Fix tests for Neon load/store intrinsics to match the i8* types expected by
the intrinsics. The reason for those i8* types is that the intrinsics are
overloaded on the vector type and we don't have a way to declare an intrinsic
where one argument is an overloaded vector type and another argument is a
pointer to the vector element type. The bitcasts added here will match what
the frontend will typically generate when these intrinsics are used.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@101840 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/test/CodeGen/ARM/vst3.ll b/test/CodeGen/ARM/vst3.ll
index a831a0c..2599bc0 100644
--- a/test/CodeGen/ARM/vst3.ll
+++ b/test/CodeGen/ARM/vst3.ll
@@ -11,32 +11,36 @@
define void @vst3i16(i16* %A, <4 x i16>* %B) nounwind {
;CHECK: vst3i16:
;CHECK: vst3.16
+ %tmp0 = bitcast i16* %A to i8*
%tmp1 = load <4 x i16>* %B
- call void @llvm.arm.neon.vst3.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1)
+ call void @llvm.arm.neon.vst3.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1)
ret void
}
define void @vst3i32(i32* %A, <2 x i32>* %B) nounwind {
;CHECK: vst3i32:
;CHECK: vst3.32
+ %tmp0 = bitcast i32* %A to i8*
%tmp1 = load <2 x i32>* %B
- call void @llvm.arm.neon.vst3.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1)
+ call void @llvm.arm.neon.vst3.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1)
ret void
}
define void @vst3f(float* %A, <2 x float>* %B) nounwind {
;CHECK: vst3f:
;CHECK: vst3.32
+ %tmp0 = bitcast float* %A to i8*
%tmp1 = load <2 x float>* %B
- call void @llvm.arm.neon.vst3.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1)
+ call void @llvm.arm.neon.vst3.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1)
ret void
}
define void @vst3i64(i64* %A, <1 x i64>* %B) nounwind {
;CHECK: vst3i64:
;CHECK: vst1.64
+ %tmp0 = bitcast i64* %A to i8*
%tmp1 = load <1 x i64>* %B
- call void @llvm.arm.neon.vst3.v1i64(i64* %A, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1)
+ call void @llvm.arm.neon.vst3.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1)
ret void
}
@@ -53,8 +57,9 @@
;CHECK: vst3Qi16:
;CHECK: vst3.16
;CHECK: vst3.16
+ %tmp0 = bitcast i16* %A to i8*
%tmp1 = load <8 x i16>* %B
- call void @llvm.arm.neon.vst3.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1)
+ call void @llvm.arm.neon.vst3.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1)
ret void
}
@@ -62,8 +67,9 @@
;CHECK: vst3Qi32:
;CHECK: vst3.32
;CHECK: vst3.32
+ %tmp0 = bitcast i32* %A to i8*
%tmp1 = load <4 x i32>* %B
- call void @llvm.arm.neon.vst3.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1)
+ call void @llvm.arm.neon.vst3.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1)
ret void
}
@@ -71,8 +77,9 @@
;CHECK: vst3Qf:
;CHECK: vst3.32
;CHECK: vst3.32
+ %tmp0 = bitcast float* %A to i8*
%tmp1 = load <4 x float>* %B
- call void @llvm.arm.neon.vst3.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1)
+ call void @llvm.arm.neon.vst3.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1)
ret void
}