[DA] GPUDivergenceAnalysis for unstructured GPU kernels

Summary:
This is patch #3 of the new DivergenceAnalysis

  <https://lists.llvm.org/pipermail/llvm-dev/2018-May/123606.html>

The GPUDivergenceAnalysis is intended to eventually supersede the existing
LegacyDivergenceAnalysis. The existing LegacyDivergenceAnalysis produces
incorrect results on unstructured Control-Flow Graphs:

  <https://bugs.llvm.org/show_bug.cgi?id=37185>

This patch adds the option -use-gpu-divergence-analysis to the
LegacyDivergenceAnalysis to turn it into a transparent wrapper for the
GPUDivergenceAnalysis.

Reviewers: nhaehnle

Reviewed By: nhaehnle

Subscribers: jholewinski, jvesely, jfb, llvm-commits, alex-t, sameerds, arsenm, nhaehnle

Differential Revision: https://reviews.llvm.org/D53493

llvm-svn: 348048

Author: nhaehnle

llvm/include/llvm/Analysis/DivergenceAnalysis.h

@@ -173,6 +173,33 @@ class DivergenceAnalysis {
   std::vector<const Instruction *> Worklist;
 };
 
+/// \brief Divergence analysis frontend for GPU kernels.
+class GPUDivergenceAnalysis {
+  SyncDependenceAnalysis SDA;
+  DivergenceAnalysis DA;
+
+public:
+  /// Runs the divergence analysis on @F, a GPU kernel
+  GPUDivergenceAnalysis(Function &F, const DominatorTree &DT,
+                        const PostDominatorTree &PDT, const LoopInfo &LI,
+                        const TargetTransformInfo &TTI);
+
+  /// Whether any divergence was detected.
+  bool hasDivergence() const { return DA.hasDetectedDivergence(); }
+
+  /// The GPU kernel this analysis result is for
+  const Function &getFunction() const { return DA.getFunction(); }
+
+  /// Whether \p V is divergent.
+  bool isDivergent(const Value &V) const;
+
+  /// Whether \p V is uniform/non-divergent
+  bool isUniform(const Value &V) const { return !isDivergent(V); }
+
+  /// Print all divergent values in the kernel.
+  void print(raw_ostream &OS, const Module *) const;
+};
+
 } // namespace llvm
 
 #endif // LLVM_ANALYSIS_DIVERGENCE_ANALYSIS_H

llvm/include/llvm/Analysis/LegacyDivergenceAnalysis.h

@@ -19,9 +19,11 @@
 #include "llvm/ADT/DenseSet.h"
 #include "llvm/IR/Function.h"
 #include "llvm/Pass.h"
+#include "llvm/Analysis/DivergenceAnalysis.h"
 
 namespace llvm {
 class Value;
+class GPUDivergenceAnalysis;
 class LegacyDivergenceAnalysis : public FunctionPass {
 public:
   static char ID;
@@ -41,7 +43,7 @@ class LegacyDivergenceAnalysis : public FunctionPass {
   //
   // 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); }
+  bool isDivergent(const Value *V) const;
 
   // Returns true if V is uniform/non-divergent.
   //
@@ -53,6 +55,12 @@ class LegacyDivergenceAnalysis : public FunctionPass {
   void removeValue(const Value *V) { DivergentValues.erase(V); }
 
 private:
+  // Whether analysis should be performed by GPUDivergenceAnalysis.
+  bool shouldUseGPUDivergenceAnalysis(const Function &F) const;
+
+  // (optional) handle to new DivergenceAnalysis
+  std::unique_ptr<GPUDivergenceAnalysis> gpuDA;
+
   // Stores all divergent values.
   DenseSet<const Value *> DivergentValues;
 };

llvm/lib/Analysis/DivergenceAnalysis.cpp

@@ -422,3 +422,36 @@ void DivergenceAnalysis::print(raw_ostream &OS, const Module *) const {
       OS << "DIVERGENT:" << I << '\n';
   }
 }
+
+// class GPUDivergenceAnalysis
+GPUDivergenceAnalysis::GPUDivergenceAnalysis(Function &F,
+                                             const DominatorTree &DT,
+                                             const PostDominatorTree &PDT,
+                                             const LoopInfo &LI,
+                                             const TargetTransformInfo &TTI)
+    : SDA(DT, PDT, LI), DA(F, nullptr, DT, LI, SDA, false) {
+  for (auto &I : instructions(F)) {
+    if (TTI.isSourceOfDivergence(&I)) {
+      DA.markDivergent(I);
+    } else if (TTI.isAlwaysUniform(&I)) {
+      DA.addUniformOverride(I);
+    }
+  }
+  for (auto &Arg : F.args()) {
+    if (TTI.isSourceOfDivergence(&Arg)) {
+      DA.markDivergent(Arg);
+    }
+  }
+
+  DA.compute();
+}
+
+bool GPUDivergenceAnalysis::isDivergent(const Value &val) const {
+  return DA.isDivergent(val);
+}
+
+void GPUDivergenceAnalysis::print(raw_ostream &OS, const Module *mod) const {
+  OS << "Divergence of kernel " << DA.getFunction().getName() << " {\n";
+  DA.print(OS, mod);
+  OS << "}\n";
+}

llvm/lib/Analysis/LegacyDivergenceAnalysis.cpp

@@ -1,4 +1,5 @@
-//===- LegacyDivergenceAnalysis.cpp --------- Legacy Divergence Analysis Implementation -==//
+//===- LegacyDivergenceAnalysis.cpp --------- Legacy Divergence Analysis
+//Implementation -==//
 //
 //                     The LLVM Compiler Infrastructure
 //
@@ -64,6 +65,9 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include "llvm/ADT/PostOrderIterator.h"
+#include "llvm/Analysis/CFG.h"
+#include "llvm/Analysis/DivergenceAnalysis.h"
 #include "llvm/Analysis/LegacyDivergenceAnalysis.h"
 #include "llvm/Analysis/Passes.h"
 #include "llvm/Analysis/PostDominators.h"
@@ -79,6 +83,12 @@ using namespace llvm;
 
 #define DEBUG_TYPE "divergence"
 
+// transparently use the GPUDivergenceAnalysis
+static cl::opt<bool> UseGPUDA("use-gpu-divergence-analysis", cl::init(false),
+                              cl::Hidden,
+                              cl::desc("turn the LegacyDivergenceAnalysis into "
+                                       "a wrapper for GPUDivergenceAnalysis"));
+
 namespace {
 
 class DivergencePropagator {
@@ -262,16 +272,17 @@ void DivergencePropagator::propagate() {
   }
 }
 
-} /// end namespace anonymous
+} // namespace
 
 // Register this pass.
 char LegacyDivergenceAnalysis::ID = 0;
-INITIALIZE_PASS_BEGIN(LegacyDivergenceAnalysis, "divergence", "Legacy Divergence Analysis",
-                      false, true)
+INITIALIZE_PASS_BEGIN(LegacyDivergenceAnalysis, "divergence",
+                      "Legacy Divergence Analysis", false, true)
 INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(PostDominatorTreeWrapperPass)
-INITIALIZE_PASS_END(LegacyDivergenceAnalysis, "divergence", "Legacy Divergence Analysis",
-                    false, true)
+INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
+INITIALIZE_PASS_END(LegacyDivergenceAnalysis, "divergence",
+                    "Legacy Divergence Analysis", false, true)
 
 FunctionPass *llvm::createLegacyDivergenceAnalysisPass() {
   return new LegacyDivergenceAnalysis();
@@ -280,9 +291,24 @@ FunctionPass *llvm::createLegacyDivergenceAnalysisPass() {
 void LegacyDivergenceAnalysis::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.addRequired<DominatorTreeWrapperPass>();
   AU.addRequired<PostDominatorTreeWrapperPass>();
+  if (UseGPUDA)
+    AU.addRequired<LoopInfoWrapperPass>();
   AU.setPreservesAll();
 }
 
+bool LegacyDivergenceAnalysis::shouldUseGPUDivergenceAnalysis(
+    const Function &F) const {
+  if (!UseGPUDA)
+    return false;
+
+  // GPUDivergenceAnalysis requires a reducible CFG.
+  auto &LI = getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
+  using RPOTraversal = ReversePostOrderTraversal<const Function *>;
+  RPOTraversal FuncRPOT(&F);
+  return !containsIrreducibleCFG<const BasicBlock *, const RPOTraversal,
+                                 const LoopInfo>(FuncRPOT, LI);
+}
+
 bool LegacyDivergenceAnalysis::runOnFunction(Function &F) {
   auto *TTIWP = getAnalysisIfAvailable<TargetTransformInfoWrapperPass>();
   if (TTIWP == nullptr)
@@ -295,44 +321,67 @@ bool LegacyDivergenceAnalysis::runOnFunction(Function &F) {
     return false;
 
   DivergentValues.clear();
+  gpuDA = nullptr;
+
+  auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
   auto &PDT = getAnalysis<PostDominatorTreeWrapperPass>().getPostDomTree();
-  DivergencePropagator DP(F, TTI,
-                          getAnalysis<DominatorTreeWrapperPass>().getDomTree(),
-                          PDT, DivergentValues);
-  DP.populateWithSourcesOfDivergence();
-  DP.propagate();
-  LLVM_DEBUG(
-    dbgs() << "\nAfter divergence analysis on " << F.getName() << ":\n";
-    print(dbgs(), F.getParent())
-  );
+
+  if (shouldUseGPUDivergenceAnalysis(F)) {
+    // run the new GPU divergence analysis
+    auto &LI = getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
+    gpuDA = llvm::make_unique<GPUDivergenceAnalysis>(F, DT, PDT, LI, TTI);
+
+  } else {
+    // run LLVM's existing DivergenceAnalysis
+    DivergencePropagator DP(F, TTI, DT, PDT, DivergentValues);
+    DP.populateWithSourcesOfDivergence();
+    DP.propagate();
+  }
+
+  LLVM_DEBUG(dbgs() << "\nAfter divergence analysis on " << F.getName()
+                    << ":\n";
+             print(dbgs(), F.getParent()));
+
   return false;
 }
 
+bool LegacyDivergenceAnalysis::isDivergent(const Value *V) const {
+  if (gpuDA) {
+    return gpuDA->isDivergent(*V);
+  }
+  return DivergentValues.count(V);
+}
+
 void LegacyDivergenceAnalysis::print(raw_ostream &OS, const Module *) const {
-  if (DivergentValues.empty())
+  if ((!gpuDA || !gpuDA->hasDivergence()) && DivergentValues.empty())
     return;
-  const Value *FirstDivergentValue = *DivergentValues.begin();
+
   const Function *F;
-  if (const Argument *Arg = dyn_cast<Argument>(FirstDivergentValue)) {
-    F = Arg->getParent();
-  } else if (const Instruction *I =
-                 dyn_cast<Instruction>(FirstDivergentValue)) {
-    F = I->getParent()->getParent();
-  } else {
-    llvm_unreachable("Only arguments and instructions can be divergent");
+  if (!DivergentValues.empty()) {
+    const Value *FirstDivergentValue = *DivergentValues.begin();
+    if (const Argument *Arg = dyn_cast<Argument>(FirstDivergentValue)) {
+      F = Arg->getParent();
+    } else if (const Instruction *I =
+                   dyn_cast<Instruction>(FirstDivergentValue)) {
+      F = I->getParent()->getParent();
+    } else {
+      llvm_unreachable("Only arguments and instructions can be divergent");
+    }
+  } else if (gpuDA) {
+    F = &gpuDA->getFunction();
   }
 
   // Dumps all divergent values in F, arguments and then instructions.
   for (auto &Arg : F->args()) {
-    OS << (DivergentValues.count(&Arg) ? "DIVERGENT: " : "           ");
+    OS << (isDivergent(&Arg) ? "DIVERGENT: " : "           ");
     OS << Arg << "\n";
   }
   // Iterate instructions using instructions() to ensure a deterministic order.
   for (auto BI = F->begin(), BE = F->end(); BI != BE; ++BI) {
     auto &BB = *BI;
     OS << "\n           " << BB.getName() << ":\n";
     for (auto &I : BB.instructionsWithoutDebug()) {
-      OS << (DivergentValues.count(&I) ? "DIVERGENT:     " : "               ");
+      OS << (isDivergent(&I) ? "DIVERGENT:     " : "               ");
       OS << I << "\n";
     }
   }

llvm/test/Analysis/DivergenceAnalysis/AMDGPU/always_uniform.ll

@@ -0,0 +1,14 @@
+; RUN: opt  -mtriple amdgcn-unknown-amdhsa -analyze -divergence -use-gpu-divergence-analysis %s | FileCheck %s
+
+define amdgpu_kernel void @workitem_id_x() #1 {
+  %id.x = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK: DIVERGENT:  %id.x = call i32 @llvm.amdgcn.workitem.id.x()
+  %first.lane = call i32 @llvm.amdgcn.readfirstlane(i32 %id.x)
+; CHECK-NOT: DIVERGENT:  %first.lane = call i32 @llvm.amdgcn.readfirstlane(i32 %id.x)
+  ret void
+}
+
+declare i32 @llvm.amdgcn.workitem.id.x() #0
+declare i32 @llvm.amdgcn.readfirstlane(i32) #0
+
+attributes #0 = { nounwind readnone }

llvm/test/Analysis/DivergenceAnalysis/AMDGPU/atomics.ll

@@ -0,0 +1,45 @@
+; RUN: opt -mtriple=amdgcn-- -analyze -divergence -use-gpu-divergence-analysis %s | FileCheck %s
+
+; CHECK: DIVERGENT: %orig = atomicrmw xchg i32* %ptr, i32 %val seq_cst
+define i32 @test1(i32* %ptr, i32 %val) #0 {
+  %orig = atomicrmw xchg i32* %ptr, i32 %val seq_cst
+  ret i32 %orig
+}
+
+; CHECK: DIVERGENT: %orig = cmpxchg i32* %ptr, i32 %cmp, i32 %new seq_cst seq_cst
+define {i32, i1} @test2(i32* %ptr, i32 %cmp, i32 %new) {
+  %orig = cmpxchg i32* %ptr, i32 %cmp, i32 %new seq_cst seq_cst
+  ret {i32, i1} %orig
+}
+
+; CHECK: DIVERGENT: %ret = call i32 @llvm.amdgcn.atomic.inc.i32.p1i32(i32 addrspace(1)* %ptr, i32 %val, i32 0, i32 0, i1 false)
+define i32 @test_atomic_inc_i32(i32 addrspace(1)* %ptr, i32 %val) #0 {
+  %ret = call i32 @llvm.amdgcn.atomic.inc.i32.p1i32(i32 addrspace(1)* %ptr, i32 %val, i32 0, i32 0, i1 false)
+  ret i32 %ret
+}
+
+; CHECK: DIVERGENT: %ret = call i64 @llvm.amdgcn.atomic.inc.i64.p1i64(i64 addrspace(1)* %ptr, i64 %val, i32 0, i32 0, i1 false)
+define i64 @test_atomic_inc_i64(i64 addrspace(1)* %ptr, i64 %val) #0 {
+  %ret = call i64 @llvm.amdgcn.atomic.inc.i64.p1i64(i64 addrspace(1)* %ptr, i64 %val, i32 0, i32 0, i1 false)
+  ret i64 %ret
+}
+
+; CHECK: DIVERGENT: %ret = call i32 @llvm.amdgcn.atomic.dec.i32.p1i32(i32 addrspace(1)* %ptr, i32 %val, i32 0, i32 0, i1 false)
+define i32 @test_atomic_dec_i32(i32 addrspace(1)* %ptr, i32 %val) #0 {
+  %ret = call i32 @llvm.amdgcn.atomic.dec.i32.p1i32(i32 addrspace(1)* %ptr, i32 %val, i32 0, i32 0, i1 false)
+  ret i32 %ret
+}
+
+; CHECK: DIVERGENT: %ret = call i64 @llvm.amdgcn.atomic.dec.i64.p1i64(i64 addrspace(1)* %ptr, i64 %val, i32 0, i32 0, i1 false)
+define i64 @test_atomic_dec_i64(i64 addrspace(1)* %ptr, i64 %val) #0 {
+  %ret = call i64 @llvm.amdgcn.atomic.dec.i64.p1i64(i64 addrspace(1)* %ptr, i64 %val, i32 0, i32 0, i1 false)
+  ret i64 %ret
+}
+
+declare i32 @llvm.amdgcn.atomic.inc.i32.p1i32(i32 addrspace(1)* nocapture, i32, i32, i32, i1) #1
+declare i64 @llvm.amdgcn.atomic.inc.i64.p1i64(i64 addrspace(1)* nocapture, i64, i32, i32, i1) #1
+declare i32 @llvm.amdgcn.atomic.dec.i32.p1i32(i32 addrspace(1)* nocapture, i32, i32, i32, i1) #1
+declare i64 @llvm.amdgcn.atomic.dec.i64.p1i64(i64 addrspace(1)* nocapture, i64, i32, i32, i1) #1
+
+attributes #0 = { nounwind }
+attributes #1 = { nounwind argmemonly }

llvm/test/Analysis/DivergenceAnalysis/AMDGPU/hidden_diverge.ll

@@ -0,0 +1,26 @@
+; RUN: opt -mtriple amdgcn-unknown-amdhsa -analyze -divergence -use-gpu-divergence-analysis %s | FileCheck %s
+
+define amdgpu_kernel void @hidden_diverge(i32 %n, i32 %a, i32 %b) #0 {
+; CHECK-LABEL: Printing analysis 'Legacy Divergence Analysis' for function 'hidden_diverge'
+entry:
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %cond.var = icmp slt i32 %tid, 0
+  br i1 %cond.var, label %B, label %C ; divergent
+; CHECK: DIVERGENT: br i1 %cond.var,
+B:
+  %cond.uni = icmp slt i32 %n, 0
+  br i1 %cond.uni, label %C, label %merge ; uniform
+; CHECK-NOT: DIVERGENT: br i1 %cond.uni,
+C:
+  %phi.var.hidden = phi i32 [ 1, %entry ], [ 2, %B  ]
+; CHECK: DIVERGENT: %phi.var.hidden = phi i32
+  br label %merge
+merge:
+  %phi.ipd = phi i32 [ %a, %B ], [ %b, %C ]
+; CHECK: DIVERGENT: %phi.ipd = phi i32
+  ret void
+}
+
+declare i32 @llvm.amdgcn.workitem.id.x() #0
+
+attributes #0 = { nounwind readnone }