diff --git a/lib/Target/X86/X86InstrMMX.td b/lib/Target/X86/X86InstrMMX.td
index c8e0723..eea0eb8 100644
--- a/lib/Target/X86/X86InstrMMX.td
+++ b/lib/Target/X86/X86InstrMMX.td
@@ -160,7 +160,8 @@
                            "movq2dq\t{$src, $dst|$dst, $src}",
           [(set VR128:$dst,
             (movl immAllZerosV,
-                  (v2i64 (scalar_to_vector (i64 (bitconvert VR64:$src))))))]>;
+                  (v2i64 (scalar_to_vector
+                              (i64 (bitconvert (v1i64 VR64:$src)))))))]>;
 
 let neverHasSideEffects = 1 in
 def MMX_MOVQ2FR64rr: SSDIi8<0xD6, MRMSrcReg, (outs FR64:$dst), (ins VR64:$src),
@@ -271,9 +272,9 @@
 
 // Shift up / down and insert zero's.
 def : Pat<(v1i64 (X86vshl     VR64:$src, (i8 imm:$amt))),
-          (v1i64 (MMX_PSLLQri VR64:$src, imm:$amt))>;
+          (MMX_PSLLQri VR64:$src, imm:$amt)>;
 def : Pat<(v1i64 (X86vshr     VR64:$src, (i8 imm:$amt))),
-          (v1i64 (MMX_PSRLQri VR64:$src, imm:$amt))>;
+          (MMX_PSRLQri VR64:$src, imm:$amt)>;
 
 // Comparison Instructions
 defm MMX_PCMPEQB : MMXI_binop_rm_int<0x74, "pcmpeqb", int_x86_mmx_pcmpeq_b>;
@@ -577,7 +578,7 @@
 // Clear top half.
 let AddedComplexity = 15 in {
   def : Pat<(v2i32 (X86vzmovl VR64:$src)),
-            (MMX_PUNPCKLDQrr VR64:$src, (MMX_V_SET0))>;
+            (MMX_PUNPCKLDQrr VR64:$src, (v2i32 (MMX_V_SET0)))>;
 }
 
 // Patterns to perform canonical versions of vector shuffling.
diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td
index 67d987e..bd6e1b8 100644
--- a/lib/Target/X86/X86InstrSSE.td
+++ b/lib/Target/X86/X86InstrSSE.td
@@ -385,7 +385,7 @@
 // Extract the low 32-bit value from one vector and insert it into another.
 let AddedComplexity = 15 in
 def : Pat<(v4f32 (movl VR128:$src1, VR128:$src2)),
-          (MOVSSrr VR128:$src1,
+          (MOVSSrr (v4f32 VR128:$src1),
                    (EXTRACT_SUBREG (v4f32 VR128:$src2), x86_subreg_ss))>;
 
 // Implicitly promote a 32-bit scalar to a vector.
@@ -827,7 +827,7 @@
 
 
 def : Pat<(movlhps VR128:$src1, (bc_v4i32 (v2i64 (X86vzload addr:$src2)))),
-          (MOVHPSrm VR128:$src1, addr:$src2)>;
+          (MOVHPSrm (v4i32 VR128:$src1), addr:$src2)>;
 
 def MOVLPSmr : PSI<0x13, MRMDestMem, (outs), (ins f64mem:$dst, VR128:$src),
                    "movlps\t{$src, $dst|$dst, $src}",
@@ -860,9 +860,9 @@
 
 let AddedComplexity = 20 in {
 def : Pat<(v4f32 (movddup VR128:$src, (undef))),
-          (MOVLHPSrr VR128:$src, VR128:$src)>;
+          (MOVLHPSrr (v4f32 VR128:$src), (v4f32 VR128:$src))>;
 def : Pat<(v2i64 (movddup VR128:$src, (undef))),
-          (MOVLHPSrr VR128:$src, VR128:$src)>;
+          (MOVLHPSrr (v2i64 VR128:$src), (v2i64 VR128:$src))>;
 }
 
 
@@ -1011,9 +1011,9 @@
                                             (memop addr:$src), imm:$cc))]>;
 }
 def : Pat<(v4i32 (X86cmpps (v4f32 VR128:$src1), VR128:$src2, imm:$cc)),
-          (CMPPSrri VR128:$src1, VR128:$src2, imm:$cc)>;
+          (CMPPSrri (v4f32 VR128:$src1), (v4f32 VR128:$src2), imm:$cc)>;
 def : Pat<(v4i32 (X86cmpps (v4f32 VR128:$src1), (memop addr:$src2), imm:$cc)),
-          (CMPPSrmi VR128:$src1, addr:$src2, imm:$cc)>;
+          (CMPPSrmi (v4f32 VR128:$src1), addr:$src2, imm:$cc)>;
 
 // Shuffle and unpack instructions
 let Constraints = "$src1 = $dst" in {
@@ -1147,7 +1147,7 @@
 // Extract the low 64-bit value from one vector and insert it into another.
 let AddedComplexity = 15 in
 def : Pat<(v2f64 (movl VR128:$src1, VR128:$src2)),
-          (MOVSDrr VR128:$src1,
+          (MOVSDrr (v2f64 VR128:$src1),
                    (EXTRACT_SUBREG (v2f64 VR128:$src2), x86_subreg_sd))>;
 
 // Implicitly promote a 64-bit scalar to a vector.
@@ -2391,9 +2391,6 @@
 def MOVNTDQmr : PDI<0xE7, MRMDestMem, (outs), (ins f128mem:$dst, VR128:$src),
                     "movntdq\t{$src, $dst|$dst, $src}",
                     [(alignednontemporalstore (v4f32 VR128:$src), addr:$dst)]>;
-
-def : Pat<(alignednontemporalstore (v4i32 VR128:$src), addr:$dst),
-          (MOVNTDQmr VR128:$src, addr:$dst)>;
 }
 
 // Flush cache