blob: 62afded30b21efb7a22d86d7406af7d046d1c9e2 [file] [log] [blame]
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt "-passes=loop-rotate,indvars" -S < %s | FileCheck %s
; RUN: opt "-passes=loop-rotate" < %s | opt "-passes=indvars" -S - | FileCheck %s
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64-unknown-linux-gnu"
define dso_local float @foo(float* noalias %dst, float* %src, i32 %offset, i32 %N) {
; CHECK-LABEL: @foo(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP1:%.*]] = icmp slt i32 1, [[N:%.*]]
; CHECK-NEXT: br i1 [[CMP1]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[TMP0:%.*]] = sext i32 [[OFFSET:%.*]] to i64
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[N]] to i64
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.cond.for.cond.cleanup_crit_edge:
; CHECK-NEXT: br label [[FOR_COND_CLEANUP]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: ret float undef
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 1, [[FOR_BODY_LR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[TMP1:%.*]] = add nsw i64 [[INDVARS_IV]], [[TMP0]]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 [[TMP1]]
; CHECK-NEXT: [[TMP2:%.*]] = load float, float* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = add nsw i64 [[TMP1]], 1
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 [[TMP3]]
; CHECK-NEXT: [[TMP4:%.*]] = load float, float* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[ADD4:%.*]] = fadd fast float [[TMP2]], [[TMP4]]
; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: store float [[ADD4]], float* [[ARRAYIDX6]], align 4
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_COND_FOR_COND_CLEANUP_CRIT_EDGE:%.*]], !llvm.loop [[LOOP0:![0-9]+]]
;
entry:
br label %for.cond
for.cond: ; preds = %for.body, %entry
%i.0 = phi i32 [ 1, %entry ], [ %inc, %for.body ]
%cmp = icmp slt i32 %i.0, %N
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond
ret float undef
for.body: ; preds = %for.cond
%add = add nsw i32 %i.0, %offset
%idxprom = sext i32 %add to i64
%arrayidx = getelementptr inbounds float, float* %src, i64 %idxprom
%0 = load float, float* %arrayidx, align 4
%add1 = add nsw i32 %add, 1
%idxprom2 = sext i32 %add1 to i64
%arrayidx3 = getelementptr inbounds float, float* %src, i64 %idxprom2
%1 = load float, float* %arrayidx3, align 4
%add4 = fadd fast float %0, %1
%idxprom5 = zext i32 %i.0 to i64
%arrayidx6 = getelementptr inbounds float, float* %dst, i64 %idxprom5
store float %add4, float* %arrayidx6, align 4
%inc = add nuw nsw i32 %i.0, 1
br label %for.cond, !llvm.loop !1
}
!1 = distinct !{!1, !2}
!2 = !{!"llvm.loop.mustprogress"}