llvm/test/Transforms/SimpleLoopUnswitch/AMDGPU/uniform-unswitch.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 3
; RUN: opt -mtriple=amdgpu-- -passes='default<O3>' -S %s | FileCheck %s

; Check that loop unswitch happened and condition hoisted out of the loop.
; Condition is uniform so even targets with divergence should perform unswitching.

; This fails with the new pass manager:
; https://bugs.llvm.org/show_bug.cgi?id=48819
; The correct behaviour (allow uniform non-trivial branches to be
; unswitched on all targets) requires access to the function-level
; divergence analysis from a loop transform, which is currently not
; supported in the new pass manager.

; SHOULDBE-LABEL: {{^}}define amdgpu_kernel void @uniform_unswitch
; SHOULDBE: entry:
; SHOULDBE-NEXT: [[LOOP_COND:%[a-z0-9]+]] = icmp
; SHOULDBE-NEXT: [[IF_COND:%[a-z0-9]+]] = icmp eq i32 %x, 123456
; SHOULDBE-NEXT: and i1 [[LOOP_COND]], [[IF_COND]]
; SHOULDBE-NEXT: br i1

define amdgpu_kernel void @uniform_unswitch(ptr nocapture %out, i32 %n, i32 %x) {
; CHECK-LABEL: define amdgpu_kernel void @uniform_unswitch(
; CHECK-SAME: ptr nofree captures(none) [[OUT:%.*]], i32 [[N:%.*]], i32 [[X:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[OUT_GLOBAL:%.*]] = addrspacecast ptr [[OUT]] to ptr addrspace(1)
; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N]], 0
; CHECK-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body.lr.ph:
; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i32 [[X]], 123456
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    ret void
; CHECK:       for.body:
; CHECK-NEXT:    [[I_07:%.*]] = phi i32 [ 0, [[FOR_BODY_LR_PH]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = zext nneg i32 [[I_07]] to i64
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds nuw [4 x i8], ptr addrspace(1) [[OUT_GLOBAL]], i64 [[TMP0]]
; CHECK-NEXT:    br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
; CHECK:       if.then:
; CHECK-NEXT:    store i32 [[I_07]], ptr addrspace(1) [[ARRAYIDX]], align 4
; CHECK-NEXT:    br label [[FOR_INC]]
; CHECK:       if.else:
; CHECK-NEXT:    [[TMP2:%.*]] = addrspacecast ptr addrspace(1) [[ARRAYIDX]] to ptr
; CHECK-NEXT:    store volatile i32 0, ptr [[TMP2]], align 4
; CHECK-NEXT:    br label [[FOR_INC]]
; CHECK:       for.inc:
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_07]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.lr.ph, label %for.cond.cleanup

for.body.lr.ph:                                   ; preds = %entry
  %cmp1 = icmp eq i32 %x, 123456
  br label %for.body

for.cond.cleanup.loopexit:                        ; preds = %for.inc
  br label %for.cond.cleanup

for.cond.cleanup:                                 ; preds = %for.cond.cleanup.loopexit, %entry
  ret void

for.body:                                         ; preds = %for.inc, %for.body.lr.ph
  %i.07 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
  br i1 %cmp1, label %if.then, label %if.else

if.then:                                          ; preds = %for.body
  %arrayidx = getelementptr inbounds i32, ptr %out, i32 %i.07
  store i32 %i.07, ptr %arrayidx, align 4
  br label %for.inc

if.else:                                          ; preds = %for.body
  %arrayidx2 = getelementptr inbounds i32, ptr %out, i32 %i.07
  store volatile i32 0, ptr %arrayidx2, align 4
  br label %for.inc

for.inc:                                          ; preds = %if.else, %if.then
  %inc = add nuw nsw i32 %i.07, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body, !llvm.loop !0
}

declare i32 @llvm.amdgcn.workitem.id.x() #0

attributes #0 = { nounwind readnone }

!0 = distinct !{!0, !1}
!1 = !{!"llvm.loop.unroll.disable"}