Add alignment arguments to all the NEON load/store intrinsics.
Update all the tests using those intrinsics and add support for
auto-upgrading bitcode files with the old versions of the intrinsics.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112271 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/test/CodeGen/ARM/vld2.ll b/test/CodeGen/ARM/vld2.ll
index 0838636..811f6e6 100644
--- a/test/CodeGen/ARM/vld2.ll
+++ b/test/CodeGen/ARM/vld2.ll
@@ -14,7 +14,7 @@
define <8 x i8> @vld2i8(i8* %A) nounwind {
;CHECK: vld2i8:
;CHECK: vld2.8
- %tmp1 = call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2.v8i8(i8* %A)
+ %tmp1 = call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2.v8i8(i8* %A, i32 1)
%tmp2 = extractvalue %struct.__neon_int8x8x2_t %tmp1, 0
%tmp3 = extractvalue %struct.__neon_int8x8x2_t %tmp1, 1
%tmp4 = add <8 x i8> %tmp2, %tmp3
@@ -25,7 +25,7 @@
;CHECK: vld2i16:
;CHECK: vld2.16
%tmp0 = bitcast i16* %A to i8*
- %tmp1 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2.v4i16(i8* %tmp0)
+ %tmp1 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2.v4i16(i8* %tmp0, i32 1)
%tmp2 = extractvalue %struct.__neon_int16x4x2_t %tmp1, 0
%tmp3 = extractvalue %struct.__neon_int16x4x2_t %tmp1, 1
%tmp4 = add <4 x i16> %tmp2, %tmp3
@@ -36,7 +36,7 @@
;CHECK: vld2i32:
;CHECK: vld2.32
%tmp0 = bitcast i32* %A to i8*
- %tmp1 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2.v2i32(i8* %tmp0)
+ %tmp1 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2.v2i32(i8* %tmp0, i32 1)
%tmp2 = extractvalue %struct.__neon_int32x2x2_t %tmp1, 0
%tmp3 = extractvalue %struct.__neon_int32x2x2_t %tmp1, 1
%tmp4 = add <2 x i32> %tmp2, %tmp3
@@ -47,7 +47,7 @@
;CHECK: vld2f:
;CHECK: vld2.32
%tmp0 = bitcast float* %A to i8*
- %tmp1 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2.v2f32(i8* %tmp0)
+ %tmp1 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2.v2f32(i8* %tmp0, i32 1)
%tmp2 = extractvalue %struct.__neon_float32x2x2_t %tmp1, 0
%tmp3 = extractvalue %struct.__neon_float32x2x2_t %tmp1, 1
%tmp4 = fadd <2 x float> %tmp2, %tmp3
@@ -58,7 +58,7 @@
;CHECK: vld2i64:
;CHECK: vld1.64
%tmp0 = bitcast i64* %A to i8*
- %tmp1 = call %struct.__neon_int64x1x2_t @llvm.arm.neon.vld2.v1i64(i8* %tmp0)
+ %tmp1 = call %struct.__neon_int64x1x2_t @llvm.arm.neon.vld2.v1i64(i8* %tmp0, i32 1)
%tmp2 = extractvalue %struct.__neon_int64x1x2_t %tmp1, 0
%tmp3 = extractvalue %struct.__neon_int64x1x2_t %tmp1, 1
%tmp4 = add <1 x i64> %tmp2, %tmp3
@@ -68,7 +68,7 @@
define <16 x i8> @vld2Qi8(i8* %A) nounwind {
;CHECK: vld2Qi8:
;CHECK: vld2.8
- %tmp1 = call %struct.__neon_int8x16x2_t @llvm.arm.neon.vld2.v16i8(i8* %A)
+ %tmp1 = call %struct.__neon_int8x16x2_t @llvm.arm.neon.vld2.v16i8(i8* %A, i32 1)
%tmp2 = extractvalue %struct.__neon_int8x16x2_t %tmp1, 0
%tmp3 = extractvalue %struct.__neon_int8x16x2_t %tmp1, 1
%tmp4 = add <16 x i8> %tmp2, %tmp3
@@ -79,7 +79,7 @@
;CHECK: vld2Qi16:
;CHECK: vld2.16
%tmp0 = bitcast i16* %A to i8*
- %tmp1 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2.v8i16(i8* %tmp0)
+ %tmp1 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2.v8i16(i8* %tmp0, i32 1)
%tmp2 = extractvalue %struct.__neon_int16x8x2_t %tmp1, 0
%tmp3 = extractvalue %struct.__neon_int16x8x2_t %tmp1, 1
%tmp4 = add <8 x i16> %tmp2, %tmp3
@@ -90,7 +90,7 @@
;CHECK: vld2Qi32:
;CHECK: vld2.32
%tmp0 = bitcast i32* %A to i8*
- %tmp1 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8* %tmp0)
+ %tmp1 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8* %tmp0, i32 1)
%tmp2 = extractvalue %struct.__neon_int32x4x2_t %tmp1, 0
%tmp3 = extractvalue %struct.__neon_int32x4x2_t %tmp1, 1
%tmp4 = add <4 x i32> %tmp2, %tmp3
@@ -101,20 +101,20 @@
;CHECK: vld2Qf:
;CHECK: vld2.32
%tmp0 = bitcast float* %A to i8*
- %tmp1 = call %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2.v4f32(i8* %tmp0)
+ %tmp1 = call %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2.v4f32(i8* %tmp0, i32 1)
%tmp2 = extractvalue %struct.__neon_float32x4x2_t %tmp1, 0
%tmp3 = extractvalue %struct.__neon_float32x4x2_t %tmp1, 1
%tmp4 = fadd <4 x float> %tmp2, %tmp3
ret <4 x float> %tmp4
}
-declare %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2.v8i8(i8*) nounwind readonly
-declare %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2.v4i16(i8*) nounwind readonly
-declare %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2.v2i32(i8*) nounwind readonly
-declare %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2.v2f32(i8*) nounwind readonly
-declare %struct.__neon_int64x1x2_t @llvm.arm.neon.vld2.v1i64(i8*) nounwind readonly
+declare %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2.v8i8(i8*, i32) nounwind readonly
+declare %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2.v4i16(i8*, i32) nounwind readonly
+declare %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2.v2i32(i8*, i32) nounwind readonly
+declare %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2.v2f32(i8*, i32) nounwind readonly
+declare %struct.__neon_int64x1x2_t @llvm.arm.neon.vld2.v1i64(i8*, i32) nounwind readonly
-declare %struct.__neon_int8x16x2_t @llvm.arm.neon.vld2.v16i8(i8*) nounwind readonly
-declare %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2.v8i16(i8*) nounwind readonly
-declare %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8*) nounwind readonly
-declare %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2.v4f32(i8*) nounwind readonly
+declare %struct.__neon_int8x16x2_t @llvm.arm.neon.vld2.v16i8(i8*, i32) nounwind readonly
+declare %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2.v8i16(i8*, i32) nounwind readonly
+declare %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8*, i32) nounwind readonly
+declare %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2.v4f32(i8*, i32) nounwind readonly