Simplify n-ary adds by reassociation

Summary:
This transformation reassociates a n-ary add so that the add can partially reuse
existing instructions. For example, this pass can simplify

  void foo(int a, int b) {
    bar(a + b);
    bar((a + 2) + b);
  }

to

  void foo(int a, int b) {
    int t = a + b;
    bar(t);
    bar(t + 2);
  }

saving one add instruction.

Fixes PR22357 (https://llvm.org/bugs/show_bug.cgi?id=22357).

Test Plan: nary-add.ll

Reviewers: broune, dberlin, hfinkel, meheff, sanjoy, atrick

Reviewed By: sanjoy, atrick

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D8950

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@234855 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/InitializePasses.h

@@ -206,6 +206,7 @@ void initializeMergedLoadStoreMotionPass(PassRegistry &);
 void initializeMetaRenamerPass(PassRegistry&);
 void initializeMergeFunctionsPass(PassRegistry&);
 void initializeModuleDebugInfoPrinterPass(PassRegistry&);
+void initializeNaryReassociatePass(PassRegistry&);
 void initializeNoAAPass(PassRegistry&);
 void initializeObjCARCAliasAnalysisPass(PassRegistry&);
 void initializeObjCARCAPElimPass(PassRegistry&);

include/llvm/LinkAllPasses.h

@@ -109,6 +109,7 @@ namespace {
       (void) llvm::createLowerExpectIntrinsicPass();
       (void) llvm::createLowerInvokePass();
       (void) llvm::createLowerSwitchPass();
+      (void) llvm::createNaryReassociatePass();
       (void) llvm::createNoAAPass();
       (void) llvm::createObjCARCAliasAnalysisPass();
       (void) llvm::createObjCARCAPElimPass();

include/llvm/Transforms/Scalar.h

@@ -457,6 +457,12 @@ FunctionPass *createRewriteStatepointsForGCPass();
 //
 FunctionPass *createFloat2IntPass();
 
+//===----------------------------------------------------------------------===//
+//
+// NaryReassociate - Simplify n-ary operations by reassociation.
+//
+FunctionPass *createNaryReassociatePass();
+
 } // End llvm namespace
 
 #endif

lib/Transforms/Scalar/CMakeLists.txt

@@ -29,6 +29,7 @@ add_llvm_library(LLVMScalarOpts
   LowerExpectIntrinsic.cpp
   MemCpyOptimizer.cpp
   MergedLoadStoreMotion.cpp
+  NaryReassociate.cpp
   PartiallyInlineLibCalls.cpp
   PlaceSafepoints.cpp
   Reassociate.cpp

lib/Transforms/Scalar/NaryReassociate.cpp

@@ -0,0 +1,206 @@
+//===- NaryReassociate.cpp - Reassociate n-ary expressions ----------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This pass reassociates n-ary add expressions and eliminates the redundancy
+// exposed by the reassociation.
+//
+// A motivating example:
+//
+//   void foo(int a, int b) {
+//     bar(a + b);
+//     bar((a + 2) + b);
+//   }
+//
+// An ideal compiler should reassociate (a + 2) + b to (a + b) + 2 and simplify
+// the above code to
+//
+//   int t = a + b;
+//   bar(t);
+//   bar(t + 2);
+//
+// However, the Reassociate pass is unable to do that because it processes each
+// instruction individually and believes (a + 2) + b is the best form according
+// to its rank system.
+//
+// To address this limitation, NaryReassociate reassociates an expression in a
+// form that reuses existing instructions. As a result, NaryReassociate can
+// reassociate (a + 2) + b in the example to (a + b) + 2 because it detects that
+// (a + b) is computed before.
+//
+// NaryReassociate works as follows. For every instruction in the form of (a +
+// b) + c, it checks whether a + c or b + c is already computed by a dominating
+// instruction. If so, it then reassociates (a + b) + c into (a + c) + b or (b +
+// c) + a respectively. To efficiently look up whether an expression is
+// computed before, we store each instruction seen and its SCEV into an
+// SCEV-to-instruction map.
+//
+// Although the algorithm pattern-matches only ternary additions, it
+// automatically handles many >3-ary expressions by walking through the function
+// in the depth-first order. For example, given
+//
+//   (a + c) + d
+//   ((a + b) + c) + d
+//
+// NaryReassociate first rewrites (a + b) + c to (a + c) + b, and then rewrites
+// ((a + c) + b) + d into ((a + c) + d) + b.
+//
+// Limitations and TODO items:
+//
+// 1) We only considers n-ary adds for now. This should be extended and
+// generalized.
+//
+// 2) Besides arithmetic operations, similar reassociation can be applied to
+// GEPs. For example, if
+//   X = &arr[a]
+// dominates
+//   Y = &arr[a + b]
+// we may rewrite Y into X + b.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Analysis/ScalarEvolution.h"
+#include "llvm/IR/Dominators.h"
+#include "llvm/IR/Module.h"
+#include "llvm/IR/PatternMatch.h"
+#include "llvm/Transforms/Scalar.h"
+using namespace llvm;
+using namespace PatternMatch;
+
+#define DEBUG_TYPE "nary-reassociate"
+
+namespace {
+class NaryReassociate : public FunctionPass {
+public:
+  static char ID;
+
+  NaryReassociate(): FunctionPass(ID) {
+    initializeNaryReassociatePass(*PassRegistry::getPassRegistry());
+  }
+
+  bool runOnFunction(Function &F) override;
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.addPreserved<DominatorTreeWrapperPass>();
+    AU.addRequired<DominatorTreeWrapperPass>();
+    // TODO: can we preserve ScalarEvolution?
+    AU.addRequired<ScalarEvolution>();
+    AU.setPreservesCFG();
+  }
+
+private:
+  // Reasssociates I to a better form.
+  Instruction *tryReassociateAdd(Instruction *I);
+  // A helper function for tryReassociateAdd. LHS and RHS are explicitly passed.
+  Instruction *tryReassociateAdd(Value *LHS, Value *RHS, Instruction *I);
+  // Rewrites I to LHS + RHS if LHS is computed already.
+  Instruction *tryReassociatedAdd(const SCEV *LHS, Value *RHS, Instruction *I);
+
+  DominatorTree *DT;
+  ScalarEvolution *SE;
+  // A lookup table quickly telling which instructions compute the given SCEV.
+  // Note that there can be multiple instructions at different locations
+  // computing to the same SCEV.  For example,
+  //   if (p1)
+  //     foo(a + b);
+  //   if (p2)
+  //     bar(a + b);
+  DenseMap<const SCEV *, SmallVector<Instruction *, 2>> SeenExprs;
+};
+} // anonymous namespace
+
+char NaryReassociate::ID = 0;
+INITIALIZE_PASS_BEGIN(NaryReassociate, "nary-reassociate", "Nary reassociation",
+                      false, false)
+INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(ScalarEvolution)
+INITIALIZE_PASS_END(NaryReassociate, "nary-reassociate", "Nary reassociation",
+                    false, false)
+
+FunctionPass *llvm::createNaryReassociatePass() {
+  return new NaryReassociate();
+}
+
+bool NaryReassociate::runOnFunction(Function &F) {
+  if (skipOptnoneFunction(F))
+    return false;
+
+  DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
+  SE = &getAnalysis<ScalarEvolution>();
+
+  // Traverse the dominator tree in the depth-first order. This order makes sure
+  // all bases of a candidate are in Candidates when we process it.
+  bool Changed = false;
+  SeenExprs.clear();
+  for (auto Node = GraphTraits<DominatorTree *>::nodes_begin(DT);
+       Node != GraphTraits<DominatorTree *>::nodes_end(DT); ++Node) {
+    BasicBlock *BB = Node->getBlock();
+    for (auto I = BB->begin(); I != BB->end(); ++I) {
+      if (I->getOpcode() == Instruction::Add) {
+        if (Instruction *NewI = tryReassociateAdd(I)) {
+          I->replaceAllUsesWith(NewI);
+          I->eraseFromParent();
+          I = NewI;
+        }
+        // We should add the rewritten instruction because tryReassociateAdd may
+        // have invalidated the original one.
+        SeenExprs[SE->getSCEV(I)].push_back(I);
+      }
+    }
+  }
+  return Changed;
+}
+
+Instruction *NaryReassociate::tryReassociateAdd(Instruction *I) {
+  Value *LHS = I->getOperand(0), *RHS = I->getOperand(1);
+  if (auto *NewI = tryReassociateAdd(LHS, RHS, I))
+    return NewI;
+  if (auto *NewI = tryReassociateAdd(RHS, LHS, I))
+    return NewI;
+  return nullptr;
+}
+
+Instruction *NaryReassociate::tryReassociateAdd(Value *LHS, Value *RHS,
+                                                Instruction *I) {
+  Value *A = nullptr, *B = nullptr;
+  // To be conservative, we reassociate I only when it is the only user of A+B.
+  if (LHS->hasOneUse() && match(LHS, m_Add(m_Value(A), m_Value(B)))) {
+    // I = (A + B) + RHS
+    //   = (A + RHS) + B or (B + RHS) + A
+    const SCEV *AExpr = SE->getSCEV(A), *BExpr = SE->getSCEV(B);
+    const SCEV *RHSExpr = SE->getSCEV(RHS);
+    if (auto *NewI = tryReassociatedAdd(SE->getAddExpr(AExpr, RHSExpr), B, I))
+      return NewI;
+    if (auto *NewI = tryReassociatedAdd(SE->getAddExpr(BExpr, RHSExpr), A, I))
+      return NewI;
+  }
+  return nullptr;
+}
+
+Instruction *NaryReassociate::tryReassociatedAdd(const SCEV *LHSExpr,
+                                                 Value *RHS, Instruction *I) {
+  auto Pos = SeenExprs.find(LHSExpr);
+  // Bail out if LHSExpr is not previously seen.
+  if (Pos == SeenExprs.end())
+    return nullptr;
+
+  auto &LHSCandidates = Pos->second;
+  unsigned NumIterations = 0;
+  // Search at most 10 items to avoid running quadratically.
+  static const unsigned MaxNumIterations = 10;
+  for (auto LHS = LHSCandidates.rbegin();
+       LHS != LHSCandidates.rend() && NumIterations < MaxNumIterations;
+       ++LHS, ++NumIterations) {
+    if (DT->dominates(*LHS, I)) {
+      Instruction *NewI = BinaryOperator::CreateAdd(*LHS, RHS, "", I);
+      NewI->takeName(I);
+      return NewI;
+    }
+  }
+  return nullptr;
+}

lib/Transforms/Scalar/Scalar.cpp

@@ -59,6 +59,7 @@ void llvm::initializeScalarOpts(PassRegistry &Registry) {
   initializeLowerExpectIntrinsicPass(Registry);
   initializeMemCpyOptPass(Registry);
   initializeMergedLoadStoreMotionPass(Registry);
+  initializeNaryReassociatePass(Registry);
   initializePartiallyInlineLibCallsPass(Registry);
   initializeReassociatePass(Registry);
   initializeRegToMemPass(Registry);

test/Transforms/NaryReassociate/nary-add.ll

@@ -0,0 +1,127 @@
+; RUN: opt < %s -nary-reassociate -S | FileCheck %s
+
+target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
+
+declare void @foo(i32 %a)
+
+; foo(a + c);
+; foo((a + (b + c));
+;   =>
+; t = a + c;
+; foo(t);
+; foo(t + b);
+define void @left_reassociate(i32 %a, i32 %b, i32 %c) {
+; CHECK-LABEL: @left_reassociate(
+  %1 = add i32 %a, %c
+; CHECK: [[BASE:%[a-zA-Z0-9]+]] = add i32 %a, %c
+  call void @foo(i32 %1)
+  %2 = add i32 %b, %c
+  %3 = add i32 %a, %2
+; CHECK: add i32 [[BASE]], %b
+  call void @foo(i32 %3)
+  ret void
+}
+
+; foo(a + c);
+; foo((a + b) + c);
+;   =>
+; t = a + c;
+; foo(t);
+; foo(t + b);
+define void @right_reassociate(i32 %a, i32 %b, i32 %c) {
+; CHECK-LABEL: @right_reassociate(
+  %1 = add i32 %a, %c
+; CHECK: [[BASE:%[a-zA-Z0-9]+]] = add i32 %a, %c
+  call void @foo(i32 %1)
+  %2 = add i32 %a, %b
+  %3 = add i32 %2, %c
+; CHECK: add i32 [[BASE]], %b
+  call void @foo(i32 %3)
+  ret void
+}
+
+; t1 = a + c;
+; foo(t1);
+; t2 = a + b;
+; foo(t2);
+; t3 = t2 + c;
+; foo(t3);
+;
+; Do not rewrite t3 into t1 + b because t2 is used elsewhere and is likely free.
+define void @no_reassociate(i32 %a, i32 %b, i32 %c) {
+; CHECK-LABEL: @no_reassociate(
+  %1 = add i32 %a, %c
+; CHECK: add i32 %a, %c
+  call void @foo(i32 %1)
+  %2 = add i32 %a, %b
+; CHECK: add i32 %a, %b
+  call void @foo(i32 %2)
+  %3 = add i32 %2, %c
+; CHECK: add i32 %2, %c
+  call void @foo(i32 %3)
+  ret void
+}
+
+; if (p1)
+;   foo(a + c);
+; if (p2)
+;   foo(a + c);
+; if (p3)
+;   foo((a + b) + c);
+;
+; No action because (a + c) does not dominate ((a + b) + c).
+define void @conditional(i1 %p1, i1 %p2, i1 %p3, i32 %a, i32 %b, i32 %c) {
+; CHECK-LABEL: @conditional(
+entry:
+  br i1 %p1, label %then1, label %branch1
+
+then1:
+  %0 = add i32 %a, %c
+; CHECK: add i32 %a, %c
+  call void @foo(i32 %0)
+  br label %branch1
+
+branch1:
+  br i1 %p2, label %then2, label %branch2
+
+then2:
+  %1 = add i32 %a, %c
+; CHECK: add i32 %a, %c
+  call void @foo(i32 %1)
+  br label %branch2
+
+branch2:
+  br i1 %p3, label %then3, label %return
+
+then3:
+  %2 = add i32 %a, %b
+; CHECK: %2 = add i32 %a, %b
+  %3 = add i32 %2, %c
+; CHECK: add i32 %2, %c
+  call void @foo(i32 %3)
+  br label %return
+
+return:
+  ret void
+}
+
+; foo((a + b) + c)
+; foo(((a + d) + b) + c)
+;   =>
+; t = (a + b) + c;
+; foo(t);
+; foo(t + d);
+define void @quaternary(i32 %a, i32 %b, i32 %c, i32 %d) {
+; CHECK-LABEL: @quaternary(
+  %1 = add i32 %a, %b
+  %2 = add i32 %1, %c
+  call void @foo(i32 %2)
+; CHECK: call void @foo(i32 [[TMP1:%[a-zA-Z0-9]]])
+  %3 = add i32 %a, %d
+  %4 = add i32 %3, %b
+  %5 = add i32 %4, %c
+; CHECK: [[TMP2:%[a-zA-Z0-9]]] = add i32 [[TMP1]], %d
+  call void @foo(i32 %5)
+; CHECK: call void @foo(i32 [[TMP2]]
+  ret void
+}