At -O123 the early-cse pass is run before instcombine has run. According to my

auto-simplier the transform most missed by early-cse is (zext X) != 0 -> X != 0.
This patch adds this transform and some related logic to InstructionSimplify
and removes some of the logic from instcombine (unfortunately not all because
there are several situations in which instcombine can improve things by making
new instructions, whereas instsimplify is not allowed to do this).  At -O2 this
often results in more than 15% more simplifications by early-cse, and results in
hundreds of lines of bitcode being eliminated from the testsuite.  I did see some
small negative effects in the testsuite, for example a few additional instructions
in three programs.  One program, 483.xalancbmk, got an additional 35 instructions,
which seems to be due to a function getting an additional instruction and then
being inlined all over the place.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123911 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 162 insertions, 0 deletions

diff --git a/lib/Analysis/InstructionSimplify.cpp b/lib/Analysis/InstructionSimplify.cpp
index 7935a2fb04..0cbaea3f93 100644
--- a/lib/Analysis/InstructionSimplify.cpp
+++ b/lib/Analysis/InstructionSimplify.cpp
@@ -1203,6 +1203,168 @@ static Value *SimplifyICmpInst(unsigned Predicate, Value *LHS, Value *RHS,
     // We already know that LHS != LHS.
     return ConstantInt::get(ITy, CmpInst::isFalseWhenEqual(Pred));
 
+  // Compare of cast, for example (zext X) != 0 -> X != 0
+  if (isa<CastInst>(LHS) && (isa<Constant>(RHS) || isa<CastInst>(RHS))) {
+    Instruction *LI = cast<CastInst>(LHS);
+    Value *SrcOp = LI->getOperand(0);
+    const Type *SrcTy = SrcOp->getType();
+    const Type *DstTy = LI->getType();
+
+    // Turn icmp (ptrtoint x), (ptrtoint/constant) into a compare of the input
+    // if the integer type is the same size as the pointer type.
+    if (MaxRecurse && TD && isa<PtrToIntInst>(LI) &&
+        TD->getPointerSizeInBits() == DstTy->getPrimitiveSizeInBits()) {
+      if (Constant *RHSC = dyn_cast<Constant>(RHS)) {
+        // Transfer the cast to the constant.
+        if (Value *V = SimplifyICmpInst(Pred, SrcOp,
+                                        ConstantExpr::getIntToPtr(RHSC, SrcTy),
+                                        TD, DT, MaxRecurse-1))
+          return V;
+      } else if (PtrToIntInst *RI = dyn_cast<PtrToIntInst>(RHS)) {
+        if (RI->getOperand(0)->getType() == SrcTy)
+          // Compare without the cast.
+          if (Value *V = SimplifyICmpInst(Pred, SrcOp, RI->getOperand(0),
+                                          TD, DT, MaxRecurse-1))
+            return V;
+      }
+    }
+
+    if (isa<ZExtInst>(LHS)) {
+      // Turn icmp (zext X), (zext Y) into a compare of X and Y if they have the
+      // same type.
+      if (ZExtInst *RI = dyn_cast<ZExtInst>(RHS)) {
+        if (MaxRecurse && SrcTy == RI->getOperand(0)->getType())
+          // Compare X and Y.  Note that signed predicates become unsigned.
+          if (Value *V = SimplifyICmpInst(ICmpInst::getUnsignedPredicate(Pred),
+                                          SrcOp, RI->getOperand(0), TD, DT,
+                                          MaxRecurse-1))
+            return V;
+      }
+      // Turn icmp (zext X), Cst into a compare of X and Cst if Cst is extended
+      // too.  If not, then try to deduce the result of the comparison.
+      else if (ConstantInt *CI = dyn_cast<ConstantInt>(RHS)) {
+        // Compute the constant that would happen if we truncated to SrcTy then
+        // reextended to DstTy.
+        Constant *Trunc = ConstantExpr::getTrunc(CI, SrcTy);
+        Constant *RExt = ConstantExpr::getCast(CastInst::ZExt, Trunc, DstTy);
+
+        // If the re-extended constant didn't change then this is effectively
+        // also a case of comparing two zero-extended values.
+        if (RExt == CI && MaxRecurse)
+          if (Value *V = SimplifyICmpInst(ICmpInst::getUnsignedPredicate(Pred),
+                                          SrcOp, Trunc, TD, DT, MaxRecurse-1))
+            return V;
+
+        // Otherwise the upper bits of LHS are zero while RHS has a non-zero bit
+        // there.  Use this to work out the result of the comparison.
+        if (RExt != CI) {
+          switch (Pred) {
+          default:
+            assert(false && "Unknown ICmp predicate!");
+          // LHS <u RHS.
+          case ICmpInst::ICMP_EQ:
+          case ICmpInst::ICMP_UGT:
+          case ICmpInst::ICMP_UGE:
+            return ConstantInt::getFalse(CI->getContext());
+
+          case ICmpInst::ICMP_NE:
+          case ICmpInst::ICMP_ULT:
+          case ICmpInst::ICMP_ULE:
+            return ConstantInt::getTrue(CI->getContext());
+
+          // LHS is non-negative.  If RHS is negative then LHS >s LHS.  If RHS
+          // is non-negative then LHS <s RHS.
+          case ICmpInst::ICMP_SGT:
+          case ICmpInst::ICMP_SGE:
+            return CI->getValue().isNegative() ?
+              ConstantInt::getTrue(CI->getContext()) :
+              ConstantInt::getFalse(CI->getContext());
+
+          case ICmpInst::ICMP_SLT:
+          case ICmpInst::ICMP_SLE:
+            return CI->getValue().isNegative() ?
+              ConstantInt::getFalse(CI->getContext()) :
+              ConstantInt::getTrue(CI->getContext());
+          }
+        }
+      }
+    }
+
+    if (isa<SExtInst>(LHS)) {
+      // Turn icmp (sext X), (sext Y) into a compare of X and Y if they have the
+      // same type.
+      if (SExtInst *RI = dyn_cast<SExtInst>(RHS)) {
+        if (MaxRecurse && SrcTy == RI->getOperand(0)->getType())
+          // Compare X and Y.  Note that the predicate does not change.
+          if (Value *V = SimplifyICmpInst(Pred, SrcOp, RI->getOperand(0),
+                                          TD, DT, MaxRecurse-1))
+            return V;
+      }
+      // Turn icmp (sext X), Cst into a compare of X and Cst if Cst is extended
+      // too.  If not, then try to deduce the result of the comparison.
+      else if (ConstantInt *CI = dyn_cast<ConstantInt>(RHS)) {
+        // Compute the constant that would happen if we truncated to SrcTy then
+        // reextended to DstTy.
+        Constant *Trunc = ConstantExpr::getTrunc(CI, SrcTy);
+        Constant *RExt = ConstantExpr::getCast(CastInst::SExt, Trunc, DstTy);
+
+        // If the re-extended constant didn't change then this is effectively
+        // also a case of comparing two sign-extended values.
+        if (RExt == CI && MaxRecurse)
+          if (Value *V = SimplifyICmpInst(Pred, SrcOp, Trunc, TD, DT,
+                                          MaxRecurse-1))
+            return V;
+
+        // Otherwise the upper bits of LHS are all equal, while RHS has varying
+        // bits there.  Use this to work out the result of the comparison.
+        if (RExt != CI) {
+          switch (Pred) {
+          default:
+            assert(false && "Unknown ICmp predicate!");
+          case ICmpInst::ICMP_EQ:
+            return ConstantInt::getFalse(CI->getContext());
+          case ICmpInst::ICMP_NE:
+            return ConstantInt::getTrue(CI->getContext());
+
+          // If RHS is non-negative then LHS <s RHS.  If RHS is negative then
+          // LHS >s RHS.
+          case ICmpInst::ICMP_SGT:
+          case ICmpInst::ICMP_SGE:
+            return CI->getValue().isNegative() ?
+              ConstantInt::getTrue(CI->getContext()) :
+              ConstantInt::getFalse(CI->getContext());
+          case ICmpInst::ICMP_SLT:
+          case ICmpInst::ICMP_SLE:
+            return CI->getValue().isNegative() ?
+              ConstantInt::getFalse(CI->getContext()) :
+              ConstantInt::getTrue(CI->getContext());
+
+          // If LHS is non-negative then LHS <u RHS.  If LHS is negative then
+          // LHS >u RHS.
+          case ICmpInst::ICMP_UGT:
+          case ICmpInst::ICMP_UGE:
+            // Comparison is true iff the LHS <s 0.
+            if (MaxRecurse)
+              if (Value *V = SimplifyICmpInst(ICmpInst::ICMP_SLT, SrcOp,
+                                              Constant::getNullValue(SrcTy),
+                                              TD, DT, MaxRecurse-1))
+                return V;
+            break;
+          case ICmpInst::ICMP_ULT:
+          case ICmpInst::ICMP_ULE:
+            // Comparison is true iff the LHS >=s 0.
+            if (MaxRecurse)
+              if (Value *V = SimplifyICmpInst(ICmpInst::ICMP_SGE, SrcOp,
+                                              Constant::getNullValue(SrcTy),
+                                              TD, DT, MaxRecurse-1))
+                return V;
+            break;
+          }
+        }
+      }
+    }
+  }
+
   // If the comparison is with the result of a select instruction, check whether
   // comparing with either branch of the select always yields the same value.
   if (isa<SelectInst>(LHS) || isa<SelectInst>(RHS))