test/Transforms/LoopVectorize/PowerPC/vectorize-force-tail-with-evl.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=loop-vectorize \
; RUN: -force-tail-folding-style=data-with-evl \
; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
; RUN: -mtriple=powerpc64le-unknown-linux-gnu \
; RUN: -mcpu=pwr10 -S < %s | FileCheck %s

; RUN: opt -passes=loop-vectorize \
; RUN: -force-tail-folding-style=none \
; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
; RUN: -mtriple=powerpc64le-unknown-linux-gnu \
; RUN: -mcpu=pwr10 -S < %s | FileCheck %s

define void @foo(ptr noalias %a, ptr noalias %b, ptr noalias %c, i64 %N) {
; CHECK-LABEL: @foo(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[B:%.*]], i64 [[IV]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, ptr [[C:%.*]], i64 [[IV]]
; CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP1]], [[TMP0]]
; CHECK-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[IV]]
; CHECK-NEXT:    store i32 [[ADD]], ptr [[ARRAYIDX4]], align 4
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N:%.*]]
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.body

for.body:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
  %arrayidx = getelementptr inbounds i32, ptr %b, i64 %iv
  %0 = load i32, ptr %arrayidx, align 4
  %arrayidx2 = getelementptr inbounds i32, ptr %c, i64 %iv
  %1 = load i32, ptr %arrayidx2, align 4
  %add = add nsw i32 %1, %0
  %arrayidx4 = getelementptr inbounds i32, ptr %a, i64 %iv
  store i32 %add, ptr %arrayidx4, align 4
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, %N
  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body

for.cond.cleanup:
  ret void
}