diff --git a/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp b/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp
index 30c5606..5fbefae 100644
--- a/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp
+++ b/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp
@@ -674,9 +674,15 @@
     // MRMDestReg instructions forms:
     //  dst(ModR/M), src(ModR/M)
     //  dst(ModR/M), src(ModR/M), imm8
-    if (X86II::isX86_64ExtendedReg(MI.getOperand(0).getReg()))
+    //  dst(ModR/M), src1(VEX_4V), src2(ModR/M)
+    if (X86II::isX86_64ExtendedReg(MI.getOperand(CurOp).getReg()))
       VEX_B = 0x0;
-    if (X86II::isX86_64ExtendedReg(MI.getOperand(1).getReg()))
+    CurOp++;
+
+    if (HasVEX_4V)
+      VEX_4V = getVEXRegisterEncoding(MI, CurOp++);
+
+    if (X86II::isX86_64ExtendedReg(MI.getOperand(CurOp).getReg()))
       VEX_R = 0x0;
     break;
   case X86II::MRM0r: case X86II::MRM1r:
@@ -1046,9 +1052,14 @@
 
   case X86II::MRMDestReg:
     EmitByte(BaseOpcode, CurByte, OS);
+    SrcRegNum = CurOp + 1;
+
+    if (HasVEX_4V) // Skip 1st src (which is encoded in VEX_VVVV)
+      ++SrcRegNum;
+
     EmitRegModRMByte(MI.getOperand(CurOp),
-                     GetX86RegNum(MI.getOperand(CurOp+1)), CurByte, OS);
-    CurOp += 2;
+                     GetX86RegNum(MI.getOperand(SrcRegNum)), CurByte, OS);
+    CurOp = SrcRegNum + 1;
     break;
 
   case X86II::MRMDestMem:
diff --git a/lib/Target/X86/X86CodeEmitter.cpp b/lib/Target/X86/X86CodeEmitter.cpp
index 5d9dfa9..2518e02 100644
--- a/lib/Target/X86/X86CodeEmitter.cpp
+++ b/lib/Target/X86/X86CodeEmitter.cpp
@@ -1047,9 +1047,15 @@
       // MRMDestReg instructions forms:
       //  dst(ModR/M), src(ModR/M)
       //  dst(ModR/M), src(ModR/M), imm8
-      if (X86II::isX86_64ExtendedReg(MI.getOperand(0).getReg()))
+      //  dst(ModR/M), src1(VEX_4V), src2(ModR/M)
+      if (X86II::isX86_64ExtendedReg(MI.getOperand(CurOp).getReg()))
         VEX_B = 0x0;
-      if (X86II::isX86_64ExtendedReg(MI.getOperand(1).getReg()))
+      CurOp++;
+
+      if (HasVEX_4V)
+        VEX_4V = getVEXRegisterEncoding(MI, CurOp++);
+
+      if (X86II::isX86_64ExtendedReg(MI.getOperand(CurOp).getReg()))
         VEX_R = 0x0;
       break;
     case X86II::MRM0r: case X86II::MRM1r:
@@ -1284,9 +1290,14 @@
 
   case X86II::MRMDestReg: {
     MCE.emitByte(BaseOpcode);
+
+    unsigned SrcRegNum = CurOp+1;
+    if (HasVEX_4V) // Skip 1st src (which is encoded in VEX_VVVV)
+      SrcRegNum++;
+
     emitRegModRMByte(MI.getOperand(CurOp).getReg(),
-                     getX86RegNum(MI.getOperand(CurOp+1).getReg()));
-    CurOp += 2;
+                     getX86RegNum(MI.getOperand(SrcRegNum).getReg()));
+    CurOp = SrcRegNum + 1;
     break;
   }
   case X86II::MRMDestMem: {
diff --git a/lib/Target/X86/X86MCInstLower.cpp b/lib/Target/X86/X86MCInstLower.cpp
index 1e8347d..a8a9fd8 100644
--- a/lib/Target/X86/X86MCInstLower.cpp
+++ b/lib/Target/X86/X86MCInstLower.cpp
@@ -417,35 +417,44 @@
   case X86::VMOVDQAYrr:
   case X86::VMOVDQUrr:
   case X86::VMOVDQUYrr:
-  case X86::VMOVSDrr:
-  case X86::VMOVSSrr:
   case X86::VMOVUPDrr:
   case X86::VMOVUPDYrr:
   case X86::VMOVUPSrr:
   case X86::VMOVUPSYrr: {
-    if (X86II::isX86_64ExtendedReg(OutMI.getOperand(0).getReg()) &&
-        !X86II::isX86_64ExtendedReg(OutMI.getOperand(1).getReg()))
-      break;
-
-    unsigned NewOpc;
-    switch (OutMI.getOpcode()) {
-    default: llvm_unreachable("Invalid opcode");
-    case X86::VMOVAPDrr:  NewOpc = X86::VMOVAPDrr_REV;  break;
-    case X86::VMOVAPDYrr: NewOpc = X86::VMOVAPDYrr_REV; break;
-    case X86::VMOVAPSrr:  NewOpc = X86::VMOVAPSrr_REV;  break;
-    case X86::VMOVAPSYrr: NewOpc = X86::VMOVAPSYrr_REV; break;
-    case X86::VMOVDQArr:  NewOpc = X86::VMOVDQArr_REV;  break;
-    case X86::VMOVDQAYrr: NewOpc = X86::VMOVDQAYrr_REV; break;
-    case X86::VMOVDQUrr:  NewOpc = X86::VMOVDQUrr_REV;  break;
-    case X86::VMOVDQUYrr: NewOpc = X86::VMOVDQUYrr_REV; break;
-    case X86::VMOVSDrr:   NewOpc = X86::VMOVSDrr_REV;   break;
-    case X86::VMOVSSrr:   NewOpc = X86::VMOVSSrr_REV;   break;
-    case X86::VMOVUPDrr:  NewOpc = X86::VMOVUPDrr_REV;  break;
-    case X86::VMOVUPDYrr: NewOpc = X86::VMOVUPDYrr_REV; break;
-    case X86::VMOVUPSrr:  NewOpc = X86::VMOVUPSrr_REV;  break;
-    case X86::VMOVUPSYrr: NewOpc = X86::VMOVUPSYrr_REV; break;
+    if (!X86II::isX86_64ExtendedReg(OutMI.getOperand(0).getReg()) &&
+        X86II::isX86_64ExtendedReg(OutMI.getOperand(1).getReg())) {
+      unsigned NewOpc;
+      switch (OutMI.getOpcode()) {
+      default: llvm_unreachable("Invalid opcode");
+      case X86::VMOVAPDrr:  NewOpc = X86::VMOVAPDrr_REV;  break;
+      case X86::VMOVAPDYrr: NewOpc = X86::VMOVAPDYrr_REV; break;
+      case X86::VMOVAPSrr:  NewOpc = X86::VMOVAPSrr_REV;  break;
+      case X86::VMOVAPSYrr: NewOpc = X86::VMOVAPSYrr_REV; break;
+      case X86::VMOVDQArr:  NewOpc = X86::VMOVDQArr_REV;  break;
+      case X86::VMOVDQAYrr: NewOpc = X86::VMOVDQAYrr_REV; break;
+      case X86::VMOVDQUrr:  NewOpc = X86::VMOVDQUrr_REV;  break;
+      case X86::VMOVDQUYrr: NewOpc = X86::VMOVDQUYrr_REV; break;
+      case X86::VMOVUPDrr:  NewOpc = X86::VMOVUPDrr_REV;  break;
+      case X86::VMOVUPDYrr: NewOpc = X86::VMOVUPDYrr_REV; break;
+      case X86::VMOVUPSrr:  NewOpc = X86::VMOVUPSrr_REV;  break;
+      case X86::VMOVUPSYrr: NewOpc = X86::VMOVUPSYrr_REV; break;
+      }
+      OutMI.setOpcode(NewOpc);
     }
-    OutMI.setOpcode(NewOpc);
+    break;
+  }
+  case X86::VMOVSDrr:
+  case X86::VMOVSSrr: {
+    if (!X86II::isX86_64ExtendedReg(OutMI.getOperand(0).getReg()) &&
+        X86II::isX86_64ExtendedReg(OutMI.getOperand(2).getReg())) {
+      unsigned NewOpc;
+      switch (OutMI.getOpcode()) {
+      default: llvm_unreachable("Invalid opcode");
+      case X86::VMOVSDrr:   NewOpc = X86::VMOVSDrr_REV;   break;
+      case X86::VMOVSSrr:   NewOpc = X86::VMOVSSrr_REV;   break;
+      }
+      OutMI.setOpcode(NewOpc);
+    }
     break;
   }
 
diff --git a/test/CodeGen/X86/2013-03-13-VEX-DestReg.ll b/test/CodeGen/X86/2013-03-13-VEX-DestReg.ll
new file mode 100644
index 0000000..03b6bde
--- /dev/null
+++ b/test/CodeGen/X86/2013-03-13-VEX-DestReg.ll
@@ -0,0 +1,31 @@
+; RUN: llc < %s -mtriple=x86_64-apple-macosx10.8.0 -mcpu=core-avx-i -show-mc-encoding
+
+; ModuleID = 'bugpoint-reduced-simplified.bc'
+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-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+@b = external global [8 x float], align 32
+@e = external global [8 x float], align 16
+
+define void @main() #0 {
+entry:
+  %0 = load <8 x float>* bitcast ([8 x float]* @b to <8 x float>*), align 32, !tbaa !0
+  %bitcast.i = extractelement <8 x float> %0, i32 0
+  %vecinit.i.i = insertelement <4 x float> undef, float %bitcast.i, i32 0
+  %vecinit2.i.i = insertelement <4 x float> %vecinit.i.i, float 0.000000e+00, i32 1
+  %vecinit3.i.i = insertelement <4 x float> %vecinit2.i.i, float 0.000000e+00, i32 2
+  %vecinit4.i.i = insertelement <4 x float> %vecinit3.i.i, float 0.000000e+00, i32 3
+  %1 = tail call <4 x float> @llvm.x86.sse.rcp.ss(<4 x float> %vecinit4.i.i) #2
+  %vecext.i.i = extractelement <4 x float> %1, i32 0
+  store float %vecext.i.i, float* getelementptr inbounds ([8 x float]* @e, i64 0, i64 0), align 16, !tbaa !0
+  unreachable
+}
+
+declare <4 x float> @llvm.x86.sse.rcp.ss(<4 x float>) #1
+
+attributes #0 = { nounwind ssp uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { nounwind readnone }
+attributes #2 = { nounwind }
+
+!0 = metadata !{metadata !"omnipotent char", metadata !1}
+!1 = metadata !{metadata !"Simple C/C++ TBAA"}