; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=arm-eabi -mattr=+neon -mcpu=cortex-a8 | FileCheck %s

define <8 x i8> @v_andi8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_andi8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vand d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = and <8 x i8> %tmp1, %tmp2
	ret <8 x i8> %tmp3
}

define <4 x i16> @v_andi16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_andi16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vand d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = and <4 x i16> %tmp1, %tmp2
	ret <4 x i16> %tmp3
}

define <2 x i32> @v_andi32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_andi32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vand d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = and <2 x i32> %tmp1, %tmp2
	ret <2 x i32> %tmp3
}

define <1 x i64> @v_andi64(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_andi64:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vand d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <1 x i64>, ptr %A
	%tmp2 = load <1 x i64>, ptr %B
	%tmp3 = and <1 x i64> %tmp1, %tmp2
	ret <1 x i64> %tmp3
}

define <16 x i8> @v_andQi8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_andQi8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vand q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp2 = load <16 x i8>, ptr %B
	%tmp3 = and <16 x i8> %tmp1, %tmp2
	ret <16 x i8> %tmp3
}

define <8 x i16> @v_andQi16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_andQi16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vand q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = load <8 x i16>, ptr %B
	%tmp3 = and <8 x i16> %tmp1, %tmp2
	ret <8 x i16> %tmp3
}

define <4 x i32> @v_andQi32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_andQi32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vand q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = load <4 x i32>, ptr %B
	%tmp3 = and <4 x i32> %tmp1, %tmp2
	ret <4 x i32> %tmp3
}

define <2 x i64> @v_andQi64(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_andQi64:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vand q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i64>, ptr %A
	%tmp2 = load <2 x i64>, ptr %B
	%tmp3 = and <2 x i64> %tmp1, %tmp2
	ret <2 x i64> %tmp3
}

define <8 x i8> @v_bici8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_bici8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vbic d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = xor <8 x i8> %tmp2, < i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1 >
	%tmp4 = and <8 x i8> %tmp1, %tmp3
	ret <8 x i8> %tmp4
}

define <4 x i16> @v_bici16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_bici16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vbic d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = xor <4 x i16> %tmp2, < i16 -1, i16 -1, i16 -1, i16 -1 >
	%tmp4 = and <4 x i16> %tmp1, %tmp3
	ret <4 x i16> %tmp4
}

define <2 x i32> @v_bici32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_bici32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vbic d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = xor <2 x i32> %tmp2, < i32 -1, i32 -1 >
	%tmp4 = and <2 x i32> %tmp1, %tmp3
	ret <2 x i32> %tmp4
}

define <1 x i64> @v_bici64(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_bici64:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vbic d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <1 x i64>, ptr %A
	%tmp2 = load <1 x i64>, ptr %B
	%tmp3 = xor <1 x i64> %tmp2, < i64 -1 >
	%tmp4 = and <1 x i64> %tmp1, %tmp3
	ret <1 x i64> %tmp4
}

define <16 x i8> @v_bicQi8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_bicQi8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vbic q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp2 = load <16 x i8>, ptr %B
	%tmp3 = xor <16 x i8> %tmp2, < i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1 >
	%tmp4 = and <16 x i8> %tmp1, %tmp3
	ret <16 x i8> %tmp4
}

define <8 x i16> @v_bicQi16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_bicQi16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vbic q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = load <8 x i16>, ptr %B
	%tmp3 = xor <8 x i16> %tmp2, < i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1 >
	%tmp4 = and <8 x i16> %tmp1, %tmp3
	ret <8 x i16> %tmp4
}

define <4 x i32> @v_bicQi32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_bicQi32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vbic q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = load <4 x i32>, ptr %B
	%tmp3 = xor <4 x i32> %tmp2, < i32 -1, i32 -1, i32 -1, i32 -1 >
	%tmp4 = and <4 x i32> %tmp1, %tmp3
	ret <4 x i32> %tmp4
}

define <2 x i64> @v_bicQi64(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_bicQi64:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vbic q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i64>, ptr %A
	%tmp2 = load <2 x i64>, ptr %B
	%tmp3 = xor <2 x i64> %tmp2, < i64 -1, i64 -1 >
	%tmp4 = and <2 x i64> %tmp1, %tmp3
	ret <2 x i64> %tmp4
}

define <8 x i8> @v_eori8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_eori8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    veor d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = xor <8 x i8> %tmp1, %tmp2
	ret <8 x i8> %tmp3
}

define <4 x i16> @v_eori16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_eori16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    veor d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = xor <4 x i16> %tmp1, %tmp2
	ret <4 x i16> %tmp3
}

define <2 x i32> @v_eori32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_eori32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    veor d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = xor <2 x i32> %tmp1, %tmp2
	ret <2 x i32> %tmp3
}

define <1 x i64> @v_eori64(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_eori64:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    veor d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <1 x i64>, ptr %A
	%tmp2 = load <1 x i64>, ptr %B
	%tmp3 = xor <1 x i64> %tmp1, %tmp2
	ret <1 x i64> %tmp3
}

define <16 x i8> @v_eorQi8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_eorQi8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    veor q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp2 = load <16 x i8>, ptr %B
	%tmp3 = xor <16 x i8> %tmp1, %tmp2
	ret <16 x i8> %tmp3
}

define <8 x i16> @v_eorQi16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_eorQi16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    veor q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = load <8 x i16>, ptr %B
	%tmp3 = xor <8 x i16> %tmp1, %tmp2
	ret <8 x i16> %tmp3
}

define <4 x i32> @v_eorQi32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_eorQi32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    veor q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = load <4 x i32>, ptr %B
	%tmp3 = xor <4 x i32> %tmp1, %tmp2
	ret <4 x i32> %tmp3
}

define <2 x i64> @v_eorQi64(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_eorQi64:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    veor q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i64>, ptr %A
	%tmp2 = load <2 x i64>, ptr %B
	%tmp3 = xor <2 x i64> %tmp1, %tmp2
	ret <2 x i64> %tmp3
}

define <8 x i8> @v_mvni8(ptr %A) nounwind {
; CHECK-LABEL: v_mvni8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r0]
; CHECK-NEXT:    vmvn d16, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = xor <8 x i8> %tmp1, < i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1 >
	ret <8 x i8> %tmp2
}

define <4 x i16> @v_mvni16(ptr %A) nounwind {
; CHECK-LABEL: v_mvni16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r0]
; CHECK-NEXT:    vmvn d16, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = xor <4 x i16> %tmp1, < i16 -1, i16 -1, i16 -1, i16 -1 >
	ret <4 x i16> %tmp2
}

define <2 x i32> @v_mvni32(ptr %A) nounwind {
; CHECK-LABEL: v_mvni32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r0]
; CHECK-NEXT:    vmvn d16, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = xor <2 x i32> %tmp1, < i32 -1, i32 -1 >
	ret <2 x i32> %tmp2
}

define <1 x i64> @v_mvni64(ptr %A) nounwind {
; CHECK-LABEL: v_mvni64:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r0]
; CHECK-NEXT:    vmvn d16, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <1 x i64>, ptr %A
	%tmp2 = xor <1 x i64> %tmp1, < i64 -1 >
	ret <1 x i64> %tmp2
}

define <16 x i8> @v_mvnQi8(ptr %A) nounwind {
; CHECK-LABEL: v_mvnQi8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r0]
; CHECK-NEXT:    vmvn q8, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp2 = xor <16 x i8> %tmp1, < i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1 >
	ret <16 x i8> %tmp2
}

define <8 x i16> @v_mvnQi16(ptr %A) nounwind {
; CHECK-LABEL: v_mvnQi16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r0]
; CHECK-NEXT:    vmvn q8, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = xor <8 x i16> %tmp1, < i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1 >
	ret <8 x i16> %tmp2
}

define <4 x i32> @v_mvnQi32(ptr %A) nounwind {
; CHECK-LABEL: v_mvnQi32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r0]
; CHECK-NEXT:    vmvn q8, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = xor <4 x i32> %tmp1, < i32 -1, i32 -1, i32 -1, i32 -1 >
	ret <4 x i32> %tmp2
}

define <2 x i64> @v_mvnQi64(ptr %A) nounwind {
; CHECK-LABEL: v_mvnQi64:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r0]
; CHECK-NEXT:    vmvn q8, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i64>, ptr %A
	%tmp2 = xor <2 x i64> %tmp1, < i64 -1, i64 -1 >
	ret <2 x i64> %tmp2
}

define <8 x i8> @v_orri8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_orri8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vorr d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = or <8 x i8> %tmp1, %tmp2
	ret <8 x i8> %tmp3
}

define <4 x i16> @v_orri16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_orri16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vorr d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = or <4 x i16> %tmp1, %tmp2
	ret <4 x i16> %tmp3
}

define <2 x i32> @v_orri32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_orri32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vorr d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = or <2 x i32> %tmp1, %tmp2
	ret <2 x i32> %tmp3
}

define <1 x i64> @v_orri64(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_orri64:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vorr d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <1 x i64>, ptr %A
	%tmp2 = load <1 x i64>, ptr %B
	%tmp3 = or <1 x i64> %tmp1, %tmp2
	ret <1 x i64> %tmp3
}

define <16 x i8> @v_orrQi8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_orrQi8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vorr q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp2 = load <16 x i8>, ptr %B
	%tmp3 = or <16 x i8> %tmp1, %tmp2
	ret <16 x i8> %tmp3
}

define <8 x i16> @v_orrQi16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_orrQi16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vorr q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = load <8 x i16>, ptr %B
	%tmp3 = or <8 x i16> %tmp1, %tmp2
	ret <8 x i16> %tmp3
}

define <4 x i32> @v_orrQi32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_orrQi32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vorr q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = load <4 x i32>, ptr %B
	%tmp3 = or <4 x i32> %tmp1, %tmp2
	ret <4 x i32> %tmp3
}

define <2 x i64> @v_orrQi64(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_orrQi64:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vorr q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i64>, ptr %A
	%tmp2 = load <2 x i64>, ptr %B
	%tmp3 = or <2 x i64> %tmp1, %tmp2
	ret <2 x i64> %tmp3
}

define <8 x i8> @v_orni8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_orni8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vorn d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = xor <8 x i8> %tmp2, < i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1 >
	%tmp4 = or <8 x i8> %tmp1, %tmp3
	ret <8 x i8> %tmp4
}

define <4 x i16> @v_orni16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_orni16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vorn d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = xor <4 x i16> %tmp2, < i16 -1, i16 -1, i16 -1, i16 -1 >
	%tmp4 = or <4 x i16> %tmp1, %tmp3
	ret <4 x i16> %tmp4
}

define <2 x i32> @v_orni32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_orni32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vorn d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = xor <2 x i32> %tmp2, < i32 -1, i32 -1 >
	%tmp4 = or <2 x i32> %tmp1, %tmp3
	ret <2 x i32> %tmp4
}

define <1 x i64> @v_orni64(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_orni64:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vorn d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <1 x i64>, ptr %A
	%tmp2 = load <1 x i64>, ptr %B
	%tmp3 = xor <1 x i64> %tmp2, < i64 -1 >
	%tmp4 = or <1 x i64> %tmp1, %tmp3
	ret <1 x i64> %tmp4
}

define <16 x i8> @v_ornQi8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_ornQi8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vorn q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp2 = load <16 x i8>, ptr %B
	%tmp3 = xor <16 x i8> %tmp2, < i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1 >
	%tmp4 = or <16 x i8> %tmp1, %tmp3
	ret <16 x i8> %tmp4
}

define <8 x i16> @v_ornQi16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_ornQi16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vorn q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = load <8 x i16>, ptr %B
	%tmp3 = xor <8 x i16> %tmp2, < i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1 >
	%tmp4 = or <8 x i16> %tmp1, %tmp3
	ret <8 x i16> %tmp4
}

define <4 x i32> @v_ornQi32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_ornQi32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vorn q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = load <4 x i32>, ptr %B
	%tmp3 = xor <4 x i32> %tmp2, < i32 -1, i32 -1, i32 -1, i32 -1 >
	%tmp4 = or <4 x i32> %tmp1, %tmp3
	ret <4 x i32> %tmp4
}

define <2 x i64> @v_ornQi64(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: v_ornQi64:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vorn q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i64>, ptr %A
	%tmp2 = load <2 x i64>, ptr %B
	%tmp3 = xor <2 x i64> %tmp2, < i64 -1, i64 -1 >
	%tmp4 = or <2 x i64> %tmp1, %tmp3
	ret <2 x i64> %tmp4
}

define <8 x i8> @vtsti8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vtsti8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vtst.8 d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp2 = load <8 x i8>, ptr %B
	%tmp3 = and <8 x i8> %tmp1, %tmp2
	%tmp4 = icmp ne <8 x i8> %tmp3, zeroinitializer
        %tmp5 = sext <8 x i1> %tmp4 to <8 x i8>
	ret <8 x i8> %tmp5
}

define <4 x i16> @vtsti16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vtsti16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vtst.16 d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i16>, ptr %A
	%tmp2 = load <4 x i16>, ptr %B
	%tmp3 = and <4 x i16> %tmp1, %tmp2
	%tmp4 = icmp ne <4 x i16> %tmp3, zeroinitializer
        %tmp5 = sext <4 x i1> %tmp4 to <4 x i16>
	ret <4 x i16> %tmp5
}

define <2 x i32> @vtsti32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vtsti32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r1]
; CHECK-NEXT:    vldr d17, [r0]
; CHECK-NEXT:    vtst.32 d16, d17, d16
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <2 x i32>, ptr %A
	%tmp2 = load <2 x i32>, ptr %B
	%tmp3 = and <2 x i32> %tmp1, %tmp2
	%tmp4 = icmp ne <2 x i32> %tmp3, zeroinitializer
        %tmp5 = sext <2 x i1> %tmp4 to <2 x i32>
	ret <2 x i32> %tmp5
}

define <16 x i8> @vtstQi8(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vtstQi8:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vtst.8 q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp2 = load <16 x i8>, ptr %B
	%tmp3 = and <16 x i8> %tmp1, %tmp2
	%tmp4 = icmp ne <16 x i8> %tmp3, zeroinitializer
        %tmp5 = sext <16 x i1> %tmp4 to <16 x i8>
	ret <16 x i8> %tmp5
}

define <8 x i16> @vtstQi16(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vtstQi16:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vtst.16 q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i16>, ptr %A
	%tmp2 = load <8 x i16>, ptr %B
	%tmp3 = and <8 x i16> %tmp1, %tmp2
	%tmp4 = icmp ne <8 x i16> %tmp3, zeroinitializer
        %tmp5 = sext <8 x i1> %tmp4 to <8 x i16>
	ret <8 x i16> %tmp5
}

define <4 x i32> @vtstQi32(ptr %A, ptr %B) nounwind {
; CHECK-LABEL: vtstQi32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r1]
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0]
; CHECK-NEXT:    vtst.32 q8, q9, q8
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <4 x i32>, ptr %A
	%tmp2 = load <4 x i32>, ptr %B
	%tmp3 = and <4 x i32> %tmp1, %tmp2
	%tmp4 = icmp ne <4 x i32> %tmp3, zeroinitializer
        %tmp5 = sext <4 x i1> %tmp4 to <4 x i32>
	ret <4 x i32> %tmp5
}

define <8 x i8> @v_orrimm(ptr %A) nounwind {
; CHECK-LABEL: v_orrimm:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r0]
; CHECK-NEXT:    vorr.i32 d16, #0x1000000
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp3 = or <8 x i8> %tmp1, <i8 0, i8 0, i8 0, i8 1, i8 0, i8 0, i8 0, i8 1>
	ret <8 x i8> %tmp3
}

define <16 x i8> @v_orrimmQ(ptr %A) nounwind {
; CHECK-LABEL: v_orrimmQ:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r0]
; CHECK-NEXT:    vorr.i32 q8, #0x1000000
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp3 = or <16 x i8> %tmp1, <i8 0, i8 0, i8 0, i8 1, i8 0, i8 0, i8 0, i8 1, i8 0, i8 0, i8 0, i8 1, i8 0, i8 0, i8 0, i8 1>
	ret <16 x i8> %tmp3
}

define <8 x i8> @v_bicimm(ptr %A) nounwind {
; CHECK-LABEL: v_bicimm:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vldr d16, [r0]
; CHECK-NEXT:    vbic.i32 d16, #0xff000000
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    bx lr
	%tmp1 = load <8 x i8>, ptr %A
	%tmp3 = and <8 x i8> %tmp1, < i8 -1, i8 -1, i8 -1, i8 0, i8 -1, i8 -1, i8 -1, i8 0 >
	ret <8 x i8> %tmp3
}

define <16 x i8> @v_bicimmQ(ptr %A) nounwind {
; CHECK-LABEL: v_bicimmQ:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vld1.64 {d16, d17}, [r0]
; CHECK-NEXT:    vbic.i32 q8, #0xff000000
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
	%tmp1 = load <16 x i8>, ptr %A
	%tmp3 = and <16 x i8> %tmp1, < i8 -1, i8 -1, i8 -1, i8 0, i8 -1, i8 -1, i8 -1, i8 0, i8 -1, i8 -1, i8 -1, i8 0, i8 -1, i8 -1, i8 -1, i8 0 >
	ret <16 x i8> %tmp3
}

define <4 x i32> @hidden_not_v4i32(<4 x i32> %x) nounwind {
; CHECK-LABEL: hidden_not_v4i32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    vmov d19, r2, r3
; CHECK-NEXT:    vmov.i32 q8, #0x6
; CHECK-NEXT:    vmov d18, r0, r1
; CHECK-NEXT:    vbic q8, q8, q9
; CHECK-NEXT:    vmov r0, r1, d16
; CHECK-NEXT:    vmov r2, r3, d17
; CHECK-NEXT:    bx lr
  %xor = xor <4 x i32> %x, <i32 15, i32 15, i32 15, i32 15>
  %and = and <4 x i32> %xor, <i32 6, i32 6, i32 6, i32 6>
  ret <4 x i32> %and
}