; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds double, ptr [[TMP2]], i64 -3
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x double>, ptr [[TMP3]], align 8
; CHECK-NEXT: [[REVERSE:%.*]] = shufflevector <4 x double> [[WIDE_LOAD]], <4 x double> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
-; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds double, ptr [[TMP2]], i64 -4
-; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds double, ptr [[TMP5]], i64 -3
-; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <4 x double>, ptr [[TMP6]], align 8
+; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds double, ptr [[TMP2]], i64 -7
+; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <4 x double>, ptr [[TMP4]], align 8
; CHECK-NEXT: [[REVERSE2:%.*]] = shufflevector <4 x double> [[WIDE_LOAD1]], <4 x double> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
-; CHECK-NEXT: [[TMP8:%.*]] = fcmp une <4 x double> [[REVERSE]], zeroinitializer
-; CHECK-NEXT: [[TMP9:%.*]] = fcmp une <4 x double> [[REVERSE2]], zeroinitializer
-; CHECK-NEXT: [[TMP10:%.*]] = getelementptr double, ptr [[A:%.*]], i64 [[TMP1]]
-; CHECK-NEXT: [[TMP11:%.*]] = getelementptr double, ptr [[TMP10]], i64 -3
-; CHECK-NEXT: [[REVERSE3:%.*]] = shufflevector <4 x i1> [[TMP8]], <4 x i1> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
-; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0(ptr [[TMP11]], i32 8, <4 x i1> [[REVERSE3]], <4 x double> poison)
-; CHECK-NEXT: [[TMP13:%.*]] = getelementptr double, ptr [[TMP10]], i64 -4
-; CHECK-NEXT: [[TMP14:%.*]] = getelementptr double, ptr [[TMP13]], i64 -3
-; CHECK-NEXT: [[REVERSE5:%.*]] = shufflevector <4 x i1> [[TMP9]], <4 x i1> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
-; CHECK-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0(ptr [[TMP14]], i32 8, <4 x i1> [[REVERSE5]], <4 x double> poison)
-; CHECK-NEXT: [[TMP16:%.*]] = fadd <4 x double> [[WIDE_MASKED_LOAD]], <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>
-; CHECK-NEXT: [[TMP17:%.*]] = fadd <4 x double> [[WIDE_MASKED_LOAD6]], <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>
-; CHECK-NEXT: call void @llvm.masked.store.v4f64.p0(<4 x double> [[TMP16]], ptr [[TMP11]], i32 8, <4 x i1> [[REVERSE3]])
-; CHECK-NEXT: call void @llvm.masked.store.v4f64.p0(<4 x double> [[TMP17]], ptr [[TMP14]], i32 8, <4 x i1> [[REVERSE5]])
+; CHECK-NEXT: [[TMP5:%.*]] = fcmp une <4 x double> [[REVERSE]], zeroinitializer
+; CHECK-NEXT: [[TMP6:%.*]] = fcmp une <4 x double> [[REVERSE2]], zeroinitializer
+; CHECK-NEXT: [[TMP7:%.*]] = getelementptr double, ptr [[A:%.*]], i64 [[TMP1]]
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr double, ptr [[TMP7]], i64 -3
+; CHECK-NEXT: [[REVERSE3:%.*]] = shufflevector <4 x i1> [[TMP5]], <4 x i1> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0(ptr [[TMP8]], i32 8, <4 x i1> [[REVERSE3]], <4 x double> poison)
+; CHECK-NEXT: [[TMP9:%.*]] = getelementptr double, ptr [[TMP7]], i64 -7
+; CHECK-NEXT: [[REVERSE5:%.*]] = shufflevector <4 x i1> [[TMP6]], <4 x i1> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+; CHECK-NEXT: [[WIDE_MASKED_LOAD6:%.*]] = call <4 x double> @llvm.masked.load.v4f64.p0(ptr [[TMP9]], i32 8, <4 x i1> [[REVERSE5]], <4 x double> poison)
+; CHECK-NEXT: [[TMP10:%.*]] = fadd <4 x double> [[WIDE_MASKED_LOAD]], <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>
+; CHECK-NEXT: [[TMP11:%.*]] = fadd <4 x double> [[WIDE_MASKED_LOAD6]], <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>
+; CHECK-NEXT: call void @llvm.masked.store.v4f64.p0(<4 x double> [[TMP10]], ptr [[TMP8]], i32 8, <4 x i1> [[REVERSE3]])
+; CHECK-NEXT: call void @llvm.masked.store.v4f64.p0(<4 x double> [[TMP11]], ptr [[TMP9]], i32 8, <4 x i1> [[REVERSE5]])
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
-; CHECK-NEXT: [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_VEC]], [[N]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK-NEXT: [[I_08_IN:%.*]] = phi i64 [ [[I_08:%.*]], [[FOR_INC:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[I_08]] = add nsw i64 [[I_08_IN]], -1
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, ptr [[COND]], i64 [[I_08]]
-; CHECK-NEXT: [[TMP21:%.*]] = load double, ptr [[ARRAYIDX]], align 8
-; CHECK-NEXT: [[TOBOOL:%.*]] = fcmp une double [[TMP21]], 0.000000e+00
+; CHECK-NEXT: [[TMP13:%.*]] = load double, ptr [[ARRAYIDX]], align 8
+; CHECK-NEXT: [[TOBOOL:%.*]] = fcmp une double [[TMP13]], 0.000000e+00
; CHECK-NEXT: br i1 [[TOBOOL]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds double, ptr [[A]], i64 [[I_08]]
-; CHECK-NEXT: [[TMP22:%.*]] = load double, ptr [[ARRAYIDX1]], align 8
-; CHECK-NEXT: [[ADD:%.*]] = fadd double [[TMP22]], 1.000000e+00
+; CHECK-NEXT: [[TMP14:%.*]] = load double, ptr [[ARRAYIDX1]], align 8
+; CHECK-NEXT: [[ADD:%.*]] = fadd double [[TMP14]], 1.000000e+00
; CHECK-NEXT: store double [[ADD]], ptr [[ARRAYIDX1]], align 8
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i64 [[I_08_IN]], 1
-; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP_LOOPEXIT]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP_LOOPEXIT]], !llvm.loop [[LOOP4:![0-9]+]]
;
entry:
; INTER: vector.body:
; INTER-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %vector.body ]
; INTER-NEXT: [[TMP4:%.*]] = getelementptr inbounds i64, ptr %A, i64 [[INDEX]]
-; INTER-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i64 3
-; INTER-NEXT: [[TMP6:%.*]] = getelementptr inbounds i8, ptr [[TMP5]], i64 -3
-; INTER-NEXT: [[WIDE_VEC:%.*]] = load <32 x i8>, ptr [[TMP6]], align 1
+; INTER-NEXT: [[WIDE_VEC:%.*]] = load <32 x i8>, ptr [[TMP4]], align 1
; INTER-NEXT: [[STRIDED_VEC:%.*]] = shufflevector <32 x i8> [[WIDE_VEC]], <32 x i8> poison, <4 x i32> <i32 0, i32 8, i32 16, i32 24>
-; INTER-NEXT: [[STRIDED_VEC5:%.*]] = shufflevector <32 x i8> [[WIDE_VEC]], <32 x i8> poison, <4 x i32> <i32 3, i32 11, i32 19, i32 27>
-; INTER-NEXT: [[TMP6:%.*]] = xor <4 x i8> [[STRIDED_VEC5]], [[STRIDED_VEC]]
-; INTER-NEXT: [[TMP7:%.*]] = getelementptr inbounds i8, ptr %B, i64 [[INDEX]]
-; INTER-NEXT: store <4 x i8> [[TMP6]], ptr [[TMP7]], align 1
+; INTER-NEXT: [[STRIDED_VEC3:%.*]] = shufflevector <32 x i8> [[WIDE_VEC]], <32 x i8> poison, <4 x i32> <i32 3, i32 11, i32 19, i32 27>
+; INTER-NEXT: [[TMP5:%.*]] = xor <4 x i8> [[STRIDED_VEC3]], [[STRIDED_VEC]]
+; INTER-NEXT: [[TMP6:%.*]] = getelementptr inbounds i8, ptr %B, i64 [[INDEX]]
+; INTER-NEXT: store <4 x i8> [[TMP5]], ptr [[TMP6]], align 1
; INTER-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; INTER: br i1 {{.*}}, label %middle.block, label %vector.body
;
; CHECK-NEXT: [[STRIDED_VEC2:%.*]] = shufflevector <12 x i32> [[WIDE_VEC]], <12 x i32> poison, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
; CHECK-NEXT: [[STRIDED_VEC3:%.*]] = shufflevector <12 x i32> [[WIDE_VEC]], <12 x i32> poison, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
; CHECK-NEXT: [[TMP1:%.*]] = add <4 x i32> [[STRIDED_VEC]], [[VEC_IND]]
-; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[NEXT_GEP]], i64 2
-; CHECK-NEXT: [[TMP3:%.*]] = add <4 x i32> [[STRIDED_VEC2]], [[VEC_IND]]
-; CHECK-NEXT: [[TMP4:%.*]] = add <4 x i32> [[STRIDED_VEC3]], [[VEC_IND]]
-; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i32, ptr [[TMP2]], i64 -2
-; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP3]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT: [[INTERLEAVED_VEC:%.*]] = shufflevector <8 x i32> [[TMP6]], <8 x i32> [[TMP7]], <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>
-; CHECK-NEXT: store <12 x i32> [[INTERLEAVED_VEC]], ptr [[TMP5]], align 4
+; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i32> [[STRIDED_VEC2]], [[VEC_IND]]
+; CHECK-NEXT: [[TMP3:%.*]] = add <4 x i32> [[STRIDED_VEC3]], [[VEC_IND]]
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT: [[INTERLEAVED_VEC:%.*]] = shufflevector <8 x i32> [[TMP4]], <8 x i32> [[TMP5]], <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>
+; CHECK-NEXT: store <12 x i32> [[INTERLEAVED_VEC]], ptr [[NEXT_GEP]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], <i32 4, i32 4, i32 4, i32 4>
-; CHECK-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; CHECK-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
+; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
+; CHECK-NEXT: br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph: