StructurizeCFG: Test for branch divergence correctly

Fixes cases like the new test @nonuniform. In that test, %cc itself
is a uniform value; however, when reading it after the end of the loop in
basic block %if, its value is effectively non-uniform, so the branch is
non-uniform.

This problem was encountered in
https://bugs.freedesktop.org/show_bug.cgi?id=103743; however, this change
in itself is not sufficient to fix that bug, as there is another issue
in the AMDGPU backend.

As discovered after committing an earlier version of this change, this
exposes a subtle interaction between this pass and DivergenceAnalysis:
since we remove and re-create branch instructions, we can no longer rely
on DivergenceAnalysis for branches in subregions that were already
processed by the pass.

Explicitly remove branch instructions from DivergenceAnalysis to
avoid dangling pointers as a matter of defensive programming, and
change how we detect non-uniform subregions.

Change-Id: I32bbffece4a32f686fab54964dae1a5dd72949d4

Differential Revision: https://reviews.llvm.org/D43743

llvm-svn: 329165

1 files changed, 82 insertions, 0 deletions

diff --git a/llvm/test/Transforms/StructurizeCFG/AMDGPU/uniform-regions.ll b/llvm/test/Transforms/StructurizeCFG/AMDGPU/uniform-regions.ll
new file mode 100644
index 00000000000..0e613721564
--- /dev/null
+++ b/llvm/test/Transforms/StructurizeCFG/AMDGPU/uniform-regions.ll
@@ -0,0 +1,82 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -mtriple=amdgcn-- -S -o - -structurizecfg -structurizecfg-skip-uniform-regions < %s | FileCheck %s
+
+define amdgpu_cs void @uniform(i32 inreg %v) {
+; CHECK-LABEL: @uniform(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[CC:%.*]] = icmp eq i32 [[V:%.*]], 0
+; CHECK-NEXT:    br i1 [[CC]], label [[IF:%.*]], label [[END:%.*]], !structurizecfg.uniform !0
+; CHECK:       if:
+; CHECK-NEXT:    br label [[END]], !structurizecfg.uniform !0
+; CHECK:       end:
+; CHECK-NEXT:    ret void
+;
+entry:
+  %cc = icmp eq i32 %v, 0
+  br i1 %cc, label %if, label %end
+
+if:
+  br label %end
+
+end:
+  ret void
+}
+
+define amdgpu_cs void @nonuniform(i32 addrspace(2)* %ptr) {
+; CHECK-LABEL: @nonuniform(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP0:%.*]], [[FLOW:%.*]] ]
+; CHECK-NEXT:    [[CC:%.*]] = icmp ult i32 [[I]], 4
+; CHECK-NEXT:    br i1 [[CC]], label [[MID_LOOP:%.*]], label [[FLOW]]
+; CHECK:       mid.loop:
+; CHECK-NEXT:    [[V:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[CC2:%.*]] = icmp eq i32 [[V]], 0
+; CHECK-NEXT:    br i1 [[CC2]], label [[END_LOOP:%.*]], label [[FLOW1:%.*]]
+; CHECK:       Flow:
+; CHECK-NEXT:    [[TMP0]] = phi i32 [ [[TMP2:%.*]], [[FLOW1]] ], [ undef, [[FOR_BODY]] ]
+; CHECK-NEXT:    [[TMP1:%.*]] = phi i1 [ [[TMP3:%.*]], [[FLOW1]] ], [ true, [[FOR_BODY]] ]
+; CHECK-NEXT:    br i1 [[TMP1]], label [[FOR_END:%.*]], label [[FOR_BODY]]
+; CHECK:       end.loop:
+; CHECK-NEXT:    [[I_INC:%.*]] = add i32 [[I]], 1
+; CHECK-NEXT:    br label [[FLOW1]]
+; CHECK:       Flow1:
+; CHECK-NEXT:    [[TMP2]] = phi i32 [ [[I_INC]], [[END_LOOP]] ], [ undef, [[MID_LOOP]] ]
+; CHECK-NEXT:    [[TMP3]] = phi i1 [ false, [[END_LOOP]] ], [ true, [[MID_LOOP]] ]
+; CHECK-NEXT:    br label [[FLOW]]
+; CHECK:       for.end:
+; CHECK-NEXT:    br i1 [[CC]], label [[IF:%.*]], label [[END:%.*]]
+; CHECK:       if:
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       end:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i32 [0, %entry], [%i.inc, %end.loop]
+  %cc = icmp ult i32 %i, 4
+  br i1 %cc, label %mid.loop, label %for.end
+
+mid.loop:
+  %v = call i32 @llvm.amdgcn.workitem.id.x()
+  %cc2 = icmp eq i32 %v, 0
+  br i1 %cc2, label %end.loop, label %for.end
+
+end.loop:
+  %i.inc = add i32 %i, 1
+  br label %for.body
+
+for.end:
+  br i1 %cc, label %if, label %end
+
+if:
+  br label %end
+
+end:
+  ret void
+}
+
+declare i32 @llvm.amdgcn.workitem.id.x()