diff --git a/llvm/test/Transforms/InferAddressSpaces/AMDGPU/old-pass-regressions-inseltpoison.ll b/llvm/test/Transforms/InferAddressSpaces/AMDGPU/old-pass-regressions-inseltpoison.ll
deleted file mode 100644
index 5a2244b9796e8..0000000000000
--- a/llvm/test/Transforms/InferAddressSpaces/AMDGPU/old-pass-regressions-inseltpoison.ll
+++ /dev/null
@@ -1,138 +0,0 @@
-; RUN: opt -data-layout=A5 -S -mtriple=amdgcn-amd-amdhsa -passes=infer-address-spaces %s | FileCheck %s
-
-; Regression tests from old HSAIL addrspacecast optimization pass
-
-@data = internal addrspace(1) global [100 x double] [double 0.00, double 1.000000e-01, double 2.000000e-01, double 3.000000e-01, double 4.000000e-01, double 5.000000e-01, double 6.000000e-01, double 7.000000e-01, double 8.000000e-01, double 9.000000e-01, double 1.00, double 1.10, double 1.20, double 1.30, double 1.40, double 1.50, double 1.60, double 1.70, double 1.80, double 1.90, double 2.00, double 2.10, double 2.20, double 2.30, double 2.40, double 2.50, double 2.60, double 2.70, double 2.80, double 2.90, double 3.00, double 3.10, double 3.20, double 3.30, double 3.40, double 3.50, double 3.60, double 3.70, double 3.80, double 3.90, double 4.00, double 4.10, double 4.20, double 4.30, double 4.40, double 4.50, double 4.60, double 4.70, double 4.80, double 4.90, double 5.00, double 5.10, double 5.20, double 5.30, double 5.40, double 5.50, double 5.60, double 5.70, double 5.80, double 5.90, double 6.00, double 6.10, double 6.20, double 6.30, double 6.40, double 6.50, double 6.60, double 6.70, double 6.80, double 6.90, double 7.00, double 7.10, double 7.20, double 7.30, double 7.40, double 7.50, double 7.60, double 7.70, double 7.80, double 7.90, double 8.00, double 8.10, double 8.20, double 8.30, double 8.40, double 8.50, double 8.60, double 8.70, double 8.80, double 8.90, double 9.00, double 9.10, double 9.20, double 9.30, double 9.40, double 9.50, double 9.60, double 9.70, double 9.80, double 9.90], align 8
-
-
-; Should generate flat load
-
-; CHECK-LABEL: @generic_address_bitcast_const(
-; CHECK: %vecload1 = load <2 x double>, ptr addrspace(1) getelementptr ([100 x double], ptr addrspace(1) @data, i64 0, i64 4), align 8
-define amdgpu_kernel void @generic_address_bitcast_const(i64 %arg0, ptr addrspace(1) nocapture %results) #0 {
-entry:
-  %tmp1 = call i32 @llvm.amdgcn.workitem.id.x()
-  %tmp2 = zext i32 %tmp1 to i64
-  %tmp3 = add i64 %tmp2, %arg0
-  %vecload1 = load <2 x double>, ptr bitcast (ptr getelementptr ([100 x double], ptr addrspacecast (ptr addrspace(1) @data to ptr), i64 0, i64 4) to ptr), align 8
-  %cmp = fcmp ord <2 x double> %vecload1, zeroinitializer
-  %sext = sext <2 x i1> %cmp to <2 x i64>
-  %tmp4 = extractelement <2 x i64> %sext, i64 0
-  %tmp5 = extractelement <2 x i64> %sext, i64 1
-  %tmp6 = and i64 %tmp4, %tmp5
-  %tmp7 = lshr i64 %tmp6, 63
-  %tmp8 = trunc i64 %tmp7 to i32
-  %idxprom = and i64 %tmp3, 4294967295
-  %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %results, i64 %idxprom
-  store i32 %tmp8, ptr addrspace(1) %arrayidx, align 4
-  ret void
-}
-
-@generic_address_bug9749.val = internal addrspace(1) global float 0.0, align 4
-
-declare i32 @_Z9get_fencePv(ptr)
-%opencl.pipe_t = type opaque
-
-; This is a compile time assert bug, but we still want to check optimization
-; is performed to generate ld_global.
-; CHECK-LABEL: @generic_address_pipe_bug9673(
-; CHECK: %add.ptr = getelementptr inbounds i32, ptr addrspace(3) %in_pipe, i32 2
-; CHECK: %tmp2 = load i32, ptr addrspace(3) %add.ptr, align 4
-define amdgpu_kernel void @generic_address_pipe_bug9673(ptr addrspace(3) nocapture %in_pipe, ptr addrspace(1) nocapture %dst) #0 {
-entry:
-  %tmp = call i32 @llvm.amdgcn.workitem.id.x()
-  %add.ptr = getelementptr inbounds i32, ptr addrspace(3) %in_pipe, i32 2
-  %tmp2 = load i32, ptr addrspace(3) %add.ptr, align 4
-  %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %dst, i32 %tmp
-  store i32 %tmp2, ptr addrspace(1) %arrayidx, align 4
-  ret void
-}
-
-; Should generate flat load
-; CHECK-LABEL: @generic_address_bug9749(
-; CHECK: br i1
-; CHECK: load float, ptr
-; CHECK: br label
-define amdgpu_kernel void @generic_address_bug9749(ptr addrspace(1) nocapture %results) #0 {
-entry:
-  %ptr = alloca ptr, align 8, addrspace(5)
-  %tmp = call i32 @llvm.amdgcn.workitem.id.x()
-  %tmp1 = zext i32 %tmp to i64
-  store float 0x3FB99999A0000000, ptr addrspace(1) @generic_address_bug9749.val, align 4
-  store volatile ptr addrspacecast (ptr addrspace(1) @generic_address_bug9749.val to ptr), ptr addrspace(5) %ptr, align 8
-  %tmp2 = load volatile ptr, ptr addrspace(5) %ptr, align 8
-  %tmp3 = load float, ptr addrspace(1) @generic_address_bug9749.val, align 4
-  %call.i = call i32 @_Z9get_fencePv(ptr %tmp2) #1
-  %switch.i.i = icmp ult i32 %call.i, 4
-  br i1 %switch.i.i, label %if.end.i, label %helperFunction.exit
-
-if.end.i:                                         ; preds = %entry
-  %tmp5 = load float, ptr %tmp2, align 4
-  %not.cmp.i = fcmp oeq float %tmp5, %tmp3
-  %phitmp = zext i1 %not.cmp.i to i32
-  br label %helperFunction.exit
-
-helperFunction.exit:                              ; preds = %if.end.i, %entry
-  %retval.0.i = phi i32 [ 0, %entry ], [ %phitmp, %if.end.i ]
-  %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %results, i64 %tmp1
-  store i32 %retval.0.i, ptr addrspace(1) %arrayidx, align 4
-  ret void
-}
-
-; CHECK-LABEL: @generic_address_opt_phi_bug9776_simple_phi_kernel(
-; CHECK: phi ptr addrspace(3)
-; CHECK: store i32 %i.03, ptr addrspace(3) %
-define amdgpu_kernel void @generic_address_opt_phi_bug9776_simple_phi_kernel(ptr addrspace(3) nocapture %in, i32 %numElems) #0 {
-entry:
-  %cmp1 = icmp eq i32 %numElems, 0
-  br i1 %cmp1, label %for.end, label %for.body.lr.ph
-
-for.body.lr.ph:                                   ; preds = %entry
-  %tmp = addrspacecast ptr addrspace(3) %in to ptr
-  br label %for.body
-
-for.body:                                         ; preds = %for.body, %for.body.lr.ph
-  %i.03 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.body ]
-  %ptr.02 = phi ptr [ %tmp, %for.body.lr.ph ], [ %add.ptr, %for.body ]
-  store i32 %i.03, ptr %ptr.02, align 4
-  %add.ptr = getelementptr inbounds i32, ptr %ptr.02, i64 4
-  %inc = add nuw i32 %i.03, 1
-  %exitcond = icmp eq i32 %inc, %numElems
-  br i1 %exitcond, label %for.end, label %for.body
-
-for.end:                                          ; preds = %for.body, %entry
-  ret void
-}
-
-; CHECK-LABEL: @generic_address_bug9899(
-; CHECK: %vecload = load <2 x i32>, ptr addrspace(3)
-; CHECK: store <2 x i32> %tmp16, ptr addrspace(3)
-define amdgpu_kernel void @generic_address_bug9899(i64 %arg0, ptr addrspace(3) nocapture %sourceA, ptr addrspace(3) nocapture %destValues) #0 {
-entry:
-  %tmp1 = call i32 @llvm.amdgcn.workitem.id.x()
-  %tmp2 = zext i32 %tmp1 to i64
-  %tmp3 = add i64 %tmp2, %arg0
-  %sext = shl i64 %tmp3, 32
-  %tmp4 = addrspacecast ptr addrspace(3) %destValues to ptr
-  %tmp5 = addrspacecast ptr addrspace(3) %sourceA to ptr
-  %tmp6 = ashr exact i64 %sext, 31
-  %tmp7 = getelementptr inbounds i32, ptr %tmp5, i64 %tmp6
-  %vecload = load <2 x i32>, ptr %tmp7, align 4
-  %tmp8 = extractelement <2 x i32> %vecload, i32 0
-  %tmp9 = extractelement <2 x i32> %vecload, i32 1
-  %tmp10 = icmp eq i32 %tmp8, 0
-  %tmp11 = select i1 %tmp10, i32 32, i32 %tmp8
-  %tmp12 = icmp eq i32 %tmp9, 0
-  %tmp13 = select i1 %tmp12, i32 32, i32 %tmp9
-  %tmp14 = getelementptr inbounds i32, ptr %tmp4, i64 %tmp6
-  %tmp15 = insertelement <2 x i32> poison, i32 %tmp11, i32 0
-  %tmp16 = insertelement <2 x i32> %tmp15, i32 %tmp13, i32 1
-  store <2 x i32> %tmp16, ptr %tmp14, align 4
-  ret void
-}
-
-declare i32 @llvm.amdgcn.workitem.id.x() #2
-
-attributes #0 = { nounwind }
-attributes #1 = { nounwind readonly }
-attributes #2 = { nounwind readnone }
diff --git a/llvm/test/Transforms/InterleavedAccess/AArch64/interleaved-accesses-inseltpoison.ll b/llvm/test/Transforms/InterleavedAccess/AArch64/interleaved-accesses-inseltpoison.ll
deleted file mode 100644
index 14986d9eb85c5..0000000000000
--- a/llvm/test/Transforms/InterleavedAccess/AArch64/interleaved-accesses-inseltpoison.ll
+++ /dev/null
@@ -1,755 +0,0 @@
-; RUN: opt < %s -interleaved-access -S | FileCheck %s -check-prefix=NEON
-; RUN: opt < %s -mattr=-neon -interleaved-access -S | FileCheck %s -check-prefix=NO_NEON
-; RUN: opt < %s -passes=interleaved-access -S | FileCheck %s -check-prefix=NEON
-; RUN: opt < %s -mattr=-neon -passes=interleaved-access -S | FileCheck %s -check-prefix=NO_NEON
-
-target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
-target triple = "aarch64--linux-gnu"
-
-define void @load_factor2(ptr %ptr) {
-; NEON-LABEL:    @load_factor2(
-; NEON-NEXT:       [[LDN:%.*]] = call { <8 x i8>, <8 x i8> } @llvm.aarch64.neon.ld2.v8i8.p0(ptr %ptr)
-; NEON-NEXT:       [[TMP2:%.*]] = extractvalue { <8 x i8>, <8 x i8> } [[LDN]], 1
-; NEON-NEXT:       [[TMP3:%.*]] = extractvalue { <8 x i8>, <8 x i8> } [[LDN]], 0
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_factor2(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <16 x i8>, ptr %ptr, align 4
-  %v0 = shufflevector <16 x i8> %interleaved.vec, <16 x i8> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
-  %v1 = shufflevector <16 x i8> %interleaved.vec, <16 x i8> poison, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
-  ret void
-}
-
-define void @load_factor3(ptr %ptr) {
-; NEON-LABEL:    @load_factor3(
-; NEON-NEXT:       [[LDN:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld3.v4i32.p0(ptr %ptr)
-; NEON-NEXT:       [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 2
-; NEON-NEXT:       [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 1
-; NEON-NEXT:       [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 0
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_factor3(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <12 x i32>, ptr %ptr, align 4
-  %v0 = shufflevector <12 x i32> %interleaved.vec, <12 x i32> poison, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
-  %v1 = shufflevector <12 x i32> %interleaved.vec, <12 x i32> poison, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
-  %v2 = shufflevector <12 x i32> %interleaved.vec, <12 x i32> poison, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
-  ret void
-}
-
-define void @load_factor4(ptr %ptr) {
-; NEON-LABEL:    @load_factor4(
-; NEON-NEXT:       [[LDN:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld4.v4i32.p0(ptr %ptr)
-; NEON-NEXT:       [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 3
-; NEON-NEXT:       [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 2
-; NEON-NEXT:       [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 1
-; NEON-NEXT:       [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 0
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_factor4(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <16 x i32>, ptr %ptr, align 4
-  %v0 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
-  %v1 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
-  %v2 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
-  %v3 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
-  ret void
-}
-
-define void @store_factor2(ptr %ptr, <8 x i8> %v0, <8 x i8> %v1) {
-; NEON-LABEL:    @store_factor2(
-; NEON-NEXT:       [[TMP1:%.*]] = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st2.v8i8.p0(<8 x i8> [[TMP1]], <8 x i8> [[TMP2]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_factor2(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <8 x i8> %v0, <8 x i8> %v1, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
-  store <16 x i8> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_factor3(ptr %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2) {
-; NEON-LABEL:    @store_factor3(
-; NEON:            [[TMP1:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st3.v4i32.p0(<4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_factor3(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %s0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-  %s1 = shufflevector <4 x i32> %v2, <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
-  %interleaved.vec = shufflevector <8 x i32> %s0, <8 x i32> %s1, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>
-  store <12 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_factor4(ptr %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2, <4 x i32> %v3) {
-; NEON-LABEL:    @store_factor4(
-; NEON:            [[TMP1:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; NEON-NEXT:       [[TMP4:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st4.v4i32.p0(<4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_factor4(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %s0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-  %s1 = shufflevector <4 x i32> %v2, <4 x i32> %v3, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-  %interleaved.vec = shufflevector <8 x i32> %s0, <8 x i32> %s1, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 1, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>
-  store <16 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @load_ptrvec_factor2(ptr %ptr) {
-; NEON-LABEL:    @load_ptrvec_factor2(
-; NEON-NEXT:       [[LDN:%.*]] = call { <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld2.v2i64.p0(ptr %ptr)
-; NEON-NEXT:       [[TMP2:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[LDN]], 1
-; NEON-NEXT:       [[TMP3:%.*]] = inttoptr <2 x i64> [[TMP2]] to <2 x ptr>
-; NEON-NEXT:       [[TMP4:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[LDN]], 0
-; NEON-NEXT:       [[TMP5:%.*]] = inttoptr <2 x i64> [[TMP4]] to <2 x ptr>
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_ptrvec_factor2(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <4 x ptr>, ptr %ptr, align 4
-  %v0 = shufflevector <4 x ptr> %interleaved.vec, <4 x ptr> poison, <2 x i32> <i32 0, i32 2>
-  %v1 = shufflevector <4 x ptr> %interleaved.vec, <4 x ptr> poison, <2 x i32> <i32 1, i32 3>
-  ret void
-}
-
-define void @load_ptrvec_factor3(ptr %ptr) {
-; NEON-LABEL:    @load_ptrvec_factor3(
-; NEON-NEXT:       [[LDN:%.*]] = call { <2 x i64>, <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld3.v2i64.p0(ptr %ptr)
-; NEON-NEXT:       [[TMP2:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64> } [[LDN]], 2
-; NEON-NEXT:       [[TMP3:%.*]] = inttoptr <2 x i64> [[TMP2]] to <2 x ptr>
-; NEON-NEXT:       [[TMP4:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64> } [[LDN]], 1
-; NEON-NEXT:       [[TMP5:%.*]] = inttoptr <2 x i64> [[TMP4]] to <2 x ptr>
-; NEON-NEXT:       [[TMP6:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64> } [[LDN]], 0
-; NEON-NEXT:       [[TMP7:%.*]] = inttoptr <2 x i64> [[TMP6]] to <2 x ptr>
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_ptrvec_factor3(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <6 x ptr>, ptr %ptr, align 4
-  %v0 = shufflevector <6 x ptr> %interleaved.vec, <6 x ptr> poison, <2 x i32> <i32 0, i32 3>
-  %v1 = shufflevector <6 x ptr> %interleaved.vec, <6 x ptr> poison, <2 x i32> <i32 1, i32 4>
-  %v2 = shufflevector <6 x ptr> %interleaved.vec, <6 x ptr> poison, <2 x i32> <i32 2, i32 5>
-  ret void
-}
-
-define void @load_ptrvec_factor4(ptr %ptr) {
-; NEON-LABEL:    @load_ptrvec_factor4(
-; NEON-NEXT:       [[LDN:%.*]] = call { <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld4.v2i64.p0(ptr %ptr)
-; NEON-NEXT:       [[TMP2:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } [[LDN]], 3
-; NEON-NEXT:       [[TMP3:%.*]] = inttoptr <2 x i64> [[TMP2]] to <2 x ptr>
-; NEON-NEXT:       [[TMP4:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } [[LDN]], 2
-; NEON-NEXT:       [[TMP5:%.*]] = inttoptr <2 x i64> [[TMP4]] to <2 x ptr>
-; NEON-NEXT:       [[TMP6:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } [[LDN]], 1
-; NEON-NEXT:       [[TMP7:%.*]] = inttoptr <2 x i64> [[TMP6]] to <2 x ptr>
-; NEON-NEXT:       [[TMP8:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } [[LDN]], 0
-; NEON-NEXT:       [[TMP9:%.*]] = inttoptr <2 x i64> [[TMP8]] to <2 x ptr>
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_ptrvec_factor4(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <8 x ptr>, ptr %ptr, align 4
-  %v0 = shufflevector <8 x ptr> %interleaved.vec, <8 x ptr> poison, <2 x i32> <i32 0, i32 4>
-  %v1 = shufflevector <8 x ptr> %interleaved.vec, <8 x ptr> poison, <2 x i32> <i32 1, i32 5>
-  %v2 = shufflevector <8 x ptr> %interleaved.vec, <8 x ptr> poison, <2 x i32> <i32 2, i32 6>
-  %v3 = shufflevector <8 x ptr> %interleaved.vec, <8 x ptr> poison, <2 x i32> <i32 3, i32 7>
-  ret void
-}
-
-define void @store_ptrvec_factor2(ptr %ptr, <2 x ptr> %v0, <2 x ptr> %v1) {
-; NEON-LABEL:    @store_ptrvec_factor2(
-; NEON-NEXT:       [[TMP1:%.*]] = ptrtoint <2 x ptr> %v0 to <2 x i64>
-; NEON-NEXT:       [[TMP2:%.*]] = ptrtoint <2 x ptr> %v1 to <2 x i64>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <2 x i64> [[TMP1]], <2 x i64> [[TMP2]], <2 x i32> <i32 0, i32 1>
-; NEON-NEXT:       [[TMP4:%.*]] = shufflevector <2 x i64> [[TMP1]], <2 x i64> [[TMP2]], <2 x i32> <i32 2, i32 3>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st2.v2i64.p0(<2 x i64> [[TMP3]], <2 x i64> [[TMP4]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_ptrvec_factor2(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <2 x ptr> %v0, <2 x ptr> %v1, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
-  store <4 x ptr> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_ptrvec_factor3(ptr %ptr, <2 x ptr> %v0, <2 x ptr> %v1, <2 x ptr> %v2) {
-; NEON-LABEL:    @store_ptrvec_factor3(
-; NEON:            [[TMP1:%.*]] = ptrtoint <4 x ptr> %s0 to <4 x i64>
-; NEON-NEXT:       [[TMP2:%.*]] = ptrtoint <4 x ptr> %s1 to <4 x i64>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> [[TMP2]], <2 x i32> <i32 0, i32 1>
-; NEON-NEXT:       [[TMP4:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> [[TMP2]], <2 x i32> <i32 2, i32 3>
-; NEON-NEXT:       [[TMP5:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> [[TMP2]], <2 x i32> <i32 4, i32 5>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st3.v2i64.p0(<2 x i64> [[TMP3]], <2 x i64> [[TMP4]], <2 x i64> [[TMP5]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_ptrvec_factor3(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %s0 = shufflevector <2 x ptr> %v0, <2 x ptr> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-  %s1 = shufflevector <2 x ptr> %v2, <2 x ptr> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
-  %interleaved.vec = shufflevector <4 x ptr> %s0, <4 x ptr> %s1, <6 x i32> <i32 0, i32 2, i32 4, i32 1, i32 3, i32 5>
-  store <6 x ptr> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_ptrvec_factor4(ptr %ptr, <2 x ptr> %v0, <2 x ptr> %v1, <2 x ptr> %v2, <2 x ptr> %v3) {
-; NEON-LABEL:    @store_ptrvec_factor4(
-; NEON:            [[TMP1:%.*]] = ptrtoint <4 x ptr> %s0 to <4 x i64>
-; NEON-NEXT:       [[TMP2:%.*]] = ptrtoint <4 x ptr> %s1 to <4 x i64>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> [[TMP2]], <2 x i32> <i32 0, i32 1>
-; NEON-NEXT:       [[TMP4:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> [[TMP2]], <2 x i32> <i32 2, i32 3>
-; NEON-NEXT:       [[TMP5:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> [[TMP2]], <2 x i32> <i32 4, i32 5>
-; NEON-NEXT:       [[TMP6:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> [[TMP2]], <2 x i32> <i32 6, i32 7>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st4.v2i64.p0(<2 x i64> [[TMP3]], <2 x i64> [[TMP4]], <2 x i64> [[TMP5]], <2 x i64> [[TMP6]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_ptrvec_factor4(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %s0 = shufflevector <2 x ptr> %v0, <2 x ptr> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-  %s1 = shufflevector <2 x ptr> %v2, <2 x ptr> %v3, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-  %interleaved.vec = shufflevector <4 x ptr> %s0, <4 x ptr> %s1, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>
-  store <8 x ptr> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @load_undef_mask_factor2(ptr %ptr) {
-; NEON-LABEL:    @load_undef_mask_factor2(
-; NEON-NEXT:       [[LDN:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0(ptr %ptr)
-; NEON-NEXT:       [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN]], 1
-; NEON-NEXT:       [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN]], 0
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_undef_mask_factor2(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <8 x i32>, ptr %ptr, align 4
-  %v0 = shufflevector <8 x i32> %interleaved.vec, <8 x i32> poison, <4 x i32> <i32 undef, i32 2, i32 undef, i32 6>
-  %v1 = shufflevector <8 x i32> %interleaved.vec, <8 x i32> poison, <4 x i32> <i32 undef, i32 3, i32 undef, i32 7>
-  ret void
-}
-
-define void @load_undef_mask_factor3(ptr %ptr) {
-; NEON-LABEL:    @load_undef_mask_factor3(
-; NEON-NEXT:       [[LDN:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld3.v4i32.p0(ptr %ptr)
-; NEON-NEXT:       [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 2
-; NEON-NEXT:       [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 1
-; NEON-NEXT:       [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 0
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_undef_mask_factor3(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <12 x i32>, ptr %ptr, align 4
-  %v0 = shufflevector <12 x i32> %interleaved.vec, <12 x i32> poison, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
-  %v1 = shufflevector <12 x i32> %interleaved.vec, <12 x i32> poison, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
-  %v2 = shufflevector <12 x i32> %interleaved.vec, <12 x i32> poison, <4 x i32> <i32 2, i32 undef, i32 undef, i32 undef>
-  ret void
-}
-
-define void @load_undef_mask_factor4(ptr %ptr) {
-; NEON-LABEL:    @load_undef_mask_factor4(
-; NEON-NEXT:       [[LDN:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld4.v4i32.p0(ptr %ptr)
-; NEON-NEXT:       [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 3
-; NEON-NEXT:       [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 2
-; NEON-NEXT:       [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 1
-; NEON-NEXT:       [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 0
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_undef_mask_factor4(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <16 x i32>, ptr %ptr, align 4
-  %v0 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <4 x i32> <i32 0, i32 4, i32 undef, i32 undef>
-  %v1 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <4 x i32> <i32 1, i32 5, i32 undef, i32 undef>
-  %v2 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <4 x i32> <i32 2, i32 6, i32 undef, i32 undef>
-  %v3 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <4 x i32> <i32 3, i32 7, i32 undef, i32 undef>
-  ret void
-}
-
-define void @store_undef_mask_factor2(ptr %ptr, <4 x i32> %v0, <4 x i32> %v1) {
-; NEON-LABEL:    @store_undef_mask_factor2(
-; NEON-NEXT:       [[TMP1:%.*]] = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st2.v4i32.p0(<4 x i32> [[TMP1]], <4 x i32> [[TMP2]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_undef_mask_factor2(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 2, i32 6, i32 3, i32 7>
-  store <8 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_undef_mask_factor3(ptr %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2) {
-; NEON-LABEL:    @store_undef_mask_factor3(
-; NEON:            [[TMP1:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st3.v4i32.p0(<4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_undef_mask_factor3(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %s0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-  %s1 = shufflevector <4 x i32> %v2, <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
-  %interleaved.vec = shufflevector <8 x i32> %s0, <8 x i32> %s1, <12 x i32> <i32 0, i32 4, i32 undef, i32 1, i32 undef, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>
-  store <12 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_undef_mask_factor4(ptr %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2, <4 x i32> %v3) {
-; NEON-LABEL:    @store_undef_mask_factor4(
-; NEON:            [[TMP1:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; NEON-NEXT:       [[TMP4:%.*]] = shufflevector <8 x i32> %s0, <8 x i32> %s1, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st4.v4i32.p0(<4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_undef_mask_factor4(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %s0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-  %s1 = shufflevector <4 x i32> %v2, <4 x i32> %v3, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-  %interleaved.vec = shufflevector <8 x i32> %s0, <8 x i32> %s1, <16 x i32> <i32 0, i32 4, i32 8, i32 undef, i32 undef, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>
-  store <16 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @load_illegal_factor2(ptr %ptr) nounwind {
-; NEON-LABEL:    @load_illegal_factor2(
-; NEON-NOT:        @llvm.aarch64.neon
-; NEON:            ret void
-; NO_NEON-LABEL: @load_illegal_factor2(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <3 x float>, ptr %ptr, align 16
-  %v0 = shufflevector <3 x float> %interleaved.vec, <3 x float> poison, <3 x i32> <i32 0, i32 2, i32 undef>
-  ret void
-}
-
-define void @store_illegal_factor2(ptr %ptr, <3 x float> %v0) nounwind {
-; NEON-LABEL:    @store_illegal_factor2(
-; NEON-NOT:        @llvm.aarch64.neon
-; NEON:            ret void
-; NO_NEON-LABEL: @store_illegal_factor2(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <3 x float> %v0, <3 x float> poison, <3 x i32> <i32 0, i32 2, i32 undef>
-  store <3 x float> %interleaved.vec, ptr %ptr, align 16
-  ret void
-}
-
-define void @store_general_mask_factor4(ptr %ptr, <32 x i32> %v0, <32 x i32> %v1) {
-; NEON-LABEL:    @store_general_mask_factor4(
-; NEON-NEXT:       [[TMP1:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 4, i32 5>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 16, i32 17>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 32, i32 33>
-; NEON-NEXT:       [[TMP4:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 8, i32 9>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st4.v2i32.p0(<2 x i32> [[TMP1]], <2 x i32> [[TMP2]], <2 x i32> [[TMP3]], <2 x i32> [[TMP4]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_general_mask_factor4(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <8 x i32> <i32 4, i32 16, i32 32, i32 8, i32 5, i32 17, i32 33, i32 9>
-  store <8 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_general_mask_factor4_undefbeg(ptr %ptr, <32 x i32> %v0, <32 x i32> %v1) {
-; NEON-LABEL:    @store_general_mask_factor4_undefbeg(
-; NEON-NEXT:       [[TMP1:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 4, i32 5>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 16, i32 17>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 32, i32 33>
-; NEON-NEXT:       [[TMP4:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 8, i32 9>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st4.v2i32.p0(<2 x i32> [[TMP1]], <2 x i32> [[TMP2]], <2 x i32> [[TMP3]], <2 x i32> [[TMP4]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_general_mask_factor4_undefbeg(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <8 x i32> <i32 undef, i32 16, i32 32, i32 8, i32 5, i32 17, i32 33, i32 9>
-  store <8 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_general_mask_factor4_undefend(ptr %ptr, <32 x i32> %v0, <32 x i32> %v1) {
-; NEON-LABEL:    @store_general_mask_factor4_undefend(
-; NEON-NEXT:       [[TMP1:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 4, i32 5>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 16, i32 17>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 32, i32 33>
-; NEON-NEXT:       [[TMP4:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 8, i32 9>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st4.v2i32.p0(<2 x i32> [[TMP1]], <2 x i32> [[TMP2]], <2 x i32> [[TMP3]], <2 x i32> [[TMP4]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_general_mask_factor4_undefend(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <8 x i32> <i32 4, i32 16, i32 32, i32 8, i32 5, i32 17, i32 33, i32 undef>
-  store <8 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_general_mask_factor4_undefmid(ptr %ptr, <32 x i32> %v0, <32 x i32> %v1) {
-; NEON-LABEL:    @store_general_mask_factor4_undefmid(
-; NEON-NEXT:       [[TMP1:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 4, i32 5>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 16, i32 17>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 32, i32 33>
-; NEON-NEXT:       [[TMP4:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 8, i32 9>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st4.v2i32.p0(<2 x i32> [[TMP1]], <2 x i32> [[TMP2]], <2 x i32> [[TMP3]], <2 x i32> [[TMP4]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_general_mask_factor4_undefmid(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <8 x i32> <i32 4, i32 undef, i32 32, i32 8, i32 5, i32 17, i32 undef, i32 9>
-  store <8 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_general_mask_factor4_undefmulti(ptr %ptr, <32 x i32> %v0, <32 x i32> %v1) {
-; NEON-LABEL:    @store_general_mask_factor4_undefmulti(
-; NEON-NEXT:       [[TMP1:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 4, i32 5>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 0, i32 1>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 0, i32 1>
-; NEON-NEXT:       [[TMP4:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <2 x i32> <i32 8, i32 9>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st4.v2i32.p0(<2 x i32> [[TMP1]], <2 x i32> [[TMP2]], <2 x i32> [[TMP3]], <2 x i32> [[TMP4]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_general_mask_factor4_undefmulti(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <8 x i32> <i32 4, i32 undef, i32 undef, i32 8, i32 undef, i32 undef, i32 undef, i32 9>
-  store <8 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_general_mask_factor3(ptr %ptr, <32 x i32> %v0, <32 x i32> %v1) {
-; NEON-LABEL:    @store_general_mask_factor3(
-; NEON-NEXT:       [[TMP1:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <4 x i32> <i32 32, i32 33, i32 34, i32 35>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <4 x i32> <i32 16, i32 17, i32 18, i32 19>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st3.v4i32.p0(<4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_general_mask_factor3(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <12 x i32> <i32 4, i32 32, i32 16, i32 5, i32 33, i32 17, i32 6, i32 34, i32 18, i32 7, i32 35, i32 19>
-  store <12 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_general_mask_factor3_undefmultimid(ptr %ptr, <32 x i32> %v0, <32 x i32> %v1) {
-; NEON-LABEL:    @store_general_mask_factor3_undefmultimid(
-; NEON-NEXT:       [[TMP1:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <4 x i32> <i32 32, i32 33, i32 34, i32 35>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <4 x i32> <i32 16, i32 17, i32 18, i32 19>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st3.v4i32.p0(<4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_general_mask_factor3_undefmultimid(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <12 x i32> <i32 4, i32 32, i32 16, i32 undef, i32 33, i32 17, i32 undef, i32 34, i32 18, i32 7, i32 35, i32 19>
-  store <12 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_general_mask_factor3_undef_fail(ptr %ptr, <32 x i32> %v0, <32 x i32> %v1) {
-; NEON-LABEL:    @store_general_mask_factor3_undef_fail(
-; NEON-NOT:        @llvm.aarch64.neon
-; NEON:            ret void
-; NO_NEON-LABEL: @store_general_mask_factor3_undef_fail(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <12 x i32> <i32 4, i32 32, i32 16, i32 undef, i32 33, i32 17, i32 undef, i32 34, i32 18, i32 8, i32 35, i32 19>
-  store <12 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_general_mask_factor3_undeflane(ptr %ptr, <32 x i32> %v0, <32 x i32> %v1) {
-; NEON-LABEL:    @store_general_mask_factor3_undeflane(
-; NEON-NEXT:       [[TMP1:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <4 x i32> <i32 32, i32 33, i32 34, i32 35>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <32 x i32> %v0, <32 x i32> %v1, <4 x i32> <i32 16, i32 17, i32 18, i32 19>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st3.v4i32.p0(<4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], ptr %ptr)
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_general_mask_factor3_undeflane(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <12 x i32> <i32 undef, i32 32, i32 16, i32 undef, i32 33, i32 17, i32 undef, i32 34, i32 18, i32 undef, i32 35, i32 19>
-  store <12 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_general_mask_factor3_negativestart(ptr %ptr, <32 x i32> %v0, <32 x i32> %v1) {
-; NEON-LABEL:    @store_general_mask_factor3_negativestart(
-; NEON-NOT:        @llvm.aarch64.neon
-; NEON:            ret void
-; NO_NEON-LABEL: @store_general_mask_factor3_negativestart(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <12 x i32> <i32 undef, i32 32, i32 16, i32 undef, i32 33, i32 17, i32 undef, i32 34, i32 18, i32 2, i32 35, i32 19>
-  store <12 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-@g = external global <4 x float>
-
-; The following does not give a valid interleaved store
-; NEON-LABEL: define void @no_interleave
-; NEON-NOT: call void @llvm.aarch64.neon.st2
-; NEON: shufflevector
-; NEON: store
-; NEON: ret void
-; NO_NEON-LABEL: define void @no_interleave
-; NO_NEON: shufflevector
-; NO_NEON: store
-; NO_NEON: ret void
-define void @no_interleave(<4 x float> %a0) {
-  %v0 = shufflevector <4 x float> %a0, <4 x float> %a0, <4 x i32> <i32 0, i32 3, i32 7, i32 undef>
-  store <4 x float> %v0, ptr @g, align 16
-  ret void
-}
-
-define void @load_factor2_wide2(ptr %ptr) {
-; NEON-LABEL:    @load_factor2_wide2(
-; NEON-NEXT:       [[LDN:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0(ptr %ptr)
-; NEON-NEXT:       [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN]], 1
-; NEON-NEXT:       [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN]], 0
-; NEON-NEXT:       [[TMP5:%.*]] = getelementptr i32, ptr %ptr, i32 8
-; NEON-NEXT:       [[LDN1:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0(ptr [[TMP5]])
-; NEON-NEXT:       [[TMP7:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN1]], 1
-; NEON-NEXT:       [[TMP8:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN1]], 0
-; NEON-NEXT:       [[TMP9:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> [[TMP7]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP10:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_factor2_wide2(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <16 x i32>, ptr %ptr, align 4
-  %v0 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
-  %v1 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
-  ret void
-}
-
-define void @load_factor2_wide3(ptr %ptr) {
-; NEON-LABEL:    @load_factor2_wide3(
-; NEON-NEXT:       [[LDN:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0(ptr [[PTR:%.*]])
-; NEON-NEXT:       [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN]], 1
-; NEON-NEXT:       [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN]], 0
-; NEON-NEXT:       [[TMP5:%.*]] = getelementptr i32, ptr [[PTR]], i32 8
-; NEON-NEXT:       [[LDN1:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0(ptr [[TMP5]])
-; NEON-NEXT:       [[TMP7:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN1]], 1
-; NEON-NEXT:       [[TMP8:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN1]], 0
-; NEON-NEXT:       [[TMP9:%.*]] = getelementptr i32, ptr [[TMP5]], i32 8
-; NEON-NEXT:       [[LDN2:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0(ptr [[TMP9]])
-; NEON-NEXT:       [[TMP11:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN2]], 1
-; NEON-NEXT:       [[TMP12:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN2]], 0
-; NEON-NEXT:       [[TMP13:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> [[TMP7]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP14:%.*]] = shufflevector <4 x i32> [[TMP11]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
-; NEON-NEXT:       [[TMP15:%.*]] = shufflevector <8 x i32> [[TMP13]], <8 x i32> [[TMP14]], <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
-; NEON-NEXT:       [[TMP16:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP17:%.*]] = shufflevector <4 x i32> [[TMP12]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
-; NEON-NEXT:       [[TMP18:%.*]] = shufflevector <8 x i32> [[TMP16]], <8 x i32> [[TMP17]], <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_factor2_wide3(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <24 x i32>, ptr %ptr, align 4
-  %v0 = shufflevector <24 x i32> %interleaved.vec, <24 x i32> poison, <12 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22>
-  %v1 = shufflevector <24 x i32> %interleaved.vec, <24 x i32> poison, <12 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23>
-  ret void
-}
-
-define void @load_factor3_wide(ptr %ptr) {
-; NEON-LABEL: @load_factor3_wide(
-; NEON-NEXT:       [[LDN:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld3.v4i32.p0(ptr %ptr)
-; NEON-NEXT:       [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 2
-; NEON-NEXT:       [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 1
-; NEON-NEXT:       [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 0
-; NEON-NEXT:       [[TMP6:%.*]] = getelementptr i32, ptr %ptr, i32 12
-; NEON-NEXT:       [[LDN1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld3.v4i32.p0(ptr [[TMP6]])
-; NEON-NEXT:       [[TMP8:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[LDN1]], 2
-; NEON-NEXT:       [[TMP9:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[LDN1]], 1
-; NEON-NEXT:       [[TMP10:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[LDN1]], 0
-; NEON-NEXT:       [[TMP11:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP12:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP13:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> [[TMP10]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_factor3_wide(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <24 x i32>, ptr %ptr, align 4
-  %v0 = shufflevector <24 x i32> %interleaved.vec, <24 x i32> poison, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
-  %v1 = shufflevector <24 x i32> %interleaved.vec, <24 x i32> poison, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
-  %v2 = shufflevector <24 x i32> %interleaved.vec, <24 x i32> poison, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
-  ret void
-}
-
-define void @load_factor4_wide(ptr %ptr) {
-; NEON-LABEL: @load_factor4_wide(
-; NEON-NEXT:       [[LDN:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld4.v4i32.p0(ptr %ptr)
-; NEON-NEXT:       [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 3
-; NEON-NEXT:       [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 2
-; NEON-NEXT:       [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 1
-; NEON-NEXT:       [[TMP6:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN]], 0
-; NEON-NEXT:       [[TMP7:%.*]] = getelementptr i32, ptr %ptr, i32 16
-; NEON-NEXT:       [[LDN1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld4.v4i32.p0(ptr [[TMP7]])
-; NEON-NEXT:       [[TMP9:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN1]], 3
-; NEON-NEXT:       [[TMP10:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN1]], 2
-; NEON-NEXT:       [[TMP11:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN1]], 1
-; NEON-NEXT:       [[TMP12:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[LDN1]], 0
-; NEON-NEXT:       [[TMP13:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP14:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> [[TMP10]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP15:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> [[TMP11]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP16:%.*]] = shufflevector <4 x i32> [[TMP6]], <4 x i32> [[TMP12]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @load_factor4_wide(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <32 x i32>, ptr %ptr, align 4
-  %v0 = shufflevector <32 x i32> %interleaved.vec, <32 x i32> poison, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
-  %v1 = shufflevector <32 x i32> %interleaved.vec, <32 x i32> poison, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
-  %v2 = shufflevector <32 x i32> %interleaved.vec, <32 x i32> poison, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
-  %v3 = shufflevector <32 x i32> %interleaved.vec, <32 x i32> poison, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
-  ret void
-}
-
-define void @store_factor2_wide(ptr %ptr, <8 x i32> %v0, <8 x i32> %v1) {
-; NEON-LABEL:    @store_factor2_wide(
-; NEON-NEXT:       [[TMP2:%.*]] = shufflevector <8 x i32> %v0, <8 x i32> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <8 x i32> %v0, <8 x i32> %v1, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st2.v4i32.p0(<4 x i32> [[TMP2]], <4 x i32> [[TMP3]], ptr %ptr)
-; NEON-NEXT:       [[TMP5:%.*]] = shufflevector <8 x i32> %v0, <8 x i32> %v1, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP6:%.*]] = shufflevector <8 x i32> %v0, <8 x i32> %v1, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
-; NEON-NEXT:       [[TMP7:%.*]] = getelementptr i32, ptr %ptr, i32 8
-; NEON-NEXT:       call void @llvm.aarch64.neon.st2.v4i32.p0(<4 x i32> [[TMP5]], <4 x i32> [[TMP6]], ptr [[TMP7]])
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_factor2_wide(
-; NO_NEON:         ret void
-;
-  %interleaved.vec = shufflevector <8 x i32> %v0, <8 x i32> %v1, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
-  store <16 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_factor3_wide(ptr %ptr, <8 x i32> %v0, <8 x i32> %v1, <8 x i32> %v2) {
-; NEON-LABEL:    @store_factor3_wide(
-; NEON:       [[TMP2:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; NEON-NEXT:       [[TMP4:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 16, i32 17, i32 18, i32 19>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st3.v4i32.p0(<4 x i32> [[TMP2]], <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], ptr %ptr)
-; NEON-NEXT:       [[TMP6:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP7:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
-; NEON-NEXT:       [[TMP8:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 20, i32 21, i32 22, i32 23>
-; NEON-NEXT:       [[TMP9:%.*]] = getelementptr i32, ptr %ptr, i32 12
-; NEON-NEXT:       call void @llvm.aarch64.neon.st3.v4i32.p0(<4 x i32> [[TMP6]], <4 x i32> [[TMP7]], <4 x i32> [[TMP8]], ptr [[TMP9]])
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_factor3_wide(
-; NO_NEON:         ret void
-;
-  %s0 = shufflevector <8 x i32> %v0, <8 x i32> %v1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-  %s1 = shufflevector <8 x i32> %v2, <8 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-  %interleaved.vec = shufflevector <16 x i32> %s0, <16 x i32> %s1, <24 x i32> <i32 0, i32 8, i32 16, i32 1, i32 9, i32 17, i32 2, i32 10, i32 18, i32 3, i32 11, i32 19, i32 4, i32 12, i32 20, i32 5, i32 13, i32 21, i32 6, i32 14, i32 22, i32 7, i32 15, i32 23>
-  store <24 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @store_factor4_wide(ptr %ptr, <8 x i32> %v0, <8 x i32> %v1, <8 x i32> %v2, <8 x i32> %v3) {
-; NEON-LABEL:    @store_factor4_wide(
-; NEON:       [[TMP2:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; NEON-NEXT:       [[TMP3:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; NEON-NEXT:       [[TMP4:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 16, i32 17, i32 18, i32 19>
-; NEON-NEXT:       [[TMP5:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 24, i32 25, i32 26, i32 27>
-; NEON-NEXT:       call void @llvm.aarch64.neon.st4.v4i32.p0(<4 x i32> [[TMP2]], <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], <4 x i32> [[TMP5]], ptr %ptr)
-; NEON-NEXT:       [[TMP7:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; NEON-NEXT:       [[TMP8:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
-; NEON-NEXT:       [[TMP9:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 20, i32 21, i32 22, i32 23>
-; NEON-NEXT:       [[TMP10:%.*]] = shufflevector <16 x i32> %s0, <16 x i32> %s1, <4 x i32> <i32 28, i32 29, i32 30, i32 31>
-; NEON-NEXT:       [[TMP11:%.*]] = getelementptr i32, ptr %ptr, i32 16
-; NEON-NEXT:       call void @llvm.aarch64.neon.st4.v4i32.p0(<4 x i32> [[TMP7]], <4 x i32> [[TMP8]], <4 x i32> [[TMP9]], <4 x i32> [[TMP10]], ptr [[TMP11]])
-; NEON-NEXT:       ret void
-; NO_NEON-LABEL: @store_factor4_wide(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %s0 = shufflevector <8 x i32> %v0, <8 x i32> %v1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-  %s1 = shufflevector <8 x i32> %v2, <8 x i32> %v3, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-  %interleaved.vec = shufflevector <16 x i32> %s0, <16 x i32> %s1, <32 x i32> <i32 0, i32 8, i32 16, i32 24, i32 1, i32 9, i32 17, i32 25, i32 2, i32 10, i32 18, i32 26, i32 3, i32 11, i32 19, i32 27, i32 4, i32 12, i32 20, i32 28, i32 5, i32 13, i32 21, i32 29, i32 6, i32 14, i32 22, i32 30, i32 7, i32 15, i32 23, i32 31>
-  store <32 x i32> %interleaved.vec, ptr %ptr, align 4
-  ret void
-}
-
-define void @load_factor2_fp128(ptr %ptr) {
-; NEON-LABEL:    @load_factor2_fp128(
-; NEON-NOT:        @llvm.aarch64.neon
-; NEON:            ret void
-; NO_NEON-LABEL: @load_factor2_fp128(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret void
-;
-  %interleaved.vec = load <4 x fp128>, ptr %ptr, align 16
-  %v0 = shufflevector <4 x fp128> %interleaved.vec, <4 x fp128> poison, <2 x i32> <i32 0, i32 2>
-  %v1 = shufflevector <4 x fp128> %interleaved.vec, <4 x fp128> poison, <2 x i32> <i32 1, i32 3>
-  ret void
-}
-
-define <4 x i1> @load_large_vector(ptr %p) {
-; NEON-LABEL:    @load_large_vector(
-; NEON:            [[LDN:%.*]] = call { <2 x i64>, <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld3.v2i64.p0(ptr
-; NEON-NEXT:       [[TMP1:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64> } [[LDN]], 1
-; NEON-NEXT:       [[TMP2:%.*]] = inttoptr <2 x i64> [[TMP1]] to <2 x ptr>
-; NEON-NEXT:       [[TMP3:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64> } [[LDN]], 0
-; NEON-NEXT:       [[TMP4:%.*]] = inttoptr <2 x i64> [[TMP3]] to <2 x ptr>
-; NEON:            [[LDN1:%.*]] = call { <2 x i64>, <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld3.v2i64.p0(ptr
-; NEON-NEXT:       [[TMP5:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64> } [[LDN1]], 1
-; NEON-NEXT:       [[TMP6:%.*]] = inttoptr <2 x i64> [[TMP5]] to <2 x ptr>
-; NEON-NEXT:       [[TMP7:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64> } [[LDN1]], 0
-; NEON-NEXT:       [[TMP8:%.*]] = inttoptr <2 x i64> [[TMP7]] to <2 x ptr>
-; NEON-NEXT:       shufflevector <2 x ptr> [[TMP2]], <2 x ptr> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; NEON-NEXT:       shufflevector <2 x ptr> [[TMP4]], <2 x ptr> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; NO_NEON-LABEL: @load_large_vector(
-; NO_NEON-NOT:     @llvm.aarch64.neon
-; NO_NEON:         ret
-;
-  %l = load <12 x ptr>, ptr %p
-  %s1 = shufflevector <12 x ptr> %l, <12 x ptr> poison, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
-  %s2 = shufflevector <12 x ptr> %l, <12 x ptr> poison, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
-  %ret = icmp ne <4 x ptr> %s1, %s2
-  ret <4 x i1> %ret
-}