StructurizeCFG: Test for branch divergence correctly

Summary:
This 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.

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.

Change-Id: I32bbffece4a32f686fab54964dae1a5dd72949d4

Reviewers: arsenm, rampitec, jlebar

Subscribers: wdng, tpr, llvm-commits

Differential Revision: https://reviews.llvm.org/D40546

llvm-svn: 325881

include/llvm/Analysis/DivergenceAnalysis.h

@@ -35,10 +35,16 @@ public:
   // Print all divergent branches in the function.
   void print(raw_ostream &OS, const Module *) const override;
 
-  // Returns true if V is divergent.
+  // Returns true if V is divergent at its definition.
+  //
+  // Even if this function returns false, V may still be divergent when used
+  // in a different basic block.
   bool isDivergent(const Value *V) const { return DivergentValues.count(V); }
 
   // Returns true if V is uniform/non-divergent.
+  //
+  // Even if this function returns true, V may still be divergent when used
+  // in a different basic block.
   bool isUniform(const Value *V) const { return !isDivergent(V); }
 
 private:

lib/Transforms/Scalar/StructurizeCFG.cpp

@@ -55,6 +55,12 @@ static const char *const FlowBlockName = "Flow";
 
 namespace {
 
+static cl::opt<bool> ForceSkipUniformRegions(
+  "structurizecfg-skip-uniform-regions",
+  cl::Hidden,
+  cl::desc("Force whether the StructurizeCFG pass skips uniform regions"),
+  cl::init(false));
+
 // Definition of the complex types used in this pass.
 
 using BBValuePair = std::pair<BasicBlock *, Value *>;
@@ -242,8 +248,11 @@ class StructurizeCFG : public RegionPass {
 public:
   static char ID;
 
-  explicit StructurizeCFG(bool SkipUniformRegions = false)
-      : RegionPass(ID), SkipUniformRegions(SkipUniformRegions) {
+  explicit StructurizeCFG(bool SkipUniformRegions_ = false)
+      : RegionPass(ID),
+        SkipUniformRegions(SkipUniformRegions_) {
+    if (ForceSkipUniformRegions.getNumOccurrences())
+      SkipUniformRegions = ForceSkipUniformRegions.getValue();
     initializeStructurizeCFGPass(*PassRegistry::getPassRegistry());
   }
 
@@ -885,7 +894,7 @@ static bool hasOnlyUniformBranches(const Region *R,
     if (!Br || !Br->isConditional())
       continue;
 
-    if (!DA.isUniform(Br->getCondition()))
+    if (!DA.isUniform(Br))
       return false;
     DEBUG(dbgs() << "BB: " << BB->getName() << " has uniform terminator\n");
   }

test/CodeGen/AMDGPU/control-flow-optnone.ll

@@ -15,8 +15,8 @@
 ; GCN: s_mov_b64 exec
 
 ; GCN: s_or_b64 exec, exec
-; GCN: v_cmp_eq_u32
-; GCN: s_cbranch_vccnz
+; GCN: s_cmp_eq_u32
+; GCN: s_cbranch_scc1
 ; GCN-NEXT: s_branch
 define amdgpu_kernel void @copytoreg_divergent_brcond(i32 %arg, i32 %arg1, i32 %arg2) #0 {
 bb:

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()