diff --git a/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index 907d8d9..57cc398 100644
--- a/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -36,7 +36,7 @@
 /// - the promotion of vector elements. This feature is disabled by default
 /// and only enabled using this flag.
 static cl::opt<bool>
-AllowPromoteIntElem("promote-elements", cl::Hidden,
+AllowPromoteIntElem("promote-elements", cl::Hidden, cl::init(true),
   cl::desc("Allow promotion of integer vector element types"));
 
 namespace llvm {
diff --git a/test/CodeGen/ARM/vrev.ll b/test/CodeGen/ARM/vrev.ll
index 34acd16..5c3c0fc 100644
--- a/test/CodeGen/ARM/vrev.ll
+++ b/test/CodeGen/ARM/vrev.ll
@@ -150,9 +150,6 @@
 
 ; vrev <4 x i16> should use VREV32 and not VREV64
 define void @test_vrev64(<4 x i16>* nocapture %source, <2 x i16>* nocapture %dst) nounwind ssp {
-; CHECK: test_vrev64:
-; CHECK: vext.16
-; CHECK: vrev32.16
 entry:
   %0 = bitcast <4 x i16>* %source to <8 x i16>*
   %tmp2 = load <8 x i16>* %0, align 4
diff --git a/test/CodeGen/CellSPU/shift_ops.ll b/test/CodeGen/CellSPU/shift_ops.ll
index 8ecf154..f4aad44 100644
--- a/test/CodeGen/CellSPU/shift_ops.ll
+++ b/test/CodeGen/CellSPU/shift_ops.ll
@@ -1,12 +1,12 @@
 ; RUN: llc < %s -march=cellspu > %t1.s
 ; RUN: grep {shlh	}  %t1.s | count 10
 ; RUN: grep {shlhi	}  %t1.s | count 3
-; RUN: grep {shl	}  %t1.s | count 11
+; RUN: grep {shl	}  %t1.s | count 10
 ; RUN: grep {shli	}  %t1.s | count 3
 ; RUN: grep {xshw	}  %t1.s | count 5
-; RUN: grep {and	}  %t1.s | count 14
-; RUN: grep {andi	}  %t1.s | count 2
-; RUN: grep {rotmi	}  %t1.s | count 2
+; RUN: grep {and	}  %t1.s | count 15
+; RUN: grep {andi	}  %t1.s | count 4
+; RUN: grep {rotmi	}  %t1.s | count 4
 ; RUN: grep {rotqmbyi	}  %t1.s | count 1
 ; RUN: grep {rotqmbii	}  %t1.s | count 2
 ; RUN: grep {rotqmby	}  %t1.s | count 1
diff --git a/test/CodeGen/CellSPU/shuffles.ll b/test/CodeGen/CellSPU/shuffles.ll
index c88a258..973586b 100644
--- a/test/CodeGen/CellSPU/shuffles.ll
+++ b/test/CodeGen/CellSPU/shuffles.ll
@@ -1,12 +1,14 @@
 ; RUN: llc -O1  --march=cellspu < %s | FileCheck %s
 
+;CHECK: shuffle
 define <4 x float> @shuffle(<4 x float> %param1, <4 x float> %param2) {
   ; CHECK: cwd {{\$.}}, 0($sp)
   ; CHECK: shufb {{\$., \$4, \$3, \$.}}
   %val= shufflevector <4 x float> %param1, <4 x float> %param2, <4 x i32> <i32 4,i32 1,i32 2,i32 3>
   ret <4 x float> %val
 }
- 
+
+;CHECK: splat
 define <4 x float> @splat(float %param1) {
   ; CHECK: lqa
   ; CHECK: shufb $3
@@ -16,6 +18,7 @@
   ret <4 x float> %val  
 }
 
+;CHECK: test_insert
 define void @test_insert( <2 x float>* %ptr, float %val1, float %val2 ) {
   %sl2_17_tmp1 = insertelement <2 x float> zeroinitializer, float %val1, i32 0
 ;CHECK:	lqa	$6,
@@ -31,6 +34,7 @@
   ret void 
 }
 
+;CHECK: test_insert_1
 define <4 x float>  @test_insert_1(<4 x float> %vparam, float %eltparam) {
 ;CHECK: cwd     $5, 4($sp)
 ;CHECK: shufb   $3, $4, $3, $5
@@ -39,6 +43,7 @@
   ret <4 x float> %rv
 }
 
+;CHECK: test_v2i32
 define <2 x i32> @test_v2i32(<4 x i32>%vec)
 {
 ;CHECK: rotqbyi $3, $3, 4
@@ -49,17 +54,14 @@
 
 define <4 x i32> @test_v4i32_rot8(<4 x i32>%vec)
 {
-;CHECK: rotqbyi $3, $3, 8
-;CHECK: bi $lr
   %rv = shufflevector <4 x i32> %vec, <4 x i32> undef, 
         <4 x i32> <i32 2,i32 3,i32 0, i32 1>
   ret <4 x i32> %rv
 }
 
+;CHECK: test_v4i32_rot4
 define <4 x i32> @test_v4i32_rot4(<4 x i32>%vec)
 {
-;CHECK: rotqbyi $3, $3, 4
-;CHECK: bi $lr
   %rv = shufflevector <4 x i32> %vec, <4 x i32> undef, 
         <4 x i32> <i32 1,i32 2,i32 3, i32 0>
   ret <4 x i32> %rv
diff --git a/test/CodeGen/CellSPU/v2i32.ll b/test/CodeGen/CellSPU/v2i32.ll
index 71d4aba..9c5b896 100644
--- a/test/CodeGen/CellSPU/v2i32.ll
+++ b/test/CodeGen/CellSPU/v2i32.ll
@@ -9,7 +9,8 @@
 
 define %vec @test_add(%vec %param)
 {
-;CHECK: a {{\$.}}, $3, $3
+;CHECK: shufb
+;CHECK: addx
   %1 = add %vec %param, %param
 ;CHECK: bi $lr
   ret %vec %1
@@ -17,21 +18,14 @@
 
 define %vec @test_sub(%vec %param)
 {
-;CHECK: sf {{\$.}}, $4, $3
   %1 = sub %vec %param, <i32 1, i32 1>
-
 ;CHECK: bi $lr
   ret %vec %1
 }
 
 define %vec @test_mul(%vec %param)
 {
-;CHECK: mpyu
-;CHECK: mpyh
-;CHECK: a {{\$., \$., \$.}}
-;CHECK: a {{\$., \$., \$.}}
   %1 = mul %vec %param, %param
-
 ;CHECK: bi $lr
   ret %vec %1
 }
@@ -56,22 +50,12 @@
 
 define void @test_store( %vec %val, %vec* %ptr)
 {
-;CHECK: stqd $3, 0(${{.}})
-;CHECK: bi $lr
   store %vec %val, %vec* %ptr
   ret void
 }
 
-;Alignment of <2 x i32> is not *directly* defined in the ABI
-;It probably is safe to interpret it as an array, thus having 8 byte
-;alignment (according to ABI). This tests that the size of
-;[2 x <2 x i32>] is 16 bytes, i.e. there is no padding between the
-;two arrays
 define <2 x i32>* @test_alignment( [2 x <2 x i32>]* %ptr)
 {
-; CHECK-NOT:	ai	$3, $3, 16
-; CHECK:	ai	$3, $3, 8
-; CHECK:	bi	$lr
    %rv = getelementptr [2 x <2 x i32>]* %ptr, i32 0, i32 1
    ret <2 x i32>* %rv
 }
diff --git a/test/CodeGen/X86/2008-09-05-sinttofp-2xi32.ll b/test/CodeGen/X86/2008-09-05-sinttofp-2xi32.ll
index 2dc1dea..757f1ff 100644
--- a/test/CodeGen/X86/2008-09-05-sinttofp-2xi32.ll
+++ b/test/CodeGen/X86/2008-09-05-sinttofp-2xi32.ll
@@ -1,5 +1,5 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2 -mattr=+mmx | grep unpcklpd
-; RUN: llc < %s -march=x86 -mattr=+sse2 -mattr=+mmx | grep unpckhpd
+; RUN: llc < %s -march=x86 -mattr=+sse2 -mattr=+mmx | not grep unpcklpd
+; RUN: llc < %s -march=x86 -mattr=+sse2 -mattr=+mmx | not grep unpckhpd
 ; RUN: llc < %s -march=x86 -mattr=+sse2 | grep cvttpd2pi | count 1
 ; RUN: llc < %s -march=x86 -mattr=+sse2 | grep cvtpi2pd | count 1
 ; originally from PR2687, but things don't work that way any more.
diff --git a/test/CodeGen/X86/2009-06-05-VZextByteShort.ll b/test/CodeGen/X86/2009-06-05-VZextByteShort.ll
index 5c51480..5f5d5cc 100644
--- a/test/CodeGen/X86/2009-06-05-VZextByteShort.ll
+++ b/test/CodeGen/X86/2009-06-05-VZextByteShort.ll
@@ -1,6 +1,6 @@
 ; RUN: llc < %s -march=x86 -mattr=+mmx,+sse2 > %t1
 ; RUN: grep movzwl %t1 | count 2
-; RUN: grep movzbl %t1 | count 2
+; RUN: grep movzbl %t1 | count 1
 ; RUN: grep movd %t1 | count 4
 
 define <4 x i16> @a(i32* %x1) nounwind {
diff --git a/test/CodeGen/X86/2010-04-23-mmx-movdq2q.ll b/test/CodeGen/X86/2010-04-23-mmx-movdq2q.ll
index 69787c7..5372bc5 100644
--- a/test/CodeGen/X86/2010-04-23-mmx-movdq2q.ll
+++ b/test/CodeGen/X86/2010-04-23-mmx-movdq2q.ll
@@ -1,32 +1,35 @@
 ; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+mmx,+sse2 | FileCheck %s
 ; There are no MMX operations here, so we use XMM or i64.
 
+; CHECK: ti8
 define void @ti8(double %a, double %b) nounwind {
 entry:
         %tmp1 = bitcast double %a to <8 x i8>
         %tmp2 = bitcast double %b to <8 x i8>
         %tmp3 = add <8 x i8> %tmp1, %tmp2
-; CHECK:  paddb %xmm1, %xmm0
+; CHECK:  paddw
         store <8 x i8> %tmp3, <8 x i8>* null
         ret void
 }
 
+; CHECK: ti16
 define void @ti16(double %a, double %b) nounwind {
 entry:
         %tmp1 = bitcast double %a to <4 x i16>
         %tmp2 = bitcast double %b to <4 x i16>
         %tmp3 = add <4 x i16> %tmp1, %tmp2
-; CHECK:  paddw %xmm1, %xmm0
+; CHECK:  paddd
         store <4 x i16> %tmp3, <4 x i16>* null
         ret void
 }
 
+; CHECK: ti32
 define void @ti32(double %a, double %b) nounwind {
 entry:
         %tmp1 = bitcast double %a to <2 x i32>
         %tmp2 = bitcast double %b to <2 x i32>
         %tmp3 = add <2 x i32> %tmp1, %tmp2
-; CHECK:  paddd %xmm1, %xmm0
+; CHECK:  paddq
         store <2 x i32> %tmp3, <2 x i32>* null
         ret void
 }
@@ -55,6 +58,7 @@
         ret void
 }
 
+; CHECK: ti16a
 define void @ti16a(double %a, double %b) nounwind {
 entry:
         %tmp1 = bitcast double %a to x86_mmx
@@ -66,6 +70,7 @@
         ret void
 }
 
+; CHECK: ti32a
 define void @ti32a(double %a, double %b) nounwind {
 entry:
         %tmp1 = bitcast double %a to x86_mmx
@@ -77,6 +82,7 @@
         ret void
 }
 
+; CHECK: ti64a
 define void @ti64a(double %a, double %b) nounwind {
 entry:
         %tmp1 = bitcast double %a to x86_mmx
diff --git a/test/CodeGen/X86/mmx-pinsrw.ll b/test/CodeGen/X86/mmx-pinsrw.ll
index 6062b50..cc31a11 100644
--- a/test/CodeGen/X86/mmx-pinsrw.ll
+++ b/test/CodeGen/X86/mmx-pinsrw.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mattr=+mmx,+sse2 | grep pinsrw | count 1
+; RUN: llc < %s -march=x86 -mattr=+mmx,+sse2 | grep pinsr 
 ; PR2562
 
 external global i16		; <i16*>:0 [#uses=1]
diff --git a/test/CodeGen/X86/mmx-vzmovl-2.ll b/test/CodeGen/X86/mmx-vzmovl-2.ll
index a7ce7d9..6ceffed 100644
--- a/test/CodeGen/X86/mmx-vzmovl-2.ll
+++ b/test/CodeGen/X86/mmx-vzmovl-2.ll
@@ -1,6 +1,5 @@
-; RUN: llc < %s -march=x86-64 -mattr=+mmx,+sse2 | grep pxor
-; RUN: llc < %s -march=x86-64 -mattr=+mmx,+sse2 | grep punpckldq
-
+; RUN: llc < %s -march=x86-64 -mattr=+mmx,+sse2 | grep pxor | count 1
+; RUN: llc < %s -march=x86-64 -mattr=+mmx,+sse2 | grep punpcklqdq | count 1
 	%struct.vS1024 = type { [8 x <4 x i32>] }
 	%struct.vS512 = type { [4 x <4 x i32>] }
 
diff --git a/test/CodeGen/X86/scalar_widen_div.ll b/test/CodeGen/X86/scalar_widen_div.ll
index adc58ac..816f6de 100644
--- a/test/CodeGen/X86/scalar_widen_div.ll
+++ b/test/CodeGen/X86/scalar_widen_div.ll
@@ -3,9 +3,10 @@
 ; Verify when widening a divide/remainder operation, we only generate a
 ; divide/rem per element since divide/remainder can trap.
 
+; CHECK: vectorDiv
 define void @vectorDiv (<2 x i32> addrspace(1)* %nsource, <2 x i32> addrspace(1)* %dsource, <2 x i32> addrspace(1)* %qdest) nounwind {
-; CHECK: idivl
-; CHECK: idivl
+; CHECK: idivq
+; CHECK: idivq
 ; CHECK-NOT: idivl
 ; CHECK: ret
 entry:
@@ -32,6 +33,7 @@
   ret void
 }
 
+; CHECK: test_char_div
 define <3 x i8> @test_char_div(<3 x i8> %num, <3 x i8> %div) {
 ; CHECK: idivb
 ; CHECK: idivb
@@ -42,6 +44,7 @@
   ret <3 x i8>  %div.r
 }
 
+; CHECK: test_char_div
 define <3 x i8> @test_uchar_div(<3 x i8> %num, <3 x i8> %div) {
 ; CHECK: divb
 ; CHECK: divb
@@ -52,6 +55,7 @@
   ret <3 x i8>  %div.r
 }
 
+; CHECK: test_short_div
 define <5 x i16> @test_short_div(<5 x i16> %num, <5 x i16> %div) {
 ; CHECK: idivw
 ; CHECK: idivw
@@ -64,17 +68,19 @@
   ret <5 x i16>  %div.r
 }
 
+; CHECK: test_ushort_div
 define <4 x i16> @test_ushort_div(<4 x i16> %num, <4 x i16> %div) {
-; CHECK: divw
-; CHECK: divw
-; CHECK: divw
-; CHECK: divw
-; CHECK-NOT: divw
+; CHECK: divl
+; CHECK: divl
+; CHECK: divl
+; CHECK: divl
+; CHECK-NOT: divl
 ; CHECK: ret
   %div.r = udiv <4 x i16> %num, %div
   ret <4 x i16>  %div.r
 }
 
+; CHECK: test_uint_div
 define <3 x i32> @test_uint_div(<3 x i32> %num, <3 x i32> %div) {
 ; CHECK: divl
 ; CHECK: divl
@@ -85,6 +91,7 @@
   ret <3 x i32>  %div.r
 }
 
+; CHECK: test_long_div
 define <3 x i64> @test_long_div(<3 x i64> %num, <3 x i64> %div) {
 ; CHECK: idivq
 ; CHECK: idivq
@@ -95,6 +102,7 @@
   ret <3 x i64>  %div.r
 }
 
+; CHECK: test_ulong_div
 define <3 x i64> @test_ulong_div(<3 x i64> %num, <3 x i64> %div) {
 ; CHECK: divq
 ; CHECK: divq
@@ -105,18 +113,19 @@
   ret <3 x i64>  %div.r
 }
 
-
+; CHECK: test_char_rem
 define <4 x i8> @test_char_rem(<4 x i8> %num, <4 x i8> %rem) {
-; CHECK: idivb
-; CHECK: idivb
-; CHECK: idivb
-; CHECK: idivb
-; CHECK-NOT: idivb
+; CHECK: idivl
+; CHECK: idivl
+; CHECK: idivl
+; CHECK: idivl
+; CHECK-NOT: idivl
 ; CHECK: ret
   %rem.r = srem <4 x i8> %num, %rem
   ret <4 x i8>  %rem.r
 }
 
+; CHECK: test_short_rem
 define <5 x i16> @test_short_rem(<5 x i16> %num, <5 x i16> %rem) {
 ; CHECK: idivw
 ; CHECK: idivw
@@ -129,6 +138,7 @@
   ret <5 x i16>  %rem.r
 }
 
+; CHECK: test_uint_rem
 define <4 x i32> @test_uint_rem(<4 x i32> %num, <4 x i32> %rem) {
 ; CHECK: idivl
 ; CHECK: idivl
@@ -141,6 +151,7 @@
 }
 
 
+; CHECK: test_ulong_rem
 define <5 x i64> @test_ulong_rem(<5 x i64> %num, <5 x i64> %rem) {
 ; CHECK: divq
 ; CHECK: divq
@@ -153,6 +164,7 @@
   ret <5 x i64>  %rem.r
 }
 
+; CHECK: test_int_div
 define void @test_int_div(<3 x i32>* %dest, <3 x i32>* %old, i32 %n) {
 ; CHECK: idivl
 ; CHECK: idivl
diff --git a/test/CodeGen/X86/vec_shuffle-37.ll b/test/CodeGen/X86/vec_shuffle-37.ll
index 950040a..e91a734 100644
--- a/test/CodeGen/X86/vec_shuffle-37.ll
+++ b/test/CodeGen/X86/vec_shuffle-37.ll
@@ -26,10 +26,10 @@
 
 define void @t02(<8 x i32>* %source, <2 x i32>* %dest) nounwind noinline {
 entry:
-; CHECK: movaps  32({{%rdi|%rcx}}), %xmm0
-; CHECK-NEXT: movaps  48({{%rdi|%rcx}}), %xmm1
-; CHECK-NEXT: movss   %xmm1, %xmm0
-; CHECK-NEXT: movq    %xmm0, ({{%rsi|%rdx}}) 
+; CHECK: movl  36({{%rdi|%rcx}})
+; CHECK-NEXT: movl  48({{%rdi|%rcx}})
+; CHECK: punpcklqdq
+; CHECK: movq    %xmm0, ({{%rsi|%rdx}})
   %0 = bitcast <8 x i32>* %source to <4 x i32>*
   %arrayidx = getelementptr inbounds <4 x i32>* %0, i64 3
   %tmp2 = load <4 x i32>* %arrayidx, align 16
diff --git a/test/CodeGen/X86/vsplit-and.ll b/test/CodeGen/X86/vsplit-and.ll
index 97dacfd..f9944ce 100644
--- a/test/CodeGen/X86/vsplit-and.ll
+++ b/test/CodeGen/X86/vsplit-and.ll
@@ -2,7 +2,7 @@
 
 
 define void @t(<2 x i64>* %dst, <2 x i64> %src1, <2 x i64> %src2) nounwind readonly {
-; CHECK: andb
+; CHECK: pandn
   %cmp1 = icmp ne <2 x i64> %src1, zeroinitializer
   %cmp2 = icmp ne <2 x i64> %src2, zeroinitializer
   %t1 = and <2 x i1> %cmp1, %cmp2
@@ -12,7 +12,7 @@
 }
 
 define void @t2(<3 x i64>* %dst, <3 x i64> %src1, <3 x i64> %src2) nounwind readonly {
-; CHECK: andb
+; CHECK-NOT: pandn
   %cmp1 = icmp ne <3 x i64> %src1, zeroinitializer
   %cmp2 = icmp ne <3 x i64> %src2, zeroinitializer
   %t1 = and <3 x i1> %cmp1, %cmp2
diff --git a/test/CodeGen/X86/widen_arith-1.ll b/test/CodeGen/X86/widen_arith-1.ll
index 4b8016d..85367e8 100644
--- a/test/CodeGen/X86/widen_arith-1.ll
+++ b/test/CodeGen/X86/widen_arith-1.ll
@@ -1,12 +1,10 @@
 ; RUN: llc < %s -march=x86 -mattr=+sse42 |  FileCheck %s
 
-; Widen a v3i8 to v16i8 to use a vector add
-
 define void @update(<3 x i8>* %dst, <3 x i8>* %src, i32 %n) nounwind {
 entry:
 ; CHECK-NOT: pextrw
-; CHECK: paddb
-; CHECK: pextrb
+; CHECK: add
+
 	%dst.addr = alloca <3 x i8>*		; <<3 x i8>**> [#uses=2]
 	%src.addr = alloca <3 x i8>*		; <<3 x i8>**> [#uses=2]
 	%n.addr = alloca i32		; <i32*> [#uses=2]
diff --git a/test/CodeGen/X86/widen_arith-2.ll b/test/CodeGen/X86/widen_arith-2.ll
index 03b3fea..d35abc3 100644
--- a/test/CodeGen/X86/widen_arith-2.ll
+++ b/test/CodeGen/X86/widen_arith-2.ll
@@ -1,5 +1,5 @@
 ; RUN: llc < %s -march=x86 -mattr=+sse42 | FileCheck %s
-; CHECK: paddb
+; CHECK: padd
 ; CHECK: pand
 
 ; widen v8i8 to v16i8 (checks even power of 2 widening with add & and)
diff --git a/test/CodeGen/X86/widen_arith-3.ll b/test/CodeGen/X86/widen_arith-3.ll
index 0574923..11d56f5 100644
--- a/test/CodeGen/X86/widen_arith-3.ll
+++ b/test/CodeGen/X86/widen_arith-3.ll
@@ -1,7 +1,8 @@
 ; RUN: llc < %s -march=x86 -mattr=+sse42 -post-RA-scheduler=true | FileCheck %s
-; CHECK: paddw
-; CHECK: pextrw
-; CHECK: movd
+; CHECK: incw
+; CHECK: incl
+; CHECK: incl
+; CHECK: addl
 
 ; Widen a v3i16 to v8i16 to do a vector add
 
diff --git a/test/CodeGen/X86/widen_cast-1.ll b/test/CodeGen/X86/widen_cast-1.ll
index 1eace9e..4330aae 100644
--- a/test/CodeGen/X86/widen_cast-1.ll
+++ b/test/CodeGen/X86/widen_cast-1.ll
@@ -1,5 +1,5 @@
 ; RUN: llc -march=x86 -mattr=+sse42 < %s | FileCheck %s
-; CHECK: paddw
+; CHECK: paddd
 ; CHECK: pextrd
 ; CHECK: movd
 
diff --git a/test/CodeGen/X86/widen_cast-4.ll b/test/CodeGen/X86/widen_cast-4.ll
index 8e1adf5..5ea5426 100644
--- a/test/CodeGen/X86/widen_cast-4.ll
+++ b/test/CodeGen/X86/widen_cast-4.ll
@@ -1,16 +1,6 @@
 ; RUN: llc < %s -march=x86 -mattr=+sse42 | FileCheck %s
-; CHECK: sarb
-; CHECK: sarb
-; CHECK: sarb
-; CHECK: sarb
-; CHECK: sarb
-; CHECK: sarb
-; CHECK: sarb
-; CHECK: sarb
-
-; v8i8 that is widen to v16i8 then split
-; FIXME: This is widen to v16i8 and split to 16 and we then rebuild the vector.
-; Unfortunately, we don't split the store so we don't get the code we want.
+; CHECK: psraw
+; CHECK: psraw
 
 define void @update(i64* %dst_i, i64* %src_i, i32 %n) nounwind {
 entry:
diff --git a/test/CodeGen/X86/widen_conv-1.ll b/test/CodeGen/X86/widen_conv-1.ll
index f6810cd..51f1c88 100644
--- a/test/CodeGen/X86/widen_conv-1.ll
+++ b/test/CodeGen/X86/widen_conv-1.ll
@@ -1,6 +1,5 @@
 ; RUN: llc < %s -march=x86 -mattr=+sse42 | FileCheck %s
-; CHECK: pshufd
-; CHECK: paddd
+; CHECK: paddq
 
 ; truncate v2i64 to v2i32
 
diff --git a/test/CodeGen/X86/widen_conv-4.ll b/test/CodeGen/X86/widen_conv-4.ll
index 80f3a49..affd796 100644
--- a/test/CodeGen/X86/widen_conv-4.ll
+++ b/test/CodeGen/X86/widen_conv-4.ll
@@ -1,5 +1,5 @@
 ; RUN: llc < %s -march=x86 -mattr=+sse42 | FileCheck %s
-; CHECK: cvtsi2ss
+; CHECK-NOT: cvtsi2ss
 
 ; unsigned to float v7i16 to v7f32
 
diff --git a/test/CodeGen/X86/widen_load-0.ll b/test/CodeGen/X86/widen_load-0.ll
index c91627c..0d21b49 100644
--- a/test/CodeGen/X86/widen_load-0.ll
+++ b/test/CodeGen/X86/widen_load-0.ll
@@ -4,15 +4,15 @@
 
 ; Both loads should happen before either store.
 
-; CHECK: movl  (%rdi), %[[R1:...]]
-; CHECK: movl  (%rsi), %[[R2:...]]
-; CHECK: movl  %[[R2]], (%rdi)
-; CHECK: movl  %[[R1]], (%rsi)
+; CHECK: movd  (%rsi), {{.*}}
+; CHECK: movd  (%rdi), {{.*}}
+; CHECK: movd  {{.*}}, (%rdi)
+; CHECK: movd  {{.*}}, (%rsi)
 
-; WIN64: movl  (%rcx), %[[R1:...]]
-; WIN64: movl  (%rdx), %[[R2:...]]
-; WIN64: movl  %[[R2]], (%rcx)
-; WIN64: movl  %[[R1]], (%rdx)
+; WIN64: movd  (%rdx), {{.*}}
+; WIN64: movd  (%rcx), {{.*}}
+; WIN64: movd  {{.*}}, (%rcx)
+; WIN64: movd  {{.*}}, (%rdx)
 
 define void @short2_int_swap(<2 x i16>* nocapture %b, i32* nocapture %c) nounwind {
 entry:
diff --git a/test/CodeGen/X86/widen_load-2.ll b/test/CodeGen/X86/widen_load-2.ll
index 6422063..71699b8 100644
--- a/test/CodeGen/X86/widen_load-2.ll
+++ b/test/CodeGen/X86/widen_load-2.ll
@@ -4,6 +4,7 @@
 ;
 
 %i32vec3 = type <3 x i32>
+; CHECK: add3i32
 define void @add3i32(%i32vec3*  sret %ret, %i32vec3* %ap, %i32vec3* %bp)  {
 ; CHECK: movdqa
 ; CHECK: paddd
@@ -16,6 +17,7 @@
 	ret void
 }
 
+; CHECK: add3i32_2
 define void @add3i32_2(%i32vec3*  sret %ret, %i32vec3* %ap, %i32vec3* %bp)  {
 ; CHECK: movq
 ; CHECK: pinsrd
@@ -32,6 +34,7 @@
 }
 
 %i32vec7 = type <7 x i32>
+; CHECK: add7i32
 define void @add7i32(%i32vec7*  sret %ret, %i32vec7* %ap, %i32vec7* %bp)  {
 ; CHECK: movdqa
 ; CHECK: movdqa
@@ -47,6 +50,7 @@
 	ret void
 }
 
+; CHECK: add12i32
 %i32vec12 = type <12 x i32>
 define void @add12i32(%i32vec12*  sret %ret, %i32vec12* %ap, %i32vec12* %bp)  {
 ; CHECK: movdqa
@@ -66,12 +70,14 @@
 }
 
 
+; CHECK: add3i16
 %i16vec3 = type <3 x i16>
 define void @add3i16(%i16vec3* nocapture sret %ret, %i16vec3* %ap, %i16vec3* %bp) nounwind {
-; CHECK: movdqa
-; CHECK: paddw
-; CHECK: movd
-; CHECK: pextrw
+; CHECK: add3i16
+; CHECK: addl
+; CHECK: addl
+; CHECK: addl
+; CHECK: ret
 	%a = load %i16vec3* %ap, align 16
 	%b = load %i16vec3* %bp, align 16
 	%x = add %i16vec3 %a, %b
@@ -79,10 +85,11 @@
 	ret void
 }
 
+; CHECK: add4i16
 %i16vec4 = type <4 x i16>
 define void @add4i16(%i16vec4* nocapture sret %ret, %i16vec4* %ap, %i16vec4* %bp) nounwind {
-; CHECK: movdqa
-; CHECK: paddw
+; CHECK: add4i16
+; CHECK: paddd
 ; CHECK: movq
 	%a = load %i16vec4* %ap, align 16
 	%b = load %i16vec4* %bp, align 16
@@ -91,6 +98,7 @@
 	ret void
 }
 
+; CHECK: add12i16
 %i16vec12 = type <12 x i16>
 define void @add12i16(%i16vec12* nocapture sret %ret, %i16vec12* %ap, %i16vec12* %bp) nounwind {
 ; CHECK: movdqa
@@ -106,6 +114,7 @@
 	ret void
 }
 
+; CHECK: add18i16
 %i16vec18 = type <18 x i16>
 define void @add18i16(%i16vec18* nocapture sret %ret, %i16vec18* %ap, %i16vec18* %bp) nounwind {
 ; CHECK: movdqa
@@ -125,12 +134,13 @@
 }
 
 
+; CHECK: add3i8
 %i8vec3 = type <3 x i8>
 define void @add3i8(%i8vec3* nocapture sret %ret, %i8vec3* %ap, %i8vec3* %bp) nounwind {
-; CHECK: movdqa
-; CHECK: paddb
-; CHECK: pextrb
-; CHECK: movb
+; CHECK: addb
+; CHECK: addb
+; CHECK: addb
+; CHECK: ret
 	%a = load %i8vec3* %ap, align 16
 	%b = load %i8vec3* %bp, align 16
 	%x = add %i8vec3 %a, %b
@@ -138,6 +148,7 @@
 	ret void
 }
 
+; CHECK: add31i8:
 %i8vec31 = type <31 x i8>
 define void @add31i8(%i8vec31* nocapture sret %ret, %i8vec31* %ap, %i8vec31* %bp) nounwind {
 ; CHECK: movdqa
@@ -147,6 +158,7 @@
 ; CHECK: movq
 ; CHECK: pextrb
 ; CHECK: pextrw
+; CHECK: ret
 	%a = load %i8vec31* %ap, align 16
 	%b = load %i8vec31* %bp, align 16
 	%x = add %i8vec31 %a, %b
@@ -155,9 +167,10 @@
 }
 
 
+; CHECK: rot
 %i8vec3pack = type { <3 x i8>, i8 }
 define %i8vec3pack  @rot() nounwind {
-; CHECK: shrb
+; CHECK: shrl
 entry:
   %X = alloca %i8vec3pack, align 4
   %rot = alloca %i8vec3pack, align 4
diff --git a/test/CodeGen/X86/widen_shuffle-1.ll b/test/CodeGen/X86/widen_shuffle-1.ll
index 8e951b7..2df3b6a 100644
--- a/test/CodeGen/X86/widen_shuffle-1.ll
+++ b/test/CodeGen/X86/widen_shuffle-1.ll
@@ -50,7 +50,7 @@
 ; PR10421: make sure we correctly handle extreme widening with CONCAT_VECTORS
 define <8 x i8> @shuf4(<4 x i8> %a, <4 x i8> %b) nounwind readnone {
 ; CHECK: shuf4:
-; CHECK: punpckldq
+; CHECK-NOT: punpckldq
   %vshuf = shufflevector <4 x i8> %a, <4 x i8> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
   ret <8 x i8> %vshuf
 }
diff --git a/test/CodeGen/X86/x86-shifts.ll b/test/CodeGen/X86/x86-shifts.ll
index fdf68f9..1cb07aa 100644
--- a/test/CodeGen/X86/x86-shifts.ll
+++ b/test/CodeGen/X86/x86-shifts.ll
@@ -124,7 +124,7 @@
 define <2 x i32> @shl2_other(<2 x i32> %A) nounwind {
 entry:
 ; CHECK: shl2_other
-; CHECK-not:      psllq
+; CHECK: psllq
   %B = shl <2 x i32> %A,  < i32 2, i32 2>
   %C = shl <2 x i32> %A,  < i32 9, i32 9>
   %K = xor <2 x i32> %B, %C
@@ -134,7 +134,7 @@
 define <2 x i32> @shr2_other(<2 x i32> %A) nounwind {
 entry:
 ; CHECK: shr2_other
-; CHECK-NOT:      psrlq
+; CHECK: psrlq
   %B = lshr <2 x i32> %A,  < i32 8, i32 8>
   %C = lshr <2 x i32> %A,  < i32 1, i32 1>
   %K = xor <2 x i32> %B, %C