[llvm-commits] [llvm] r134520 - in /llvm/trunk: lib/Transforms/Scalar/LICM.cpp test/Transforms/LICM/2011-07-06-Alignment.ll

[Tobias Grosser]

Author: grosser
Date: Wed Jul  6 14:19:55 2011
New Revision: 134520

URL: http://llvm.org/viewvc/llvm-project?rev=134520&view=rev
Log:
LICM: Do not loose alignment on promotion

The promotion code lost any alignment information, when hoisting loads and
stores out of the loop. This lead to incorrect aligned memory accesses. We now
use the largest alignment we can prove to be correct.

Added:
    llvm/trunk/test/Transforms/LICM/2011-07-06-Alignment.ll
Modified:
    llvm/trunk/lib/Transforms/Scalar/LICM.cpp

Modified: llvm/trunk/lib/Transforms/Scalar/LICM.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Scalar/LICM.cpp?rev=134520&r1=134519&r2=134520&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Scalar/LICM.cpp (original)
+++ llvm/trunk/lib/Transforms/Scalar/LICM.cpp Wed Jul  6 14:19:55 2011
@@ -606,14 +606,16 @@
     SmallVectorImpl<BasicBlock*> &LoopExitBlocks;
     AliasSetTracker &AST;
     DebugLoc DL;
+    int Alignment;
   public:
     LoopPromoter(Value *SP,
                  const SmallVectorImpl<Instruction*> &Insts, SSAUpdater &S,
                  SmallPtrSet<Value*, 4> &PMA,
                  SmallVectorImpl<BasicBlock*> &LEB, AliasSetTracker &ast,
-                 DebugLoc dl)
+                 DebugLoc dl, int alignment)
       : LoadAndStorePromoter(Insts, S, 0, 0), SomePtr(SP),
-        PointerMustAliases(PMA), LoopExitBlocks(LEB), AST(ast), DL(dl) {}
+        PointerMustAliases(PMA), LoopExitBlocks(LEB), AST(ast), DL(dl),
+        Alignment(alignment) {}
     
     virtual bool isInstInList(Instruction *I,
                               const SmallVectorImpl<Instruction*> &) const {
@@ -635,6 +637,7 @@
         Value *LiveInValue = SSA.GetValueInMiddleOfBlock(ExitBlock);
         Instruction *InsertPos = ExitBlock->getFirstNonPHI();
         StoreInst *NewSI = new StoreInst(LiveInValue, SomePtr, InsertPos);
+        NewSI->setAlignment(Alignment);
         NewSI->setDebugLoc(DL);
       }
     }
@@ -680,10 +683,14 @@
   // It is safe to promote P if all uses are direct load/stores and if at
   // least one is guaranteed to be executed.
   bool GuaranteedToExecute = false;
-  
+
   SmallVector<Instruction*, 64> LoopUses;
   SmallPtrSet<Value*, 4> PointerMustAliases;
 
+  // We start with an alignment of one and try to find instructions that allow
+  // us to prove better alignment.
+  unsigned Alignment = 1;
+
   // Check that all of the pointers in the alias set have the same type.  We
   // cannot (yet) promote a memory location that is loaded and stored in
   // different sizes.
@@ -706,24 +713,38 @@
       
       // If there is an non-load/store instruction in the loop, we can't promote
       // it.
-      if (isa<LoadInst>(Use))
+      unsigned InstAlignment;
+      if (LoadInst *load = dyn_cast<LoadInst>(Use)) {
         assert(!cast<LoadInst>(Use)->isVolatile() && "AST broken");
-      else if (isa<StoreInst>(Use)) {
+        InstAlignment = load->getAlignment();
+      } else if (StoreInst *store = dyn_cast<StoreInst>(Use)) {
         // Stores *of* the pointer are not interesting, only stores *to* the
         // pointer.
         if (Use->getOperand(1) != ASIV)
           continue;
+        InstAlignment = store->getAlignment();
         assert(!cast<StoreInst>(Use)->isVolatile() && "AST broken");
       } else
         return; // Not a load or store.
-      
+
+      // If the alignment of this instruction allows us to specify a more
+      // restrictive (and performant) alignment and if we are sure this
+      // instruction will be executed, update the alignment.
+      // Larger is better, with the exception of 0 being the best alignment.
+      if ((InstAlignment > Alignment || InstAlignment == 0)
+          && (Alignment != 0))
+        if (isSafeToExecuteUnconditionally(*Use)) {
+          GuaranteedToExecute = true;
+          Alignment = InstAlignment;
+        }
+
       if (!GuaranteedToExecute)
         GuaranteedToExecute = isSafeToExecuteUnconditionally(*Use);
       
       LoopUses.push_back(Use);
     }
   }
-  
+
   // If there isn't a guaranteed-to-execute instruction, we can't promote.
   if (!GuaranteedToExecute)
     return;
@@ -746,13 +767,14 @@
   SmallVector<PHINode*, 16> NewPHIs;
   SSAUpdater SSA(&NewPHIs);
   LoopPromoter Promoter(SomePtr, LoopUses, SSA, PointerMustAliases, ExitBlocks,
-                        *CurAST, DL);
+                        *CurAST, DL, Alignment);
   
   // Set up the preheader to have a definition of the value.  It is the live-out
   // value from the preheader that uses in the loop will use.
   LoadInst *PreheaderLoad =
     new LoadInst(SomePtr, SomePtr->getName()+".promoted",
                  Preheader->getTerminator());
+  PreheaderLoad->setAlignment(Alignment);
   PreheaderLoad->setDebugLoc(DL);
   SSA.AddAvailableValue(Preheader, PreheaderLoad);
 

Added: llvm/trunk/test/Transforms/LICM/2011-07-06-Alignment.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LICM/2011-07-06-Alignment.ll?rev=134520&view=auto
==============================================================================
--- llvm/trunk/test/Transforms/LICM/2011-07-06-Alignment.ll (added)
+++ llvm/trunk/test/Transforms/LICM/2011-07-06-Alignment.ll Wed Jul  6 14:19:55 2011
@@ -0,0 +1,26 @@
+; RUN: opt -licm -S %s | FileCheck %s
+
+ at A = common global [1024 x float] zeroinitializer, align 4
+
+define i32 @main() nounwind {
+entry:
+  br label %for.cond
+
+for.cond:
+  %indvar = phi i64 [ %indvar.next, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr [1024 x float]* @A, i64 0, i64 3
+  %vecidx = bitcast float* %arrayidx to <4 x float>*
+  store <4 x float> zeroinitializer, <4 x float>* %vecidx, align 4
+  %indvar.next = add i64 %indvar, 1
+  %exitcond = icmp ne i64 %indvar, 1024
+  br i1 %exitcond, label %for.body, label %for.end
+
+for.body:
+  br label %for.cond
+
+for.end:
+  ret i32 0
+}
+
+;CHECK: store <4 x float> {{.*}} align 4
+