| Bob Wilson | 8a3198b | 2009-09-01 18:51:56 +0000 | [diff] [blame^] | 1 | ; RUN: llvm-as < %s | llc -march=arm -mattr=+neon | FileCheck %s |
| 2 | |
| 3 | define void @vst2lanei8(i8* %A, <8 x i8>* %B) nounwind { |
| 4 | ;CHECK: vst2lanei8: |
| 5 | ;CHECK: vst2.8 |
| 6 | %tmp1 = load <8 x i8>* %B |
| 7 | call void @llvm.arm.neon.vst2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1) |
| 8 | ret void |
| 9 | } |
| 10 | |
| 11 | define void @vst2lanei16(i16* %A, <4 x i16>* %B) nounwind { |
| 12 | ;CHECK: vst2lanei16: |
| 13 | ;CHECK: vst2.16 |
| 14 | %tmp1 = load <4 x i16>* %B |
| 15 | call void @llvm.arm.neon.vst2lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1) |
| 16 | ret void |
| 17 | } |
| 18 | |
| 19 | define void @vst2lanei32(i32* %A, <2 x i32>* %B) nounwind { |
| 20 | ;CHECK: vst2lanei32: |
| 21 | ;CHECK: vst2.32 |
| 22 | %tmp1 = load <2 x i32>* %B |
| 23 | call void @llvm.arm.neon.vst2lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1) |
| 24 | ret void |
| 25 | } |
| 26 | |
| 27 | define void @vst2lanef(float* %A, <2 x float>* %B) nounwind { |
| 28 | ;CHECK: vst2lanef: |
| 29 | ;CHECK: vst2.32 |
| 30 | %tmp1 = load <2 x float>* %B |
| 31 | call void @llvm.arm.neon.vst2lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) |
| 32 | ret void |
| 33 | } |
| 34 | |
| 35 | declare void @llvm.arm.neon.vst2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32) nounwind |
| 36 | declare void @llvm.arm.neon.vst2lane.v4i16(i8*, <4 x i16>, <4 x i16>, i32) nounwind |
| 37 | declare void @llvm.arm.neon.vst2lane.v2i32(i8*, <2 x i32>, <2 x i32>, i32) nounwind |
| 38 | declare void @llvm.arm.neon.vst2lane.v2f32(i8*, <2 x float>, <2 x float>, i32) nounwind |
| 39 | |
| 40 | define void @vst3lanei8(i8* %A, <8 x i8>* %B) nounwind { |
| 41 | ;CHECK: vst3lanei8: |
| 42 | ;CHECK: vst3.8 |
| 43 | %tmp1 = load <8 x i8>* %B |
| 44 | call void @llvm.arm.neon.vst3lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1) |
| 45 | ret void |
| 46 | } |
| 47 | |
| 48 | define void @vst3lanei16(i16* %A, <4 x i16>* %B) nounwind { |
| 49 | ;CHECK: vst3lanei16: |
| 50 | ;CHECK: vst3.16 |
| 51 | %tmp1 = load <4 x i16>* %B |
| 52 | call void @llvm.arm.neon.vst3lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1) |
| 53 | ret void |
| 54 | } |
| 55 | |
| 56 | define void @vst3lanei32(i32* %A, <2 x i32>* %B) nounwind { |
| 57 | ;CHECK: vst3lanei32: |
| 58 | ;CHECK: vst3.32 |
| 59 | %tmp1 = load <2 x i32>* %B |
| 60 | call void @llvm.arm.neon.vst3lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1) |
| 61 | ret void |
| 62 | } |
| 63 | |
| 64 | define void @vst3lanef(float* %A, <2 x float>* %B) nounwind { |
| 65 | ;CHECK: vst3lanef: |
| 66 | ;CHECK: vst3.32 |
| 67 | %tmp1 = load <2 x float>* %B |
| 68 | call void @llvm.arm.neon.vst3lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) |
| 69 | ret void |
| 70 | } |
| 71 | |
| 72 | declare void @llvm.arm.neon.vst3lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind |
| 73 | declare void @llvm.arm.neon.vst3lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind |
| 74 | declare void @llvm.arm.neon.vst3lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind |
| 75 | declare void @llvm.arm.neon.vst3lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32) nounwind |
| 76 | |
| 77 | |
| 78 | define void @vst4lanei8(i8* %A, <8 x i8>* %B) nounwind { |
| 79 | ;CHECK: vst4lanei8: |
| 80 | ;CHECK: vst4.8 |
| 81 | %tmp1 = load <8 x i8>* %B |
| 82 | 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) |
| 83 | ret void |
| 84 | } |
| 85 | |
| 86 | define void @vst4lanei16(i16* %A, <4 x i16>* %B) nounwind { |
| 87 | ;CHECK: vst4lanei16: |
| 88 | ;CHECK: vst4.16 |
| 89 | %tmp1 = load <4 x i16>* %B |
| 90 | call void @llvm.arm.neon.vst4lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1) |
| 91 | ret void |
| 92 | } |
| 93 | |
| 94 | define void @vst4lanei32(i32* %A, <2 x i32>* %B) nounwind { |
| 95 | ;CHECK: vst4lanei32: |
| 96 | ;CHECK: vst4.32 |
| 97 | %tmp1 = load <2 x i32>* %B |
| 98 | call void @llvm.arm.neon.vst4lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1) |
| 99 | ret void |
| 100 | } |
| 101 | |
| 102 | define void @vst4lanef(float* %A, <2 x float>* %B) nounwind { |
| 103 | ;CHECK: vst4lanef: |
| 104 | ;CHECK: vst4.32 |
| 105 | %tmp1 = load <2 x float>* %B |
| 106 | call void @llvm.arm.neon.vst4lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) |
| 107 | ret void |
| 108 | } |
| 109 | |
| 110 | declare void @llvm.arm.neon.vst4lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind |
| 111 | declare void @llvm.arm.neon.vst4lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind |
| 112 | declare void @llvm.arm.neon.vst4lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind |
| 113 | declare void @llvm.arm.neon.vst4lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32) nounwind |