diff options
| -rw-r--r-- | llvm/lib/CodeGen/CodeGenPrepare.cpp | 7 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/sink-gep-before-mem-inst.ll | 25 |
2 files changed, 30 insertions, 2 deletions
diff --git a/llvm/lib/CodeGen/CodeGenPrepare.cpp b/llvm/lib/CodeGen/CodeGenPrepare.cpp index b50e76f2e3b..9351f2dd46b 100644 --- a/llvm/lib/CodeGen/CodeGenPrepare.cpp +++ b/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; } diff --git a/llvm/test/CodeGen/X86/sink-gep-before-mem-inst.ll b/llvm/test/CodeGen/X86/sink-gep-before-mem-inst.ll new file mode 100644 index 00000000000..b9c94adda99 --- /dev/null +++ b/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 +} |
