[AlignmentFromAssumptions] Set source and dest alignments of memory intrinsiscs separately

[dneilson]

Summary

This change is part of step five in the series of changes to remove alignment argument from
memcpy/memmove/memset in favour of alignment attributes. In particular, this changes the
AlignmentFromAssumptions pass to cease using the old getAlignment()/setAlignment API of
MemoryIntrinsic in favour of getting/setting source & dest specific alignments through
the new API. This allows us to simplify some of the code in this pass and also be more
aggressive about setting the source and destination alignments separately.

Steps:
Step 1) Remove alignment parameter and create alignment parameter attributes for
memcpy/memmove/memset. ( rL322965, rC322964, rL322963 )
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
source and dest alignments. ( rL323597 )
Step 3) Update Clang to use the new IRBuilder API. ( rC323617 )
Step 4) Update Polly to use the new IRBuilder API. ( rL323618 )
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
and those that use use MemIntrinsicInst::[get|set]Alignment() to use [get|set]DestAlignment()
and [get|set]SourceAlignment() instead. ( rL323886, rL323891, rL324148, rL324273, rL324278,
rL324384, rL324395, rL324402, rL324626 )
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
MemIntrinsicInst::[get|set]Alignment() methods.

Reference

http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html

[dneilson]

@hfinkel I hope that you don't mind being added as a reviewer; it looks like you're the original author of much of the memory intrinsic handling in this pass.

[dneilson]

ping

[reames]

LGTM provided that the backend changes to take the min of the two have already landed.

llvm/trunk/include/llvm/Transforms/Scalar/AlignmentFromAssumptions.h

 struct AlignmentFromAssumptionsPass
     : public PassInfoMixin<AlignmentFromAssumptionsPass> {
   PreservedAnalyses run(Function &F, FunctionAnalysisManager &AM);
 
   // Glue for old PM.
   bool runImpl(Function &F, AssumptionCache &AC, ScalarEvolution *SE_,
                DominatorTree *DT_);
 
-  // For memory transfers, we need a common alignment for both the source and
-  // destination. If we have a new alignment for only one operand of a transfer
-  // instruction, save it in these maps.  If we reach the other operand through
-  // another assumption later, then we may change the alignment at that point.
-  DenseMap<MemTransferInst *, unsigned> NewDestAlignments, NewSrcAlignments;
-
   ScalarEvolution *SE = nullptr;
   DominatorTree *DT = nullptr;
 
   bool extractAlignmentInfo(CallInst *I, Value *&AAPtr, const SCEV *&AlignSCEV,
                             const SCEV *&OffSCEV);
   bool processAssumption(CallInst *I);
 };
 }
 
 #endif // LLVM_TRANSFORMS_SCALAR_ALIGNMENTFROMASSUMPTIONS_H

llvm/trunk/lib/Transforms/Scalar/AlignmentFromAssumptions.cpp

if (LoadInst *LI = dyn_cast<LoadInst>(J)) {
       if (NewAlignment > SI->getAlignment()) {
         SI->setAlignment(NewAlignment);
         ++NumStoreAlignChanged;
       }
     } else if (MemIntrinsic *MI = dyn_cast<MemIntrinsic>(J)) {
       unsigned NewDestAlignment = getNewAlignment(AASCEV, AlignSCEV, OffSCEV,
         MI->getDest(), SE);
 
-      // For memory transfers, we need a common alignment for both the
-      // source and destination. If we have a new alignment for this
-      // instruction, but only for one operand, save it. If we reach the
-      // other operand through another assumption later, then we may
-      // change the alignment at that point.
+      DEBUG(dbgs() << "\tmem inst: " << NewDestAlignment << "\n";);
+      if (NewDestAlignment > MI->getDestAlignment()) {
+        MI->setDestAlignment(NewDestAlignment);
+        ++NumMemIntAlignChanged;
+      }
+
+      // For memory transfers, there is also a source alignment that
+      // can be set.
       if (MemTransferInst *MTI = dyn_cast<MemTransferInst>(MI)) {
         unsigned NewSrcAlignment = getNewAlignment(AASCEV, AlignSCEV, OffSCEV,
           MTI->getSource(), SE);
 
-        DenseMap<MemTransferInst *, unsigned>::iterator DI =
-          NewDestAlignments.find(MTI);
-        unsigned AltDestAlignment = (DI == NewDestAlignments.end()) ?
-                                    0 : DI->second;
-
-        DenseMap<MemTransferInst *, unsigned>::iterator SI =
-          NewSrcAlignments.find(MTI);
-        unsigned AltSrcAlignment = (SI == NewSrcAlignments.end()) ?
-                                   0 : SI->second;
-
-        DEBUG(dbgs() << "\tmem trans: " << NewDestAlignment << " " <<
-                        AltDestAlignment << " " << NewSrcAlignment <<
-                        " " << AltSrcAlignment << "\n");
-
-        // Of these four alignments, pick the largest possible...
-        unsigned NewAlignment = 0;
-        if (NewDestAlignment <= std::max(NewSrcAlignment, AltSrcAlignment))
-          NewAlignment = std::max(NewAlignment, NewDestAlignment);
-        if (AltDestAlignment <= std::max(NewSrcAlignment, AltSrcAlignment))
-          NewAlignment = std::max(NewAlignment, AltDestAlignment);
-        if (NewSrcAlignment <= std::max(NewDestAlignment, AltDestAlignment))
-          NewAlignment = std::max(NewAlignment, NewSrcAlignment);
-        if (AltSrcAlignment <= std::max(NewDestAlignment, AltDestAlignment))
-          NewAlignment = std::max(NewAlignment, AltSrcAlignment);
+        DEBUG(dbgs() << "\tmem trans: " << NewSrcAlignment << "\n";);
 
-        if (NewAlignment > MI->getAlignment()) {
-          MI->setAlignment(NewAlignment);
+        if (NewSrcAlignment > MTI->getSourceAlignment()) {
+          MTI->setSourceAlignment(NewSrcAlignment);
           ++NumMemIntAlignChanged;
         }
-
-        NewDestAlignments.insert(std::make_pair(MTI, NewDestAlignment));
-        NewSrcAlignments.insert(std::make_pair(MTI, NewSrcAlignment));
-      } else if (NewDestAlignment > MI->getAlignment()) {
-        assert((!isa<MemIntrinsic>(MI) || isa<MemSetInst>(MI)) &&
-               "Unknown memory intrinsic");
-
-        MI->setAlignment(NewDestAlignment);
-        ++NumMemIntAlignChanged;
       }
     }
 
     // Now that we've updated that use of the pointer, look for other uses of
     // the pointer to update.
     Visited.insert(J);
     for (User *UJ : J->users()) {
       Instruction *K = cast<Instruction>(UJ);

 }
 
 bool AlignmentFromAssumptionsPass::runImpl(Function &F, AssumptionCache &AC,
                                            ScalarEvolution *SE_,
                                            DominatorTree *DT_) {
   SE = SE_;
   DT = DT_;
 
-  NewDestAlignments.clear();
-  NewSrcAlignments.clear();
-
   bool Changed = false;
   for (auto &AssumeVH : AC.assumptions())
     if (AssumeVH)
       Changed |= processAssumption(cast<CallInst>(AssumeVH));
 
   return Changed;
 }
 

llvm/trunk/test/Transforms/AlignmentFromAssumptions/simple.ll

entry:
   %maskcond4 = icmp eq i64 %maskedptr3, 0
   tail call void @llvm.assume(i1 %maskcond4)
   %0 = bitcast i32* %a to i8*
   %1 = bitcast i32* %b to i8*
   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 64, i1 false)
   ret i32 undef
 
 ; CHECK-LABEL: @moo2
-; CHECK: @llvm.memcpy.p0i8.p0i8.i64(i8* align 32 %0, i8* align 32 %1, i64 64, i1 false)
+; CHECK: @llvm.memcpy.p0i8.p0i8.i64(i8* align 32 %0, i8* align 128 %1, i64 64, i1 false)
 ; CHECK: ret i32 undef
 }
 
 declare void @llvm.assume(i1) nounwind
 
 declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
 declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
 

llvm/trunk/test/Transforms/AlignmentFromAssumptions/simple32.ll

entry:
   %maskcond4 = icmp eq i64 %maskedptr3, 0
   tail call void @llvm.assume(i1 %maskcond4)
   %0 = bitcast i32* %a to i8*
   %1 = bitcast i32* %b to i8*
   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 64, i1 false)
   ret i32 undef
 
 ; CHECK-LABEL: @moo2
-; CHECK: @llvm.memcpy.p0i8.p0i8.i64(i8* align 32 %0, i8* align 32 %1, i64 64, i1 false)
+; CHECK: @llvm.memcpy.p0i8.p0i8.i64(i8* align 32 %0, i8* align 128 %1, i64 64, i1 false)
 ; CHECK: ret i32 undef
 }
 
 declare void @llvm.assume(i1) nounwind
 
 declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
 declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind