test/Transforms/LoopVectorize/strict-fadd-interleave-only.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 3
; RUN: opt -passes=loop-vectorize -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -force-vector-interleave=2 -force-vector-width=1 -force-ordered-reductions -S %s | FileCheck %s
; RUN: opt -passes=loop-vectorize -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -force-vector-interleave=2 -force-vector-width=1 -force-ordered-reductions -force-tail-folding-style=data -S %s | FileCheck --check-prefix=CHECK-ALM %s

define float @pr70988() {
; CHECK-LABEL: define float @pr70988() {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX1:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT3:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi float [ 0.000000e+00, [[VECTOR_PH]] ], [ [[TMP5:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IV:%.*]] = add i32 [[INDEX1]], 0
; CHECK-NEXT:    [[VEC_IV2:%.*]] = add i32 [[INDEX1]], 1
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ule i32 [[VEC_IV]], 1020
; CHECK-NEXT:    [[TMP1:%.*]] = icmp ule i32 [[VEC_IV2]], 1020
; CHECK-NEXT:    [[TMP2:%.*]] = select contract i1 [[TMP0]], float 1.000000e+00, float -0.000000e+00
; CHECK-NEXT:    [[TMP3:%.*]] = fadd contract float [[VEC_PHI]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = select contract i1 [[TMP1]], float 1.000000e+00, float -0.000000e+00
; CHECK-NEXT:    [[TMP5]] = fadd contract float [[TMP3]], [[TMP4]]
; CHECK-NEXT:    [[INDEX_NEXT3]] = add nuw i32 [[INDEX1]], 2
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT3]], 1022
; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 1022, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi float [ [[TMP5]], [[MIDDLE_BLOCK]] ], [ 0.000000e+00, [[ENTRY]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDEX_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[RDX:%.*]] = phi float [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[RDX_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[RDX_NEXT]] = fadd contract float [[RDX]], 1.000000e+00
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw nsw i32 [[INDEX]], 1
; CHECK-NEXT:    [[COND:%.*]] = icmp ult i32 [[INDEX_NEXT]], 1021
; CHECK-NEXT:    br i1 [[COND]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    [[DOTLCSSA:%.*]] = phi float [ [[RDX_NEXT]], [[LOOP]] ], [ [[TMP5]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret float [[DOTLCSSA]]
;
; CHECK-ALM-LABEL: define float @pr70988() {
; CHECK-ALM-NEXT:  entry:
; CHECK-ALM-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK-ALM:       vector.ph:
; CHECK-ALM-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK-ALM:       vector.body:
; CHECK-ALM-NEXT:    [[INDEX1:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT3:%.*]], [[VECTOR_BODY]] ]
; CHECK-ALM-NEXT:    [[VEC_PHI:%.*]] = phi float [ 0.000000e+00, [[VECTOR_PH]] ], [ [[TMP5:%.*]], [[VECTOR_BODY]] ]
; CHECK-ALM-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX1]], 0
; CHECK-ALM-NEXT:    [[TMP1:%.*]] = add i32 [[INDEX1]], 1
; CHECK-ALM-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = icmp ult i32 [[TMP0]], 1021
; CHECK-ALM-NEXT:    [[ACTIVE_LANE_MASK2:%.*]] = icmp ult i32 [[TMP1]], 1021
; CHECK-ALM-NEXT:    [[TMP2:%.*]] = select contract i1 [[ACTIVE_LANE_MASK]], float 1.000000e+00, float -0.000000e+00
; CHECK-ALM-NEXT:    [[TMP3:%.*]] = fadd contract float [[VEC_PHI]], [[TMP2]]
; CHECK-ALM-NEXT:    [[TMP4:%.*]] = select contract i1 [[ACTIVE_LANE_MASK2]], float 1.000000e+00, float -0.000000e+00
; CHECK-ALM-NEXT:    [[TMP5]] = fadd contract float [[TMP3]], [[TMP4]]
; CHECK-ALM-NEXT:    [[INDEX_NEXT3]] = add nuw i32 [[INDEX1]], 2
; CHECK-ALM-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT3]], 1022
; CHECK-ALM-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK-ALM:       middle.block:
; CHECK-ALM-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK-ALM:       scalar.ph:
; CHECK-ALM-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 1022, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-ALM-NEXT:    [[BC_MERGE_RDX:%.*]] = phi float [ [[TMP5]], [[MIDDLE_BLOCK]] ], [ 0.000000e+00, [[ENTRY]] ]
; CHECK-ALM-NEXT:    br label [[LOOP:%.*]]
; CHECK-ALM:       loop:
; CHECK-ALM-NEXT:    [[INDEX:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDEX_NEXT:%.*]], [[LOOP]] ]
; CHECK-ALM-NEXT:    [[RDX:%.*]] = phi float [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[RDX_NEXT:%.*]], [[LOOP]] ]
; CHECK-ALM-NEXT:    [[RDX_NEXT]] = fadd contract float [[RDX]], 1.000000e+00
; CHECK-ALM-NEXT:    [[INDEX_NEXT]] = add nuw nsw i32 [[INDEX]], 1
; CHECK-ALM-NEXT:    [[COND:%.*]] = icmp ult i32 [[INDEX_NEXT]], 1021
; CHECK-ALM-NEXT:    br i1 [[COND]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK-ALM:       exit:
; CHECK-ALM-NEXT:    [[DOTLCSSA:%.*]] = phi float [ [[RDX_NEXT]], [[LOOP]] ], [ [[TMP5]], [[MIDDLE_BLOCK]] ]
; CHECK-ALM-NEXT:    ret float [[DOTLCSSA]]
;
entry:
  br label %loop

loop:
  %index = phi i32 [ 0, %entry ], [ %index.next, %loop ]
  %rdx = phi float [ 0.000000e+00, %entry ], [ %rdx.next, %loop ]
  %rdx.next = fadd contract float %rdx, 1.000000e+00
  %index.next = add nuw nsw i32 %index, 1
  %cond = icmp ult i32 %index.next, 1021
  br i1 %cond, label %loop, label %exit

exit:
  %.lcssa = phi float [ %rdx.next, %loop ]
  ret float %.lcssa
}

define float @pr72720reduction_using_active_lane_mask(ptr %src) {
; CHECK-LABEL: define float @pr72720reduction_using_active_lane_mask(
; CHECK-SAME: ptr [[SRC:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE3:%.*]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi float [ 0.000000e+00, [[VECTOR_PH]] ], [ [[TMP13:%.*]], [[PRED_LOAD_CONTINUE3]] ]
; CHECK-NEXT:    [[VEC_IV:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[VEC_IV1:%.*]] = add i32 [[INDEX]], 1
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ule i32 [[VEC_IV]], 14
; CHECK-NEXT:    [[TMP1:%.*]] = icmp ule i32 [[VEC_IV1]], 14
; CHECK-NEXT:    br i1 [[TMP0]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr float, ptr [[SRC]], i32 [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = load float, ptr [[TMP3]], align 4
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP5:%.*]] = phi float [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF2:%.*]], label [[PRED_LOAD_CONTINUE3]]
; CHECK:       pred.load.if2:
; CHECK-NEXT:    [[TMP6:%.*]] = add i32 [[INDEX]], 1
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr float, ptr [[SRC]], i32 [[TMP6]]
; CHECK-NEXT:    [[TMP8:%.*]] = load float, ptr [[TMP7]], align 4
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE3]]
; CHECK:       pred.load.continue3:
; CHECK-NEXT:    [[TMP9:%.*]] = phi float [ poison, [[PRED_LOAD_CONTINUE]] ], [ [[TMP8]], [[PRED_LOAD_IF2]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = select contract i1 [[TMP0]], float [[TMP5]], float -0.000000e+00
; CHECK-NEXT:    [[TMP11:%.*]] = fadd contract float [[VEC_PHI]], [[TMP10]]
; CHECK-NEXT:    [[TMP12:%.*]] = select contract i1 [[TMP1]], float [[TMP9]], float -0.000000e+00
; CHECK-NEXT:    [[TMP13]] = fadd contract float [[TMP11]], [[TMP12]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 2
; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i32 [[INDEX_NEXT]], 16
; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 16, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi float [ [[TMP13]], [[MIDDLE_BLOCK]] ], [ 0.000000e+00, [[ENTRY]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NARROW:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[RDX:%.*]] = phi float [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[RDX_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[NARROW]] = add nuw nsw i32 [[IV]], 1
; CHECK-NEXT:    [[GEP:%.*]] = getelementptr float, ptr [[SRC]], i32 [[IV]]
; CHECK-NEXT:    [[L:%.*]] = load float, ptr [[GEP]], align 4
; CHECK-NEXT:    [[RDX_NEXT]] = fadd contract float [[RDX]], [[L]]
; CHECK-NEXT:    [[EC:%.*]] = icmp ult i32 [[NARROW]], 15
; CHECK-NEXT:    br i1 [[EC]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    [[DOTLCSSA:%.*]] = phi float [ [[RDX_NEXT]], [[LOOP]] ], [ [[TMP13]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret float [[DOTLCSSA]]
;
; CHECK-ALM-LABEL: define float @pr72720reduction_using_active_lane_mask(
; CHECK-ALM-SAME: ptr [[SRC:%.*]]) {
; CHECK-ALM-NEXT:  entry:
; CHECK-ALM-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK-ALM:       vector.ph:
; CHECK-ALM-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK-ALM:       vector.body:
; CHECK-ALM-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE3:%.*]] ]
; CHECK-ALM-NEXT:    [[VEC_PHI:%.*]] = phi float [ 0.000000e+00, [[VECTOR_PH]] ], [ [[TMP11:%.*]], [[PRED_LOAD_CONTINUE3]] ]
; CHECK-ALM-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-ALM-NEXT:    [[TMP1:%.*]] = add i32 [[INDEX]], 1
; CHECK-ALM-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = icmp ult i32 [[TMP0]], 15
; CHECK-ALM-NEXT:    [[ACTIVE_LANE_MASK1:%.*]] = icmp ult i32 [[TMP1]], 15
; CHECK-ALM-NEXT:    br i1 [[ACTIVE_LANE_MASK]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK-ALM:       pred.load.if:
; CHECK-ALM-NEXT:    [[TMP2:%.*]] = getelementptr float, ptr [[SRC]], i32 [[TMP0]]
; CHECK-ALM-NEXT:    [[TMP3:%.*]] = load float, ptr [[TMP2]], align 4
; CHECK-ALM-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK-ALM:       pred.load.continue:
; CHECK-ALM-NEXT:    [[TMP4:%.*]] = phi float [ poison, [[VECTOR_BODY]] ], [ [[TMP3]], [[PRED_LOAD_IF]] ]
; CHECK-ALM-NEXT:    br i1 [[ACTIVE_LANE_MASK1]], label [[PRED_LOAD_IF2:%.*]], label [[PRED_LOAD_CONTINUE3]]
; CHECK-ALM:       pred.load.if2:
; CHECK-ALM-NEXT:    [[TMP5:%.*]] = getelementptr float, ptr [[SRC]], i32 [[TMP1]]
; CHECK-ALM-NEXT:    [[TMP6:%.*]] = load float, ptr [[TMP5]], align 4
; CHECK-ALM-NEXT:    br label [[PRED_LOAD_CONTINUE3]]
; CHECK-ALM:       pred.load.continue3:
; CHECK-ALM-NEXT:    [[TMP7:%.*]] = phi float [ poison, [[PRED_LOAD_CONTINUE]] ], [ [[TMP6]], [[PRED_LOAD_IF2]] ]
; CHECK-ALM-NEXT:    [[TMP8:%.*]] = select contract i1 [[ACTIVE_LANE_MASK]], float [[TMP4]], float -0.000000e+00
; CHECK-ALM-NEXT:    [[TMP9:%.*]] = fadd contract float [[VEC_PHI]], [[TMP8]]
; CHECK-ALM-NEXT:    [[TMP10:%.*]] = select contract i1 [[ACTIVE_LANE_MASK1]], float [[TMP7]], float -0.000000e+00
; CHECK-ALM-NEXT:    [[TMP11]] = fadd contract float [[TMP9]], [[TMP10]]
; CHECK-ALM-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 2
; CHECK-ALM-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[INDEX_NEXT]], 16
; CHECK-ALM-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK-ALM:       middle.block:
; CHECK-ALM-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK-ALM:       scalar.ph:
; CHECK-ALM-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 16, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-ALM-NEXT:    [[BC_MERGE_RDX:%.*]] = phi float [ [[TMP11]], [[MIDDLE_BLOCK]] ], [ 0.000000e+00, [[ENTRY]] ]
; CHECK-ALM-NEXT:    br label [[LOOP:%.*]]
; CHECK-ALM:       loop:
; CHECK-ALM-NEXT:    [[IV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NARROW:%.*]], [[LOOP]] ]
; CHECK-ALM-NEXT:    [[RDX:%.*]] = phi float [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[RDX_NEXT:%.*]], [[LOOP]] ]
; CHECK-ALM-NEXT:    [[NARROW]] = add nuw nsw i32 [[IV]], 1
; CHECK-ALM-NEXT:    [[GEP:%.*]] = getelementptr float, ptr [[SRC]], i32 [[IV]]
; CHECK-ALM-NEXT:    [[L:%.*]] = load float, ptr [[GEP]], align 4
; CHECK-ALM-NEXT:    [[RDX_NEXT]] = fadd contract float [[RDX]], [[L]]
; CHECK-ALM-NEXT:    [[EC:%.*]] = icmp ult i32 [[NARROW]], 15
; CHECK-ALM-NEXT:    br i1 [[EC]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK-ALM:       exit:
; CHECK-ALM-NEXT:    [[DOTLCSSA:%.*]] = phi float [ [[RDX_NEXT]], [[LOOP]] ], [ [[TMP11]], [[MIDDLE_BLOCK]] ]
; CHECK-ALM-NEXT:    ret float [[DOTLCSSA]]
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry ], [ %narrow, %loop ]
  %rdx = phi float [ 0.0, %entry ], [ %rdx.next, %loop ]
  %narrow = add nuw nsw i32 %iv, 1
  %gep = getelementptr float, ptr %src, i32 %iv
  %l = load float, ptr %gep, align 4
  %rdx.next = fadd contract float %rdx, %l
  %ec = icmp ult i32 %narrow, 15
  br i1 %ec, label %loop, label %exit

exit:
  %.lcssa = phi float [ %rdx.next, %loop ]
  ret float %.lcssa
}