ret <8 x i8> %tmp5
}
-define <4 x i16> @vld2dupi16(i16* %A) nounwind {
+define <4 x i16> @vld2dupi16(i8* %A) nounwind {
;CHECK: vld2dupi16:
;Check that a power-of-two alignment smaller than the total size of the memory
;being loaded is ignored.
;CHECK: vld2.16 {d16[], d17[]}, [r0]
- %tmp0 = tail call %struct.__neon_int4x16x2_t @llvm.arm.neon.vld2lane.v4i16(i16* %A, <4 x i16> undef, <4 x i16> undef, i32 0, i32 2)
+ %tmp0 = tail call %struct.__neon_int4x16x2_t @llvm.arm.neon.vld2lane.v4i16(i8* %A, <4 x i16> undef, <4 x i16> undef, i32 0, i32 2)
%tmp1 = extractvalue %struct.__neon_int4x16x2_t %tmp0, 0
%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> zeroinitializer
%tmp3 = extractvalue %struct.__neon_int4x16x2_t %tmp0, 1
;CHECK: vld2dupi16_update:
;CHECK: vld2.16 {d16[], d17[]}, [r1]!
%A = load i16** %ptr
- %tmp0 = tail call %struct.__neon_int4x16x2_t @llvm.arm.neon.vld2lane.v4i16(i16* %A, <4 x i16> undef, <4 x i16> undef, i32 0, i32 2)
+ %A2 = bitcast i16* %A to i8*
+ %tmp0 = tail call %struct.__neon_int4x16x2_t @llvm.arm.neon.vld2lane.v4i16(i8* %A2, <4 x i16> undef, <4 x i16> undef, i32 0, i32 2)
%tmp1 = extractvalue %struct.__neon_int4x16x2_t %tmp0, 0
%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> zeroinitializer
%tmp3 = extractvalue %struct.__neon_int4x16x2_t %tmp0, 1
ret <4 x i16> %tmp5
}
-define <2 x i32> @vld2dupi32(i32* %A) nounwind {
+define <2 x i32> @vld2dupi32(i8* %A) nounwind {
;CHECK: vld2dupi32:
;Check the alignment value. Max for this instruction is 64 bits:
;CHECK: vld2.32 {d16[], d17[]}, [r0, :64]
- %tmp0 = tail call %struct.__neon_int2x32x2_t @llvm.arm.neon.vld2lane.v2i32(i32* %A, <2 x i32> undef, <2 x i32> undef, i32 0, i32 16)
+ %tmp0 = tail call %struct.__neon_int2x32x2_t @llvm.arm.neon.vld2lane.v2i32(i8* %A, <2 x i32> undef, <2 x i32> undef, i32 0, i32 16)
%tmp1 = extractvalue %struct.__neon_int2x32x2_t %tmp0, 0
%tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> zeroinitializer
%tmp3 = extractvalue %struct.__neon_int2x32x2_t %tmp0, 1
}
declare %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32, i32) nounwind readonly
-declare %struct.__neon_int4x16x2_t @llvm.arm.neon.vld2lane.v4i16(i16*, <4 x i16>, <4 x i16>, i32, i32) nounwind readonly
-declare %struct.__neon_int2x32x2_t @llvm.arm.neon.vld2lane.v2i32(i32*, <2 x i32>, <2 x i32>, i32, i32) nounwind readonly
+declare %struct.__neon_int4x16x2_t @llvm.arm.neon.vld2lane.v4i16(i8*, <4 x i16>, <4 x i16>, i32, i32) nounwind readonly
+declare %struct.__neon_int2x32x2_t @llvm.arm.neon.vld2lane.v2i32(i8*, <2 x i32>, <2 x i32>, i32, i32) nounwind readonly
%struct.__neon_int8x8x3_t = type { <8 x i8>, <8 x i8>, <8 x i8> }
%struct.__neon_int16x4x3_t = type { <4 x i16>, <4 x i16>, <4 x i16> }
ret <8 x i8> %tmp8
}
-define <4 x i16> @vld3dupi16(i16* %A) nounwind {
+define <4 x i16> @vld3dupi16(i8* %A) nounwind {
;CHECK: vld3dupi16:
;Check the (default) alignment value. VLD3 does not support alignment.
;CHECK: vld3.16 {d16[], d17[], d18[]}, [r0]
- %tmp0 = tail call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i16* %A, <4 x i16> undef, <4 x i16> undef, <4 x i16> undef, i32 0, i32 8)
+ %tmp0 = tail call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i8* %A, <4 x i16> undef, <4 x i16> undef, <4 x i16> undef, i32 0, i32 8)
%tmp1 = extractvalue %struct.__neon_int16x4x3_t %tmp0, 0
%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> zeroinitializer
%tmp3 = extractvalue %struct.__neon_int16x4x3_t %tmp0, 1
}
declare %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32, i32) nounwind readonly
-declare %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i16*, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind readonly
+declare %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind readonly
%struct.__neon_int16x4x4_t = type { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> }
%struct.__neon_int32x2x4_t = type { <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32> }
;CHECK: vld4dupi16_update:
;CHECK: vld4.16 {d16[], d17[], d18[], d19[]}, [r1]!
%A = load i16** %ptr
- %tmp0 = tail call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i16* %A, <4 x i16> undef, <4 x i16> undef, <4 x i16> undef, <4 x i16> undef, i32 0, i32 1)
+ %A2 = bitcast i16* %A to i8*
+ %tmp0 = tail call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i8* %A2, <4 x i16> undef, <4 x i16> undef, <4 x i16> undef, <4 x i16> undef, i32 0, i32 1)
%tmp1 = extractvalue %struct.__neon_int16x4x4_t %tmp0, 0
%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> zeroinitializer
%tmp3 = extractvalue %struct.__neon_int16x4x4_t %tmp0, 1
ret <4 x i16> %tmp11
}
-define <2 x i32> @vld4dupi32(i32* %A) nounwind {
+define <2 x i32> @vld4dupi32(i8* %A) nounwind {
;CHECK: vld4dupi32:
;Check the alignment value. An 8-byte alignment is allowed here even though
;it is smaller than the total size of the memory being loaded.
;CHECK: vld4.32 {d16[], d17[], d18[], d19[]}, [r0, :64]
- %tmp0 = tail call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i32* %A, <2 x i32> undef, <2 x i32> undef, <2 x i32> undef, <2 x i32> undef, i32 0, i32 8)
+ %tmp0 = tail call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i8* %A, <2 x i32> undef, <2 x i32> undef, <2 x i32> undef, <2 x i32> undef, i32 0, i32 8)
%tmp1 = extractvalue %struct.__neon_int32x2x4_t %tmp0, 0
%tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> zeroinitializer
%tmp3 = extractvalue %struct.__neon_int32x2x4_t %tmp0, 1
ret <2 x i32> %tmp11
}
-declare %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i16*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind readonly
-declare %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i32*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32, i32) nounwind readonly
+declare %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind readonly
+declare %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32, i32) nounwind readonly