diff options
Diffstat (limited to 'test/CodeGen/ARM/vstlane.ll')
| -rw-r--r-- | test/CodeGen/ARM/vstlane.ll | 26 |
1 files changed, 13 insertions, 13 deletions
diff --git a/test/CodeGen/ARM/vstlane.ll b/test/CodeGen/ARM/vstlane.ll index 758b355..67f251f 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) |