39 lines
1.6 KiB
LLVM
39 lines
1.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -mtriple=amdgcn-- -S -amdgpu-unify-divergent-exit-nodes -verify -simplifycfg-require-and-preserve-domtree=1 %s | FileCheck -check-prefix=IR %s
|
|
|
|
; Make sure that the phi in n28 is updated when the block is split by unify
|
|
; divergent exit nodes.
|
|
|
|
define amdgpu_ps void @_amdgpu_ps_main() local_unnamed_addr #3 {
|
|
; IR-LABEL: @_amdgpu_ps_main(
|
|
; IR-NEXT: .entry:
|
|
; IR-NEXT: br label [[DOTLOOPEXIT:%.*]]
|
|
; IR: .loopexit:
|
|
; IR-NEXT: br label [[N28:%.*]]
|
|
; IR: n28:
|
|
; IR-NEXT: [[DOT01:%.*]] = phi float [ 0.000000e+00, [[DOTLOOPEXIT]] ], [ [[N29:%.*]], [[TRANSITIONBLOCK:%.*]] ]
|
|
; IR-NEXT: [[N29]] = fadd float [[DOT01]], 1.000000e+00
|
|
; IR-NEXT: [[N30:%.*]] = fcmp ogt float [[N29]], 4.000000e+00
|
|
; IR-NEXT: br i1 true, label [[TRANSITIONBLOCK]], label [[UNIFIEDRETURNBLOCK:%.*]]
|
|
; IR: TransitionBlock:
|
|
; IR-NEXT: br i1 [[N30]], label [[DOTLOOPEXIT]], label [[N28]]
|
|
; IR: UnifiedReturnBlock:
|
|
; IR-NEXT: call void @llvm.amdgcn.exp.f32(i32 9, i32 0, float undef, float undef, float undef, float undef, i1 true, i1 true)
|
|
; IR-NEXT: ret void
|
|
;
|
|
.entry:
|
|
br label %.loopexit
|
|
|
|
.loopexit: ; preds = %n28, %.entry
|
|
br label %n28
|
|
|
|
n28: ; preds = %.loopexit, %n28
|
|
%.01 = phi float [ 0.000000e+00, %.loopexit ], [ %n29, %n28 ]
|
|
%n29 = fadd float %.01, 1.0
|
|
%n30 = fcmp ogt float %n29, 4.000000e+00
|
|
br i1 %n30, label %.loopexit, label %n28
|
|
|
|
n31: ; preds =
|
|
ret void
|
|
}
|