Index: llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp =================================================================== --- llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp +++ llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp @@ -178,6 +178,7 @@ MachineLoop &ML; MachineLoopInfo &MLI; ReachingDefAnalysis &RDA; + const TargetRegisterInfo &TRI; MachineFunction *MF = nullptr; MachineInstr *InsertPt = nullptr; MachineInstr *Start = nullptr; @@ -192,7 +193,8 @@ bool CannotTailPredicate = false; LowOverheadLoop(MachineLoop &ML, MachineLoopInfo &MLI, - ReachingDefAnalysis &RDA) : ML(ML), MLI(MLI), RDA(RDA) { + ReachingDefAnalysis &RDA, const TargetRegisterInfo &TRI) + : ML(ML), MLI(MLI), RDA(RDA), TRI(TRI) { MF = ML.getHeader()->getParent(); } @@ -619,8 +621,28 @@ return false; } + // If the instruction is already explicitly predicated, then the conversion + // will be fine. + if (IsUse) + return true; + // Ensure that all memory operations are predicated. - return !IsUse && MI->mayLoadOrStore() ? false : true; + if (MI->mayLoadOrStore()) + return false; + + // If the instruction isn't predicated, then check that no q-regs are live + // outside the loop since. If the last iteration has lanes predicated, it may + // not necessarily match the semantics of the uses in the exit blocks. + const TargetRegisterClass *QPRs = TRI.getRegClass(ARM::MQPRRegClassID); + SmallVector LiveOuts; + for (auto &MO : MI->operands()) { + if (!MO.isReg() || MO.getReg() == 0 || !QPRs->contains(MO.getReg())) + continue; + else if (MO.isDef() && isRegLiveInExitBlocks(&ML, MO.getReg())) + LiveOuts.push_back(MO.getReg()); + } + + return LiveOuts.empty(); } bool ARMLowOverheadLoops::runOnMachineFunction(MachineFunction &mf) { @@ -682,7 +704,7 @@ return nullptr; }; - LowOverheadLoop LoLoop(*ML, *MLI, *RDA); + LowOverheadLoop LoLoop(*ML, *MLI, *RDA, *TRI); // Search the preheader for the start intrinsic. // FIXME: I don't see why we shouldn't be supporting multiple predecessors // with potentially multiple set.loop.iterations, so we need to enable this. Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/cond-vector-reduce-mve-codegen.ll =================================================================== --- llvm/test/CodeGen/Thumb2/LowOverheadLoops/cond-vector-reduce-mve-codegen.ll +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/cond-vector-reduce-mve-codegen.ll @@ -213,22 +213,27 @@ ; CHECK-NEXT: vmov.i32 q1, #0x0 ; CHECK-NEXT: bic r4, r4, #3 ; CHECK-NEXT: subs r5, r4, #4 +; CHECK-NEXT: movs r4, #1 +; CHECK-NEXT: add.w lr, r4, r5, lsr #2 ; CHECK-NEXT: lsrs r4, r5, #2 ; CHECK-NEXT: sub.w r4, r12, r4, lsl #2 -; CHECK-NEXT: dlstp.32 lr, r12 +; CHECK-NEXT: dls lr, lr ; CHECK-NEXT: .LBB2_2: @ %vector.body ; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1 +; CHECK-NEXT: vctp.32 r12 ; CHECK-NEXT: vmov q0, q1 -; CHECK-NEXT: vldrw.u32 q1, [r1], #16 -; CHECK-NEXT: vldrw.u32 q2, [r0], #16 -; CHECK-NEXT: vsub.i32 q1, q2, q1 -; CHECK-NEXT: vcmp.i32 eq, q1, zr ; CHECK-NEXT: vpstt +; CHECK-NEXT: vldrwt.u32 q1, [r1], #16 +; CHECK-NEXT: vldrwt.u32 q2, [r0], #16 +; CHECK-NEXT: sub.w r12, r12, #4 +; CHECK-NEXT: vsub.i32 q1, q2, q1 +; CHECK-NEXT: vpsttt +; CHECK-NEXT: vcmpt.i32 eq, q1, zr ; CHECK-NEXT: vldrwt.u32 q1, [r3], #16 ; CHECK-NEXT: vldrwt.u32 q2, [r2], #16 ; CHECK-NEXT: vmul.i32 q1, q2, q1 ; CHECK-NEXT: vadd.i32 q1, q1, q0 -; CHECK-NEXT: letp lr, .LBB2_2 +; CHECK-NEXT: le lr, .LBB2_2 ; CHECK-NEXT: @ %bb.3: @ %middle.block ; CHECK-NEXT: vctp.32 r4 ; CHECK-NEXT: vpsel q0, q1, q0 Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/extract-element.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/extract-element.mir @@ -0,0 +1,186 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py +# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - --verify-machineinstrs | FileCheck %s + +# Test that the scalar register that aliases a Q reg prevents the tail +# predication. + +--- | + define dso_local i32 @no_vpsel_liveout(i16* nocapture readonly %a, i16* nocapture readonly %b, i32 %N) local_unnamed_addr #0 { + entry: + %cmp9 = icmp eq i32 %N, 0 + %tmp = add i32 %N, 3 + %tmp1 = lshr i32 %tmp, 2 + %tmp2 = shl nuw i32 %tmp1, 2 + %tmp3 = add i32 %tmp2, -4 + %tmp4 = lshr i32 %tmp3, 2 + %tmp5 = add nuw nsw i32 %tmp4, 1 + br i1 %cmp9, label %for.cond.cleanup, label %vector.ph + + vector.ph: ; preds = %entry + call void @llvm.set.loop.iterations.i32(i32 %tmp5) + br label %vector.body + + vector.body: ; preds = %vector.body, %vector.ph + %lsr.iv1 = phi i32 [ %lsr.iv.next, %vector.body ], [ %tmp5, %vector.ph ] + %lsr.iv18 = phi i16* [ %scevgep19, %vector.body ], [ %b, %vector.ph ] + %lsr.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ] + %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %tmp13, %vector.body ] + %tmp7 = phi i32 [ %N, %vector.ph ], [ %tmp9, %vector.body ] + %lsr.iv17 = bitcast i16* %lsr.iv to <4 x i16>* + %lsr.iv1820 = bitcast i16* %lsr.iv18 to <4 x i16>* + %tmp8 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %tmp7) + %tmp9 = sub i32 %tmp7, 4 + %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv17, i32 2, <4 x i1> %tmp8, <4 x i16> undef) + %tmp10 = sext <4 x i16> %wide.masked.load to <4 x i32> + %wide.masked.load14 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv1820, i32 2, <4 x i1> %tmp8, <4 x i16> undef) + %tmp11 = sext <4 x i16> %wide.masked.load14 to <4 x i32> + %tmp12 = mul nsw <4 x i32> %tmp11, %tmp10 + %tmp13 = add <4 x i32> %tmp12, %vec.phi + %scevgep = getelementptr i16, i16* %lsr.iv, i32 4 + %scevgep19 = getelementptr i16, i16* %lsr.iv18, i32 4 + %tmp14 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv1, i32 1) + %tmp15 = icmp ne i32 %tmp14, 0 + %lsr.iv.next = add nsw i32 %lsr.iv1, -1 + br i1 %tmp15, label %vector.body, label %middle.block + + middle.block: ; preds = %vector.body + %tmp16 = extractelement <4 x i32> %tmp13, i32 3 + br label %for.cond.cleanup + + for.cond.cleanup: ; preds = %middle.block, %entry + %res.0.lcssa = phi i32 [ 0, %entry ], [ %tmp16, %middle.block ] + ret i32 %res.0.lcssa + } + declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32 immarg, <4 x i1>, <4 x i16>) + declare void @llvm.set.loop.iterations.i32(i32) + declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) + declare <4 x i1> @llvm.arm.mve.vctp32(i32) + +... +--- +name: no_vpsel_liveout +alignment: 2 +exposesReturnsTwice: false +legalized: false +regBankSelected: false +selected: false +failedISel: false +tracksRegLiveness: true +hasWinCFI: false +registers: [] +liveins: + - { reg: '$r0', virtual-reg: '' } + - { reg: '$r1', virtual-reg: '' } + - { reg: '$r2', virtual-reg: '' } +frameInfo: + isFrameAddressTaken: false + isReturnAddressTaken: false + hasStackMap: false + hasPatchPoint: false + stackSize: 8 + offsetAdjustment: 0 + maxAlignment: 4 + adjustsStack: false + hasCalls: false + stackProtector: '' + maxCallFrameSize: 0 + cvBytesOfCalleeSavedRegisters: 0 + hasOpaqueSPAdjustment: false + hasVAStart: false + hasMustTailInVarArgFunc: false + localFrameSize: 0 + savePoint: '' + restorePoint: '' +fixedStack: [] +stack: + - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } + - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } +callSites: [] +constants: [] +machineFunctionInfo: {} +body: | + ; CHECK-LABEL: name: no_vpsel_liveout + ; CHECK: bb.0.entry: + ; CHECK: successors: %bb.1(0x80000000) + ; CHECK: liveins: $lr, $r0, $r1, $r2, $r7 + ; CHECK: tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + ; CHECK: t2IT 0, 4, implicit-def $itstate + ; CHECK: renamable $r0 = tMOVi8 $noreg, 0, 0, $cpsr, implicit killed $r0, implicit $itstate + ; CHECK: tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + ; CHECK: frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8 + ; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8 + ; CHECK: renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg + ; CHECK: renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0 + ; CHECK: renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg + ; CHECK: renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg + ; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + ; CHECK: renamable $r12 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg + ; CHECK: dead $lr = t2DLS renamable $r12 + ; CHECK: $r3 = tMOVr killed $r12, 14, $noreg + ; CHECK: bb.1.vector.body: + ; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000) + ; CHECK: liveins: $q0, $r0, $r1, $r2, $r3 + ; CHECK: renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg + ; CHECK: MVE_VPST 4, implicit $vpr + ; CHECK: renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2) + ; CHECK: renamable $r1, renamable $q2 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv1820, align 2) + ; CHECK: $lr = tMOVr $r3, 14, $noreg + ; CHECK: renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 + ; CHECK: renamable $r3, dead $cpsr = nsw tSUBi8 killed $r3, 1, 14, $noreg + ; CHECK: renamable $q0 = MVE_VADDi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0 + ; CHECK: dead $lr = t2LEUpdate killed renamable $lr, %bb.1 + ; CHECK: bb.2.middle.block: + ; CHECK: liveins: $q0 + ; CHECK: $r0 = VMOVRS killed $s3, 14, $noreg, implicit killed $q0 + ; CHECK: tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + bb.0.entry: + successors: %bb.1(0x80000000) + liveins: $r0, $r1, $r2, $lr, $r7 + + tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + t2IT 0, 4, implicit-def $itstate + renamable $r0 = tMOVi8 $noreg, 0, 0, $cpsr, implicit killed $r0, implicit $itstate + tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + frame-setup CFI_INSTRUCTION def_cfa_offset 8 + frame-setup CFI_INSTRUCTION offset $lr, -4 + frame-setup CFI_INSTRUCTION offset $r7, -8 + renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg + renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0 + renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg + renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg + renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + renamable $r12 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg + t2DoLoopStart renamable $r12 + $r3 = tMOVr killed $r12, 14, $noreg + + bb.1.vector.body: + successors: %bb.1(0x7c000000), %bb.2(0x04000000) + liveins: $q0, $r0, $r1, $r2, $r3 + + renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg + MVE_VPST 4, implicit $vpr + renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2) + renamable $r1, renamable $q2 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv1820, align 2) + $lr = tMOVr $r3, 14, $noreg + renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 + renamable $r3, dead $cpsr = nsw tSUBi8 killed $r3, 1, 14, $noreg + renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg + renamable $q0 = MVE_VADDi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0 + renamable $lr = t2LoopDec killed renamable $lr, 1 + t2LoopEnd killed renamable $lr, %bb.1, implicit-def dead $cpsr + tB %bb.2, 14, $noreg + + bb.2.middle.block: + liveins: $q0 + + $r0 = VMOVRS killed $s3, 14, $noreg, implicit $q0 + tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + +... Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/matrix.mir =================================================================== --- llvm/test/CodeGen/Thumb2/LowOverheadLoops/matrix.mir +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/matrix.mir @@ -1,5 +1,5 @@ # NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py -# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - | FileCheck %s +# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - --verify-machineinstrs | FileCheck %s # A decent sized test to handle a matrix, with scalar and vector low-overhead loops. @@ -270,9 +270,7 @@ ; CHECK: renamable $r0 = t2BICri killed renamable $r0, 3, 14, $noreg, $noreg ; CHECK: renamable $r3 = t2LSLri $r10, 1, 14, $noreg, $noreg ; CHECK: renamable $r1, dead $cpsr = tSUBi3 killed renamable $r0, 4, 14, $noreg - ; CHECK: renamable $r0, dead $cpsr = tMOVi8 1, 14, $noreg ; CHECK: renamable $q0 = MVE_VDUP32 renamable $r7, 0, $noreg, undef renamable $q0 - ; CHECK: renamable $r0 = nuw nsw t2ADDrs killed renamable $r0, renamable $r1, 19, 14, $noreg, $noreg ; CHECK: renamable $r1, dead $cpsr = tLSRri killed renamable $r1, 2, 14, $noreg ; CHECK: renamable $r9 = t2SUBrs $r10, killed renamable $r1, 18, 14, $noreg, $noreg ; CHECK: bb.5.for.cond4.preheader.us: @@ -284,16 +282,19 @@ ; CHECK: renamable $q1 = MVE_VMOV_to_lane_32 killed renamable $q1, killed renamable $r1, 0, 14, $noreg ; CHECK: $r6 = tMOVr $r5, 14, $noreg ; CHECK: $r1 = tMOVr $r8, 14, $noreg - ; CHECK: $lr = MVE_DLSTP_32 killed renamable $r2 + ; CHECK: $lr = t2DLS renamable $r0 ; CHECK: bb.6.vector.body: ; CHECK: successors: %bb.6(0x7c000000), %bb.7(0x04000000) - ; CHECK: liveins: $lr, $q0, $q1, $r0, $r1, $r3, $r4, $r5, $r6, $r7, $r8, $r9, $r10, $r12 + ; CHECK: liveins: $lr, $q0, $q1, $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r7, $r8, $r9, $r10, $r12 + ; CHECK: renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg ; CHECK: $q2 = MVE_VORR killed $q1, killed $q1, 0, $noreg, undef $q2 - ; CHECK: renamable $r6, renamable $q1 = MVE_VLDRHS32_post killed renamable $r6, 8, 0, $noreg :: (load 8 from %ir.lsr.iv1012, align 2) - ; CHECK: renamable $r1, renamable $q3 = MVE_VLDRHS32_post killed renamable $r1, 8, 0, killed $noreg :: (load 8 from %ir.lsr.iv46, align 2) + ; CHECK: MVE_VPST 4, implicit $vpr + ; CHECK: renamable $r6, renamable $q1 = MVE_VLDRHS32_post killed renamable $r6, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv1012, align 2) + ; CHECK: renamable $r1, renamable $q3 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv46, align 2) + ; CHECK: renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg ; CHECK: renamable $q1 = nsw MVE_VMULi32 killed renamable $q3, killed renamable $q1, 0, $noreg, undef renamable $q1 ; CHECK: renamable $q1 = MVE_VADDi32 killed renamable $q1, renamable $q2, 0, $noreg, undef renamable $q1 - ; CHECK: $lr = MVE_LETP killed renamable $lr, %bb.6 + ; CHECK: $lr = t2LEUpdate killed renamable $lr, %bb.6 ; CHECK: bb.7.middle.block: ; CHECK: successors: %bb.8(0x04000000), %bb.5(0x7c000000) ; CHECK: liveins: $q0, $q1, $q2, $r0, $r3, $r4, $r5, $r7, $r8, $r9, $r10, $r12 Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/multiple-do-loops.mir =================================================================== --- llvm/test/CodeGen/Thumb2/LowOverheadLoops/multiple-do-loops.mir +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/multiple-do-loops.mir @@ -563,7 +563,6 @@ ; CHECK: early-clobber $sp = frame-setup t2STR_PRE killed $r8, $sp, -4, 14, $noreg ; CHECK: frame-setup CFI_INSTRUCTION offset $r8, -24 ; CHECK: renamable $r6, dead $cpsr = tMOVi8 0, 14, $noreg - ; CHECK: dead renamable $r12 = t2MOVi 1, 14, $noreg, $noreg ; CHECK: t2CMPrs killed renamable $r6, renamable $r3, 11, 14, $noreg, implicit-def $cpsr ; CHECK: tBcc %bb.3, 0, killed $cpsr ; CHECK: bb.1.vector.ph: @@ -801,7 +800,6 @@ ; CHECK: successors: %bb.6(0x30000000), %bb.4(0x50000000) ; CHECK: liveins: $r0, $r1, $r2, $r3 ; CHECK: renamable $r6, dead $cpsr = tMOVi8 0, 14, $noreg - ; CHECK: dead renamable $r8 = t2MOVi 1, 14, $noreg, $noreg ; CHECK: t2CMPrs killed renamable $r6, renamable $r3, 11, 14, $noreg, implicit-def $cpsr ; CHECK: tBcc %bb.6, 0, killed $cpsr ; CHECK: bb.4.vector.ph66: Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-tail-data-types.ll =================================================================== --- llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-tail-data-types.ll +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-tail-data-types.ll @@ -13,15 +13,20 @@ ; CHECK-NEXT: vmov.i32 q0, #0x0 ; CHECK-NEXT: bic r3, r3, #3 ; CHECK-NEXT: sub.w r12, r3, #4 +; CHECK-NEXT: movs r3, #1 +; CHECK-NEXT: add.w lr, r3, r12, lsr #2 ; CHECK-NEXT: lsr.w r3, r12, #2 ; CHECK-NEXT: sub.w r3, r2, r3, lsl #2 -; CHECK-NEXT: dlstp.32 lr, r2 +; CHECK-NEXT: dls lr, lr ; CHECK-NEXT: .LBB0_1: @ %vector.body ; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1 +; CHECK-NEXT: vctp.32 r2 +; CHECK-NEXT: subs r2, #4 ; CHECK-NEXT: vmov q1, q0 -; CHECK-NEXT: vldrb.u32 q2, [r1], #4 +; CHECK-NEXT: vpst +; CHECK-NEXT: vldrbt.u32 q2, [r1], #4 ; CHECK-NEXT: vmla.u32 q0, q2, r0 -; CHECK-NEXT: letp lr, .LBB0_1 +; CHECK-NEXT: le lr, .LBB0_1 ; CHECK-NEXT: @ %bb.2: @ %middle.block ; CHECK-NEXT: vctp.32 r3 ; CHECK-NEXT: vpsel q0, q0, q1 @@ -81,15 +86,20 @@ ; CHECK-NEXT: vmov.i32 q0, #0x0 ; CHECK-NEXT: bic r3, r3, #3 ; CHECK-NEXT: sub.w r12, r3, #4 +; CHECK-NEXT: movs r3, #1 +; CHECK-NEXT: add.w lr, r3, r12, lsr #2 ; CHECK-NEXT: lsr.w r3, r12, #2 ; CHECK-NEXT: sub.w r3, r2, r3, lsl #2 -; CHECK-NEXT: dlstp.32 lr, r2 +; CHECK-NEXT: dls lr, lr ; CHECK-NEXT: .LBB1_1: @ %vector.body ; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1 +; CHECK-NEXT: vctp.32 r2 +; CHECK-NEXT: subs r2, #4 ; CHECK-NEXT: vmov q1, q0 -; CHECK-NEXT: vldrh.s32 q2, [r1], #8 +; CHECK-NEXT: vpst +; CHECK-NEXT: vldrht.s32 q2, [r1], #8 ; CHECK-NEXT: vmla.u32 q0, q2, r0 -; CHECK-NEXT: letp lr, .LBB1_1 +; CHECK-NEXT: le lr, .LBB1_1 ; CHECK-NEXT: @ %bb.2: @ %middle.block ; CHECK-NEXT: vctp.32 r3 ; CHECK-NEXT: vpsel q0, q0, q1 @@ -149,15 +159,20 @@ ; CHECK-NEXT: vmov.i32 q0, #0x0 ; CHECK-NEXT: bic r3, r3, #3 ; CHECK-NEXT: sub.w r12, r3, #4 +; CHECK-NEXT: movs r3, #1 +; CHECK-NEXT: add.w lr, r3, r12, lsr #2 ; CHECK-NEXT: lsr.w r3, r12, #2 ; CHECK-NEXT: sub.w r3, r2, r3, lsl #2 -; CHECK-NEXT: dlstp.32 lr, r2 +; CHECK-NEXT: dls lr, lr ; CHECK-NEXT: .LBB2_1: @ %vector.body ; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1 +; CHECK-NEXT: vctp.32 r2 +; CHECK-NEXT: subs r2, #4 ; CHECK-NEXT: vmov q1, q0 -; CHECK-NEXT: vldrb.u32 q2, [r1], #4 +; CHECK-NEXT: vpst +; CHECK-NEXT: vldrbt.u32 q2, [r1], #4 ; CHECK-NEXT: vmla.u32 q0, q2, r0 -; CHECK-NEXT: letp lr, .LBB2_1 +; CHECK-NEXT: le lr, .LBB2_1 ; CHECK-NEXT: @ %bb.2: @ %middle.block ; CHECK-NEXT: vctp.32 r3 ; CHECK-NEXT: vpsel q0, q0, q1 @@ -217,15 +232,20 @@ ; CHECK-NEXT: vmov.i32 q0, #0x0 ; CHECK-NEXT: bic r3, r3, #3 ; CHECK-NEXT: sub.w r12, r3, #4 +; CHECK-NEXT: movs r3, #1 +; CHECK-NEXT: add.w lr, r3, r12, lsr #2 ; CHECK-NEXT: lsr.w r3, r12, #2 ; CHECK-NEXT: sub.w r3, r2, r3, lsl #2 -; CHECK-NEXT: dlstp.32 lr, r2 +; CHECK-NEXT: dls lr, lr ; CHECK-NEXT: .LBB3_1: @ %vector.body ; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1 +; CHECK-NEXT: vctp.32 r2 +; CHECK-NEXT: subs r2, #4 ; CHECK-NEXT: vmov q1, q0 -; CHECK-NEXT: vldrh.u32 q2, [r1], #8 +; CHECK-NEXT: vpst +; CHECK-NEXT: vldrht.u32 q2, [r1], #8 ; CHECK-NEXT: vmla.u32 q0, q2, r0 -; CHECK-NEXT: letp lr, .LBB3_1 +; CHECK-NEXT: le lr, .LBB3_1 ; CHECK-NEXT: @ %bb.2: @ %middle.block ; CHECK-NEXT: vctp.32 r3 ; CHECK-NEXT: vpsel q0, q0, q1 @@ -285,15 +305,20 @@ ; CHECK-NEXT: vmov.i32 q0, #0x0 ; CHECK-NEXT: bic r3, r3, #3 ; CHECK-NEXT: sub.w r12, r3, #4 +; CHECK-NEXT: movs r3, #1 +; CHECK-NEXT: add.w lr, r3, r12, lsr #2 ; CHECK-NEXT: lsr.w r3, r12, #2 ; CHECK-NEXT: sub.w r3, r2, r3, lsl #2 -; CHECK-NEXT: dlstp.32 lr, r2 +; CHECK-NEXT: dls lr, lr ; CHECK-NEXT: .LBB4_1: @ %vector.body ; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1 +; CHECK-NEXT: vctp.32 r2 +; CHECK-NEXT: subs r2, #4 ; CHECK-NEXT: vmov q1, q0 -; CHECK-NEXT: vldrw.u32 q2, [r1], #16 +; CHECK-NEXT: vpst +; CHECK-NEXT: vldrwt.u32 q2, [r1], #16 ; CHECK-NEXT: vmla.u32 q0, q2, r0 -; CHECK-NEXT: letp lr, .LBB4_1 +; CHECK-NEXT: le lr, .LBB4_1 ; CHECK-NEXT: @ %bb.2: @ %middle.block ; CHECK-NEXT: vctp.32 r3 ; CHECK-NEXT: vpsel q0, q0, q1 Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/no-vpsel-liveout.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/no-vpsel-liveout.mir @@ -0,0 +1,183 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py +# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - | FileCheck %s +--- | + define dso_local i32 @no_vpsel_liveout(i16* nocapture readonly %a, i16* nocapture readonly %b, i32 %N) local_unnamed_addr #0 { + entry: + %cmp9 = icmp eq i32 %N, 0 + %tmp = add i32 %N, 3 + %tmp1 = lshr i32 %tmp, 2 + %tmp2 = shl nuw i32 %tmp1, 2 + %tmp3 = add i32 %tmp2, -4 + %tmp4 = lshr i32 %tmp3, 2 + %tmp5 = add nuw nsw i32 %tmp4, 1 + br i1 %cmp9, label %for.cond.cleanup, label %vector.ph + + vector.ph: ; preds = %entry + call void @llvm.set.loop.iterations.i32(i32 %tmp5) + br label %vector.body + + vector.body: ; preds = %vector.body, %vector.ph + %lsr.iv1 = phi i32 [ %lsr.iv.next, %vector.body ], [ %tmp5, %vector.ph ] + %lsr.iv18 = phi i16* [ %scevgep19, %vector.body ], [ %b, %vector.ph ] + %lsr.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ] + %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %tmp13, %vector.body ] + %tmp7 = phi i32 [ %N, %vector.ph ], [ %tmp9, %vector.body ] + %lsr.iv17 = bitcast i16* %lsr.iv to <4 x i16>* + %lsr.iv1820 = bitcast i16* %lsr.iv18 to <4 x i16>* + %tmp8 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %tmp7) + %tmp9 = sub i32 %tmp7, 4 + %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv17, i32 2, <4 x i1> %tmp8, <4 x i16> undef) + %tmp10 = sext <4 x i16> %wide.masked.load to <4 x i32> + %wide.masked.load14 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv1820, i32 2, <4 x i1> %tmp8, <4 x i16> undef) + %tmp11 = sext <4 x i16> %wide.masked.load14 to <4 x i32> + %tmp12 = mul nsw <4 x i32> %tmp11, %tmp10 + %tmp13 = add <4 x i32> %tmp12, %vec.phi + %scevgep = getelementptr i16, i16* %lsr.iv, i32 4 + %scevgep19 = getelementptr i16, i16* %lsr.iv18, i32 4 + %tmp14 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv1, i32 1) + %tmp15 = icmp ne i32 %tmp14, 0 + %lsr.iv.next = add nsw i32 %lsr.iv1, -1 + br i1 %tmp15, label %vector.body, label %middle.block + + middle.block: ; preds = %vector.body + %tmp16 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %tmp13) + br label %for.cond.cleanup + + for.cond.cleanup: ; preds = %middle.block, %entry + %res.0.lcssa = phi i32 [ 0, %entry ], [ %tmp16, %middle.block ] + ret i32 %res.0.lcssa + } + declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32 immarg, <4 x i1>, <4 x i16>) #1 + declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>) #2 + declare void @llvm.set.loop.iterations.i32(i32) #3 + declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #3 + declare <4 x i1> @llvm.arm.mve.vctp32(i32) #4 + +... +--- +name: no_vpsel_liveout +alignment: 2 +exposesReturnsTwice: false +legalized: false +regBankSelected: false +selected: false +failedISel: false +tracksRegLiveness: true +hasWinCFI: false +registers: [] +liveins: + - { reg: '$r0', virtual-reg: '' } + - { reg: '$r1', virtual-reg: '' } + - { reg: '$r2', virtual-reg: '' } +frameInfo: + isFrameAddressTaken: false + isReturnAddressTaken: false + hasStackMap: false + hasPatchPoint: false + stackSize: 8 + offsetAdjustment: 0 + maxAlignment: 4 + adjustsStack: false + hasCalls: false + stackProtector: '' + maxCallFrameSize: 0 + cvBytesOfCalleeSavedRegisters: 0 + hasOpaqueSPAdjustment: false + hasVAStart: false + hasMustTailInVarArgFunc: false + localFrameSize: 0 + savePoint: '' + restorePoint: '' +fixedStack: [] +stack: + - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } + - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } +callSites: [] +constants: [] +machineFunctionInfo: {} +body: | + ; CHECK-LABEL: name: no_vpsel_liveout + ; CHECK: bb.0.entry: + ; CHECK: successors: %bb.1(0x80000000) + ; CHECK: liveins: $lr, $r0, $r1, $r2, $r7 + ; CHECK: tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + ; CHECK: t2IT 0, 4, implicit-def $itstate + ; CHECK: renamable $r0 = tMOVi8 $noreg, 0, 0, $cpsr, implicit killed $r0, implicit $itstate + ; CHECK: tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + ; CHECK: frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8 + ; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8 + ; CHECK: renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg + ; CHECK: renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0 + ; CHECK: renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg + ; CHECK: renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg + ; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + ; CHECK: renamable $r12 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg + ; CHECK: dead $lr = t2DLS renamable $r12 + ; CHECK: $r3 = tMOVr killed $r12, 14, $noreg + ; CHECK: bb.1.vector.body: + ; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000) + ; CHECK: liveins: $q0, $r0, $r1, $r2, $r3 + ; CHECK: renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg + ; CHECK: MVE_VPST 4, implicit $vpr + ; CHECK: renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2) + ; CHECK: renamable $r1, renamable $q2 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv1820, align 2) + ; CHECK: $lr = tMOVr $r3, 14, $noreg + ; CHECK: renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 + ; CHECK: renamable $r3, dead $cpsr = nsw tSUBi8 killed $r3, 1, 14, $noreg + ; CHECK: renamable $q0 = MVE_VADDi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0 + ; CHECK: dead $lr = t2LEUpdate killed renamable $lr, %bb.1 + ; CHECK: bb.2.middle.block: + ; CHECK: liveins: $q0 + ; CHECK: renamable $r0 = MVE_VADDVu32no_acc killed renamable $q0, 0, $noreg + ; CHECK: tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + bb.0.entry: + successors: %bb.1(0x80000000) + liveins: $r0, $r1, $r2, $lr, $r7 + + tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + t2IT 0, 4, implicit-def $itstate + renamable $r0 = tMOVi8 $noreg, 0, 0, $cpsr, implicit killed $r0, implicit $itstate + tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + frame-setup CFI_INSTRUCTION def_cfa_offset 8 + frame-setup CFI_INSTRUCTION offset $lr, -4 + frame-setup CFI_INSTRUCTION offset $r7, -8 + renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg + renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0 + renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg + renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg + renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + renamable $r12 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg + t2DoLoopStart renamable $r12 + $r3 = tMOVr killed $r12, 14, $noreg + + bb.1.vector.body: + successors: %bb.1(0x7c000000), %bb.2(0x04000000) + liveins: $q0, $r0, $r1, $r2, $r3 + + renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg + MVE_VPST 4, implicit $vpr + renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2) + renamable $r1, renamable $q2 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv1820, align 2) + $lr = tMOVr $r3, 14, $noreg + renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 + renamable $r3, dead $cpsr = nsw tSUBi8 killed $r3, 1, 14, $noreg + renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg + renamable $q0 = MVE_VADDi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0 + renamable $lr = t2LoopDec killed renamable $lr, 1 + t2LoopEnd killed renamable $lr, %bb.1, implicit-def dead $cpsr + tB %bb.2, 14, $noreg + + bb.2.middle.block: + liveins: $q0 + + renamable $r0 = MVE_VADDVu32no_acc killed renamable $q0, 0, $noreg + tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + +... Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-add-operand-liveout.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-add-operand-liveout.mir @@ -0,0 +1,199 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py +# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - | FileCheck %s + +# This example is actually equivalent as there's a sub in the loop, which is +# then used by the add in the exit - making the vctp operands equivalent. + +--- | + define dso_local i32 @wrong_vctp_liveout(i16* nocapture readonly %a, i16* nocapture readonly %b, i32 %N) local_unnamed_addr #0 { + entry: + %cmp9 = icmp eq i32 %N, 0 + %0 = add i32 %N, 3 + %1 = lshr i32 %0, 2 + %2 = shl nuw i32 %1, 2 + %3 = add i32 %2, -4 + %4 = lshr i32 %3, 2 + %5 = add nuw nsw i32 %4, 1 + br i1 %cmp9, label %for.cond.cleanup, label %vector.ph + + vector.ph: ; preds = %entry + call void @llvm.set.loop.iterations.i32(i32 %5) + br label %vector.body + + vector.body: ; preds = %vector.body, %vector.ph + %lsr.iv1 = phi i32 [ %lsr.iv.next, %vector.body ], [ %5, %vector.ph ] + %lsr.iv18 = phi i16* [ %scevgep19, %vector.body ], [ %b, %vector.ph ] + %lsr.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ] + %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %12, %vector.body ] + %6 = phi i32 [ %N, %vector.ph ], [ %8, %vector.body ] + %lsr.iv17 = bitcast i16* %lsr.iv to <4 x i16>* + %lsr.iv1820 = bitcast i16* %lsr.iv18 to <4 x i16>* + %7 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %6) + %8 = sub i32 %6, 4 + %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv17, i32 2, <4 x i1> %7, <4 x i16> undef) + %9 = sext <4 x i16> %wide.masked.load to <4 x i32> + %wide.masked.load14 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv1820, i32 2, <4 x i1> %7, <4 x i16> undef) + %10 = sext <4 x i16> %wide.masked.load14 to <4 x i32> + %11 = mul nsw <4 x i32> %10, %9 + %12 = add <4 x i32> %11, %vec.phi + %scevgep = getelementptr i16, i16* %lsr.iv, i32 4 + %scevgep19 = getelementptr i16, i16* %lsr.iv18, i32 4 + %13 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv1, i32 1) + %14 = icmp ne i32 %13, 0 + %lsr.iv.next = add nsw i32 %lsr.iv1, -1 + br i1 %14, label %vector.body, label %middle.block + + middle.block: ; preds = %vector.body + %15 = add i32 %8, 4 + %16 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %15) + %17 = select <4 x i1> %16, <4 x i32> %12, <4 x i32> %vec.phi + %18 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %17) + br label %for.cond.cleanup + + for.cond.cleanup: ; preds = %middle.block, %entry + %res.0.lcssa = phi i32 [ 0, %entry ], [ %18, %middle.block ] + ret i32 %res.0.lcssa + } + declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32 immarg, <4 x i1>, <4 x i16>) + declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>) + declare void @llvm.set.loop.iterations.i32(i32) + declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) + declare <4 x i1> @llvm.arm.mve.vctp32(i32) + +... +--- +name: wrong_vctp_liveout +alignment: 2 +exposesReturnsTwice: false +legalized: false +regBankSelected: false +selected: false +failedISel: false +tracksRegLiveness: true +hasWinCFI: false +registers: [] +liveins: + - { reg: '$r0', virtual-reg: '' } + - { reg: '$r1', virtual-reg: '' } + - { reg: '$r2', virtual-reg: '' } +frameInfo: + isFrameAddressTaken: false + isReturnAddressTaken: false + hasStackMap: false + hasPatchPoint: false + stackSize: 8 + offsetAdjustment: 0 + maxAlignment: 4 + adjustsStack: false + hasCalls: false + stackProtector: '' + maxCallFrameSize: 0 + cvBytesOfCalleeSavedRegisters: 0 + hasOpaqueSPAdjustment: false + hasVAStart: false + hasMustTailInVarArgFunc: false + localFrameSize: 0 + savePoint: '' + restorePoint: '' +fixedStack: [] +stack: + - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } + - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } +callSites: [] +constants: [] +machineFunctionInfo: {} +body: | + ; CHECK-LABEL: name: wrong_vctp_liveout + ; CHECK: bb.0.entry: + ; CHECK: successors: %bb.1(0x80000000) + ; CHECK: liveins: $lr, $r0, $r1, $r2, $r7 + ; CHECK: tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + ; CHECK: t2IT 0, 4, implicit-def $itstate + ; CHECK: renamable $r0 = tMOVi8 $noreg, 0, 0, $cpsr, implicit killed $r0, implicit $itstate + ; CHECK: tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + ; CHECK: frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8 + ; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8 + ; CHECK: renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg + ; CHECK: renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1 + ; CHECK: renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg + ; CHECK: renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg + ; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + ; CHECK: renamable $r12 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg + ; CHECK: dead $lr = t2DLS renamable $r12 + ; CHECK: $r3 = tMOVr killed $r12, 14, $noreg + ; CHECK: bb.1.vector.body: + ; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000) + ; CHECK: liveins: $q1, $r0, $r1, $r2, $r3 + ; CHECK: renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg + ; CHECK: $q0 = MVE_VORR killed $q1, killed $q1, 0, $noreg, undef $q0 + ; CHECK: MVE_VPST 4, implicit $vpr + ; CHECK: renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2) + ; CHECK: renamable $r1, renamable $q2 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv1820, align 2) + ; CHECK: $lr = tMOVr $r3, 14, $noreg + ; CHECK: renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 + ; CHECK: renamable $r3, dead $cpsr = nsw tSUBi8 killed $r3, 1, 14, $noreg + ; CHECK: renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg + ; CHECK: renamable $q1 = MVE_VADDi32 killed renamable $q1, renamable $q0, 0, $noreg, undef renamable $q1 + ; CHECK: dead $lr = t2LEUpdate killed renamable $lr, %bb.1 + ; CHECK: bb.2.middle.block: + ; CHECK: liveins: $q0, $q1, $r2 + ; CHECK: renamable $r0, dead $cpsr = tADDi3 killed renamable $r2, 4, 14, $noreg + ; CHECK: renamable $vpr = MVE_VCTP32 killed renamable $r0, 0, $noreg + ; CHECK: renamable $q0 = MVE_VPSEL killed renamable $q1, killed renamable $q0, 0, killed renamable $vpr + ; CHECK: renamable $r0 = MVE_VADDVu32no_acc killed renamable $q0, 0, $noreg + ; CHECK: tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + bb.0.entry: + successors: %bb.1(0x80000000) + liveins: $r0, $r1, $r2, $lr, $r7 + + tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + t2IT 0, 4, implicit-def $itstate + renamable $r0 = tMOVi8 $noreg, 0, 0, $cpsr, implicit killed $r0, implicit $itstate + tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + frame-setup CFI_INSTRUCTION def_cfa_offset 8 + frame-setup CFI_INSTRUCTION offset $lr, -4 + frame-setup CFI_INSTRUCTION offset $r7, -8 + renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg + renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1 + renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg + renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg + renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + renamable $r12 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg + t2DoLoopStart renamable $r12 + $r3 = tMOVr killed $r12, 14, $noreg + + bb.1.vector.body: + successors: %bb.1(0x7c000000), %bb.2(0x04000000) + liveins: $q1, $r0, $r1, $r2, $r3 + + renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg + $q0 = MVE_VORR killed $q1, $q1, 0, $noreg, undef $q0 + MVE_VPST 4, implicit $vpr + renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2) + renamable $r1, renamable $q2 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv1820, align 2) + $lr = tMOVr $r3, 14, $noreg + renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 + renamable $r3, dead $cpsr = nsw tSUBi8 killed $r3, 1, 14, $noreg + renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg + renamable $q1 = MVE_VADDi32 killed renamable $q1, renamable $q0, 0, $noreg, undef renamable $q1 + renamable $lr = t2LoopDec killed renamable $lr, 1 + t2LoopEnd killed renamable $lr, %bb.1, implicit-def dead $cpsr + tB %bb.2, 14, $noreg + + bb.2.middle.block: + liveins: $q0, $q1, $r2 + + renamable $r0, dead $cpsr = tADDi3 killed renamable $r2, 4, 14, $noreg + renamable $vpr = MVE_VCTP32 killed renamable $r0, 0, $noreg + renamable $q0 = MVE_VPSEL killed renamable $q1, killed renamable $q0, 0, killed renamable $vpr + renamable $r0 = MVE_VADDVu32no_acc killed renamable $q0, 0, $noreg + tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + +... Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp16-reduce.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp16-reduce.mir @@ -0,0 +1,215 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py +# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - --verify-machineinstrs | FileCheck %s + +--- | + define dso_local arm_aapcs_vfpcc signext i16 @wrong_liveout_shift(i8* nocapture readonly %b, i8* nocapture readonly %c, i32 %N) { + entry: + %cmp11 = icmp eq i32 %N, 0 + %0 = add i32 %N, 7 + %1 = lshr i32 %0, 3 + %2 = shl nuw i32 %1, 3 + %3 = add i32 %2, -8 + %4 = lshr i32 %3, 3 + %5 = add nuw nsw i32 %4, 1 + br i1 %cmp11, label %for.cond.cleanup, label %vector.ph + + vector.ph: ; preds = %entry + call void @llvm.set.loop.iterations.i32(i32 %5) + %6 = shl i32 %4, 3 + %7 = sub i32 %N, %6 + br label %vector.body + + vector.body: ; preds = %vector.body, %vector.ph + %lsr.iv20 = phi i8* [ %scevgep21, %vector.body ], [ %c, %vector.ph ] + %lsr.iv = phi i8* [ %scevgep, %vector.body ], [ %b, %vector.ph ] + %vec.phi = phi <8 x i16> [ , %vector.ph ], [ %15, %vector.body ] + %8 = phi i32 [ %5, %vector.ph ], [ %16, %vector.body ] + %9 = phi i32 [ %N, %vector.ph ], [ %11, %vector.body ] + %lsr.iv2022 = bitcast i8* %lsr.iv20 to <8 x i8>* + %lsr.iv19 = bitcast i8* %lsr.iv to <8 x i8>* + %10 = call <8 x i1> @llvm.arm.mve.vctp16(i32 %9) + %11 = sub i32 %9, 8 + %wide.masked.load = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* %lsr.iv19, i32 1, <8 x i1> %10, <8 x i8> undef) + %12 = zext <8 x i8> %wide.masked.load to <8 x i16> + %wide.masked.load16 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* %lsr.iv2022, i32 1, <8 x i1> %10, <8 x i8> undef) + %13 = zext <8 x i8> %wide.masked.load16 to <8 x i16> + %14 = mul nuw <8 x i16> %13, %12 + %15 = sub <8 x i16> %vec.phi, %14 + %scevgep = getelementptr i8, i8* %lsr.iv, i32 8 + %scevgep21 = getelementptr i8, i8* %lsr.iv20, i32 8 + %16 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %8, i32 1) + %17 = icmp ne i32 %16, 0 + br i1 %17, label %vector.body, label %middle.block + + middle.block: ; preds = %vector.body + %vec.phi.lcssa = phi <8 x i16> [ %vec.phi, %vector.body ] + %.lcssa = phi <8 x i16> [ %15, %vector.body ] + %18 = call <8 x i1> @llvm.arm.mve.vctp16(i32 %7) + %19 = select <8 x i1> %18, <8 x i16> %.lcssa, <8 x i16> %vec.phi.lcssa + %20 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> %19) + br label %for.cond.cleanup + + for.cond.cleanup: ; preds = %middle.block, %entry + %a.0.lcssa = phi i16 [ 32767, %entry ], [ %20, %middle.block ] + ret i16 %a.0.lcssa + } + declare <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>*, i32 immarg, <8 x i1>, <8 x i8>) + declare i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16>) + declare void @llvm.set.loop.iterations.i32(i32) + declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) + declare <8 x i1> @llvm.arm.mve.vctp16(i32) + +... +--- +name: wrong_liveout_shift +alignment: 16 +exposesReturnsTwice: false +legalized: false +regBankSelected: false +selected: false +failedISel: false +tracksRegLiveness: true +hasWinCFI: false +registers: [] +liveins: + - { reg: '$r0', virtual-reg: '' } + - { reg: '$r1', virtual-reg: '' } + - { reg: '$r2', virtual-reg: '' } +frameInfo: + isFrameAddressTaken: false + isReturnAddressTaken: false + hasStackMap: false + hasPatchPoint: false + stackSize: 8 + offsetAdjustment: 0 + maxAlignment: 4 + adjustsStack: false + hasCalls: false + stackProtector: '' + maxCallFrameSize: 0 + cvBytesOfCalleeSavedRegisters: 0 + hasOpaqueSPAdjustment: false + hasVAStart: false + hasMustTailInVarArgFunc: false + localFrameSize: 0 + savePoint: '' + restorePoint: '' +fixedStack: [] +stack: + - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } + - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } +callSites: [] +constants: + - id: 0 + value: '<8 x i16> ' + alignment: 16 + isTargetSpecific: false +machineFunctionInfo: {} +body: | + ; CHECK-LABEL: name: wrong_liveout_shift + ; CHECK: bb.0.entry: + ; CHECK: successors: %bb.1(0x80000000) + ; CHECK: liveins: $lr, $r0, $r1, $r2 + ; CHECK: tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + ; CHECK: t2IT 0, 2, implicit-def $itstate + ; CHECK: renamable $r0 = t2MOVi16 32767, 0, $cpsr, implicit killed $r0, implicit $itstate + ; CHECK: renamable $r0 = tSXTH killed renamable $r0, 0, $cpsr, implicit killed $r0, implicit $itstate + ; CHECK: tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + ; CHECK: frame-setup tPUSH 14, $noreg, killed $lr, implicit-def $sp, implicit $sp + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8 + ; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8 + ; CHECK: dead $r7 = frame-setup tMOVr $sp, 14, $noreg + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_register $r7 + ; CHECK: renamable $r3, dead $cpsr = tADDi3 renamable $r2, 7, 14, $noreg + ; CHECK: renamable $r3 = t2BICri killed renamable $r3, 7, 14, $noreg, $noreg + ; CHECK: renamable $r12 = t2SUBri killed renamable $r3, 8, 14, $noreg, $noreg + ; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + ; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r3, renamable $r12, 27, 14, $noreg, $noreg + ; CHECK: renamable $r3 = tLEApcrel %const.0, 14, $noreg + ; CHECK: renamable $r12 = t2LSRri killed renamable $r12, 3, 14, $noreg, $noreg + ; CHECK: renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from constant-pool) + ; CHECK: renamable $r3 = t2SUBrs renamable $r2, killed renamable $r12, 26, 14, $noreg, $noreg + ; CHECK: $lr = t2DLS killed renamable $lr + ; CHECK: bb.1.vector.body: + ; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000) + ; CHECK: liveins: $lr, $q0, $r0, $r1, $r2, $r3 + ; CHECK: renamable $vpr = MVE_VCTP16 renamable $r2, 0, $noreg + ; CHECK: $q1 = MVE_VORR killed $q0, killed $q0, 0, $noreg, undef $q1 + ; CHECK: MVE_VPST 4, implicit $vpr + ; CHECK: renamable $r0, renamable $q0 = MVE_VLDRBU16_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv19, align 1) + ; CHECK: renamable $r1, renamable $q2 = MVE_VLDRBU16_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv2022, align 1) + ; CHECK: renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 8, 14, $noreg + ; CHECK: renamable $q0 = nuw MVE_VMULi16 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0 + ; CHECK: renamable $q0 = MVE_VSUBi16 renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0 + ; CHECK: $lr = t2LEUpdate killed renamable $lr, %bb.1 + ; CHECK: bb.2.middle.block: + ; CHECK: liveins: $q0, $q1, $r3 + ; CHECK: renamable $vpr = MVE_VCTP16 killed renamable $r3, 0, $noreg + ; CHECK: renamable $q0 = MVE_VPSEL killed renamable $q0, killed renamable $q1, 0, killed renamable $vpr + ; CHECK: renamable $r0 = MVE_VADDVu16no_acc killed renamable $q0, 0, $noreg + ; CHECK: $sp = t2LDMIA_UPD $sp, 14, $noreg, def $r7, def $lr + ; CHECK: renamable $r0 = tSXTH killed renamable $r0, 14, $noreg + ; CHECK: tBX_RET 14, $noreg, implicit killed $r0 + ; CHECK: bb.3 (align 16): + ; CHECK: CONSTPOOL_ENTRY 0, %const.0, 16 + bb.0.entry: + successors: %bb.1(0x80000000) + liveins: $r0, $r1, $r2, $lr + + tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + t2IT 0, 2, implicit-def $itstate + renamable $r0 = t2MOVi16 32767, 0, $cpsr, implicit killed $r0, implicit $itstate + renamable $r0 = tSXTH killed renamable $r0, 0, $cpsr, implicit killed $r0, implicit $itstate + tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + frame-setup tPUSH 14, $noreg, killed $lr, implicit-def $sp, implicit $sp + frame-setup CFI_INSTRUCTION def_cfa_offset 8 + frame-setup CFI_INSTRUCTION offset $lr, -4 + frame-setup CFI_INSTRUCTION offset $r7, -8 + $r7 = frame-setup tMOVr $sp, 14, $noreg + frame-setup CFI_INSTRUCTION def_cfa_register $r7 + renamable $r3, dead $cpsr = tADDi3 renamable $r2, 7, 14, $noreg + renamable $r3 = t2BICri killed renamable $r3, 7, 14, $noreg, $noreg + renamable $r12 = t2SUBri killed renamable $r3, 8, 14, $noreg, $noreg + renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + renamable $lr = nuw nsw t2ADDrs killed renamable $r3, renamable $r12, 27, 14, $noreg, $noreg + renamable $r3 = tLEApcrel %const.0, 14, $noreg + renamable $r12 = t2LSRri killed renamable $r12, 3, 14, $noreg, $noreg + renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from constant-pool) + renamable $r3 = t2SUBrs renamable $r2, killed renamable $r12, 26, 14, $noreg, $noreg + t2DoLoopStart renamable $lr + + bb.1.vector.body: + successors: %bb.1(0x7c000000), %bb.2(0x04000000) + liveins: $lr, $q0, $r0, $r1, $r2, $r3 + + renamable $vpr = MVE_VCTP16 renamable $r2, 0, $noreg + $q1 = MVE_VORR killed $q0, $q0, 0, $noreg, undef $q1 + MVE_VPST 4, implicit $vpr + renamable $r0, renamable $q0 = MVE_VLDRBU16_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv19, align 1) + renamable $r1, renamable $q2 = MVE_VLDRBU16_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv2022, align 1) + renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 8, 14, $noreg + renamable $q0 = nuw MVE_VMULi16 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0 + renamable $lr = t2LoopDec killed renamable $lr, 1 + renamable $q0 = MVE_VSUBi16 renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0 + t2LoopEnd renamable $lr, %bb.1, implicit-def dead $cpsr + tB %bb.2, 14, $noreg + + bb.2.middle.block: + liveins: $q0, $q1, $r3 + + renamable $vpr = MVE_VCTP16 killed renamable $r3, 0, $noreg + renamable $q0 = MVE_VPSEL killed renamable $q0, killed renamable $q1, 0, killed renamable $vpr + renamable $r0 = MVE_VADDVu16no_acc killed renamable $q0, 0, $noreg + $sp = t2LDMIA_UPD $sp, 14, $noreg, def $r7, def $lr + renamable $r0 = tSXTH killed renamable $r0, 14, $noreg + tBX_RET 14, $noreg, implicit killed $r0 + + bb.3 (align 16): + CONSTPOOL_ENTRY 0, %const.0, 16 + +... Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/vector-arith-codegen.ll =================================================================== --- llvm/test/CodeGen/Thumb2/LowOverheadLoops/vector-arith-codegen.ll +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/vector-arith-codegen.ll @@ -13,17 +13,22 @@ ; CHECK-NEXT: vmov.i32 q0, #0x0 ; CHECK-NEXT: bic r3, r3, #3 ; CHECK-NEXT: sub.w r12, r3, #4 +; CHECK-NEXT: movs r3, #1 +; CHECK-NEXT: add.w lr, r3, r12, lsr #2 ; CHECK-NEXT: lsr.w r3, r12, #2 ; CHECK-NEXT: sub.w r3, r2, r3, lsl #2 -; CHECK-NEXT: dlstp.32 lr, r2 +; CHECK-NEXT: dls lr, lr ; CHECK-NEXT: .LBB0_1: @ %vector.body ; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1 +; CHECK-NEXT: vctp.32 r2 ; CHECK-NEXT: vmov q1, q0 -; CHECK-NEXT: vldrw.u32 q0, [r0], #16 -; CHECK-NEXT: vldrw.u32 q2, [r1], #16 +; CHECK-NEXT: vpstt +; CHECK-NEXT: vldrwt.u32 q0, [r0], #16 +; CHECK-NEXT: vldrwt.u32 q2, [r1], #16 +; CHECK-NEXT: subs r2, #4 ; CHECK-NEXT: vmul.i32 q0, q2, q0 ; CHECK-NEXT: vadd.i32 q0, q0, q1 -; CHECK-NEXT: letp lr, .LBB0_1 +; CHECK-NEXT: le lr, .LBB0_1 ; CHECK-NEXT: @ %bb.2: @ %middle.block ; CHECK-NEXT: vctp.32 r3 ; CHECK-NEXT: vpsel q0, q0, q1 @@ -79,18 +84,23 @@ ; CHECK-NEXT: bxeq lr ; CHECK-NEXT: push {r7, lr} ; CHECK-NEXT: adds r1, r2, #3 +; CHECK-NEXT: movs r3, #1 ; CHECK-NEXT: bic r1, r1, #3 ; CHECK-NEXT: vmov.i32 q0, #0x0 ; CHECK-NEXT: subs r1, #4 +; CHECK-NEXT: add.w lr, r3, r1, lsr #2 ; CHECK-NEXT: lsrs r1, r1, #2 ; CHECK-NEXT: sub.w r1, r2, r1, lsl #2 -; CHECK-NEXT: dlstp.32 lr, r2 +; CHECK-NEXT: dls lr, lr ; CHECK-NEXT: .LBB1_1: @ %vector.body ; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1 +; CHECK-NEXT: vctp.32 r2 ; CHECK-NEXT: vmov q1, q0 -; CHECK-NEXT: vldrw.u32 q0, [r0], #16 +; CHECK-NEXT: vpst +; CHECK-NEXT: vldrwt.u32 q0, [r0], #16 +; CHECK-NEXT: subs r2, #4 ; CHECK-NEXT: vadd.i32 q0, q0, q1 -; CHECK-NEXT: letp lr, .LBB1_1 +; CHECK-NEXT: le lr, .LBB1_1 ; CHECK-NEXT: @ %bb.2: @ %middle.block ; CHECK-NEXT: vctp.32 r1 ; CHECK-NEXT: vpsel q0, q0, q1 @@ -142,18 +152,23 @@ ; CHECK-NEXT: bxeq lr ; CHECK-NEXT: push {r7, lr} ; CHECK-NEXT: adds r1, r2, #3 +; CHECK-NEXT: movs r3, #1 ; CHECK-NEXT: bic r1, r1, #3 ; CHECK-NEXT: vmov.i32 q0, #0x0 ; CHECK-NEXT: subs r1, #4 +; CHECK-NEXT: add.w lr, r3, r1, lsr #2 ; CHECK-NEXT: lsrs r1, r1, #2 ; CHECK-NEXT: sub.w r1, r2, r1, lsl #2 -; CHECK-NEXT: dlstp.32 lr, r2 +; CHECK-NEXT: dls lr, lr ; CHECK-NEXT: .LBB2_1: @ %vector.body ; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1 +; CHECK-NEXT: vctp.32 r2 ; CHECK-NEXT: vmov q1, q0 -; CHECK-NEXT: vldrw.u32 q0, [r0], #16 +; CHECK-NEXT: vpst +; CHECK-NEXT: vldrwt.u32 q0, [r0], #16 +; CHECK-NEXT: subs r2, #4 ; CHECK-NEXT: vadd.i32 q0, q0, q1 -; CHECK-NEXT: letp lr, .LBB2_1 +; CHECK-NEXT: le lr, .LBB2_1 ; CHECK-NEXT: @ %bb.2: @ %middle.block ; CHECK-NEXT: vctp.32 r1 ; CHECK-NEXT: vpsel q0, q0, q1 Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/wlstp.mir =================================================================== --- llvm/test/CodeGen/Thumb2/LowOverheadLoops/wlstp.mir +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/wlstp.mir @@ -1,5 +1,5 @@ # NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py -# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - | FileCheck %s +# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - --verify-machineinstrs | FileCheck %s --- | define dso_local arm_aapcs_vfpcc void @test_wlstp8(i8* noalias nocapture %a, i8* noalias nocapture readonly %b, i8* noalias nocapture readonly %c, i32 %N) { @@ -425,8 +425,13 @@ ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8 ; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4 ; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8 + ; CHECK: renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg + ; CHECK: renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg + ; CHECK: renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg + ; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + ; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg ; CHECK: renamable $r12 = t2MOVi 0, 14, $noreg, $noreg - ; CHECK: $lr = MVE_WLSTP_32 $r2, %bb.1 + ; CHECK: $lr = t2WLS killed renamable $lr, %bb.1 ; CHECK: tB %bb.4, 14, $noreg ; CHECK: bb.1.vector.ph: ; CHECK: successors: %bb.2(0x80000000) @@ -436,15 +441,18 @@ ; CHECK: successors: %bb.3(0x04000000), %bb.2(0x7c000000) ; CHECK: liveins: $lr, $q1, $r0, $r1, $r2 ; CHECK: $q0 = MVE_VORR killed $q1, killed $q1, 0, $noreg, undef $q0 - ; CHECK: renamable $q1 = MVE_VLDRWU32 renamable $r0, 0, 0, $noreg :: (load 16 from %ir.lsr.iv24, align 4) - ; CHECK: renamable $q2 = MVE_VLDRWU32 renamable $r1, 0, 0, killed $noreg :: (load 16 from %ir.lsr.iv1, align 4) + ; CHECK: renamable $vpr = MVE_VCTP32 $r2, 0, $noreg + ; CHECK: MVE_VPST 4, implicit $vpr + ; CHECK: renamable $q1 = MVE_VLDRWU32 renamable $r0, 0, 1, renamable $vpr :: (load 16 from %ir.lsr.iv24, align 4) + ; CHECK: renamable $q2 = MVE_VLDRWU32 renamable $r1, 0, 1, renamable $vpr :: (load 16 from %ir.lsr.iv1, align 4) ; CHECK: $r3 = tMOVr $r2, 14, $noreg ; CHECK: renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 ; CHECK: renamable $r0, dead $cpsr = tADDi8 killed renamable $r0, 16, 14, $noreg ; CHECK: renamable $r1, dead $cpsr = tADDi8 killed renamable $r1, 16, 14, $noreg ; CHECK: renamable $r2, dead $cpsr = tSUBi8 killed $r2, 4, 14, $noreg - ; CHECK: renamable $q1 = nsw MVE_VADDi32 killed renamable $q1, renamable $q0, 0, $noreg, undef renamable $q1 - ; CHECK: $lr = MVE_LETP killed renamable $lr, %bb.2 + ; CHECK: MVE_VPST 8, implicit $vpr + ; CHECK: renamable $q1 = nsw MVE_VADDi32 killed renamable $q1, renamable $q0, 0, killed renamable $vpr, undef renamable $q1 + ; CHECK: $lr = t2LEUpdate killed renamable $lr, %bb.2 ; CHECK: bb.3.middle.block: ; CHECK: successors: %bb.4(0x80000000) ; CHECK: liveins: $q0, $q1, $r3 @@ -486,13 +494,14 @@ renamable $vpr = MVE_VCTP32 $r2, 0, $noreg MVE_VPST 4, implicit $vpr renamable $q1 = MVE_VLDRWU32 renamable $r0, 0, 1, renamable $vpr :: (load 16 from %ir.lsr.iv24, align 4) - renamable $q2 = MVE_VLDRWU32 renamable $r1, 0, 1, killed renamable $vpr :: (load 16 from %ir.lsr.iv1, align 4) + renamable $q2 = MVE_VLDRWU32 renamable $r1, 0, 1, renamable $vpr :: (load 16 from %ir.lsr.iv1, align 4) $r3 = tMOVr $r2, 14, $noreg renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 renamable $r0, dead $cpsr = tADDi8 killed renamable $r0, 16, 14, $noreg renamable $r1, dead $cpsr = tADDi8 killed renamable $r1, 16, 14, $noreg renamable $r2, dead $cpsr = tSUBi8 killed $r2, 4, 14, $noreg - renamable $q1 = nsw MVE_VADDi32 killed renamable $q1, renamable $q0, 0, $noreg, undef renamable $q1 + MVE_VPST 8, implicit $vpr + renamable $q1 = nsw MVE_VADDi32 killed renamable $q1, renamable $q0, 0, renamable $vpr, undef renamable $q1 renamable $lr = t2LoopDec killed renamable $lr, 1 t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr tB %bb.3, 14, $noreg Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/wrong-liveout-lsr-shift.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/wrong-liveout-lsr-shift.mir @@ -0,0 +1,214 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py +# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - --verify-machineinstrs | FileCheck %s + +--- | + define dso_local arm_aapcs_vfpcc signext i16 @wrong_liveout_shift(i8* nocapture readonly %b, i8* nocapture readonly %c, i32 %N) { + entry: + %cmp11 = icmp eq i32 %N, 0 + %0 = add i32 %N, 7 + %1 = lshr i32 %0, 3 + %2 = shl nuw i32 %1, 3 + %3 = add i32 %2, -8 + %4 = lshr i32 %3, 2 + %5 = add nuw nsw i32 %4, 1 + br i1 %cmp11, label %for.cond.cleanup, label %vector.ph + + vector.ph: ; preds = %entry + call void @llvm.set.loop.iterations.i32(i32 %5) + %6 = shl i32 %4, 3 + %7 = sub i32 %N, %6 + br label %vector.body + + vector.body: ; preds = %vector.body, %vector.ph + %lsr.iv20 = phi i8* [ %scevgep21, %vector.body ], [ %c, %vector.ph ] + %lsr.iv = phi i8* [ %scevgep, %vector.body ], [ %b, %vector.ph ] + %vec.phi = phi <8 x i16> [ , %vector.ph ], [ %15, %vector.body ] + %8 = phi i32 [ %5, %vector.ph ], [ %16, %vector.body ] + %9 = phi i32 [ %N, %vector.ph ], [ %11, %vector.body ] + %lsr.iv2022 = bitcast i8* %lsr.iv20 to <8 x i8>* + %lsr.iv19 = bitcast i8* %lsr.iv to <8 x i8>* + %10 = call <8 x i1> @llvm.arm.mve.vctp16(i32 %9) + %11 = sub i32 %9, 8 + %wide.masked.load = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* %lsr.iv19, i32 1, <8 x i1> %10, <8 x i8> undef) + %12 = zext <8 x i8> %wide.masked.load to <8 x i16> + %wide.masked.load16 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* %lsr.iv2022, i32 1, <8 x i1> %10, <8 x i8> undef) + %13 = zext <8 x i8> %wide.masked.load16 to <8 x i16> + %14 = mul nuw <8 x i16> %13, %12 + %15 = sub <8 x i16> %vec.phi, %14 + %scevgep = getelementptr i8, i8* %lsr.iv, i32 8 + %scevgep21 = getelementptr i8, i8* %lsr.iv20, i32 8 + %16 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %8, i32 1) + %17 = icmp ne i32 %16, 0 + br i1 %17, label %vector.body, label %middle.block + + middle.block: ; preds = %vector.body + %vec.phi.lcssa = phi <8 x i16> [ %vec.phi, %vector.body ] + %.lcssa = phi <8 x i16> [ %15, %vector.body ] + %18 = call <8 x i1> @llvm.arm.mve.vctp16(i32 %7) + %19 = select <8 x i1> %18, <8 x i16> %.lcssa, <8 x i16> %vec.phi.lcssa + %20 = call i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16> %19) + br label %for.cond.cleanup + + for.cond.cleanup: ; preds = %middle.block, %entry + %a.0.lcssa = phi i16 [ 32767, %entry ], [ %20, %middle.block ] + ret i16 %a.0.lcssa + } + declare <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>*, i32 immarg, <8 x i1>, <8 x i8>) + declare i16 @llvm.experimental.vector.reduce.add.v8i16(<8 x i16>) + declare void @llvm.set.loop.iterations.i32(i32) + declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) + declare <8 x i1> @llvm.arm.mve.vctp16(i32) + +... +--- +name: wrong_liveout_shift +alignment: 16 +exposesReturnsTwice: false +legalized: false +regBankSelected: false +selected: false +failedISel: false +tracksRegLiveness: true +hasWinCFI: false +registers: [] +liveins: + - { reg: '$r0', virtual-reg: '' } + - { reg: '$r1', virtual-reg: '' } + - { reg: '$r2', virtual-reg: '' } +frameInfo: + isFrameAddressTaken: false + isReturnAddressTaken: false + hasStackMap: false + hasPatchPoint: false + stackSize: 8 + offsetAdjustment: 0 + maxAlignment: 4 + adjustsStack: false + hasCalls: false + stackProtector: '' + maxCallFrameSize: 0 + cvBytesOfCalleeSavedRegisters: 0 + hasOpaqueSPAdjustment: false + hasVAStart: false + hasMustTailInVarArgFunc: false + localFrameSize: 0 + savePoint: '' + restorePoint: '' +fixedStack: [] +stack: + - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } + - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } +callSites: [] +constants: + - id: 0 + value: '<8 x i16> ' + alignment: 16 + isTargetSpecific: false +machineFunctionInfo: {} +body: | + ; CHECK-LABEL: name: wrong_liveout_shift + ; CHECK: bb.0.entry: + ; CHECK: successors: %bb.1(0x80000000) + ; CHECK: liveins: $lr, $r0, $r1, $r2 + ; CHECK: tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + ; CHECK: t2IT 0, 2, implicit-def $itstate + ; CHECK: renamable $r0 = t2MOVi16 32767, 0, $cpsr, implicit killed $r0, implicit $itstate + ; CHECK: renamable $r0 = tSXTH killed renamable $r0, 0, $cpsr, implicit killed $r0, implicit $itstate + ; CHECK: tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + ; CHECK: frame-setup tPUSH 14, $noreg, killed $lr, implicit-def $sp, implicit $sp + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8 + ; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8 + ; CHECK: dead $r7 = frame-setup tMOVr $sp, 14, $noreg + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_register $r7 + ; CHECK: renamable $r3, dead $cpsr = tADDi3 renamable $r2, 7, 14, $noreg + ; CHECK: renamable $r3 = t2BICri killed renamable $r3, 7, 14, $noreg, $noreg + ; CHECK: renamable $r12 = t2SUBri killed renamable $r3, 8, 14, $noreg, $noreg + ; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + ; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r3, renamable $r12, 27, 14, $noreg, $noreg + ; CHECK: renamable $r3 = tLEApcrel %const.0, 14, $noreg + ; CHECK: renamable $r12 = t2LSRri killed renamable $r12, 2, 14, $noreg, $noreg + ; CHECK: renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from constant-pool) + ; CHECK: renamable $r3 = t2SUBrs renamable $r2, killed renamable $r12, 26, 14, $noreg, $noreg + ; CHECK: $lr = t2DLS killed renamable $lr + ; CHECK: bb.1.vector.body: + ; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000) + ; CHECK: liveins: $lr, $q0, $r0, $r1, $r2, $r3 + ; CHECK: renamable $vpr = MVE_VCTP16 renamable $r2, 0, $noreg + ; CHECK: $q1 = MVE_VORR killed $q0, killed $q0, 0, $noreg, undef $q1 + ; CHECK: MVE_VPST 4, implicit $vpr + ; CHECK: renamable $r0, renamable $q0 = MVE_VLDRBU16_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv19, align 1) + ; CHECK: renamable $r1, renamable $q2 = MVE_VLDRBU16_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv2022, align 1) + ; CHECK: renamable $q0 = nuw MVE_VMULi16 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0 + ; CHECK: renamable $q0 = MVE_VSUBi16 renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0 + ; CHECK: $lr = t2LEUpdate killed renamable $lr, %bb.1 + ; CHECK: bb.2.middle.block: + ; CHECK: liveins: $q0, $q1, $r3 + ; CHECK: renamable $vpr = MVE_VCTP16 killed renamable $r3, 0, $noreg + ; CHECK: renamable $q0 = MVE_VPSEL killed renamable $q0, killed renamable $q1, 0, killed renamable $vpr + ; CHECK: renamable $r0 = MVE_VADDVu16no_acc killed renamable $q0, 0, $noreg + ; CHECK: $sp = t2LDMIA_UPD $sp, 14, $noreg, def $r7, def $lr + ; CHECK: renamable $r0 = tSXTH killed renamable $r0, 14, $noreg + ; CHECK: tBX_RET 14, $noreg, implicit killed $r0 + ; CHECK: bb.3 (align 16): + ; CHECK: CONSTPOOL_ENTRY 0, %const.0, 16 + bb.0.entry: + successors: %bb.1(0x80000000) + liveins: $r0, $r1, $r2, $lr + + tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + t2IT 0, 2, implicit-def $itstate + renamable $r0 = t2MOVi16 32767, 0, $cpsr, implicit killed $r0, implicit $itstate + renamable $r0 = tSXTH killed renamable $r0, 0, $cpsr, implicit killed $r0, implicit $itstate + tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + frame-setup tPUSH 14, $noreg, killed $lr, implicit-def $sp, implicit $sp + frame-setup CFI_INSTRUCTION def_cfa_offset 8 + frame-setup CFI_INSTRUCTION offset $lr, -4 + frame-setup CFI_INSTRUCTION offset $r7, -8 + $r7 = frame-setup tMOVr $sp, 14, $noreg + frame-setup CFI_INSTRUCTION def_cfa_register $r7 + renamable $r3, dead $cpsr = tADDi3 renamable $r2, 7, 14, $noreg + renamable $r3 = t2BICri killed renamable $r3, 7, 14, $noreg, $noreg + renamable $r12 = t2SUBri killed renamable $r3, 8, 14, $noreg, $noreg + renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + renamable $lr = nuw nsw t2ADDrs killed renamable $r3, renamable $r12, 27, 14, $noreg, $noreg + renamable $r3 = tLEApcrel %const.0, 14, $noreg + renamable $r12 = t2LSRri killed renamable $r12, 2, 14, $noreg, $noreg + renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from constant-pool) + renamable $r3 = t2SUBrs renamable $r2, killed renamable $r12, 26, 14, $noreg, $noreg + t2DoLoopStart renamable $lr + + bb.1.vector.body: + successors: %bb.1(0x7c000000), %bb.2(0x04000000) + liveins: $lr, $q0, $r0, $r1, $r2, $r3 + + renamable $vpr = MVE_VCTP16 renamable $r2, 0, $noreg + $q1 = MVE_VORR killed $q0, $q0, 0, $noreg, undef $q1 + MVE_VPST 4, implicit $vpr + renamable $r0, renamable $q0 = MVE_VLDRBU16_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv19, align 1) + renamable $r1, renamable $q2 = MVE_VLDRBU16_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv2022, align 1) + renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 8, 14, $noreg + renamable $q0 = nuw MVE_VMULi16 killed renamable $q2, killed renamable $q0, 0, $noreg, undef renamable $q0 + renamable $lr = t2LoopDec killed renamable $lr, 1 + renamable $q0 = MVE_VSUBi16 renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0 + t2LoopEnd renamable $lr, %bb.1, implicit-def dead $cpsr + tB %bb.2, 14, $noreg + + bb.2.middle.block: + liveins: $q0, $q1, $r3 + + renamable $vpr = MVE_VCTP16 killed renamable $r3, 0, $noreg + renamable $q0 = MVE_VPSEL killed renamable $q0, killed renamable $q1, 0, killed renamable $vpr + renamable $r0 = MVE_VADDVu16no_acc killed renamable $q0, 0, $noreg + $sp = t2LDMIA_UPD $sp, 14, $noreg, def $r7, def $lr + renamable $r0 = tSXTH killed renamable $r0, 14, $noreg + tBX_RET 14, $noreg, implicit killed $r0 + + bb.3 (align 16): + CONSTPOOL_ENTRY 0, %const.0, 16 + +... Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/wrong-vctp-opcode-liveout.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/wrong-vctp-opcode-liveout.mir @@ -0,0 +1,210 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py +# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - | FileCheck %s + +# I think this should be equivalent, but the calculation in the middle block +# is too complex to process for now. + +--- | + define dso_local i32 @wrong_vctp_liveout(i16* nocapture readonly %a, i16* nocapture readonly %b, i32 %N) local_unnamed_addr #0 { + entry: + %cmp9 = icmp eq i32 %N, 0 + %tmp = add i32 %N, 3 + %tmp1 = lshr i32 %tmp, 2 + %tmp2 = shl nuw i32 %tmp1, 2 + %tmp3 = add i32 %tmp2, -4 + %tmp4 = lshr i32 %tmp3, 2 + %tmp5 = add nuw nsw i32 %tmp4, 1 + br i1 %cmp9, label %for.cond.cleanup, label %vector.ph + + vector.ph: ; preds = %entry + call void @llvm.set.loop.iterations.i32(i32 %tmp5) + br label %vector.body + + vector.body: ; preds = %vector.body, %vector.ph + %lsr.iv1 = phi i32 [ %lsr.iv.next, %vector.body ], [ %tmp5, %vector.ph ] + %lsr.iv18 = phi i16* [ %scevgep19, %vector.body ], [ %b, %vector.ph ] + %lsr.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ] + %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %tmp13, %vector.body ] + %tmp7 = phi i32 [ %N, %vector.ph ], [ %tmp9, %vector.body ] + %lsr.iv17 = bitcast i16* %lsr.iv to <4 x i16>* + %lsr.iv1820 = bitcast i16* %lsr.iv18 to <4 x i16>* + %tmp8 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %tmp7) + %tmp9 = sub i32 %tmp7, 4 + %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv17, i32 2, <4 x i1> %tmp8, <4 x i16> undef) + %tmp10 = sext <4 x i16> %wide.masked.load to <4 x i32> + %wide.masked.load14 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv1820, i32 2, <4 x i1> %tmp8, <4 x i16> undef) + %tmp11 = sext <4 x i16> %wide.masked.load14 to <4 x i32> + %tmp12 = mul nsw <4 x i32> %tmp11, %tmp10 + %tmp13 = add <4 x i32> %tmp12, %vec.phi + %scevgep = getelementptr i16, i16* %lsr.iv, i32 4 + %scevgep19 = getelementptr i16, i16* %lsr.iv18, i32 4 + %tmp14 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv1, i32 1) + %tmp15 = icmp ne i32 %tmp14, 0 + %lsr.iv.next = add nsw i32 %lsr.iv1, -1 + br i1 %tmp15, label %vector.body, label %middle.block + + middle.block: ; preds = %vector.body + %0 = add i32 %tmp9, 4 + %insert.idx = insertelement <4 x i32> undef, i32 %0, i32 0 + %idx.splat = shufflevector <4 x i32> %insert.idx, <4 x i32> undef, <4 x i32> zeroinitializer + %n.minusone = add i32 %N, -1 + %insert.n = insertelement <4 x i32> undef, i32 %n.minusone, i32 0 + %n.splat = shufflevector <4 x i32> %insert.n, <4 x i32> undef, <4 x i32> zeroinitializer + %tmp16 = icmp ult <4 x i32> %idx.splat, %n.splat + %tmp17 = select <4 x i1> %tmp16, <4 x i32> %tmp13, <4 x i32> %vec.phi + %tmp18 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %tmp17) + br label %for.cond.cleanup + + for.cond.cleanup: ; preds = %middle.block, %entry + %res.0.lcssa = phi i32 [ 0, %entry ], [ %tmp18, %middle.block ] + ret i32 %res.0.lcssa + } + declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32 immarg, <4 x i1>, <4 x i16>) #1 + declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>) #2 + declare void @llvm.set.loop.iterations.i32(i32) #3 + declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #3 + declare <4 x i1> @llvm.arm.mve.vctp32(i32) #4 + +... +--- +name: wrong_vctp_liveout +alignment: 2 +exposesReturnsTwice: false +legalized: false +regBankSelected: false +selected: false +failedISel: false +tracksRegLiveness: true +hasWinCFI: false +registers: [] +liveins: + - { reg: '$r0', virtual-reg: '' } + - { reg: '$r1', virtual-reg: '' } + - { reg: '$r2', virtual-reg: '' } +frameInfo: + isFrameAddressTaken: false + isReturnAddressTaken: false + hasStackMap: false + hasPatchPoint: false + stackSize: 8 + offsetAdjustment: 0 + maxAlignment: 4 + adjustsStack: false + hasCalls: false + stackProtector: '' + maxCallFrameSize: 0 + cvBytesOfCalleeSavedRegisters: 0 + hasOpaqueSPAdjustment: false + hasVAStart: false + hasMustTailInVarArgFunc: false + localFrameSize: 0 + savePoint: '' + restorePoint: '' +fixedStack: [] +stack: + - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } + - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } +callSites: [] +constants: [] +machineFunctionInfo: {} +body: | + ; CHECK-LABEL: name: wrong_vctp_liveout + ; CHECK: bb.0.entry: + ; CHECK: successors: %bb.1(0x80000000) + ; CHECK: liveins: $lr, $r0, $r1, $r2, $r7 + ; CHECK: tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + ; CHECK: t2IT 0, 4, implicit-def $itstate + ; CHECK: renamable $r0 = tMOVi8 $noreg, 0, 0, $cpsr, implicit killed $r0, implicit $itstate + ; CHECK: tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + ; CHECK: frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8 + ; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8 + ; CHECK: renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg + ; CHECK: renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1 + ; CHECK: renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg + ; CHECK: renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg + ; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + ; CHECK: renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg + ; CHECK: dead $lr = t2DLS renamable $r3 + ; CHECK: $r12 = tMOVr killed $r3, 14, $noreg + ; CHECK: $r3 = tMOVr $r2, 14, $noreg + ; CHECK: bb.1.vector.body: + ; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000) + ; CHECK: liveins: $q1, $r0, $r1, $r2, $r3, $r12 + ; CHECK: renamable $vpr = MVE_VCTP32 renamable $r3, 0, $noreg + ; CHECK: $q0 = MVE_VORR killed $q1, killed $q1, 0, $noreg, undef $q0 + ; CHECK: MVE_VPST 4, implicit $vpr + ; CHECK: renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2) + ; CHECK: renamable $r1, renamable $q2 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv1820, align 2) + ; CHECK: $lr = tMOVr $r12, 14, $noreg + ; CHECK: renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 + ; CHECK: renamable $r12 = nsw t2SUBri killed $r12, 1, 14, $noreg, $noreg + ; CHECK: renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14, $noreg + ; CHECK: renamable $q1 = MVE_VADDi32 killed renamable $q1, renamable $q0, 0, $noreg, undef renamable $q1 + ; CHECK: dead $lr = t2LEUpdate killed renamable $lr, %bb.1 + ; CHECK: bb.2.middle.block: + ; CHECK: liveins: $q0, $q1, $r2, $r3 + ; CHECK: renamable $r0, dead $cpsr = tSUBi3 killed renamable $r2, 1, 14, $noreg + ; CHECK: renamable $q2 = MVE_VDUP32 killed renamable $r0, 0, $noreg, undef renamable $q2 + ; CHECK: renamable $r0, dead $cpsr = tADDi3 killed renamable $r3, 4, 14, $noreg + ; CHECK: renamable $vpr = MVE_VCMPu32r killed renamable $q2, killed renamable $r0, 8, 0, $noreg + ; CHECK: renamable $q0 = MVE_VPSEL killed renamable $q1, killed renamable $q0, 0, killed renamable $vpr + ; CHECK: renamable $r0 = MVE_VADDVu32no_acc killed renamable $q0, 0, $noreg + ; CHECK: tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + bb.0.entry: + successors: %bb.1(0x80000000) + liveins: $r0, $r1, $r2, $lr, $r7 + + tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + t2IT 0, 4, implicit-def $itstate + renamable $r0 = tMOVi8 $noreg, 0, 0, $cpsr, implicit killed $r0, implicit $itstate + tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + frame-setup CFI_INSTRUCTION def_cfa_offset 8 + frame-setup CFI_INSTRUCTION offset $lr, -4 + frame-setup CFI_INSTRUCTION offset $r7, -8 + renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg + renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1 + renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg + renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg + renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg + t2DoLoopStart renamable $r3 + $r12 = tMOVr killed $r3, 14, $noreg + $r3 = tMOVr $r2, 14, $noreg + + bb.1.vector.body: + successors: %bb.1(0x7c000000), %bb.2(0x04000000) + liveins: $q1, $r0, $r1, $r2, $r3, $r12 + + renamable $vpr = MVE_VCTP32 renamable $r3, 0, $noreg + $q0 = MVE_VORR killed $q1, $q1, 0, $noreg, undef $q0 + MVE_VPST 4, implicit $vpr + renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2) + renamable $r1, renamable $q2 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv1820, align 2) + $lr = tMOVr $r12, 14, $noreg + renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 + renamable $r12 = nsw t2SUBri killed $r12, 1, 14, $noreg, $noreg + renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14, $noreg + renamable $q1 = MVE_VADDi32 killed renamable $q1, renamable $q0, 0, $noreg, undef renamable $q1 + renamable $lr = t2LoopDec killed renamable $lr, 1 + t2LoopEnd killed renamable $lr, %bb.1, implicit-def dead $cpsr + tB %bb.2, 14, $noreg + + bb.2.middle.block: + liveins: $q0, $q1, $r2, $r3 + + renamable $r0, dead $cpsr = tSUBi3 killed renamable $r2, 1, 14, $noreg + renamable $q2 = MVE_VDUP32 killed renamable $r0, 0, $noreg, undef renamable $q2 + renamable $r0, dead $cpsr = tADDi3 killed renamable $r3, 4, 14, $noreg + renamable $vpr = MVE_VCMPu32r killed renamable $q2, killed renamable $r0, 8, 0, $noreg + renamable $q0 = MVE_VPSEL killed renamable $q1, killed renamable $q0, 0, killed renamable $vpr + renamable $r0 = MVE_VADDVu32no_acc killed renamable $q0, 0, $noreg + tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + +... Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/wrong-vctp-operand-liveout.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/wrong-vctp-operand-liveout.mir @@ -0,0 +1,194 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py +# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - | FileCheck %s + +# The VCTP uses r2, which is redefined in the loop. + +--- | + define dso_local i32 @wrong_vctp_liveout(i16* nocapture readonly %a, i16* nocapture readonly %b, i32 %N) local_unnamed_addr #0 { + entry: + %cmp9 = icmp eq i32 %N, 0 + %0 = add i32 %N, 3 + %1 = lshr i32 %0, 2 + %2 = shl nuw i32 %1, 2 + %3 = add i32 %2, -4 + %4 = lshr i32 %3, 2 + %5 = add nuw nsw i32 %4, 1 + br i1 %cmp9, label %for.cond.cleanup, label %vector.ph + + vector.ph: ; preds = %entry + call void @llvm.set.loop.iterations.i32(i32 %5) + br label %vector.body + + vector.body: ; preds = %vector.body, %vector.ph + %lsr.iv1 = phi i32 [ %lsr.iv.next, %vector.body ], [ %5, %vector.ph ] + %lsr.iv18 = phi i16* [ %scevgep19, %vector.body ], [ %b, %vector.ph ] + %lsr.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ] + %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %12, %vector.body ] + %6 = phi i32 [ %N, %vector.ph ], [ %8, %vector.body ] + %lsr.iv17 = bitcast i16* %lsr.iv to <4 x i16>* + %lsr.iv1820 = bitcast i16* %lsr.iv18 to <4 x i16>* + %7 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %6) + %8 = sub i32 %6, 4 + %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv17, i32 2, <4 x i1> %7, <4 x i16> undef) + %9 = sext <4 x i16> %wide.masked.load to <4 x i32> + %wide.masked.load14 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv1820, i32 2, <4 x i1> %7, <4 x i16> undef) + %10 = sext <4 x i16> %wide.masked.load14 to <4 x i32> + %11 = mul nsw <4 x i32> %10, %9 + %12 = add <4 x i32> %11, %vec.phi + %scevgep = getelementptr i16, i16* %lsr.iv, i32 4 + %scevgep19 = getelementptr i16, i16* %lsr.iv18, i32 4 + %13 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv1, i32 1) + %14 = icmp ne i32 %13, 0 + %lsr.iv.next = add nsw i32 %lsr.iv1, -1 + br i1 %14, label %vector.body, label %middle.block + + middle.block: ; preds = %vector.body + %15 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %8) + %16 = select <4 x i1> %15, <4 x i32> %12, <4 x i32> %vec.phi + %17 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %16) + br label %for.cond.cleanup + + for.cond.cleanup: ; preds = %middle.block, %entry + %res.0.lcssa = phi i32 [ 0, %entry ], [ %17, %middle.block ] + ret i32 %res.0.lcssa + } + declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32 immarg, <4 x i1>, <4 x i16>) #1 + declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>) #2 + declare void @llvm.set.loop.iterations.i32(i32) #3 + declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #3 + declare <4 x i1> @llvm.arm.mve.vctp32(i32) #4 +... +--- +name: wrong_vctp_liveout +alignment: 2 +exposesReturnsTwice: false +legalized: false +regBankSelected: false +selected: false +failedISel: false +tracksRegLiveness: true +hasWinCFI: false +registers: [] +liveins: + - { reg: '$r0', virtual-reg: '' } + - { reg: '$r1', virtual-reg: '' } + - { reg: '$r2', virtual-reg: '' } +frameInfo: + isFrameAddressTaken: false + isReturnAddressTaken: false + hasStackMap: false + hasPatchPoint: false + stackSize: 8 + offsetAdjustment: 0 + maxAlignment: 4 + adjustsStack: false + hasCalls: false + stackProtector: '' + maxCallFrameSize: 0 + cvBytesOfCalleeSavedRegisters: 0 + hasOpaqueSPAdjustment: false + hasVAStart: false + hasMustTailInVarArgFunc: false + localFrameSize: 0 + savePoint: '' + restorePoint: '' +fixedStack: [] +stack: + - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } + - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4, + stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true, + debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } +callSites: [] +constants: [] +machineFunctionInfo: {} +body: | + ; CHECK-LABEL: name: wrong_vctp_liveout + ; CHECK: bb.0.entry: + ; CHECK: successors: %bb.1(0x80000000) + ; CHECK: liveins: $lr, $r0, $r1, $r2, $r7 + ; CHECK: tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + ; CHECK: t2IT 0, 4, implicit-def $itstate + ; CHECK: renamable $r0 = tMOVi8 $noreg, 0, 0, $cpsr, implicit killed $r0, implicit $itstate + ; CHECK: tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + ; CHECK: frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8 + ; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4 + ; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8 + ; CHECK: renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg + ; CHECK: renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1 + ; CHECK: renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg + ; CHECK: renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg + ; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + ; CHECK: renamable $r12 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg + ; CHECK: dead $lr = t2DLS renamable $r12 + ; CHECK: $r3 = tMOVr killed $r12, 14, $noreg + ; CHECK: bb.1.vector.body: + ; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000) + ; CHECK: liveins: $q1, $r0, $r1, $r2, $r3 + ; CHECK: renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg + ; CHECK: $q0 = MVE_VORR killed $q1, killed $q1, 0, $noreg, undef $q0 + ; CHECK: MVE_VPST 4, implicit $vpr + ; CHECK: renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2) + ; CHECK: renamable $r1, renamable $q2 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv1820, align 2) + ; CHECK: $lr = tMOVr $r3, 14, $noreg + ; CHECK: renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 + ; CHECK: renamable $r3, dead $cpsr = nsw tSUBi8 killed $r3, 1, 14, $noreg + ; CHECK: renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg + ; CHECK: renamable $q1 = MVE_VADDi32 killed renamable $q1, renamable $q0, 0, $noreg, undef renamable $q1 + ; CHECK: dead $lr = t2LEUpdate killed renamable $lr, %bb.1 + ; CHECK: bb.2.middle.block: + ; CHECK: liveins: $q0, $q1, $r2 + ; CHECK: renamable $vpr = MVE_VCTP32 killed renamable $r2, 0, $noreg + ; CHECK: renamable $q0 = MVE_VPSEL killed renamable $q1, killed renamable $q0, 0, killed renamable $vpr + ; CHECK: renamable $r0 = MVE_VADDVu32no_acc killed renamable $q0, 0, $noreg + ; CHECK: tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + bb.0.entry: + successors: %bb.1(0x80000000) + liveins: $r0, $r1, $r2, $lr, $r7 + + tCMPi8 renamable $r2, 0, 14, $noreg, implicit-def $cpsr + t2IT 0, 4, implicit-def $itstate + renamable $r0 = tMOVi8 $noreg, 0, 0, $cpsr, implicit killed $r0, implicit $itstate + tBX_RET 0, killed $cpsr, implicit $r0, implicit killed $itstate + frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp + frame-setup CFI_INSTRUCTION def_cfa_offset 8 + frame-setup CFI_INSTRUCTION offset $lr, -4 + frame-setup CFI_INSTRUCTION offset $r7, -8 + renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg + renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1 + renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg + renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg + renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg + renamable $r12 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg + t2DoLoopStart renamable $r12 + $r3 = tMOVr killed $r12, 14, $noreg + + bb.1.vector.body: + successors: %bb.1(0x7c000000), %bb.2(0x04000000) + liveins: $q1, $r0, $r1, $r2, $r3 + + renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg + $q0 = MVE_VORR killed $q1, $q1, 0, $noreg, undef $q0 + MVE_VPST 4, implicit $vpr + renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2) + renamable $r1, renamable $q2 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv1820, align 2) + $lr = tMOVr $r3, 14, $noreg + renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 + renamable $r3, dead $cpsr = nsw tSUBi8 killed $r3, 1, 14, $noreg + renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg + renamable $q1 = MVE_VADDi32 killed renamable $q1, renamable $q0, 0, $noreg, undef renamable $q1 + renamable $lr = t2LoopDec killed renamable $lr, 1 + t2LoopEnd killed renamable $lr, %bb.1, implicit-def dead $cpsr + tB %bb.2, 14, $noreg + + bb.2.middle.block: + liveins: $q0, $q1, $r2 + + renamable $vpr = MVE_VCTP32 killed renamable $r2, 0, $noreg + renamable $q0 = MVE_VPSEL killed renamable $q1, killed renamable $q0, 0, killed renamable $vpr + renamable $r0 = MVE_VADDVu32no_acc killed renamable $q0, 0, $noreg + tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0 + +...