Index: llvm/lib/Target/AArch64/AArch64RegisterInfo.h =================================================================== --- llvm/lib/Target/AArch64/AArch64RegisterInfo.h +++ llvm/lib/Target/AArch64/AArch64RegisterInfo.h @@ -125,6 +125,12 @@ unsigned getLocalAddressRegister(const MachineFunction &MF) const; bool regNeedsCFI(unsigned Reg, unsigned &RegToUseForCFI) const; + + /// SrcRC and DstRC will be morphed into NewRC if this returns true + bool shouldCoalesce(MachineInstr *MI, const TargetRegisterClass *SrcRC, + unsigned SubReg, const TargetRegisterClass *DstRC, + unsigned DstSubReg, const TargetRegisterClass *NewRC, + LiveIntervals &LIS) const override; }; } // end namespace llvm Index: llvm/lib/Target/AArch64/AArch64RegisterInfo.cpp =================================================================== --- llvm/lib/Target/AArch64/AArch64RegisterInfo.cpp +++ llvm/lib/Target/AArch64/AArch64RegisterInfo.cpp @@ -726,3 +726,14 @@ return getBaseRegister(); return getFrameRegister(MF); } + +/// SrcRC and DstRC will be morphed into NewRC if this returns true +bool AArch64RegisterInfo::shouldCoalesce( + MachineInstr *MI, const TargetRegisterClass *SrcRC, unsigned SubReg, + const TargetRegisterClass *DstRC, unsigned DstSubReg, + const TargetRegisterClass *NewRC, LiveIntervals &LIS) const { + if (MI->isCopy() && (DstRC->getID() == AArch64::GPR64RegClassID) && + (SrcRC == DstRC) && MI->getOperand(0).getSubReg()) + return false; + return true; +} Index: llvm/test/CodeGen/AArch64/zext-reg-coalesce.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/AArch64/zext-reg-coalesce.mir @@ -0,0 +1,38 @@ +# RUN: llc -mtriple=aarch64-arm-none-eabi -O1 -o - %s \ +# RUN: -run-pass simple-register-coalescing | FileCheck %s + +--- | + @c = local_unnamed_addr global i8 -1, align 4 + + define i64 @bug_e(i32 %i32) local_unnamed_addr { + ret i64 0 + } +... +--- +name: bug_e +tracksRegLiveness: true +body: | + bb.0: + liveins: $w0 + + %1:gpr32 = COPY $w0 + %2:gpr64common = ADRP target-flags(aarch64-page) @c + %3:gpr64 = LDRSBXui %2, target-flags(aarch64-pageoff, aarch64-nc) @c :: (dereferenceable load 1 from @c, align 4) + %0:gpr32 = COPY %3.sub_32 + ; CHECK: {{.*}}.sub_32:gpr64 = COPY {{.*}}.sub_32 + + %4:gpr32 = ANDWrr %0, %1 + %5:gpr64 = SUBREG_TO_REG 0, killed %4, %subreg.sub_32 + %6:gpr64 = SUBSXrr %3, killed %5, implicit-def $nzcv + Bcc 1, %bb.2, implicit $nzcv + B %bb.1 + + bb.1: + STRBBui %1, %2, target-flags(aarch64-pageoff, aarch64-nc) @c :: (store 1 into @c, align 4) + + bb.2: + %8:gpr64all = SUBREG_TO_REG 0, %0, %subreg.sub_32 + $x0 = COPY %8 + ; CHECK: $x0 = COPY + RET_ReallyLR implicit $x0 +...