llvm/test/Transforms/LoopVectorize/RISCV/tail-folding-iv32.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=loop-vectorize \
; RUN: -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue \
; RUN: -mtriple=riscv64 -mattr=+v -S < %s | FileCheck --check-prefix=IF-EVL %s

; RUN: opt -passes=loop-vectorize \
; RUN: -prefer-predicate-over-epilogue=scalar-epilogue \
; RUN: -mtriple=riscv64 -mattr=+v -S < %s | FileCheck --check-prefix=NO-VP %s

define void @iv32(ptr noalias %a, ptr noalias %b, i32 %N) {
; IF-EVL-LABEL: @iv32(
; IF-EVL-NEXT:  entry:
; IF-EVL-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[ENTRY:%.*]]
; IF-EVL:       vector.ph:
; IF-EVL-NEXT:    br label [[FOR_BODY:%.*]]
; IF-EVL:       vector.body:
; IF-EVL-NEXT:    [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[INDEX_EVL_NEXT:%.*]], [[FOR_BODY]] ]
; IF-EVL-NEXT:    [[TMP11:%.*]] = phi i32 [ [[N:%.*]], [[ENTRY]] ], [ [[AVL_NEXT:%.*]], [[FOR_BODY]] ]
; IF-EVL-NEXT:    [[TMP12:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[TMP11]], i32 4, i1 true)
; IF-EVL-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[B:%.*]], i32 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP14]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
; IF-EVL-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i32 [[EVL_BASED_IV]]
; IF-EVL-NEXT:    call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[VP_OP_LOAD]], ptr align 4 [[TMP16]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
; IF-EVL-NEXT:    [[INDEX_EVL_NEXT]] = add i32 [[TMP12]], [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[AVL_NEXT]] = sub nuw i32 [[TMP11]], [[TMP12]]
; IF-EVL-NEXT:    [[TMP13:%.*]] = icmp eq i32 [[AVL_NEXT]], 0
; IF-EVL-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[FOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; IF-EVL:       middle.block:
; IF-EVL-NEXT:    br label [[FOR_COND_CLEANUP:%.*]]
; IF-EVL:       scalar.ph:
; IF-EVL-NEXT:    br label [[FOR_BODY1:%.*]]
; IF-EVL:       for.body:
; IF-EVL-NEXT:    [[IV1:%.*]] = phi i32 [ 0, [[SCALAR_PH]] ], [ [[IV_NEXT1:%.*]], [[FOR_BODY1]] ]
; IF-EVL-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[B]], i32 [[IV1]]
; IF-EVL-NEXT:    [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; IF-EVL-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, ptr [[A]], i32 [[IV1]]
; IF-EVL-NEXT:    store i32 [[TMP0]], ptr [[ARRAYIDX4]], align 4
; IF-EVL-NEXT:    [[IV_NEXT1]] = add nuw nsw i32 [[IV1]], 1
; IF-EVL-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i32 [[IV_NEXT1]], [[N]]
; IF-EVL-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY1]], !llvm.loop [[LOOP4:![0-9]+]]
; IF-EVL:       for.cond.cleanup:
; IF-EVL-NEXT:    ret void
;
; NO-VP-LABEL: @iv32(
; NO-VP-NEXT:  entry:
; NO-VP-NEXT:    [[TMP0:%.*]] = call i32 @llvm.vscale.i32()
; NO-VP-NEXT:    [[TMP10:%.*]] = shl nuw i32 [[TMP0]], 2
; NO-VP-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N:%.*]], [[TMP10]]
; NO-VP-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; NO-VP:       vector.ph:
; NO-VP-NEXT:    [[TMP1:%.*]] = call i32 @llvm.vscale.i32()
; NO-VP-NEXT:    [[TMP11:%.*]] = mul nuw i32 [[TMP1]], 4
; NO-VP-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N]], [[TMP11]]
; NO-VP-NEXT:    [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; NO-VP-NEXT:    br label [[VECTOR_BODY:%.*]]
; NO-VP:       vector.body:
; NO-VP-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; NO-VP-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, ptr [[B:%.*]], i32 [[INDEX]]
; NO-VP-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP4]], align 4
; NO-VP-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i32 [[INDEX]]
; NO-VP-NEXT:    store <vscale x 4 x i32> [[WIDE_LOAD]], ptr [[TMP6]], align 4
; NO-VP-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP11]]
; NO-VP-NEXT:    [[TMP8:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; NO-VP-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; NO-VP:       middle.block:
; NO-VP-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; NO-VP-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; NO-VP:       scalar.ph:
; NO-VP-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; NO-VP-NEXT:    br label [[FOR_BODY:%.*]]
; NO-VP:       for.body:
; NO-VP-NEXT:    [[IV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; NO-VP-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[B]], i32 [[IV]]
; NO-VP-NEXT:    [[TMP9:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; NO-VP-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, ptr [[A]], i32 [[IV]]
; NO-VP-NEXT:    store i32 [[TMP9]], ptr [[ARRAYIDX4]], align 4
; NO-VP-NEXT:    [[IV_NEXT]] = add nuw nsw i32 [[IV]], 1
; NO-VP-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i32 [[IV_NEXT]], [[N]]
; NO-VP-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; NO-VP:       for.cond.cleanup:
; NO-VP-NEXT:    ret void
;
entry:
  br label %for.body

for.body:
  %iv = phi i32 [ 0, %entry ], [ %iv.next, %for.body ]
  %arrayidx = getelementptr inbounds i32, ptr %b, i32 %iv
  %0 = load i32, ptr %arrayidx, align 4
  %arrayidx4 = getelementptr inbounds i32, ptr %a, i32 %iv
  store i32 %0, ptr %arrayidx4, align 4
  %iv.next = add nuw nsw i32 %iv, 1
  %exitcond.not = icmp eq i32 %iv.next, %N
  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body

for.cond.cleanup:
  ret void
}