 x float> @"\01hva2@@144"(%struct.HVA4 inreg %a.coerce, %struct.HVA4* inreg %b, <4 x float> inreg %c)
 // X64: define dso_local x86_vectorcallcc <4 x float> @"\01hva2@@144"(%struct.HVA4 inreg %a.coerce, %struct.HVA4* %b, <4 x float> %c)
 
 v4f32 __vectorcall hva3(v4f32 a, v4f32 b, v4f32 c, v4f32 d, v4f32 e, struct HVA2 f) {return f.x;}
-// X32: define dso_local x86_vectorcallcc <4 x float> @"\01hva3@@112"(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d, <4 x float> %e, %struct.HVA2* inreg %f)
+// X32: define dso_local x86_vectorcallcc <4 x float> @"\01hva3@@112"(<4 x float> inreg %a, <4 x float> inreg %b, <4 x float> inreg %c, <4 x float> inreg %d, <4 x float> inreg %e, %struct.HVA2* inreg %f)
 // X64: define dso_local x86_vectorcallcc <4 x float> @"\01hva3@@112"(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d, <4 x float> %e, %struct.HVA2* %f)
 
 // vector types have higher priority then HVA structures, So vector types are allocated first
 // and HVAs are allocated if enough registers are available
 v4f32 __vectorcall hva4(struct HVA4 a, struct HVA2 b, v4f32 c) {return b.y;}
-// X32: define dso_local x86_vectorcallcc <4 x float> @"\01hva4@@112"(%struct.HVA4 inreg %a.coerce, %struct.HVA2* inreg %b, <4 x float> %c)
+// X32: define dso_local x86_vectorcallcc <4 x float> @"\01hva4@@112"(%struct.HVA4 inreg %a.coerce, %struct.HVA2* inreg %b, <4 x float> inreg %c)
 // X64: define dso_local x86_vectorcallcc <4 x float> @"\01hva4@@112"(%struct.HVA4 inreg %a.coerce, %struct.HVA2* %b, <4 x float> %c)
 
 v4f32 __vectorcall hva5(struct HVA3 a, struct HVA3 b, v4f32 c, struct HVA2 d) {return d.y;}
-// X32: define dso_local x86_vectorcallcc <4 x float> @"\01hva5@@144"(%struct.HVA3 inreg %a.coerce, %struct.HVA3* inreg %b, <4 x float> %c, %struct.HVA2 inreg %d.coerce)
+// X32: define dso_local x86_vectorcallcc <4 x float> @"\01hva5@@144"(%struct.HVA3 inreg %a.coerce, %struct.HVA3* inreg %b, <4 x float> inreg %c, %struct.HVA2 inreg %d.coerce)
 // X64: define dso_local x86_vectorcallcc <4 x float> @"\01hva5@@144"(%struct.HVA3 inreg %a.coerce, %struct.HVA3* %b, <4 x float> %c, %struct.HVA2 inreg %d.coerce)
 
 struct HVA4 __vectorcall hva6(struct HVA4 a, struct HVA4 b) { return b;}
@@ -90,7 +90,7 @@
 // X64: define dso_local x86_vectorcallcc void @"\01hva7@@0"(%struct.HVA5* noalias sret %agg.result)
 
 v4f32 __vectorcall hva8(v4f32 a, v4f32 b, v4f32 c, v4f32 d, int e, v4f32 f) {return f;}
-// X32: define dso_local x86_vectorcallcc <4 x float> @"\01hva8@@84"(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d, i32 inreg %e, <4 x float> %f)
+// X32: define dso_local x86_vectorcallcc <4 x float> @"\01hva8@@84"(<4 x float> inreg %a, <4 x float> inreg %b, <4 x float> inreg %c, <4 x float> inreg %d, i32 inreg %e, <4 x float> inreg %f)
 // X64: define dso_local x86_vectorcallcc <4 x float> @"\01hva8@@88"(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d, i32 %e, <4 x float> %f)
 
 typedef float __attribute__((ext_vector_type(3))) v3f32;
@@ -104,7 +104,7 @@
 // consider 'p7' as a register.  Instead p5 gets put into the register on the second pass.
 // x86 should pass p2, p6 and p7 in registers, then p1 in the second pass.
 struct HFA2 __vectorcall AddParticles(struct HFA2 p1, float p2, struct HFA4 p3, int p4, struct HFA2 p5, float p6, float p7, int p8){ return p1;}
-// X32: define dso_local x86_vectorcallcc %struct.HFA2 @"\01AddParticles@@84"(%struct.HFA2 inreg %p1.coerce, float %p2, %struct.HFA4* inreg %p3, i32 inreg %p4, %struct.HFA2* %p5, float %p6, float %p7, i32 %p8)
+// X32: define dso_local x86_vectorcallcc %struct.HFA2 @"\01AddParticles@@84"(%struct.HFA2 inreg %p1.coerce, float inreg %p2, %struct.HFA4* inreg %p3, i32 inreg %p4, %struct.HFA2* %p5, float inreg %p6, float inreg %p7, i32 %p8)
 // X64: define dso_local x86_vectorcallcc %struct.HFA2 @"\01AddParticles@@104"(%struct.HFA2 inreg %p1.coerce, float %p2, %struct.HFA4* %p3, i32 %p4, %struct.HFA2 inreg %p5.coerce, float %p6, float %p7, i32 %p8)
 
 // Vectorcall in both architectures allows passing of an HVA as long as there is room,
@@ -113,7 +113,7 @@
 // in a register, does NOT put p7 in a register (since theres no room), then puts 
 // p8 in a register.
 void __vectorcall HVAAnywhere(struct HFA2 p1, int p2, int p3, float p4, int p5, int p6, struct HFA4 p7, struct HFA2 p8, float p9){}
-// X32: define dso_local x86_vectorcallcc void @"\01HVAAnywhere@@88"(%struct.HFA2 inreg %p1.coerce, i32 inreg %p2, i32 inreg %p3, float %p4, i32 %p5, i32 %p6, %struct.HFA4* %p7, %struct.HFA2 inreg %p8.coerce, float %p9)
+// X32: define dso_local x86_vectorcallcc void @"\01HVAAnywhere@@88"(%struct.HFA2 inreg %p1.coerce, i32 inreg %p2, i32 inreg %p3, float inreg %p4, i32 %p5, i32 %p6, %struct.HFA4* %p7, %struct.HFA2 inreg %p8.coerce, float inreg %p9)
 // X64: define dso_local x86_vectorcallcc void @"\01HVAAnywhere@@112"(%struct.HFA2 inreg %p1.coerce, i32 %p2, i32 %p3, float %p4, i32 %p5, i32 %p6, %struct.HFA4* %p7, %struct.HFA2 inreg %p8.coerce, float %p9) 
 
 #ifndef __x86_64__
@@ -127,12 +127,12 @@
 }
 
 // X32: define dso_local x86_vectorcallcc void @"\01vectorcall_indirect_vec@@{{[0-9]+}}"
-// X32-SAME: (double %xmm0,
-// X32-SAME: double %xmm1,
-// X32-SAME: double %xmm2,
-// X32-SAME: double %xmm3,
-// X32-SAME: double %xmm4,
-// X32-SAME: <4 x float> %xmm5,
+// X32-SAME: (double inreg %xmm0,
+// X32-SAME: double inreg %xmm1,
+// X32-SAME: double inreg %xmm2,
+// X32-SAME: double inreg %xmm3,
+// X32-SAME: double inreg %xmm4,
+// X32-SAME: <4 x float> inreg %xmm5,
 // X32-SAME: <4 x float>* inreg %0,
 // X32-SAME: i32 inreg %edx,
 // X32-SAME: <4 x float>* %1)
diff --git a/clang/test/CodeGenCXX/inalloca-vector.cpp b/clang/test/CodeGenCXX/inalloca-vector.cpp
--- a/clang/test/CodeGenCXX/inalloca-vector.cpp
+++ b/clang/test/CodeGenCXX/inalloca-vector.cpp
@@ -66,14 +66,13 @@
                                          __m128 w, int edx, __m128 q, NonTrivial nt) {
   gv128 = x + y + z + w + q;
 }
-// FIXME: Enable these checks, clang generates wrong IR.
 // CHECK-LABEL: define dso_local x86_vectorcallcc void @"?vectorcall_receive_vec@@Y{{[^"]*}}"
-// CHECKX-SAME: (double inreg %xmm0,
-// CHECKX-SAME: double inreg %xmm1,
-// CHECKX-SAME: double inreg %xmm2,
-// CHECKX-SAME: <4 x float> inreg %x,
-// CHECKX-SAME: <4 x float> inreg %y,
-// CHECKX-SAME: <4 x float> inreg %z,
-// CHECKX-SAME: <4 x float>* inreg %0,
-// CHECKX-SAME: i32 inreg %edx,
-// CHECKX-SAME: <{ <4 x float>*, %struct.NonTrivial }>* inalloca %1)
+// CHECK-SAME: (double inreg %xmm0,
+// CHECK-SAME: double inreg %xmm1,
+// CHECK-SAME: double inreg %xmm2,
+// CHECK-SAME: <4 x float> inreg %x,
+// CHECK-SAME: <4 x float> inreg %y,
+// CHECK-SAME: <4 x float> inreg %z,
+// CHECK-SAME: <4 x float>* inreg %0,
+// CHECK-SAME: i32 inreg %edx,
+// CHECK-SAME: <{ <4 x float>*, %struct.NonTrivial }>* inalloca %1)