Add codegen support for using post-increment NEON load/store instructions.

The vld1-lane, vld1-dup and vst1-lane instructions do not yet support using
post-increment versions, but all the rest of the NEON load/store instructions
should be handled now.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@125014 91177308-0d34-0410-b5e6-96231b3b80d8

11 files changed, 381 insertions, 0 deletions

diff --git a/test/CodeGen/ARM/vld1.ll b/test/CodeGen/ARM/vld1.ll
index 16bd832bb1..c886125a2f 100644
--- a/test/CodeGen/ARM/vld1.ll
+++ b/test/CodeGen/ARM/vld1.ll
@@ -16,6 +16,18 @@ define <4 x i16> @vld1i16(i16* %A) nounwind {
 	ret <4 x i16> %tmp1
 }
 
+;Check for a post-increment updating load. 
+define <4 x i16> @vld1i16_update(i16** %ptr) nounwind {
+;CHECK: vld1i16_update:
+;CHECK: vld1.16 {d16}, [r1]!
+	%A = load i16** %ptr
+	%tmp0 = bitcast i16* %A to i8*
+	%tmp1 = call <4 x i16> @llvm.arm.neon.vld1.v4i16(i8* %tmp0, i32 1)
+	%tmp2 = getelementptr i16* %A, i32 4
+	       store i16* %tmp2, i16** %ptr
+	ret <4 x i16> %tmp1
+}
+
 define <2 x i32> @vld1i32(i32* %A) nounwind {
 ;CHECK: vld1i32:
 ;CHECK: vld1.32
@@ -24,6 +36,18 @@ define <2 x i32> @vld1i32(i32* %A) nounwind {
 	ret <2 x i32> %tmp1
 }
 
+;Check for a post-increment updating load with register increment.
+define <2 x i32> @vld1i32_update(i32** %ptr, i32 %inc) nounwind {
+;CHECK: vld1i32_update:
+;CHECK: vld1.32 {d16}, [r2], r1
+	%A = load i32** %ptr
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = call <2 x i32> @llvm.arm.neon.vld1.v2i32(i8* %tmp0, i32 1)
+	%tmp2 = getelementptr i32* %A, i32 %inc
+	store i32* %tmp2, i32** %ptr
+	ret <2 x i32> %tmp1
+}
+
 define <2 x float> @vld1f(float* %A) nounwind {
 ;CHECK: vld1f:
 ;CHECK: vld1.32
@@ -48,6 +72,17 @@ define <16 x i8> @vld1Qi8(i8* %A) nounwind {
 	ret <16 x i8> %tmp1
 }
 
+;Check for a post-increment updating load.
+define <16 x i8> @vld1Qi8_update(i8** %ptr) nounwind {
+;CHECK: vld1Qi8_update:
+;CHECK: vld1.8 {d16, d17}, [r1, :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
+	store i8* %tmp2, i8** %ptr
+	ret <16 x i8> %tmp1
+}
+
 define <8 x i16> @vld1Qi16(i16* %A) nounwind {
 ;CHECK: vld1Qi16:
 ;Check the alignment value.  Max for this instruction is 128 bits:
diff --git a/test/CodeGen/ARM/vld2.ll b/test/CodeGen/ARM/vld2.ll
index 3fdd7b7aa8..29b379465d 100644
--- a/test/CodeGen/ARM/vld2.ll
+++ b/test/CodeGen/ARM/vld2.ll
@@ -56,6 +56,21 @@ define <2 x float> @vld2f(float* %A) nounwind {
 	ret <2 x float> %tmp4
 }
 
+;Check for a post-increment updating load. 
+define <2 x float> @vld2f_update(float** %ptr) nounwind {
+;CHECK: vld2f_update:
+;CHECK: vld2.32 {d16, d17}, [r1]!
+	%A = load float** %ptr
+	%tmp0 = bitcast float* %A to i8*
+	%tmp1 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2.v2f32(i8* %tmp0, i32 1)
+	%tmp2 = extractvalue %struct.__neon_float32x2x2_t %tmp1, 0
+	%tmp3 = extractvalue %struct.__neon_float32x2x2_t %tmp1, 1
+	%tmp4 = fadd <2 x float> %tmp2, %tmp3
+	%tmp5 = getelementptr float* %A, i32 4
+	store float* %tmp5, float** %ptr
+	ret <2 x float> %tmp4
+}
+
 define <1 x i64> @vld2i64(i64* %A) nounwind {
 ;CHECK: vld2i64:
 ;Check the alignment value.  Max for this instruction is 128 bits:
@@ -79,6 +94,20 @@ define <16 x i8> @vld2Qi8(i8* %A) nounwind {
 	ret <16 x i8> %tmp4
 }
 
+;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
+	%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
+        %tmp3 = extractvalue %struct.__neon_int8x16x2_t %tmp1, 1
+        %tmp4 = add <16 x i8> %tmp2, %tmp3
+	%tmp5 = getelementptr i8* %A, i32 %inc
+	store i8* %tmp5, i8** %ptr
+	ret <16 x i8> %tmp4
+}
+
 define <8 x i16> @vld2Qi16(i16* %A) nounwind {
 ;CHECK: vld2Qi16:
 ;Check the alignment value.  Max for this instruction is 256 bits:
diff --git a/test/CodeGen/ARM/vld3.ll b/test/CodeGen/ARM/vld3.ll
index 0e541bbb5a..dde530f6df 100644
--- a/test/CodeGen/ARM/vld3.ll
+++ b/test/CodeGen/ARM/vld3.ll
@@ -33,6 +33,21 @@ define <4 x i16> @vld3i16(i16* %A) nounwind {
 	ret <4 x i16> %tmp4
 }
 
+;Check for a post-increment updating load with register increment.
+define <4 x i16> @vld3i16_update(i16** %ptr, i32 %inc) nounwind {
+;CHECK: vld3i16_update:
+;CHECK: vld3.16 {d16, d17, d18}, [r2], r1
+	%A = load i16** %ptr
+	%tmp0 = bitcast i16* %A to i8*
+	%tmp1 = call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3.v4i16(i8* %tmp0, i32 1)
+	%tmp2 = extractvalue %struct.__neon_int16x4x3_t %tmp1, 0
+	%tmp3 = extractvalue %struct.__neon_int16x4x3_t %tmp1, 2
+	%tmp4 = add <4 x i16> %tmp2, %tmp3
+	%tmp5 = getelementptr i16* %A, i32 %inc
+	store i16* %tmp5, i16** %ptr
+	ret <4 x i16> %tmp4
+}
+
 define <2 x i32> @vld3i32(i32* %A) nounwind {
 ;CHECK: vld3i32:
 ;CHECK: vld3.32
@@ -103,6 +118,22 @@ define <4 x i32> @vld3Qi32(i32* %A) nounwind {
 	ret <4 x i32> %tmp4
 }
 
+;Check for a post-increment updating load. 
+define <4 x i32> @vld3Qi32_update(i32** %ptr) nounwind {
+;CHECK: vld3Qi32_update:
+;CHECK: vld3.32 {d16, d18, d20}, [r1]!
+;CHECK: vld3.32 {d17, d19, d21}, [r1]!
+	%A = load i32** %ptr
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = call %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3.v4i32(i8* %tmp0, i32 1)
+	%tmp2 = extractvalue %struct.__neon_int32x4x3_t %tmp1, 0
+	%tmp3 = extractvalue %struct.__neon_int32x4x3_t %tmp1, 2
+	%tmp4 = add <4 x i32> %tmp2, %tmp3
+	%tmp5 = getelementptr i32* %A, i32 12
+	store i32* %tmp5, i32** %ptr
+	ret <4 x i32> %tmp4
+}
+
 define <4 x float> @vld3Qf(float* %A) nounwind {
 ;CHECK: vld3Qf:
 ;CHECK: vld3.32
diff --git a/test/CodeGen/ARM/vld4.ll b/test/CodeGen/ARM/vld4.ll
index a616a98a25..59a73db318 100644
--- a/test/CodeGen/ARM/vld4.ll
+++ b/test/CodeGen/ARM/vld4.ll
@@ -22,6 +22,20 @@ define <8 x i8> @vld4i8(i8* %A) nounwind {
 	ret <8 x i8> %tmp4
 }
 
+;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
+	%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
+	%tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 2
+	%tmp4 = add <8 x i8> %tmp2, %tmp3
+	%tmp5 = getelementptr i8* %A, i32 %inc
+	store i8* %tmp5, i8** %ptr
+	ret <8 x i8> %tmp4
+}
+
 define <4 x i16> @vld4i16(i16* %A) nounwind {
 ;CHECK: vld4i16:
 ;Check the alignment value.  Max for this instruction is 256 bits:
@@ -94,6 +108,22 @@ define <8 x i16> @vld4Qi16(i16* %A) nounwind {
 	ret <8 x i16> %tmp4
 }
 
+;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]!
+	%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)
+	%tmp2 = extractvalue %struct.__neon_int16x8x4_t %tmp1, 0
+	%tmp3 = extractvalue %struct.__neon_int16x8x4_t %tmp1, 2
+	%tmp4 = add <8 x i16> %tmp2, %tmp3
+	%tmp5 = getelementptr i16* %A, i32 32
+	store i16* %tmp5, i16** %ptr
+	ret <8 x i16> %tmp4
+}
+
 define <4 x i32> @vld4Qi32(i32* %A) nounwind {
 ;CHECK: vld4Qi32:
 ;CHECK: vld4.32
diff --git a/test/CodeGen/ARM/vlddup.ll b/test/CodeGen/ARM/vlddup.ll
index 033febbb24..d0e9ac3ad3 100644
--- a/test/CodeGen/ARM/vlddup.ll
+++ b/test/CodeGen/ARM/vlddup.ll
@@ -89,6 +89,22 @@ define <4 x i16> @vld2dupi16(i16* %A) nounwind {
         ret <4 x i16> %tmp5
 }
 
+;Check for a post-increment updating load. 
+define <4 x i16> @vld2dupi16_update(i16** %ptr) nounwind {
+;CHECK: vld2dupi16_update:
+;CHECK: vld2.16 {d16[], d17[]}, [r1]!
+	%A = load i16** %ptr
+	%tmp0 = tail call %struct.__neon_int4x16x2_t @llvm.arm.neon.vld2lane.v4i16(i16* %A, <4 x i16> undef, <4 x i16> undef, i32 0, i32 2)
+	%tmp1 = extractvalue %struct.__neon_int4x16x2_t %tmp0, 0
+	%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> zeroinitializer
+	%tmp3 = extractvalue %struct.__neon_int4x16x2_t %tmp0, 1
+	%tmp4 = shufflevector <4 x i16> %tmp3, <4 x i16> undef, <4 x i32> zeroinitializer
+	%tmp5 = add <4 x i16> %tmp2, %tmp4
+	%tmp6 = getelementptr i16* %A, i32 2
+	store i16* %tmp6, i16** %ptr
+	ret <4 x i16> %tmp5
+}
+
 define <2 x i32> @vld2dupi32(i32* %A) nounwind {
 ;CHECK: vld2dupi32:
 ;Check the alignment value.  Max for this instruction is 64 bits:
@@ -106,8 +122,28 @@ declare %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8*, <8 x i8>, <8
 declare %struct.__neon_int4x16x2_t @llvm.arm.neon.vld2lane.v4i16(i16*, <4 x i16>, <4 x i16>, i32, i32) nounwind readonly
 declare %struct.__neon_int2x32x2_t @llvm.arm.neon.vld2lane.v2i32(i32*, <2 x i32>, <2 x i32>, i32, i32) nounwind readonly
 
+%struct.__neon_int8x8x3_t = type { <8 x i8>, <8 x i8>, <8 x i8> }
 %struct.__neon_int16x4x3_t = type { <4 x i16>, <4 x i16>, <4 x i16> }
 
+;Check for a post-increment updating load with register increment.
+define <8 x i8> @vld3dupi8_update(i8** %ptr, i32 %inc) nounwind {
+;CHECK: vld3dupi8_update:
+;CHECK: vld3.8 {d16[], d17[], d18[]}, [r2], r1
+	%A = load i8** %ptr
+	%tmp0 = tail call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3lane.v8i8(i8* %A, <8 x i8> undef, <8 x i8> undef, <8 x i8> undef, i32 0, i32 8)
+	%tmp1 = extractvalue %struct.__neon_int8x8x3_t %tmp0, 0
+	%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> zeroinitializer
+	%tmp3 = extractvalue %struct.__neon_int8x8x3_t %tmp0, 1
+	%tmp4 = shufflevector <8 x i8> %tmp3, <8 x i8> undef, <8 x i32> zeroinitializer
+	%tmp5 = extractvalue %struct.__neon_int8x8x3_t %tmp0, 2
+	%tmp6 = shufflevector <8 x i8> %tmp5, <8 x i8> undef, <8 x i32> zeroinitializer
+	%tmp7 = add <8 x i8> %tmp2, %tmp4
+	%tmp8 = add <8 x i8> %tmp7, %tmp6
+	%tmp9 = getelementptr i8* %A, i32 %inc
+	store i8* %tmp9, i8** %ptr
+	ret <8 x i8> %tmp8
+}
+
 define <4 x i16> @vld3dupi16(i16* %A) nounwind {
 ;CHECK: vld3dupi16:
 ;Check the (default) alignment value. VLD3 does not support alignment.
@@ -124,10 +160,34 @@ define <4 x i16> @vld3dupi16(i16* %A) nounwind {
         ret <4 x i16> %tmp8
 }
 
+declare %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32, i32) nounwind readonly
 declare %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i16*, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind readonly
 
+%struct.__neon_int16x4x4_t = type { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> }
 %struct.__neon_int32x2x4_t = type { <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32> }
 
+;Check for a post-increment updating load.
+define <4 x i16> @vld4dupi16_update(i16** %ptr) nounwind {
+;CHECK: vld4dupi16_update:
+;CHECK: vld4.16 {d16[], d17[], d18[], d19[]}, [r1]!
+	%A = load i16** %ptr
+	%tmp0 = tail call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i16* %A, <4 x i16> undef, <4 x i16> undef, <4 x i16> undef, <4 x i16> undef, i32 0, i32 1)
+	%tmp1 = extractvalue %struct.__neon_int16x4x4_t %tmp0, 0
+	%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> zeroinitializer
+	%tmp3 = extractvalue %struct.__neon_int16x4x4_t %tmp0, 1
+	%tmp4 = shufflevector <4 x i16> %tmp3, <4 x i16> undef, <4 x i32> zeroinitializer
+	%tmp5 = extractvalue %struct.__neon_int16x4x4_t %tmp0, 2
+	%tmp6 = shufflevector <4 x i16> %tmp5, <4 x i16> undef, <4 x i32> zeroinitializer
+	%tmp7 = extractvalue %struct.__neon_int16x4x4_t %tmp0, 3
+	%tmp8 = shufflevector <4 x i16> %tmp7, <4 x i16> undef, <4 x i32> zeroinitializer
+	%tmp9 = add <4 x i16> %tmp2, %tmp4
+	%tmp10 = add <4 x i16> %tmp6, %tmp8
+	%tmp11 = add <4 x i16> %tmp9, %tmp10
+	%tmp12 = getelementptr i16* %A, i32 4
+	store i16* %tmp12, i16** %ptr
+	ret <4 x i16> %tmp11
+}
+
 define <2 x i32> @vld4dupi32(i32* %A) nounwind {
 ;CHECK: vld4dupi32:
 ;Check the alignment value.  An 8-byte alignment is allowed here even though
@@ -148,4 +208,5 @@ define <2 x i32> @vld4dupi32(i32* %A) nounwind {
         ret <2 x i32> %tmp11
 }
 
+declare %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i16*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind readonly
 declare %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i32*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32, i32) nounwind readonly
diff --git a/test/CodeGen/ARM/vldlane.ll b/test/CodeGen/ARM/vldlane.ll
index c5514a63fd..770ed071ac 100644
--- a/test/CodeGen/ARM/vldlane.ll
+++ b/test/CodeGen/ARM/vldlane.ll
@@ -121,6 +121,22 @@ define <2 x i32> @vld2lanei32(i32* %A, <2 x i32>* %B) nounwind {
 	ret <2 x i32> %tmp5
 }
 
+;Check for a post-increment updating load.
+define <2 x i32> @vld2lanei32_update(i32** %ptr, <2 x i32>* %B) nounwind {
+;CHECK: vld2lanei32_update:
+;CHECK: vld2.32 {d16[1], d17[1]}, [r1]!
+	%A = load i32** %ptr
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = load <2 x i32>* %B
+	%tmp2 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1)
+	%tmp3 = extractvalue %struct.__neon_int32x2x2_t %tmp2, 0
+	%tmp4 = extractvalue %struct.__neon_int32x2x2_t %tmp2, 1
+	%tmp5 = add <2 x i32> %tmp3, %tmp4
+	%tmp6 = getelementptr i32* %A, i32 2
+	store i32* %tmp6, i32** %ptr
+	ret <2 x i32> %tmp5
+}
+
 define <2 x float> @vld2lanef(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vld2lanef:
 ;CHECK: vld2.32
@@ -260,6 +276,24 @@ define <8 x i16> @vld3laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 	ret <8 x i16> %tmp7
 }
 
+;Check for a post-increment updating load with register increment.
+define <8 x i16> @vld3laneQi16_update(i16** %ptr, <8 x i16>* %B, i32 %inc) nounwind {
+;CHECK: vld3laneQi16_update:
+;CHECK: vld3.16 {d16[1], d18[1], d20[1]}, [r2], r1
+	%A = load i16** %ptr
+	%tmp0 = bitcast i16* %A to i8*
+	%tmp1 = load <8 x i16>* %B
+	%tmp2 = call %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1, i32 8)
+	%tmp3 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 0
+	%tmp4 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 1
+	%tmp5 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 2
+	%tmp6 = add <8 x i16> %tmp3, %tmp4
+	%tmp7 = add <8 x i16> %tmp5, %tmp6
+	%tmp8 = getelementptr i16* %A, i32 %inc
+	store i16* %tmp8, i16** %ptr
+	ret <8 x i16> %tmp7
+}
+
 define <4 x i32> @vld3laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vld3laneQi32:
 ;CHECK: vld3.32
@@ -322,6 +356,25 @@ define <8 x i8> @vld4lanei8(i8* %A, <8 x i8>* %B) nounwind {
 	ret <8 x i8> %tmp9
 }
 
+;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]}, [r1, :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)
+	%tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 0
+	%tmp4 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 1
+	%tmp5 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 2
+	%tmp6 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 3
+	%tmp7 = add <8 x i8> %tmp3, %tmp4
+	%tmp8 = add <8 x i8> %tmp5, %tmp6
+	%tmp9 = add <8 x i8> %tmp7, %tmp8
+	%tmp10 = getelementptr i8* %A, i32 4
+	store i8* %tmp10, i8** %ptr
+	ret <8 x i8> %tmp9
+}
+
 define <4 x i16> @vld4lanei16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vld4lanei16:
 ;Check that a power-of-two alignment smaller than the total size of the memory
diff --git a/test/CodeGen/ARM/vst1.ll b/test/CodeGen/ARM/vst1.ll
index 70f3a4cfa2..364d44b711 100644
--- a/test/CodeGen/ARM/vst1.ll
+++ b/test/CodeGen/ARM/vst1.ll
@@ -36,6 +36,19 @@ define void @vst1f(float* %A, <2 x float>* %B) nounwind {
 	ret void
 }
 
+;Check for a post-increment updating store.
+define void @vst1f_update(float** %ptr, <2 x float>* %B) nounwind {
+;CHECK: vst1f_update:
+;CHECK: vst1.32 {d16}, [r1]!
+	%A = load float** %ptr
+	%tmp0 = bitcast float* %A to i8*
+	%tmp1 = load <2 x float>* %B
+	call void @llvm.arm.neon.vst1.v2f32(i8* %tmp0, <2 x float> %tmp1, i32 1)
+	%tmp2 = getelementptr float* %A, i32 2
+	store float* %tmp2, float** %ptr
+	ret void
+}
+
 define void @vst1i64(i64* %A, <1 x i64>* %B) nounwind {
 ;CHECK: vst1i64:
 ;CHECK: vst1.64
@@ -64,6 +77,19 @@ define void @vst1Qi16(i16* %A, <8 x i16>* %B) nounwind {
 	ret void
 }
 
+;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
+	%A = load i16** %ptr
+	%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 8)
+	%tmp2 = getelementptr i16* %A, i32 %inc
+	store i16* %tmp2, i16** %ptr
+	ret void
+}
+
 define void @vst1Qi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst1Qi32:
 ;CHECK: vst1.32
diff --git a/test/CodeGen/ARM/vst2.ll b/test/CodeGen/ARM/vst2.ll
index ed2498b276..915a84b677 100644
--- a/test/CodeGen/ARM/vst2.ll
+++ b/test/CodeGen/ARM/vst2.ll
@@ -9,6 +9,18 @@ define void @vst2i8(i8* %A, <8 x i8>* %B) nounwind {
 	ret void
 }
 
+;Check for a post-increment updating store with register increment.
+define void @vst2i8_update(i8** %ptr, <8 x i8>* %B, i32 %inc) nounwind {
+;CHECK: vst2i8_update:
+;CHECK: vst2.8 {d16, d17}, [r1], r2
+	%A = load i8** %ptr
+	%tmp1 = load <8 x i8>* %B
+	call void @llvm.arm.neon.vst2.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 4)
+	%tmp2 = getelementptr i8* %A, i32 %inc
+	store i8* %tmp2, i8** %ptr
+	ret void
+}
+
 define void @vst2i16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst2i16:
 ;Check the alignment value.  Max for this instruction is 128 bits:
@@ -47,6 +59,19 @@ define void @vst2i64(i64* %A, <1 x i64>* %B) nounwind {
 	ret void
 }
 
+;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]!
+	%A = load i64** %ptr
+	%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 8)
+	%tmp2 = getelementptr i64* %A, i32 2
+	store i64* %tmp2, i64** %ptr
+	ret void
+}
+
 define void @vst2Qi8(i8* %A, <16 x i8>* %B) nounwind {
 ;CHECK: vst2Qi8:
 ;Check the alignment value.  Max for this instruction is 256 bits:
diff --git a/test/CodeGen/ARM/vst3.ll b/test/CodeGen/ARM/vst3.ll
index 0a2df77aa0..d262303bc6 100644
--- a/test/CodeGen/ARM/vst3.ll
+++ b/test/CodeGen/ARM/vst3.ll
@@ -28,6 +28,19 @@ define void @vst3i32(i32* %A, <2 x i32>* %B) nounwind {
 	ret void
 }
 
+;Check for a post-increment updating store.
+define void @vst3i32_update(i32** %ptr, <2 x i32>* %B) nounwind {
+;CHECK: vst3i32_update:
+;CHECK: vst3.32 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}]!
+	%A = load i32** %ptr
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = load <2 x i32>* %B
+	call void @llvm.arm.neon.vst3.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
+	%tmp2 = getelementptr i32* %A, i32 6
+	store i32* %tmp2, i32** %ptr
+	ret void
+}
+
 define void @vst3f(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vst3f:
 ;CHECK: vst3.32
@@ -69,6 +82,20 @@ define void @vst3Qi16(i16* %A, <8 x i16>* %B) nounwind {
 	ret void
 }
 
+;Check for a post-increment updating store.
+define void @vst3Qi16_update(i16** %ptr, <8 x i16>* %B) nounwind {
+;CHECK: vst3Qi16_update:
+;CHECK: vst3.16 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}]!
+;CHECK: vst3.16 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}]!
+	%A = load i16** %ptr
+	%tmp0 = bitcast i16* %A to i8*
+	%tmp1 = load <8 x i16>* %B
+	call void @llvm.arm.neon.vst3.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
+	%tmp2 = getelementptr i16* %A, i32 24
+	store i16* %tmp2, i16** %ptr
+	ret void
+}
+
 define void @vst3Qi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst3Qi32:
 ;CHECK: vst3.32
diff --git a/test/CodeGen/ARM/vst4.ll b/test/CodeGen/ARM/vst4.ll
index 6a7e91dee9..e94acb66bf 100644
--- a/test/CodeGen/ARM/vst4.ll
+++ b/test/CodeGen/ARM/vst4.ll
@@ -9,6 +9,18 @@ define void @vst4i8(i8* %A, <8 x i8>* %B) nounwind {
 	ret void
 }
 
+;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
+	%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)
+	%tmp2 = getelementptr i8* %A, i32 %inc
+	store i8* %tmp2, i8** %ptr
+	ret void
+}
+
 define void @vst4i16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst4i16:
 ;Check the alignment value.  Max for this instruction is 256 bits:
@@ -89,6 +101,20 @@ define void @vst4Qf(float* %A, <4 x float>* %B) nounwind {
 	ret void
 }
 
+;Check for a post-increment updating store.
+define void @vst4Qf_update(float** %ptr, <4 x float>* %B) nounwind {
+;CHECK: vst4Qf_update:
+;CHECK: vst4.32 {d16, d18, d20, d22}, [r1]!
+;CHECK: vst4.32 {d17, d19, d21, d23}, [r1]!
+	%A = load float** %ptr
+	%tmp0 = bitcast float* %A to i8*
+	%tmp1 = load <4 x float>* %B
+	call void @llvm.arm.neon.vst4.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
+	%tmp2 = getelementptr float* %A, i32 16
+	store float* %tmp2, float** %ptr
+	ret void
+}
+
 declare void @llvm.arm.neon.vst4.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind
 declare void @llvm.arm.neon.vst4.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind
 declare void @llvm.arm.neon.vst4.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind
diff --git a/test/CodeGen/ARM/vstlane.ll b/test/CodeGen/ARM/vstlane.ll
index 9aa8d59a28..6cc052bbeb 100644
--- a/test/CodeGen/ARM/vstlane.ll
+++ b/test/CodeGen/ARM/vstlane.ll
@@ -94,6 +94,19 @@ define void @vst2lanei16(i16* %A, <4 x i16>* %B) nounwind {
 	ret void
 }
 
+;Check for a post-increment updating store with register increment.
+define void @vst2lanei16_update(i16** %ptr, <4 x i16>* %B, i32 %inc) nounwind {
+;CHECK: vst2lanei16_update:
+;CHECK: vst2.16 {d16[1], d17[1]}, [r1], r2
+	%A = load i16** %ptr
+	%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 2)
+	%tmp2 = getelementptr i16* %A, i32 %inc
+	store i16* %tmp2, i16** %ptr
+	ret void
+}
+
 define void @vst2lanei32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vst2lanei32:
 ;CHECK: vst2.32
@@ -205,6 +218,19 @@ define void @vst3laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 	ret void
 }
 
+;Check for a post-increment updating store.
+define void @vst3laneQi32_update(i32** %ptr, <4 x i32>* %B) nounwind {
+;CHECK: vst3laneQi32_update:
+;CHECK: vst3.32 {d16[0], d18[0], d20[0]}, [r1]!
+	%A = load i32** %ptr
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = load <4 x i32>* %B
+	call void @llvm.arm.neon.vst3lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 0, i32 1)
+	%tmp2 = getelementptr i32* %A, i32 3
+	store i32* %tmp2, i32** %ptr
+	ret void
+}
+
 define void @vst3laneQf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vst3laneQf:
 ;CHECK: vst3.32
@@ -233,6 +259,18 @@ define void @vst4lanei8(i8* %A, <8 x i8>* %B) nounwind {
 	ret void
 }
 
+;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]!
+	%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)
+	%tmp2 = getelementptr i8* %A, i32 4
+	store i8* %tmp2, i8** %ptr
+	ret void
+}
+
 define void @vst4lanei16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst4lanei16:
 ;CHECK: vst4.16