Index: llvm/lib/Target/ARM/ARMFrameLowering.cpp =================================================================== --- llvm/lib/Target/ARM/ARMFrameLowering.cpp +++ llvm/lib/Target/ARM/ARMFrameLowering.cpp @@ -1503,8 +1503,12 @@ /// instructions will require a scratch register during their expansion later. // FIXME: Move to TII? static unsigned estimateRSStackSizeLimit(MachineFunction &MF, - const TargetFrameLowering *TFI) { + const TargetFrameLowering *TFI, + bool &HasNonSPFrameIndex) { const ARMFunctionInfo *AFI = MF.getInfo(); + const ARMBaseInstrInfo &TII = + *static_cast(MF.getSubtarget().getInstrInfo()); + const TargetRegisterInfo *TRI = MF.getSubtarget().getRegisterInfo(); unsigned Limit = (1 << 12) - 1; for (auto &MBB : MF) { for (auto &MI : MBB) { @@ -1519,6 +1523,11 @@ break; } + const MCInstrDesc &MCID = MI.getDesc(); + const TargetRegisterClass *RegClass = TII.getRegClass(MCID, i, TRI, MF); + if (RegClass && !RegClass->contains(ARM::SP)) + HasNonSPFrameIndex = true; + // Otherwise check the addressing mode. switch (MI.getDesc().TSFlags & ARMII::AddrModeMask) { case ARMII::AddrMode3: @@ -1541,6 +1550,15 @@ // Addressing modes 4 & 6 (load/store) instructions can't encode an // immediate offset for stack references. return 0; + case ARMII::AddrModeT2_i7: + Limit = std::min(Limit, ((1U << 7) - 1) * 1); + break; + case ARMII::AddrModeT2_i7s2: + Limit = std::min(Limit, ((1U << 7) - 1) * 2); + break; + case ARMII::AddrModeT2_i7s4: + Limit = std::min(Limit, ((1U << 7) - 1) * 4); + break; default: break; } @@ -1784,6 +1802,7 @@ EstimatedStackSize += 16; // For possible paddings. unsigned EstimatedRSStackSizeLimit, EstimatedRSFixedSizeLimit; + bool HasNonSPFrameIndex = false; if (AFI->isThumb1OnlyFunction()) { // For Thumb1, don't bother to iterate over the function. The only // instruction that requires an emergency spill slot is a store to a @@ -1804,7 +1823,8 @@ EstimatedRSStackSizeLimit = (1U << 8) * 4; EstimatedRSFixedSizeLimit = (1U << 5) * 4; } else { - EstimatedRSStackSizeLimit = estimateRSStackSizeLimit(MF, this); + EstimatedRSStackSizeLimit = + estimateRSStackSizeLimit(MF, this, HasNonSPFrameIndex); EstimatedRSFixedSizeLimit = EstimatedRSStackSizeLimit; } // Final estimate of whether sp or bp-relative accesses might require @@ -1830,12 +1850,11 @@ HasFP && (MaxFixedOffset - MaxFPOffset) > (int)EstimatedRSFixedSizeLimit; bool BigFrameOffsets = HasLargeStack || !HasBPOrFixedSP || - HasLargeArgumentList; + HasLargeArgumentList || HasNonSPFrameIndex; LLVM_DEBUG(dbgs() << "EstimatedLimit: " << EstimatedRSStackSizeLimit - << "; EstimatedStack" << EstimatedStackSize - << "; EstimatedFPStack" << MaxFixedOffset - MaxFPOffset - << "; BigFrameOffsets: " << BigFrameOffsets - << "\n"); + << "; EstimatedStack: " << EstimatedStackSize + << "; EstimatedFPStack: " << MaxFixedOffset - MaxFPOffset + << "; BigFrameOffsets: " << BigFrameOffsets << "\n"); if (BigFrameOffsets || !CanEliminateFrame || RegInfo->cannotEliminateFrame(MF)) { AFI->setHasStackFrame(true); Index: llvm/test/CodeGen/Thumb2/mve-stacksplot.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/Thumb2/mve-stacksplot.mir @@ -0,0 +1,91 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py +# RUN: llc -o - %s -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve.fp -run-pass=stack-protector -run-pass=prologepilog | FileCheck %s +--- +name: func0 +tracksRegLiveness: true +stack: + - { id: 0, name: '', type: default, offset: 0, size: 16, alignment: 4, + stack-id: default, callee-saved-register: '', callee-saved-restored: true, + local-offset: -16, debug-info-variable: '', debug-info-expression: '', + debug-info-location: '' } +body: | + bb.0: + ; CHECK-LABEL: name: func0 + ; CHECK: liveins: $r4, $r5, $r6, $r7, $r8, $r9, $r10, $r11, $lr + ; CHECK: $sp = frame-setup t2STMDB_UPD $sp, 14, $noreg, killed $r4, killed $r5, killed $r6, killed $r7, killed $r8, killed $r9, killed $r10, killed $r11, killed $lr + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 36 + ; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r11, -8 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r10, -12 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r9, -16 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r8, -20 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -24 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r6, -28 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r5, -32 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r4, -36 + ; CHECK: $sp = frame-setup tSUBspi $sp, 5, 14, $noreg + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 56 + ; CHECK: $r0 = IMPLICIT_DEF + ; CHECK: $r1 = IMPLICIT_DEF + ; CHECK: $r2 = IMPLICIT_DEF + ; CHECK: $r3 = IMPLICIT_DEF + ; CHECK: $r4 = IMPLICIT_DEF + ; CHECK: $r5 = IMPLICIT_DEF + ; CHECK: $r6 = IMPLICIT_DEF + ; CHECK: $r7 = IMPLICIT_DEF + ; CHECK: $r8 = IMPLICIT_DEF + ; CHECK: $r9 = IMPLICIT_DEF + ; CHECK: $r10 = IMPLICIT_DEF + ; CHECK: $r11 = IMPLICIT_DEF + ; CHECK: $r12 = IMPLICIT_DEF + ; CHECK: $lr = IMPLICIT_DEF + ; CHECK: t2STRi12 killed $r0, $sp, 0, 14, $noreg :: (store 4 into %stack.1) + ; CHECK: $r0 = tMOVr killed $sp, 14, $noreg + ; CHECK: renamable $q2 = MVE_VLDRBU32 killed $r0, 16, 0, $noreg :: (load 4 from %stack.0 + 12) + ; CHECK: $r0 = t2LDRi12 $sp, 0, 14, $noreg :: (load 4 from %stack.1) + ; CHECK: KILL $r0 + ; CHECK: KILL $r1 + ; CHECK: KILL $r2 + ; CHECK: KILL $r3 + ; CHECK: KILL $r4 + ; CHECK: KILL $r5 + ; CHECK: KILL $r6 + ; CHECK: KILL $r7 + ; CHECK: KILL $r8 + ; CHECK: KILL $r9 + ; CHECK: KILL $r10 + ; CHECK: KILL $r11 + ; CHECK: KILL $r12 + ; CHECK: KILL $lr + $r0 = IMPLICIT_DEF + $r1 = IMPLICIT_DEF + $r2 = IMPLICIT_DEF + $r3 = IMPLICIT_DEF + $r4 = IMPLICIT_DEF + $r5 = IMPLICIT_DEF + $r6 = IMPLICIT_DEF + $r7 = IMPLICIT_DEF + $r8 = IMPLICIT_DEF + $r9 = IMPLICIT_DEF + $r10 = IMPLICIT_DEF + $r11 = IMPLICIT_DEF + $r12 = IMPLICIT_DEF + $lr = IMPLICIT_DEF + + renamable $q2 = MVE_VLDRBU32 %stack.0, 12, 0, $noreg :: (load 4 from %stack.0 + 12) + + KILL $r0 + KILL $r1 + KILL $r2 + KILL $r3 + KILL $r4 + KILL $r5 + KILL $r6 + KILL $r7 + KILL $r8 + KILL $r9 + KILL $r10 + KILL $r11 + KILL $r12 + KILL $lr +...