The ARM disassembler did not handle the alignment correctly for VLD*DUP* instructions

[oota-llvm.git] / test / CodeGen / ARM / vst1.ll

diff --git a/test/CodeGen/ARM/vst1.ll b/test/CodeGen/ARM/vst1.ll
index 95414c308914192a0b4501eb014c5928e2c670cd..364d44b7116f8a6b2aea9440a65adb814a9e0049 100644 (file)
--- a/test/CodeGen/ARM/vst1.ll
+++ b/test/CodeGen/ARM/vst1.ll
@@ -2,9 +2,10 @@
 
 define void @vst1i8(i8* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vst1i8:
-;CHECK: vst1.8
+;Check the alignment value.  Max for this instruction is 64 bits:
+;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)
+       call void @llvm.arm.neon.vst1.v8i8(i8* %A, <8 x i8> %tmp1, i32 16)
        ret void
 }
 
@@ -13,7 +14,7 @@ define void @vst1i16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst1.16
        %tmp0 = bitcast i16* %A to i8*
        %tmp1 = load <4 x i16>* %B
-       call void @llvm.arm.neon.vst1.v4i16(i8* %tmp0, <4 x i16> %tmp1)
+       call void @llvm.arm.neon.vst1.v4i16(i8* %tmp0, <4 x i16> %tmp1, i32 1)
        ret void
 }
 
@@ -22,7 +23,7 @@ define void @vst1i32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vst1.32
        %tmp0 = bitcast i32* %A to i8*
        %tmp1 = load <2 x i32>* %B
-       call void @llvm.arm.neon.vst1.v2i32(i8* %tmp0, <2 x i32> %tmp1)
+       call void @llvm.arm.neon.vst1.v2i32(i8* %tmp0, <2 x i32> %tmp1, i32 1)
        ret void
 }
 
@@ -31,7 +32,20 @@ define void @vst1f(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vst1.32
        %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)
+       call void @llvm.arm.neon.vst1.v2f32(i8* %tmp0, <2 x float> %tmp1, i32 1)
+       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
 }
 
@@ -40,24 +54,39 @@ define void @vst1i64(i64* %A, <1 x i64>* %B) nounwind {
 ;CHECK: vst1.64
        %tmp0 = bitcast i64* %A to i8*
        %tmp1 = load <1 x i64>* %B
-       call void @llvm.arm.neon.vst1.v1i64(i8* %tmp0, <1 x i64> %tmp1)
+       call void @llvm.arm.neon.vst1.v1i64(i8* %tmp0, <1 x i64> %tmp1, i32 1)
        ret void
 }
 
 define void @vst1Qi8(i8* %A, <16 x i8>* %B) nounwind {
 ;CHECK: vst1Qi8:
-;CHECK: vst1.8
+;Check the alignment value.  Max for this instruction is 128 bits:
+;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)
+       call void @llvm.arm.neon.vst1.v16i8(i8* %A, <16 x i8> %tmp1, i32 8)
        ret void
 }
 
 define void @vst1Qi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vst1Qi16:
-;CHECK: vst1.16
+;Check the alignment value.  Max for this instruction is 128 bits:
+;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)
+       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)
+       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
 }
 
@@ -66,7 +95,7 @@ define void @vst1Qi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst1.32
        %tmp0 = bitcast i32* %A to i8*
        %tmp1 = load <4 x i32>* %B
-       call void @llvm.arm.neon.vst1.v4i32(i8* %tmp0, <4 x i32> %tmp1)
+       call void @llvm.arm.neon.vst1.v4i32(i8* %tmp0, <4 x i32> %tmp1, i32 1)
        ret void
 }
 
@@ -75,7 +104,7 @@ define void @vst1Qf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vst1.32
        %tmp0 = bitcast float* %A to i8*
        %tmp1 = load <4 x float>* %B
-       call void @llvm.arm.neon.vst1.v4f32(i8* %tmp0, <4 x float> %tmp1)
+       call void @llvm.arm.neon.vst1.v4f32(i8* %tmp0, <4 x float> %tmp1, i32 1)
        ret void
 }
 
@@ -84,18 +113,18 @@ define void @vst1Qi64(i64* %A, <2 x i64>* %B) nounwind {
 ;CHECK: vst1.64
        %tmp0 = bitcast i64* %A to i8*
        %tmp1 = load <2 x i64>* %B
-       call void @llvm.arm.neon.vst1.v2i64(i8* %tmp0, <2 x i64> %tmp1)
+       call void @llvm.arm.neon.vst1.v2i64(i8* %tmp0, <2 x i64> %tmp1, i32 1)
        ret void
 }
 
-declare void @llvm.arm.neon.vst1.v8i8(i8*, <8 x i8>) nounwind
-declare void @llvm.arm.neon.vst1.v4i16(i8*, <4 x i16>) nounwind
-declare void @llvm.arm.neon.vst1.v2i32(i8*, <2 x i32>) nounwind
-declare void @llvm.arm.neon.vst1.v2f32(i8*, <2 x float>) nounwind
-declare void @llvm.arm.neon.vst1.v1i64(i8*, <1 x i64>) nounwind
+declare void @llvm.arm.neon.vst1.v8i8(i8*, <8 x i8>, i32) nounwind
+declare void @llvm.arm.neon.vst1.v4i16(i8*, <4 x i16>, i32) nounwind
+declare void @llvm.arm.neon.vst1.v2i32(i8*, <2 x i32>, i32) nounwind
+declare void @llvm.arm.neon.vst1.v2f32(i8*, <2 x float>, i32) nounwind
+declare void @llvm.arm.neon.vst1.v1i64(i8*, <1 x i64>, i32) nounwind
 
-declare void @llvm.arm.neon.vst1.v16i8(i8*, <16 x i8>) nounwind
-declare void @llvm.arm.neon.vst1.v8i16(i8*, <8 x i16>) nounwind
-declare void @llvm.arm.neon.vst1.v4i32(i8*, <4 x i32>) nounwind
-declare void @llvm.arm.neon.vst1.v4f32(i8*, <4 x float>) nounwind
-declare void @llvm.arm.neon.vst1.v2i64(i8*, <2 x i64>) nounwind
+declare void @llvm.arm.neon.vst1.v16i8(i8*, <16 x i8>, i32) nounwind
+declare void @llvm.arm.neon.vst1.v8i16(i8*, <8 x i16>, i32) nounwind
+declare void @llvm.arm.neon.vst1.v4i32(i8*, <4 x i32>, i32) nounwind
+declare void @llvm.arm.neon.vst1.v4f32(i8*, <4 x float>, i32) nounwind
+declare void @llvm.arm.neon.vst1.v2i64(i8*, <2 x i64>, i32) nounwind