[CGP] Relax a bit restriction for optimizeMemoryInst to extend scope

CodeGenPrepare::optimizeMemoryInst contains a check that we do nothing
if all instructions combining the address for memory instruction is in the same
block as memory instruction itself.

However if any of these instruction are placed after memory instruction then
address calculation will not be folded to memory instruction.

The added test case shows an example.

Reviewers: loladiro, spatel, efriedma
Reviewed By: efriedma
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D34862

llvm-svn: 307628

llvm/lib/CodeGen/CodeGenPrepare.cpp

@@ -4270,6 +4270,7 @@ bool CodeGenPrepare::optimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
   Value *Consensus = nullptr;
   unsigned NumUsesConsensus = 0;
   bool IsNumUsesConsensusValid = false;
+  bool PhiSeen = false;
   SmallVector<Instruction*, 16> AddrModeInsts;
   ExtAddrMode AddrMode;
   TypePromotionTransaction TPT(RemovedInsts);
@@ -4289,6 +4290,7 @@ bool CodeGenPrepare::optimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
     if (PHINode *P = dyn_cast<PHINode>(V)) {
       for (Value *IncValue : P->incoming_values())
         worklist.push_back(IncValue);
+      PhiSeen = true;
       continue;
     }
 
@@ -4342,9 +4344,10 @@ bool CodeGenPrepare::optimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
   TPT.commit();
 
   // If all the instructions matched are already in this BB, don't do anything.
-  if (none_of(AddrModeInsts, [&](Value *V) {
+  // If we saw Phi node then it is not local definitely.
+  if (!PhiSeen && none_of(AddrModeInsts, [&](Value *V) {
         return IsNonLocalValue(V, MemoryInst->getParent());
-      })) {
+                  })) {
     DEBUG(dbgs() << "CGP: Found      local addrmode: " << AddrMode << "\n");
     return false;
   }

llvm/test/CodeGen/X86/sink-gep-before-mem-inst.ll

@@ -0,0 +1,25 @@
+; RUN: opt < %s -S -codegenprepare -mtriple=x86_64-unknown-linux-gnu | FileCheck %s
+
+define i64 @test.after(i8 addrspace(1)* readonly align 8) {
+; CHECK-LABEL: test.after
+; CHECK: sunkaddr
+entry:
+  %.0 = getelementptr inbounds i8, i8 addrspace(1)* %0, i64 8
+  %addr = bitcast i8 addrspace(1)* %.0 to i32 addrspace(1)*
+  br label %header
+
+header:
+  %addr.in.loop = phi i32 addrspace(1)* [ %addr, %entry ], [ %addr.after, %header ]
+  %local_2_ = phi i64 [ 0, %entry ], [ %.9, %header ]
+  %.7 = load i32, i32 addrspace(1)* %addr.in.loop, align 8
+  fence acquire
+  %.1 = getelementptr inbounds i8, i8 addrspace(1)* %0, i64 8
+  %addr.after = bitcast i8 addrspace(1)* %.1 to i32 addrspace(1)*
+  %.8 = sext i32 %.7 to i64
+  %.9 = add i64 %local_2_, %.8
+  %not. = icmp sgt i64 %.9, 999
+  br i1 %not., label %exit, label %header
+
+exit:
+  ret i64 %.9
+}