[llvm] r303212 - The patch exclude a case from zero check skip in

[Evgeny Stupachenko via llvm-commits]

Author: evstupac
Date: Tue May 16 16:44:59 2017
New Revision: 303212

URL: http://llvm.org/viewvc/llvm-project?rev=303212&view=rev
Log:
The patch exclude a case from zero check skip in
 CTLZ idiom recognition (r303102).

Summary:

The following case:
i = 1;
if(n)
  while (n >>= 1)
    i++;
use(i);

Was converted to:

i = 1;
if(n)
  i += builtin_ctlz(n >> 1, false);
use(i);

Which is not correct. The patch make it:

i = 1;
if(n)
  i += builtin_ctlz(n >> 1, true);
use(i);

From: Evgeny Stupachenko <evstupac at gmail.com>

Modified:
    llvm/trunk/lib/Transforms/Scalar/LoopIdiomRecognize.cpp

Modified: llvm/trunk/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Scalar/LoopIdiomRecognize.cpp?rev=303212&r1=303211&r2=303212&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Scalar/LoopIdiomRecognize.cpp (original)
+++ llvm/trunk/lib/Transforms/Scalar/LoopIdiomRecognize.cpp Tue May 16 16:44:59 2017
@@ -1292,13 +1292,15 @@ bool LoopIdiomRecognize::recognizeAndIns
   BasicBlock *PH = CurLoop->getLoopPreheader();
   Value *InitX = PhiX->getIncomingValueForBlock(PH);
   // If we check X != 0 before entering the loop we don't need a zero
-  // check in CTLZ intrinsic.
-  if (BasicBlock *PreCondBB = PH->getSinglePredecessor())
-    if (BranchInst *PreCondBr =
-        dyn_cast<BranchInst>(PreCondBB->getTerminator())) {
-      if (matchCondition(PreCondBr, PH) == InitX)
-        ZeroCheck = true;
-    }
+  // check in CTLZ intrinsic, but only if Cnt Phi is not used outside of the
+  // loop (if it is used we count CTLZ(X >> 1)).
+  if (!IsCntPhiUsedOutsideLoop)
+    if (BasicBlock *PreCondBB = PH->getSinglePredecessor())
+      if (BranchInst *PreCondBr =
+          dyn_cast<BranchInst>(PreCondBB->getTerminator())) {
+        if (matchCondition(PreCondBr, PH) == InitX)
+          ZeroCheck = true;
+      }
 
   // Check if CTLZ intrinsic is profitable. Assume it is always profitable
   // if we delete the loop (the loop has only 6 instructions):