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
diff --git a/test/CodeGen/ARM/vst3.ll b/test/CodeGen/ARM/vst3.ll
index c1a6ce8..0a47efa 100644
--- a/test/CodeGen/ARM/vst3.ll
+++ b/test/CodeGen/ARM/vst3.ll
@@ -4,7 +4,7 @@
;CHECK: vst3i8:
;CHECK: vst3.8
%tmp1 = load <8 x i8>* %B
- call void @llvm.arm.neon.vst3i.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1)
+ call void @llvm.arm.neon.vst3.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1)
ret void
}
@@ -12,7 +12,7 @@
;CHECK: vst3i16:
;CHECK: vst3.16
%tmp1 = load <4 x i16>* %B
- call void @llvm.arm.neon.vst3i.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1)
+ call void @llvm.arm.neon.vst3.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1)
ret void
}
@@ -20,7 +20,7 @@
;CHECK: vst3i32:
;CHECK: vst3.32
%tmp1 = load <2 x i32>* %B
- call void @llvm.arm.neon.vst3i.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1)
+ call void @llvm.arm.neon.vst3.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1)
ret void
}
@@ -28,11 +28,11 @@
;CHECK: vst3f:
;CHECK: vst3.32
%tmp1 = load <2 x float>* %B
- call void @llvm.arm.neon.vst3f.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1)
+ call void @llvm.arm.neon.vst3.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1)
ret void
}
-declare void @llvm.arm.neon.vst3i.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>) nounwind
-declare void @llvm.arm.neon.vst3i.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>) nounwind
-declare void @llvm.arm.neon.vst3i.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>) nounwind
-declare void @llvm.arm.neon.vst3f.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>) nounwind
+declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>) nounwind
+declare void @llvm.arm.neon.vst3.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>) nounwind
+declare void @llvm.arm.neon.vst3.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>) nounwind
+declare void @llvm.arm.neon.vst3.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>) nounwind