Make ARMAsmPrinter generate the correct alignment specifier syntax in instructions.

The Printer will now print instructions with the correct alignment specifier syntax, like
    vld1.8  {d16}, [r0:64]



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175884 91177308-0d34-0410-b5e6-96231b3b80d8

16 files changed, 96 insertions, 96 deletions

diff --git a/test/CodeGen/ARM/2011-11-29-128bitArithmetics.ll b/test/CodeGen/ARM/2011-11-29-128bitArithmetics.ll
index f9ede7401a..0d0d03b23e 100644
--- a/test/CodeGen/ARM/2011-11-29-128bitArithmetics.ll
+++ b/test/CodeGen/ARM/2011-11-29-128bitArithmetics.ll
@@ -8,7 +8,7 @@ define void @test_sqrt(<4 x float>* %X) nounwind {
 
 ; CHECK:      movw    r1, :lower16:{{.*}}
 ; CHECK:      movt    r1, :upper16:{{.*}}
-; CHECK:      vld1.64 {{.*}}, [r1, :128]
+; CHECK:      vld1.64 {{.*}}, [r1:128]
 ; CHECK:      vsqrt.f32       {{s[0-9]+}}, {{s[0-9]+}}
 ; CHECK:      vsqrt.f32       {{s[0-9]+}}, {{s[0-9]+}}
 ; CHECK:      vsqrt.f32       {{s[0-9]+}}, {{s[0-9]+}}
@@ -252,7 +252,7 @@ define void @test_powi(<4 x float>* %X) nounwind {
 
 ; CHECK:       movw  [[reg0:r[0-9]+]], :lower16:{{.*}}
 ; CHECK:       movt  [[reg0]], :upper16:{{.*}}
-; CHECK:       vld1.64 {{.*}}, :128
+; CHECK:       vld1.64 {{.*}}:128
 ; CHECK:       vmul.f32 {{.*}}
 
 ; CHECK:      vst1.64
diff --git a/test/CodeGen/ARM/2012-08-09-neon-extload.ll b/test/CodeGen/ARM/2012-08-09-neon-extload.ll
index b55f1cae7f..764c58f2e1 100644
--- a/test/CodeGen/ARM/2012-08-09-neon-extload.ll
+++ b/test/CodeGen/ARM/2012-08-09-neon-extload.ll
@@ -18,7 +18,7 @@ define void @test_v2i8tov2i32() {
 
   %i32val = sext <2 x i8> %i8val to <2 x i32>
   store <2 x i32> %i32val, <2 x i32>* @var_v2i32
-; CHECK: vld1.16 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}, :16]
+; CHECK: vld1.16 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}:16]
 ; CHECK: vmovl.s8 {{q[0-9]+}}, d[[LOAD]]
 ; CHECK: vmovl.s16 {{q[0-9]+}}, {{d[0-9]+}}
 
@@ -32,7 +32,7 @@ define void @test_v2i8tov2i64() {
 
   %i64val = sext <2 x i8> %i8val to <2 x i64>
   store <2 x i64> %i64val, <2 x i64>* @var_v2i64
-; CHECK: vld1.16 {d{{[0-9]+}}[0]}, [{{r[0-9]+}}, :16]
+; CHECK: vld1.16 {d{{[0-9]+}}[0]}, [{{r[0-9]+}}:16]
 ; CHECK: vmovl.s8 {{q[0-9]+}}, d[[LOAD]]
 ; CHECK: vmovl.s16 {{q[0-9]+}}, {{d[0-9]+}}
 ; CHECK: vmovl.s32 {{q[0-9]+}}, {{d[0-9]+}}
@@ -50,7 +50,7 @@ define void @test_v4i8tov4i16() {
 
   %i16val = sext <4 x i8> %i8val to <4 x i16>
   store <4 x i16> %i16val, <4 x i16>* @var_v4i16
-; CHECK: vld1.32 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}, :32]
+; CHECK: vld1.32 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}:32]
 ; CHECK: vmovl.s8 {{q[0-9]+}}, d[[LOAD]]
 ; CHECK-NOT: vmovl.s16
 
@@ -65,7 +65,7 @@ define void @test_v4i8tov4i32() {
 
   %i16val = sext <4 x i8> %i8val to <4 x i32>
   store <4 x i32> %i16val, <4 x i32>* @var_v4i32
-; CHECK: vld1.32 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}, :32]
+; CHECK: vld1.32 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}:32]
 ; CHECK: vmovl.s8 {{q[0-9]+}}, d[[LOAD]]
 ; CHECK: vmovl.s16 {{q[0-9]+}}, {{d[0-9]+}}
 
@@ -79,7 +79,7 @@ define void @test_v2i16tov2i32() {
 
   %i32val = sext <2 x i16> %i16val to <2 x i32>
   store <2 x i32> %i32val, <2 x i32>* @var_v2i32
-; CHECK: vld1.32 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}, :32]
+; CHECK: vld1.32 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}:32]
 ; CHECK: vmovl.s16 {{q[0-9]+}}, d[[LOAD]]
 ; CHECK-NOT: vmovl
 
@@ -94,7 +94,7 @@ define void @test_v2i16tov2i64() {
 
   %i64val = sext <2 x i16> %i16val to <2 x i64>
   store <2 x i64> %i64val, <2 x i64>* @var_v2i64
-; CHECK: vld1.32 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}, :32]
+; CHECK: vld1.32 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}:32]
 ; CHECK: vmovl.s16 {{q[0-9]+}}, d[[LOAD]]
 ; CHECK: vmovl.s32 {{q[0-9]+}}, d[[LOAD]]
 
diff --git a/test/CodeGen/ARM/neon_ld2.ll b/test/CodeGen/ARM/neon_ld2.ll
index 497619ed74..25a670b097 100644
--- a/test/CodeGen/ARM/neon_ld2.ll
+++ b/test/CodeGen/ARM/neon_ld2.ll
@@ -7,10 +7,10 @@
 ; CHECK: vadd.i64 q
 ; CHECK: vst1.64
 ; SWIFT: t1
-; SWIFT: vld1.64 {{.d[0-9]+, d[0-9]+}, \[r[0-9]+, :128\]}}
-; SWIFT: vld1.64 {{.d[0-9]+, d[0-9]+}, \[r[0-9]+, :128\]}}
+; SWIFT: vld1.64 {{.d[0-9]+, d[0-9]+}, \[r[0-9]+:128\]}}
+; SWIFT: vld1.64 {{.d[0-9]+, d[0-9]+}, \[r[0-9]+:128\]}}
 ; SWIFT: vadd.i64 q
-; SWIFT: vst1.64 {{.d[0-9]+, d[0-9]+}, \[r[0-9]+, :128\]}}
+; SWIFT: vst1.64 {{.d[0-9]+, d[0-9]+}, \[r[0-9]+:128\]}}
 define void @t1(<4 x i32>* %r, <2 x i64>* %a, <2 x i64>* %b) nounwind {
 entry:
 	%0 = load <2 x i64>* %a, align 16		; <<2 x i64>> [#uses=1]
@@ -28,8 +28,8 @@ entry:
 ; CHECK: vmov r0, r1, d
 ; CHECK: vmov r2, r3, d
 ; SWIFT: t2
-; SWIFT: vld1.64 {{.d[0-9]+, d[0-9]+}, \[r[0-9]+, :128\]}}
-; SWIFT: vld1.64 {{.d[0-9]+, d[0-9]+}, \[r[0-9]+, :128\]}}
+; SWIFT: vld1.64 {{.d[0-9]+, d[0-9]+}, \[r[0-9]+:128\]}}
+; SWIFT: vld1.64 {{.d[0-9]+, d[0-9]+}, \[r[0-9]+:128\]}}
 ; SWIFT: vsub.i64 q
 ; SWIFT: vmov r0, r1, d
 ; SWIFT: vmov r2, r3, d
diff --git a/test/CodeGen/ARM/reg_sequence.ll b/test/CodeGen/ARM/reg_sequence.ll
index 6d6586e4f2..fd2083cf9f 100644
--- a/test/CodeGen/ARM/reg_sequence.ll
+++ b/test/CodeGen/ARM/reg_sequence.ll
@@ -242,8 +242,8 @@ define arm_aapcs_vfpcc float @t9(%0* nocapture, %3* nocapture) nounwind {
 ; CHECK:        vldr
 ; CHECK-NOT:    vmov d{{.*}}, d16
 ; CHECK:        vmov.i32 d17
-; CHECK-NEXT:   vst1.64 {d16, d17}, [r0, :128]
-; CHECK-NEXT:   vst1.64 {d16, d17}, [r0, :128]
+; CHECK-NEXT:   vst1.64 {d16, d17}, [r0:128]
+; CHECK-NEXT:   vst1.64 {d16, d17}, [r0:128]
   %3 = bitcast double 0.000000e+00 to <2 x float> ; <<2 x float>> [#uses=2]
   %4 = shufflevector <2 x float> %3, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3> ; <<4 x float>> [#uses=1]
   store <4 x float> %4, <4 x float>* undef, align 16
diff --git a/test/CodeGen/ARM/spill-q.ll b/test/CodeGen/ARM/spill-q.ll
index 057ea11389..e93cdbc10a 100644
--- a/test/CodeGen/ARM/spill-q.ll
+++ b/test/CodeGen/ARM/spill-q.ll
@@ -12,8 +12,8 @@ declare <4 x float> @llvm.arm.neon.vld1.v4f32(i8*, i32) nounwind readonly
 define void @aaa(%quuz* %this, i8* %block) {
 ; CHECK: aaa:
 ; CHECK: bic {{.*}}, #15
-; CHECK: vst1.64 {{.*}}sp, :128
-; CHECK: vld1.64 {{.*}}sp, :128
+; CHECK: vst1.64 {{.*}}sp:128
+; CHECK: vld1.64 {{.*}}sp:128
 entry:
   %aligned_vec = alloca <4 x float>, align 16
   %"alloca point" = bitcast i32 0 to i32
diff --git a/test/CodeGen/ARM/vld1.ll b/test/CodeGen/ARM/vld1.ll
index e524395c50..994f05dacb 100644
--- a/test/CodeGen/ARM/vld1.ll
+++ b/test/CodeGen/ARM/vld1.ll
@@ -4,7 +4,7 @@
 define <8 x i8> @vld1i8(i8* %A) nounwind {
 ;CHECK: vld1i8:
 ;Check the alignment value.  Max for this instruction is 64 bits:
-;CHECK: vld1.8 {d16}, [r0, :64]
+;CHECK: vld1.8 {d16}, [r0:64]
 	%tmp1 = call <8 x i8> @llvm.arm.neon.vld1.v8i8(i8* %A, i32 16)
 	ret <8 x i8> %tmp1
 }
@@ -68,7 +68,7 @@ define <1 x i64> @vld1i64(i64* %A) nounwind {
 define <16 x i8> @vld1Qi8(i8* %A) nounwind {
 ;CHECK: vld1Qi8:
 ;Check the alignment value.  Max for this instruction is 128 bits:
-;CHECK: vld1.8 {d16, d17}, [r0, :64]
+;CHECK: vld1.8 {d16, d17}, [r0:64]
 	%tmp1 = call <16 x i8> @llvm.arm.neon.vld1.v16i8(i8* %A, i32 8)
 	ret <16 x i8> %tmp1
 }
@@ -76,7 +76,7 @@ define <16 x i8> @vld1Qi8(i8* %A) nounwind {
 ;Check for a post-increment updating load.
 define <16 x i8> @vld1Qi8_update(i8** %ptr) nounwind {
 ;CHECK: vld1Qi8_update:
-;CHECK: vld1.8 {d16, d17}, [{{r[0-9]+}}, :64]!
+;CHECK: vld1.8 {d16, d17}, [{{r[0-9]+}}:64]!
 	%A = load i8** %ptr
 	%tmp1 = call <16 x i8> @llvm.arm.neon.vld1.v16i8(i8* %A, i32 8)
 	%tmp2 = getelementptr i8* %A, i32 16
@@ -87,7 +87,7 @@ define <16 x i8> @vld1Qi8_update(i8** %ptr) nounwind {
 define <8 x i16> @vld1Qi16(i16* %A) nounwind {
 ;CHECK: vld1Qi16:
 ;Check the alignment value.  Max for this instruction is 128 bits:
-;CHECK: vld1.16 {d16, d17}, [r0, :128]
+;CHECK: vld1.16 {d16, d17}, [r0:128]
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %tmp0, i32 32)
 	ret <8 x i16> %tmp1
diff --git a/test/CodeGen/ARM/vld2.ll b/test/CodeGen/ARM/vld2.ll
index 29b379465d..caa016e929 100644
--- a/test/CodeGen/ARM/vld2.ll
+++ b/test/CodeGen/ARM/vld2.ll
@@ -14,7 +14,7 @@
 define <8 x i8> @vld2i8(i8* %A) nounwind {
 ;CHECK: vld2i8:
 ;Check the alignment value.  Max for this instruction is 128 bits:
-;CHECK: vld2.8 {d16, d17}, [r0, :64]
+;CHECK: vld2.8 {d16, d17}, [r0:64]
 	%tmp1 = call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2.v8i8(i8* %A, i32 8)
         %tmp2 = extractvalue %struct.__neon_int8x8x2_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int8x8x2_t %tmp1, 1
@@ -25,7 +25,7 @@ define <8 x i8> @vld2i8(i8* %A) nounwind {
 define <4 x i16> @vld2i16(i16* %A) nounwind {
 ;CHECK: vld2i16:
 ;Check the alignment value.  Max for this instruction is 128 bits:
-;CHECK: vld2.16 {d16, d17}, [r0, :128]
+;CHECK: vld2.16 {d16, d17}, [r0:128]
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2.v4i16(i8* %tmp0, i32 32)
         %tmp2 = extractvalue %struct.__neon_int16x4x2_t %tmp1, 0
@@ -74,7 +74,7 @@ define <2 x float> @vld2f_update(float** %ptr) nounwind {
 define <1 x i64> @vld2i64(i64* %A) nounwind {
 ;CHECK: vld2i64:
 ;Check the alignment value.  Max for this instruction is 128 bits:
-;CHECK: vld1.64 {d16, d17}, [r0, :128]
+;CHECK: vld1.64 {d16, d17}, [r0:128]
 	%tmp0 = bitcast i64* %A to i8*
 	%tmp1 = call %struct.__neon_int64x1x2_t @llvm.arm.neon.vld2.v1i64(i8* %tmp0, i32 32)
         %tmp2 = extractvalue %struct.__neon_int64x1x2_t %tmp1, 0
@@ -86,7 +86,7 @@ define <1 x i64> @vld2i64(i64* %A) nounwind {
 define <16 x i8> @vld2Qi8(i8* %A) nounwind {
 ;CHECK: vld2Qi8:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vld2.8 {d16, d17, d18, d19}, [r0, :64]
+;CHECK: vld2.8 {d16, d17, d18, d19}, [r0:64]
 	%tmp1 = call %struct.__neon_int8x16x2_t @llvm.arm.neon.vld2.v16i8(i8* %A, i32 8)
         %tmp2 = extractvalue %struct.__neon_int8x16x2_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int8x16x2_t %tmp1, 1
@@ -97,7 +97,7 @@ define <16 x i8> @vld2Qi8(i8* %A) nounwind {
 ;Check for a post-increment updating load with register increment.
 define <16 x i8> @vld2Qi8_update(i8** %ptr, i32 %inc) nounwind {
 ;CHECK: vld2Qi8_update:
-;CHECK: vld2.8 {d16, d17, d18, d19}, [r2, :128], r1
+;CHECK: vld2.8 {d16, d17, d18, d19}, [r2:128], r1
 	%A = load i8** %ptr
 	%tmp1 = call %struct.__neon_int8x16x2_t @llvm.arm.neon.vld2.v16i8(i8* %A, i32 16)
         %tmp2 = extractvalue %struct.__neon_int8x16x2_t %tmp1, 0
@@ -111,7 +111,7 @@ define <16 x i8> @vld2Qi8_update(i8** %ptr, i32 %inc) nounwind {
 define <8 x i16> @vld2Qi16(i16* %A) nounwind {
 ;CHECK: vld2Qi16:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vld2.16 {d16, d17, d18, d19}, [r0, :128]
+;CHECK: vld2.16 {d16, d17, d18, d19}, [r0:128]
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2.v8i16(i8* %tmp0, i32 16)
         %tmp2 = extractvalue %struct.__neon_int16x8x2_t %tmp1, 0
@@ -123,7 +123,7 @@ define <8 x i16> @vld2Qi16(i16* %A) nounwind {
 define <4 x i32> @vld2Qi32(i32* %A) nounwind {
 ;CHECK: vld2Qi32:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vld2.32 {d16, d17, d18, d19}, [r0, :256]
+;CHECK: vld2.32 {d16, d17, d18, d19}, [r0:256]
 	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8* %tmp0, i32 64)
         %tmp2 = extractvalue %struct.__neon_int32x4x2_t %tmp1, 0
diff --git a/test/CodeGen/ARM/vld3.ll b/test/CodeGen/ARM/vld3.ll
index b495319830..ad63e1f716 100644
--- a/test/CodeGen/ARM/vld3.ll
+++ b/test/CodeGen/ARM/vld3.ll
@@ -15,7 +15,7 @@
 define <8 x i8> @vld3i8(i8* %A) nounwind {
 ;CHECK: vld3i8:
 ;Check the alignment value.  Max for this instruction is 64 bits:
-;CHECK: vld3.8 {d16, d17, d18}, [r0, :64]
+;CHECK: vld3.8 {d16, d17, d18}, [r0:64]
 	%tmp1 = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A, i32 32)
         %tmp2 = extractvalue %struct.__neon_int8x8x3_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int8x8x3_t %tmp1, 2
@@ -74,7 +74,7 @@ define <2 x float> @vld3f(float* %A) nounwind {
 define <1 x i64> @vld3i64(i64* %A) nounwind {
 ;CHECK: vld3i64:
 ;Check the alignment value.  Max for this instruction is 64 bits:
-;CHECK: vld1.64 {d16, d17, d18}, [r0, :64]
+;CHECK: vld1.64 {d16, d17, d18}, [r0:64]
 	%tmp0 = bitcast i64* %A to i8*
 	%tmp1 = call %struct.__neon_int64x1x3_t @llvm.arm.neon.vld3.v1i64(i8* %tmp0, i32 16)
         %tmp2 = extractvalue %struct.__neon_int64x1x3_t %tmp1, 0
@@ -86,8 +86,8 @@ define <1 x i64> @vld3i64(i64* %A) nounwind {
 define <16 x i8> @vld3Qi8(i8* %A) nounwind {
 ;CHECK: vld3Qi8:
 ;Check the alignment value.  Max for this instruction is 64 bits:
-;CHECK: vld3.8 {d16, d18, d20}, [r0, :64]!
-;CHECK: vld3.8 {d17, d19, d21}, [r0, :64]
+;CHECK: vld3.8 {d16, d18, d20}, [r0:64]!
+;CHECK: vld3.8 {d17, d19, d21}, [r0:64]
 	%tmp1 = call %struct.__neon_int8x16x3_t @llvm.arm.neon.vld3.v16i8(i8* %A, i32 32)
         %tmp2 = extractvalue %struct.__neon_int8x16x3_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int8x16x3_t %tmp1, 2
diff --git a/test/CodeGen/ARM/vld4.ll b/test/CodeGen/ARM/vld4.ll
index 59a73db318..9ee5fe46ee 100644
--- a/test/CodeGen/ARM/vld4.ll
+++ b/test/CodeGen/ARM/vld4.ll
@@ -14,7 +14,7 @@
 define <8 x i8> @vld4i8(i8* %A) nounwind {
 ;CHECK: vld4i8:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vld4.8 {d16, d17, d18, d19}, [r0, :64]
+;CHECK: vld4.8 {d16, d17, d18, d19}, [r0:64]
 	%tmp1 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8(i8* %A, i32 8)
         %tmp2 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 2
@@ -25,7 +25,7 @@ define <8 x i8> @vld4i8(i8* %A) nounwind {
 ;Check for a post-increment updating load with register increment.
 define <8 x i8> @vld4i8_update(i8** %ptr, i32 %inc) nounwind {
 ;CHECK: vld4i8_update:
-;CHECK: vld4.8 {d16, d17, d18, d19}, [r2, :128], r1
+;CHECK: vld4.8 {d16, d17, d18, d19}, [r2:128], r1
 	%A = load i8** %ptr
 	%tmp1 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8(i8* %A, i32 16)
 	%tmp2 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 0
@@ -39,7 +39,7 @@ define <8 x i8> @vld4i8_update(i8** %ptr, i32 %inc) nounwind {
 define <4 x i16> @vld4i16(i16* %A) nounwind {
 ;CHECK: vld4i16:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vld4.16 {d16, d17, d18, d19}, [r0, :128]
+;CHECK: vld4.16 {d16, d17, d18, d19}, [r0:128]
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4.v4i16(i8* %tmp0, i32 16)
         %tmp2 = extractvalue %struct.__neon_int16x4x4_t %tmp1, 0
@@ -51,7 +51,7 @@ define <4 x i16> @vld4i16(i16* %A) nounwind {
 define <2 x i32> @vld4i32(i32* %A) nounwind {
 ;CHECK: vld4i32:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vld4.32 {d16, d17, d18, d19}, [r0, :256]
+;CHECK: vld4.32 {d16, d17, d18, d19}, [r0:256]
 	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4.v2i32(i8* %tmp0, i32 32)
         %tmp2 = extractvalue %struct.__neon_int32x2x4_t %tmp1, 0
@@ -74,7 +74,7 @@ define <2 x float> @vld4f(float* %A) nounwind {
 define <1 x i64> @vld4i64(i64* %A) nounwind {
 ;CHECK: vld4i64:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vld1.64 {d16, d17, d18, d19}, [r0, :256]
+;CHECK: vld1.64 {d16, d17, d18, d19}, [r0:256]
 	%tmp0 = bitcast i64* %A to i8*
 	%tmp1 = call %struct.__neon_int64x1x4_t @llvm.arm.neon.vld4.v1i64(i8* %tmp0, i32 64)
         %tmp2 = extractvalue %struct.__neon_int64x1x4_t %tmp1, 0
@@ -86,8 +86,8 @@ define <1 x i64> @vld4i64(i64* %A) nounwind {
 define <16 x i8> @vld4Qi8(i8* %A) nounwind {
 ;CHECK: vld4Qi8:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vld4.8 {d16, d18, d20, d22}, [r0, :256]!
-;CHECK: vld4.8 {d17, d19, d21, d23}, [r0, :256]
+;CHECK: vld4.8 {d16, d18, d20, d22}, [r0:256]!
+;CHECK: vld4.8 {d17, d19, d21, d23}, [r0:256]
 	%tmp1 = call %struct.__neon_int8x16x4_t @llvm.arm.neon.vld4.v16i8(i8* %A, i32 64)
         %tmp2 = extractvalue %struct.__neon_int8x16x4_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int8x16x4_t %tmp1, 2
@@ -111,8 +111,8 @@ define <8 x i16> @vld4Qi16(i16* %A) nounwind {
 ;Check for a post-increment updating load. 
 define <8 x i16> @vld4Qi16_update(i16** %ptr) nounwind {
 ;CHECK: vld4Qi16_update:
-;CHECK: vld4.16 {d16, d18, d20, d22}, [r1, :64]!
-;CHECK: vld4.16 {d17, d19, d21, d23}, [r1, :64]!
+;CHECK: vld4.16 {d16, d18, d20, d22}, [r1:64]!
+;CHECK: vld4.16 {d17, d19, d21, d23}, [r1:64]!
 	%A = load i16** %ptr
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4.v8i16(i8* %tmp0, i32 8)
diff --git a/test/CodeGen/ARM/vlddup.ll b/test/CodeGen/ARM/vlddup.ll
index c69473f87f..7c7319c090 100644
--- a/test/CodeGen/ARM/vlddup.ll
+++ b/test/CodeGen/ARM/vlddup.ll
@@ -13,7 +13,7 @@ define <8 x i8> @vld1dupi8(i8* %A) nounwind {
 define <4 x i16> @vld1dupi16(i16* %A) nounwind {
 ;CHECK: vld1dupi16:
 ;Check the alignment value.  Max for this instruction is 16 bits:
-;CHECK: vld1.16 {d16[]}, [r0, :16]
+;CHECK: vld1.16 {d16[]}, [r0:16]
 	%tmp1 = load i16* %A, align 8
 	%tmp2 = insertelement <4 x i16> undef, i16 %tmp1, i32 0
 	%tmp3 = shufflevector <4 x i16> %tmp2, <4 x i16> undef, <4 x i32> zeroinitializer
@@ -23,7 +23,7 @@ define <4 x i16> @vld1dupi16(i16* %A) nounwind {
 define <2 x i32> @vld1dupi32(i32* %A) nounwind {
 ;CHECK: vld1dupi32:
 ;Check the alignment value.  Max for this instruction is 32 bits:
-;CHECK: vld1.32 {d16[]}, [r0, :32]
+;CHECK: vld1.32 {d16[]}, [r0:32]
 	%tmp1 = load i32* %A, align 8
 	%tmp2 = insertelement <2 x i32> undef, i32 %tmp1, i32 0
 	%tmp3 = shufflevector <2 x i32> %tmp2, <2 x i32> undef, <2 x i32> zeroinitializer
@@ -32,7 +32,7 @@ define <2 x i32> @vld1dupi32(i32* %A) nounwind {
 
 define <2 x float> @vld1dupf(float* %A) nounwind {
 ;CHECK: vld1dupf:
-;CHECK: vld1.32 {d16[]}, [r0, :32]
+;CHECK: vld1.32 {d16[]}, [r0:32]
 	%tmp0 = load float* %A
         %tmp1 = insertelement <2 x float> undef, float %tmp0, i32 0
         %tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> zeroinitializer
@@ -51,7 +51,7 @@ define <16 x i8> @vld1dupQi8(i8* %A) nounwind {
 
 define <4 x float> @vld1dupQf(float* %A) nounwind {
 ;CHECK: vld1dupQf:
-;CHECK: vld1.32 {d16[], d17[]}, [r0, :32]
+;CHECK: vld1.32 {d16[], d17[]}, [r0:32]
         %tmp0 = load float* %A
         %tmp1 = insertelement <4 x float> undef, float %tmp0, i32 0
         %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> zeroinitializer
@@ -109,7 +109,7 @@ define <4 x i16> @vld2dupi16_update(i16** %ptr) nounwind {
 define <2 x i32> @vld2dupi32(i8* %A) nounwind {
 ;CHECK: vld2dupi32:
 ;Check the alignment value.  Max for this instruction is 64 bits:
-;CHECK: vld2.32 {d16[], d17[]}, [r0, :64]
+;CHECK: vld2.32 {d16[], d17[]}, [r0:64]
 	%tmp0 = tail call %struct.__neon_int2x32x2_t @llvm.arm.neon.vld2lane.v2i32(i8* %A, <2 x i32> undef, <2 x i32> undef, i32 0, i32 16)
 	%tmp1 = extractvalue %struct.__neon_int2x32x2_t %tmp0, 0
 	%tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> zeroinitializer
@@ -194,7 +194,7 @@ define <2 x i32> @vld4dupi32(i8* %A) nounwind {
 ;CHECK: vld4dupi32:
 ;Check the alignment value.  An 8-byte alignment is allowed here even though
 ;it is smaller than the total size of the memory being loaded.
-;CHECK: vld4.32 {d16[], d17[], d18[], d19[]}, [r0, :64]
+;CHECK: vld4.32 {d16[], d17[], d18[], d19[]}, [r0:64]
 	%tmp0 = tail call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i8* %A, <2 x i32> undef, <2 x i32> undef, <2 x i32> undef, <2 x i32> undef, i32 0, i32 8)
 	%tmp1 = extractvalue %struct.__neon_int32x2x4_t %tmp0, 0
 	%tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> zeroinitializer
diff --git a/test/CodeGen/ARM/vldlane.ll b/test/CodeGen/ARM/vldlane.ll
index 7bd0cbda02..f35fa92f5d 100644
--- a/test/CodeGen/ARM/vldlane.ll
+++ b/test/CodeGen/ARM/vldlane.ll
@@ -14,7 +14,7 @@ define <8 x i8> @vld1lanei8(i8* %A, <8 x i8>* %B) nounwind {
 define <4 x i16> @vld1lanei16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vld1lanei16:
 ;Check the alignment value.  Max for this instruction is 16 bits:
-;CHECK: vld1.16 {d16[2]}, [r0, :16]
+;CHECK: vld1.16 {d16[2]}, [r0:16]
 	%tmp1 = load <4 x i16>* %B
 	%tmp2 = load i16* %A, align 8
 	%tmp3 = insertelement <4 x i16> %tmp1, i16 %tmp2, i32 2
@@ -24,7 +24,7 @@ define <4 x i16> @vld1lanei16(i16* %A, <4 x i16>* %B) nounwind {
 define <2 x i32> @vld1lanei32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vld1lanei32:
 ;Check the alignment value.  Max for this instruction is 32 bits:
-;CHECK: vld1.32 {d16[1]}, [r0, :32]
+;CHECK: vld1.32 {d16[1]}, [r0:32]
 	%tmp1 = load <2 x i32>* %B
 	%tmp2 = load i32* %A, align 8
 	%tmp3 = insertelement <2 x i32> %tmp1, i32 %tmp2, i32 1
@@ -34,7 +34,7 @@ define <2 x i32> @vld1lanei32(i32* %A, <2 x i32>* %B) nounwind {
 define <2 x i32> @vld1lanei32a32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vld1lanei32a32:
 ;Check the alignment value.  Legal values are none or :32.
-;CHECK: vld1.32 {d16[1]}, [r0, :32]
+;CHECK: vld1.32 {d16[1]}, [r0:32]
 	%tmp1 = load <2 x i32>* %B
 	%tmp2 = load i32* %A, align 4
 	%tmp3 = insertelement <2 x i32> %tmp1, i32 %tmp2, i32 1
@@ -43,7 +43,7 @@ define <2 x i32> @vld1lanei32a32(i32* %A, <2 x i32>* %B) nounwind {
 
 define <2 x float> @vld1lanef(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vld1lanef:
-;CHECK: vld1.32 {d16[1]}, [r0, :32]
+;CHECK: vld1.32 {d16[1]}, [r0:32]
 	%tmp1 = load <2 x float>* %B
 	%tmp2 = load float* %A, align 4
 	%tmp3 = insertelement <2 x float> %tmp1, float %tmp2, i32 1
@@ -61,7 +61,7 @@ define <16 x i8> @vld1laneQi8(i8* %A, <16 x i8>* %B) nounwind {
 
 define <8 x i16> @vld1laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vld1laneQi16:
-;CHECK: vld1.16 {d17[1]}, [r0, :16]
+;CHECK: vld1.16 {d17[1]}, [r0:16]
 	%tmp1 = load <8 x i16>* %B
 	%tmp2 = load i16* %A, align 8
 	%tmp3 = insertelement <8 x i16> %tmp1, i16 %tmp2, i32 5
@@ -70,7 +70,7 @@ define <8 x i16> @vld1laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 
 define <4 x i32> @vld1laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vld1laneQi32:
-;CHECK: vld1.32 {d17[1]}, [r0, :32]
+;CHECK: vld1.32 {d17[1]}, [r0:32]
 	%tmp1 = load <4 x i32>* %B
 	%tmp2 = load i32* %A, align 8
 	%tmp3 = insertelement <4 x i32> %tmp1, i32 %tmp2, i32 3
@@ -79,7 +79,7 @@ define <4 x i32> @vld1laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 
 define <4 x float> @vld1laneQf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vld1laneQf:
-;CHECK: vld1.32 {d16[0]}, [r0, :32]
+;CHECK: vld1.32 {d16[0]}, [r0:32]
 	%tmp1 = load <4 x float>* %B
 	%tmp2 = load float* %A
 	%tmp3 = insertelement <4 x float> %tmp1, float %tmp2, i32 0
@@ -98,7 +98,7 @@ define <4 x float> @vld1laneQf(float* %A, <4 x float>* %B) nounwind {
 define <8 x i8> @vld2lanei8(i8* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vld2lanei8:
 ;Check the alignment value.  Max for this instruction is 16 bits:
-;CHECK: vld2.8 {d16[1], d17[1]}, [r0, :16]
+;CHECK: vld2.8 {d16[1], d17[1]}, [r0:16]
 	%tmp1 = load <8 x i8>* %B
 	%tmp2 = call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 4)
         %tmp3 = extractvalue %struct.__neon_int8x8x2_t %tmp2, 0
@@ -110,7 +110,7 @@ define <8 x i8> @vld2lanei8(i8* %A, <8 x i8>* %B) nounwind {
 define <4 x i16> @vld2lanei16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vld2lanei16:
 ;Check the alignment value.  Max for this instruction is 32 bits:
-;CHECK: vld2.16 {d16[1], d17[1]}, [r0, :32]
+;CHECK: vld2.16 {d16[1], d17[1]}, [r0:32]
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
 	%tmp2 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 8)
@@ -176,7 +176,7 @@ define <8 x i16> @vld2laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 define <4 x i32> @vld2laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vld2laneQi32:
 ;Check the alignment value.  Max for this instruction is 64 bits:
-;CHECK: vld2.32 {d17[0], d19[0]}, [{{r[0-9]+}}, :64]
+;CHECK: vld2.32 {d17[0], d19[0]}, [{{r[0-9]+}}:64]
 	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
 	%tmp2 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2, i32 16)
@@ -354,7 +354,7 @@ declare %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3lane.v4f32(i8*, <4 x flo
 define <8 x i8> @vld4lanei8(i8* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vld4lanei8:
 ;Check the alignment value.  Max for this instruction is 32 bits:
-;CHECK: vld4.8 {d{{.*}}[1], d{{.*}}[1], d{{.*}}[1], d{{.*}}[1]}, [{{r[0-9]+}}, :32]
+;CHECK: vld4.8 {d{{.*}}[1], d{{.*}}[1], d{{.*}}[1], d{{.*}}[1]}, [{{r[0-9]+}}:32]
 	%tmp1 = load <8 x i8>* %B
 	%tmp2 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 8)
         %tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 0
@@ -370,7 +370,7 @@ define <8 x i8> @vld4lanei8(i8* %A, <8 x i8>* %B) nounwind {
 ;Check for a post-increment updating load.
 define <8 x i8> @vld4lanei8_update(i8** %ptr, <8 x i8>* %B) nounwind {
 ;CHECK: vld4lanei8_update:
-;CHECK: vld4.8 {d16[1], d17[1], d18[1], d19[1]}, [{{r[0-9]+}}, :32]!
+;CHECK: vld4.8 {d16[1], d17[1], d18[1], d19[1]}, [{{r[0-9]+}}:32]!
 	%A = load i8** %ptr
 	%tmp1 = load <8 x i8>* %B
 	%tmp2 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 8)
@@ -408,7 +408,7 @@ define <2 x i32> @vld4lanei32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vld4lanei32:
 ;Check the alignment value.  An 8-byte alignment is allowed here even though
 ;it is smaller than the total size of the memory being loaded.
-;CHECK: vld4.32 {d16[1], d17[1], d18[1], d19[1]}, [{{r[0-9]+}}, :64]
+;CHECK: vld4.32 {d16[1], d17[1], d18[1], d19[1]}, [{{r[0-9]+}}:64]
 	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
 	%tmp2 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 8)
@@ -441,7 +441,7 @@ define <2 x float> @vld4lanef(float* %A, <2 x float>* %B) nounwind {
 define <8 x i16> @vld4laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vld4laneQi16:
 ;Check the alignment value.  Max for this instruction is 64 bits:
-;CHECK: vld4.16 {d16[1], d18[1], d20[1], d22[1]}, [{{r[0-9]+}}, :64]
+;CHECK: vld4.16 {d16[1], d18[1], d20[1], d22[1]}, [{{r[0-9]+}}:64]
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
 	%tmp2 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1, i32 16)
diff --git a/test/CodeGen/ARM/vst1.ll b/test/CodeGen/ARM/vst1.ll
index 364d44b711..e1f3e88907 100644
--- a/test/CodeGen/ARM/vst1.ll
+++ b/test/CodeGen/ARM/vst1.ll
@@ -3,7 +3,7 @@
 define void @vst1i8(i8* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vst1i8:
 ;Check the alignment value.  Max for this instruction is 64 bits:
-;CHECK: vst1.8 {d16}, [r0, :64]
+;CHECK: vst1.8 {d16}, [r0:64]
 	%tmp1 = load <8 x i8>* %B
 	call void @llvm.arm.neon.vst1.v8i8(i8* %A, <8 x i8> %tmp1, i32 16)
 	ret void
@@ -61,7 +61,7 @@ define void @vst1i64(i64* %A, <1 x i64>* %B) nounwind {
 define void @vst1Qi8(i8* %A, <16 x i8>* %B) nounwind {
 ;CHECK: vst1Qi8:
 ;Check the alignment value.  Max for this instruction is 128 bits:
-;CHECK: vst1.8 {d16, d17}, [r0, :64]
+;CHECK: vst1.8 {d16, d17}, [r0:64]
 	%tmp1 = load <16 x i8>* %B
 	call void @llvm.arm.neon.vst1.v16i8(i8* %A, <16 x i8> %tmp1, i32 8)
 	ret void
@@ -70,7 +70,7 @@ define void @vst1Qi8(i8* %A, <16 x i8>* %B) nounwind {
 define void @vst1Qi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vst1Qi16:
 ;Check the alignment value.  Max for this instruction is 128 bits:
-;CHECK: vst1.16 {d16, d17}, [r0, :128]
+;CHECK: vst1.16 {d16, d17}, [r0:128]
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
 	call void @llvm.arm.neon.vst1.v8i16(i8* %tmp0, <8 x i16> %tmp1, i32 32)
@@ -80,7 +80,7 @@ define void @vst1Qi16(i16* %A, <8 x i16>* %B) nounwind {
 ;Check for a post-increment updating store with register increment.
 define void @vst1Qi16_update(i16** %ptr, <8 x i16>* %B, i32 %inc) nounwind {
 ;CHECK: vst1Qi16_update:
-;CHECK: vst1.16 {d16, d17}, [r1, :64], r2
+;CHECK: vst1.16 {d16, d17}, [r1:64], r2
 	%A = load i16** %ptr
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
diff --git a/test/CodeGen/ARM/vst2.ll b/test/CodeGen/ARM/vst2.ll
index fb05a20f66..a31f8635fe 100644
--- a/test/CodeGen/ARM/vst2.ll
+++ b/test/CodeGen/ARM/vst2.ll
@@ -3,7 +3,7 @@
 define void @vst2i8(i8* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vst2i8:
 ;Check the alignment value.  Max for this instruction is 128 bits:
-;CHECK: vst2.8 {d16, d17}, [r0, :64]
+;CHECK: vst2.8 {d16, d17}, [r0:64]
 	%tmp1 = load <8 x i8>* %B
 	call void @llvm.arm.neon.vst2.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 8)
 	ret void
@@ -24,7 +24,7 @@ define void @vst2i8_update(i8** %ptr, <8 x i8>* %B, i32 %inc) nounwind {
 define void @vst2i16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst2i16:
 ;Check the alignment value.  Max for this instruction is 128 bits:
-;CHECK: vst2.16 {d16, d17}, [r0, :128]
+;CHECK: vst2.16 {d16, d17}, [r0:128]
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
 	call void @llvm.arm.neon.vst2.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 32)
@@ -52,7 +52,7 @@ define void @vst2f(float* %A, <2 x float>* %B) nounwind {
 define void @vst2i64(i64* %A, <1 x i64>* %B) nounwind {
 ;CHECK: vst2i64:
 ;Check the alignment value.  Max for this instruction is 128 bits:
-;CHECK: vst1.64 {d16, d17}, [r0, :128]
+;CHECK: vst1.64 {d16, d17}, [r0:128]
 	%tmp0 = bitcast i64* %A to i8*
 	%tmp1 = load <1 x i64>* %B
 	call void @llvm.arm.neon.vst2.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, i32 32)
@@ -62,7 +62,7 @@ define void @vst2i64(i64* %A, <1 x i64>* %B) nounwind {
 ;Check for a post-increment updating store.
 define void @vst2i64_update(i64** %ptr, <1 x i64>* %B) nounwind {
 ;CHECK: vst2i64_update:
-;CHECK: vst1.64 {d16, d17}, [r1, :64]!
+;CHECK: vst1.64 {d16, d17}, [r1:64]!
 	%A = load i64** %ptr
 	%tmp0 = bitcast i64* %A to i8*
 	%tmp1 = load <1 x i64>* %B
@@ -75,7 +75,7 @@ define void @vst2i64_update(i64** %ptr, <1 x i64>* %B) nounwind {
 define void @vst2Qi8(i8* %A, <16 x i8>* %B) nounwind {
 ;CHECK: vst2Qi8:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vst2.8 {d16, d17, d18, d19}, [r0, :64]
+;CHECK: vst2.8 {d16, d17, d18, d19}, [r0:64]
 	%tmp1 = load <16 x i8>* %B
 	call void @llvm.arm.neon.vst2.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, i32 8)
 	ret void
@@ -84,7 +84,7 @@ define void @vst2Qi8(i8* %A, <16 x i8>* %B) nounwind {
 define void @vst2Qi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vst2Qi16:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vst2.16 {d16, d17, d18, d19}, [r0, :128]
+;CHECK: vst2.16 {d16, d17, d18, d19}, [r0:128]
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
 	call void @llvm.arm.neon.vst2.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 16)
@@ -94,7 +94,7 @@ define void @vst2Qi16(i16* %A, <8 x i16>* %B) nounwind {
 define void @vst2Qi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst2Qi32:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vst2.32 {d16, d17, d18, d19}, [r0, :256]
+;CHECK: vst2.32 {d16, d17, d18, d19}, [r0:256]
 	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
 	call void @llvm.arm.neon.vst2.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 64)
diff --git a/test/CodeGen/ARM/vst3.ll b/test/CodeGen/ARM/vst3.ll
index f117ab205d..281bb730fe 100644
--- a/test/CodeGen/ARM/vst3.ll
+++ b/test/CodeGen/ARM/vst3.ll
@@ -4,7 +4,7 @@ define void @vst3i8(i8* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vst3i8:
 ;Check the alignment value.  Max for this instruction is 64 bits:
 ;This test runs at -O0 so do not check for specific register numbers.
-;CHECK: vst3.8 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}, :64]
+;CHECK: vst3.8 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}:64]
 	%tmp1 = load <8 x i8>* %B
 	call void @llvm.arm.neon.vst3.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 32)
 	ret void
@@ -54,7 +54,7 @@ define void @vst3i64(i64* %A, <1 x i64>* %B) nounwind {
 ;CHECK: vst3i64:
 ;Check the alignment value.  Max for this instruction is 64 bits:
 ;This test runs at -O0 so do not check for specific register numbers.
-;CHECK: vst1.64 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}, :64]
+;CHECK: vst1.64 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}:64]
 	%tmp0 = bitcast i64* %A to i8*
 	%tmp1 = load <1 x i64>* %B
 	call void @llvm.arm.neon.vst3.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, i32 16)
@@ -65,8 +65,8 @@ define void @vst3Qi8(i8* %A, <16 x i8>* %B) nounwind {
 ;CHECK: vst3Qi8:
 ;Check the alignment value.  Max for this instruction is 64 bits:
 ;This test runs at -O0 so do not check for specific register numbers.
-;CHECK: vst3.8 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}, :64]!
-;CHECK: vst3.8 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}, :64]
+;CHECK: vst3.8 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}:64]!
+;CHECK: vst3.8 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}:64]
 	%tmp1 = load <16 x i8>* %B
 	call void @llvm.arm.neon.vst3.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, i32 32)
 	ret void
diff --git a/test/CodeGen/ARM/vst4.ll b/test/CodeGen/ARM/vst4.ll
index e94acb66bf..7dedb2fafe 100644
--- a/test/CodeGen/ARM/vst4.ll
+++ b/test/CodeGen/ARM/vst4.ll
@@ -3,7 +3,7 @@
 define void @vst4i8(i8* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vst4i8:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vst4.8 {d16, d17, d18, d19}, [r0, :64]
+;CHECK: vst4.8 {d16, d17, d18, d19}, [r0:64]
 	%tmp1 = load <8 x i8>* %B
 	call void @llvm.arm.neon.vst4.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 8)
 	ret void
@@ -12,7 +12,7 @@ define void @vst4i8(i8* %A, <8 x i8>* %B) nounwind {
 ;Check for a post-increment updating store with register increment.
 define void @vst4i8_update(i8** %ptr, <8 x i8>* %B, i32 %inc) nounwind {
 ;CHECK: vst4i8_update:
-;CHECK: vst4.8 {d16, d17, d18, d19}, [r1, :128], r2
+;CHECK: vst4.8 {d16, d17, d18, d19}, [r1:128], r2
 	%A = load i8** %ptr
 	%tmp1 = load <8 x i8>* %B
 	call void @llvm.arm.neon.vst4.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 16)
@@ -24,7 +24,7 @@ define void @vst4i8_update(i8** %ptr, <8 x i8>* %B, i32 %inc) nounwind {
 define void @vst4i16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst4i16:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vst4.16 {d16, d17, d18, d19}, [r0, :128]
+;CHECK: vst4.16 {d16, d17, d18, d19}, [r0:128]
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
 	call void @llvm.arm.neon.vst4.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 16)
@@ -34,7 +34,7 @@ define void @vst4i16(i16* %A, <4 x i16>* %B) nounwind {
 define void @vst4i32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vst4i32:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vst4.32 {d16, d17, d18, d19}, [r0, :256]
+;CHECK: vst4.32 {d16, d17, d18, d19}, [r0:256]
 	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
 	call void @llvm.arm.neon.vst4.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 32)
@@ -53,7 +53,7 @@ define void @vst4f(float* %A, <2 x float>* %B) nounwind {
 define void @vst4i64(i64* %A, <1 x i64>* %B) nounwind {
 ;CHECK: vst4i64:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vst1.64 {d16, d17, d18, d19}, [r0, :256]
+;CHECK: vst1.64 {d16, d17, d18, d19}, [r0:256]
 	%tmp0 = bitcast i64* %A to i8*
 	%tmp1 = load <1 x i64>* %B
 	call void @llvm.arm.neon.vst4.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, i32 64)
@@ -63,8 +63,8 @@ define void @vst4i64(i64* %A, <1 x i64>* %B) nounwind {
 define void @vst4Qi8(i8* %A, <16 x i8>* %B) nounwind {
 ;CHECK: vst4Qi8:
 ;Check the alignment value.  Max for this instruction is 256 bits:
-;CHECK: vst4.8 {d16, d18, d20, d22}, [r0, :256]!
-;CHECK: vst4.8 {d17, d19, d21, d23}, [r0, :256]
+;CHECK: vst4.8 {d16, d18, d20, d22}, [r0:256]!
+;CHECK: vst4.8 {d17, d19, d21, d23}, [r0:256]
 	%tmp1 = load <16 x i8>* %B
 	call void @llvm.arm.neon.vst4.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, i32 64)
 	ret void
diff --git a/test/CodeGen/ARM/vstlane.ll b/test/CodeGen/ARM/vstlane.ll
index 758b355736..67f251f706 100644
--- a/test/CodeGen/ARM/vstlane.ll
+++ b/test/CodeGen/ARM/vstlane.ll
@@ -26,7 +26,7 @@ define void @vst1lanei8_update(i8** %ptr, <8 x i8>* %B) nounwind {
 define void @vst1lanei16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst1lanei16:
 ;Check the alignment value.  Max for this instruction is 16 bits:
-;CHECK: vst1.16 {d16[2]}, [r0, :16]
+;CHECK: vst1.16 {d16[2]}, [r0:16]
 	%tmp1 = load <4 x i16>* %B
         %tmp2 = extractelement <4 x i16> %tmp1, i32 2
         store i16 %tmp2, i16* %A, align 8
@@ -36,7 +36,7 @@ define void @vst1lanei16(i16* %A, <4 x i16>* %B) nounwind {
 define void @vst1lanei32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vst1lanei32:
 ;Check the alignment value.  Max for this instruction is 32 bits:
-;CHECK: vst1.32 {d16[1]}, [r0, :32]
+;CHECK: vst1.32 {d16[1]}, [r0:32]
 	%tmp1 = load <2 x i32>* %B
         %tmp2 = extractelement <2 x i32> %tmp1, i32 1
         store i32 %tmp2, i32* %A, align 8
@@ -45,7 +45,7 @@ define void @vst1lanei32(i32* %A, <2 x i32>* %B) nounwind {
 
 define void @vst1lanef(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vst1lanef:
-;CHECK: vst1.32 {d16[1]}, [r0, :32]
+;CHECK: vst1.32 {d16[1]}, [r0:32]
 	%tmp1 = load <2 x float>* %B
         %tmp2 = extractelement <2 x float> %tmp1, i32 1
         store float %tmp2, float* %A
@@ -64,7 +64,7 @@ define void @vst1laneQi8(i8* %A, <16 x i8>* %B) nounwind {
 
 define void @vst1laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vst1laneQi16:
-;CHECK: vst1.16 {d17[1]}, [r0, :16]
+;CHECK: vst1.16 {d17[1]}, [r0:16]
 	%tmp1 = load <8 x i16>* %B
         %tmp2 = extractelement <8 x i16> %tmp1, i32 5
         store i16 %tmp2, i16* %A, align 8
@@ -74,7 +74,7 @@ define void @vst1laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 define void @vst1laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst1laneQi32:
 ; // Can use scalar load. No need to use vectors.
-; // CHE-CK: vst1.32 {d17[1]}, [r0, :32]
+; // CHE-CK: vst1.32 {d17[1]}, [r0:32]
 	%tmp1 = load <4 x i32>* %B
         %tmp2 = extractelement <4 x i32> %tmp1, i32 3
         store i32 %tmp2, i32* %A, align 8
@@ -85,7 +85,7 @@ define void @vst1laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 define void @vst1laneQi32_update(i32** %ptr, <4 x i32>* %B) nounwind {
 ;CHECK: vst1laneQi32_update:
 ; // Can use scalar load. No need to use vectors.
-; // CHE-CK: vst1.32 {d17[1]}, [r1, :32]!
+; // CHE-CK: vst1.32 {d17[1]}, [r1:32]!
 	%A = load i32** %ptr
 	%tmp1 = load <4 x i32>* %B
 	%tmp2 = extractelement <4 x i32> %tmp1, i32 3
@@ -108,7 +108,7 @@ define void @vst1laneQf(float* %A, <4 x float>* %B) nounwind {
 define void @vst2lanei8(i8* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vst2lanei8:
 ;Check the alignment value.  Max for this instruction is 16 bits:
-;CHECK: vst2.8 {d16[1], d17[1]}, [r0, :16]
+;CHECK: vst2.8 {d16[1], d17[1]}, [r0:16]
 	%tmp1 = load <8 x i8>* %B
 	call void @llvm.arm.neon.vst2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 4)
 	ret void
@@ -117,7 +117,7 @@ define void @vst2lanei8(i8* %A, <8 x i8>* %B) nounwind {
 define void @vst2lanei16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst2lanei16:
 ;Check the alignment value.  Max for this instruction is 32 bits:
-;CHECK: vst2.16 {d16[1], d17[1]}, [r0, :32]
+;CHECK: vst2.16 {d16[1], d17[1]}, [r0:32]
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
 	call void @llvm.arm.neon.vst2lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 8)
@@ -168,7 +168,7 @@ define void @vst2laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 define void @vst2laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst2laneQi32:
 ;Check the alignment value.  Max for this instruction is 64 bits:
-;CHECK: vst2.32 {d17[0], d19[0]}, [r0, :64]
+;CHECK: vst2.32 {d17[0], d19[0]}, [r0:64]
 	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
 	call void @llvm.arm.neon.vst2lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2, i32 16)
@@ -283,7 +283,7 @@ declare void @llvm.arm.neon.vst3lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x f
 define void @vst4lanei8(i8* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vst4lanei8:
 ;Check the alignment value.  Max for this instruction is 32 bits:
-;CHECK: vst4.8 {d16[1], d17[1], d18[1], d19[1]}, [r0, :32]
+;CHECK: vst4.8 {d16[1], d17[1], d18[1], d19[1]}, [r0:32]
 	%tmp1 = load <8 x i8>* %B
 	call void @llvm.arm.neon.vst4lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 8)
 	ret void
@@ -292,7 +292,7 @@ define void @vst4lanei8(i8* %A, <8 x i8>* %B) nounwind {
 ;Check for a post-increment updating store.
 define void @vst4lanei8_update(i8** %ptr, <8 x i8>* %B) nounwind {
 ;CHECK: vst4lanei8_update:
-;CHECK: vst4.8 {d16[1], d17[1], d18[1], d19[1]}, [r1, :32]!
+;CHECK: vst4.8 {d16[1], d17[1], d18[1], d19[1]}, [r1:32]!
 	%A = load i8** %ptr
 	%tmp1 = load <8 x i8>* %B
 	call void @llvm.arm.neon.vst4lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 8)
@@ -313,7 +313,7 @@ define void @vst4lanei16(i16* %A, <4 x i16>* %B) nounwind {
 define void @vst4lanei32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vst4lanei32:
 ;Check the alignment value.  Max for this instruction is 128 bits:
-;CHECK: vst4.32 {d16[1], d17[1], d18[1], d19[1]}, [r0, :128]
+;CHECK: vst4.32 {d16[1], d17[1], d18[1], d19[1]}, [r0:128]
 	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
 	call void @llvm.arm.neon.vst4lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 16)
@@ -332,7 +332,7 @@ define void @vst4lanef(float* %A, <2 x float>* %B) nounwind {
 define void @vst4laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vst4laneQi16:
 ;Check the alignment value.  Max for this instruction is 64 bits:
-;CHECK: vst4.16 {d17[3], d19[3], d21[3], d23[3]}, [r0, :64]
+;CHECK: vst4.16 {d17[3], d19[3], d21[3], d23[3]}, [r0:64]
 	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
 	call void @llvm.arm.neon.vst4lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 7, i32 16)