diff options
| author | Bob Wilson <bob.wilson@apple.com> | 2009-08-11 05:39:44 +0000 |
|---|---|---|
| committer | Bob Wilson <bob.wilson@apple.com> | 2009-08-11 05:39:44 +0000 |
| commit | b0abb4dc4203b903d8d0b48a952ba0a6312eeeb7 (patch) | |
| tree | da1622ea7dce5183b471d7df05bcc92522bfe737 /test/CodeGen/ARM/vst4.ll | |
| parent | 9b6a53a0cee762ca3e454eadceaa128f000e6474 (diff) | |
| download | llvm-b0abb4dc4203b903d8d0b48a952ba0a6312eeeb7.tar.gz llvm-b0abb4dc4203b903d8d0b48a952ba0a6312eeeb7.tar.bz2 llvm-b0abb4dc4203b903d8d0b48a952ba0a6312eeeb7.tar.xz | |
Use vAny type to get rid of Neon intrinsics that differed only in whether
the overloaded vector types allowed floating-point or integer vector elements.
Most of these operations actually depend on the element type, so bitcasting
was not an option.
If you include the vpadd intrinsics that I updated earlier, this gets rid
of 20 intrinsics.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78646 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/ARM/vst4.ll')
| -rw-r--r-- | test/CodeGen/ARM/vst4.ll | 16 |
1 files changed, 8 insertions, 8 deletions
diff --git a/test/CodeGen/ARM/vst4.ll b/test/CodeGen/ARM/vst4.ll index 1d6f109a72..fa745ebc13 100644 --- a/test/CodeGen/ARM/vst4.ll +++ b/test/CodeGen/ARM/vst4.ll @@ -4,7 +4,7 @@ define void @vst4i8(i8* %A, <8 x i8>* %B) nounwind { ;CHECK: vst4i8: ;CHECK: vst4.8 %tmp1 = load <8 x i8>* %B - call void @llvm.arm.neon.vst4i.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1) + 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) ret void } @@ -12,7 +12,7 @@ define void @vst4i16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vst4i16: ;CHECK: vst4.16 %tmp1 = load <4 x i16>* %B - call void @llvm.arm.neon.vst4i.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1) + call void @llvm.arm.neon.vst4.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1) ret void } @@ -20,7 +20,7 @@ define void @vst4i32(i32* %A, <2 x i32>* %B) nounwind { ;CHECK: vst4i32: ;CHECK: vst4.32 %tmp1 = load <2 x i32>* %B - call void @llvm.arm.neon.vst4i.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1) + call void @llvm.arm.neon.vst4.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1) ret void } @@ -28,11 +28,11 @@ define void @vst4f(float* %A, <2 x float>* %B) nounwind { ;CHECK: vst4f: ;CHECK: vst4.32 %tmp1 = load <2 x float>* %B - call void @llvm.arm.neon.vst4f.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1) + call void @llvm.arm.neon.vst4.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1) ret void } -declare void @llvm.arm.neon.vst4i.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>) nounwind -declare void @llvm.arm.neon.vst4i.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>) nounwind -declare void @llvm.arm.neon.vst4i.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>) nounwind -declare void @llvm.arm.neon.vst4f.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>) nounwind +declare void @llvm.arm.neon.vst4.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>) nounwind +declare void @llvm.arm.neon.vst4.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>) nounwind +declare void @llvm.arm.neon.vst4.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>) nounwind +declare void @llvm.arm.neon.vst4.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>) nounwind |