test/Transforms/LoopDataPrefetch/LoongArch/basic.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt --mtriple=loongarch64 -mattr=+d --passes=loop-data-prefetch -S < %s | FileCheck %s

define void @foo(ptr %a, ptr %b) {
; CHECK-LABEL: define void @foo(
; CHECK-SAME: ptr [[A:%.*]], ptr [[B:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  [[ENTRY:.*]]:
; CHECK-NEXT:    br label %[[FOR_BODY:.*]]
; CHECK:       [[FOR_BODY]]:
; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[FOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[TMP0]], 200
; CHECK-NEXT:    [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[A]], i64 [[TMP1]]
; CHECK-NEXT:    [[TMP2:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[TMP2]], 200
; CHECK-NEXT:    [[SCEVGEP:%.*]] = getelementptr i8, ptr [[B]], i64 [[TMP3]]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds double, ptr [[B]], i64 [[INDVARS_IV]]
; CHECK-NEXT:    call void @llvm.prefetch.p0(ptr [[SCEVGEP]], i32 0, i32 3, i32 1)
; CHECK-NEXT:    [[TMP4:%.*]] = load double, ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[ADD:%.*]] = fadd double [[TMP4]], 1.000000e+00
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds double, ptr [[A]], i64 [[INDVARS_IV]]
; CHECK-NEXT:    call void @llvm.prefetch.p0(ptr [[SCEVGEP1]], i32 1, i32 3, i32 1)
; CHECK-NEXT:    store double [[ADD]], ptr [[ARRAYIDX2]], align 8
; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1600
; CHECK-NEXT:    br i1 [[EXITCOND]], label %[[FOR_END:.*]], label %[[FOR_BODY]]
; CHECK:       [[FOR_END]]:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %arrayidx = getelementptr inbounds double, ptr %b, i64 %indvars.iv
  %0 = load double, ptr %arrayidx, align 8
  %add = fadd double %0, 1.000000e+00
  %arrayidx2 = getelementptr inbounds double, ptr %a, i64 %indvars.iv
  store double %add, ptr %arrayidx2, align 8
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1600
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  ret void
}