# 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 -verify-machineinstrs -o - | FileCheck %s --- | ; Function Attrs: nofree norecurse nounwind define dso_local arm_aapcs_vfpcc void @test(i32* noalias nocapture %a, i32* 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 %div = lshr i32 %N, 1 %trip.count.minus.1 = add i32 %N, -1 %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0 %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer %start = call i32 @llvm.start.loop.iterations.i32(i32 %5) br label %vector.body vector.body: ; preds = %vector.body, %vector.ph %lsr.iv3 = phi i32* [ %scevgep4, %vector.body ], [ %b, %vector.ph ] %lsr.iv1 = phi i32* [ %scevgep, %vector.body ], [ %a, %vector.ph ] %vec.ind = phi <4 x i32> [ , %vector.ph ], [ %vec.ind.next, %vector.body ] %elts.rem = phi i32 [ %N, %vector.ph ], [ %elts.rem.next, %vector.body ] %6 = phi i32 [ %start, %vector.ph ], [ %12, %vector.body ] %lsr.iv35 = bitcast i32* %lsr.iv3 to <4 x i32>* %lsr.iv12 = bitcast i32* %lsr.iv1 to <4 x i32>* %7 = insertelement <4 x i32> undef, i32 %div, i32 0 %8 = shufflevector <4 x i32> %7, <4 x i32> undef, <4 x i32> zeroinitializer %9 = icmp ult <4 x i32> %vec.ind, %8 %10 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %elts.rem) %11 = and <4 x i1> %9, %10 %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv35, i32 4, <4 x i1> %11, <4 x i32> undef) call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %wide.masked.load, <4 x i32>* %lsr.iv12, i32 4, <4 x i1> %11) %vec.ind.next = add <4 x i32> %vec.ind, %elts.rem.next = sub i32 %elts.rem, 4 %scevgep = getelementptr i32, i32* %lsr.iv1, i32 4 %scevgep4 = getelementptr i32, i32* %lsr.iv3, i32 4 %12 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %6, i32 1) %13 = icmp ne i32 %12, 0 br i1 %13, label %vector.body, label %for.cond.cleanup for.cond.cleanup: ; preds = %vector.body, %entry ret void } declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>) declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>) declare <4 x i1> @llvm.arm.mve.vctp32(i32) declare i32 @llvm.start.loop.iterations.i32(i32) declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) ... --- name: test alignment: 16 tracksRegLiveness: true registers: [] liveins: - { reg: '$r0', virtual-reg: '' } - { reg: '$r1', virtual-reg: '' } - { reg: '$r2', virtual-reg: '' } frameInfo: stackSize: 8 offsetAdjustment: 0 maxAlignment: 4 fixedStack: [] stack: - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4, stack-id: default, callee-saved-register: '$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: - id: 0 value: '<4 x i32> ' alignment: 16 isTargetSpecific: false machineFunctionInfo: {} body: | ; CHECK-LABEL: name: test ; CHECK: bb.0.entry: ; CHECK: successors: %bb.1(0x80000000) ; CHECK: liveins: $lr, $r0, $r1, $r2 ; CHECK: frame-setup tPUSH 14 /* CC::al */, $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 /* CC::al */, $noreg ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_register $r7 ; CHECK: tCMPi8 renamable $r2, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr ; CHECK: t2IT 0, 8, implicit-def $itstate ; CHECK: frame-destroy tPOP_RET 0 /* CC::eq */, killed $cpsr, def $r7, def $pc, implicit killed $itstate ; CHECK: bb.1.vector.ph: ; CHECK: successors: %bb.2(0x80000000) ; CHECK: liveins: $r0, $r1, $r2 ; CHECK: renamable $q2 = MVE_VMOVimmi32 4, 0, $noreg, undef renamable $q2 ; CHECK: renamable $r3 = tLEApcrel %const.0, 14 /* CC::al */, $noreg ; CHECK: renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from constant-pool) ; CHECK: renamable $r3, dead $cpsr = tLSRri renamable $r2, 1, 14 /* CC::al */, $noreg ; CHECK: renamable $q1 = MVE_VDUP32 killed renamable $r3, 0, $noreg, undef renamable $q1 ; CHECK: $lr = MVE_DLSTP_32 killed renamable $r2 ; CHECK: bb.2.vector.body: ; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000) ; CHECK: liveins: $lr, $q0, $q1, $q2, $r0, $r1 ; CHECK: MVE_VPTv4u32 4, renamable $q1, renamable $q0, 8, implicit-def $vpr ; CHECK: renamable $r1, renamable $q3 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv35, align 4) ; CHECK: renamable $r0 = MVE_VSTRWU32_post killed renamable $q3, killed renamable $r0, 16, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv12, align 4) ; CHECK: renamable $q0 = MVE_VADDi32 killed renamable $q0, renamable $q2, 0, $noreg, undef renamable $q0 ; CHECK: $lr = MVE_LETP killed renamable $lr, %bb.2 ; CHECK: bb.3.for.cond.cleanup: ; CHECK: frame-destroy tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc ; CHECK: bb.4 (align 16): ; CHECK: CONSTPOOL_ENTRY 0, %const.0, 16 bb.0.entry: successors: %bb.1(0x80000000) liveins: $r0, $r1, $r2, $lr frame-setup tPUSH 14 /* CC::al */, $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 /* CC::al */, $noreg frame-setup CFI_INSTRUCTION def_cfa_register $r7 tCMPi8 renamable $r2, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr t2IT 0, 8, implicit-def $itstate frame-destroy tPOP_RET 0 /* CC::eq */, killed $cpsr, def $r7, def $pc, implicit killed $itstate bb.1.vector.ph: successors: %bb.2(0x80000000) liveins: $r0, $r1, $r2, $lr renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg renamable $q2 = MVE_VMOVimmi32 4, 0, $noreg, undef renamable $q2 renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg renamable $r3 = tLEApcrel %const.0, 14 /* CC::al */, $noreg renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from constant-pool) renamable $r3, dead $cpsr = tLSRri renamable $r2, 1, 14 /* CC::al */, $noreg renamable $q1 = MVE_VDUP32 killed renamable $r3, 0, $noreg, undef renamable $q1 $lr = t2DoLoopStart renamable $lr bb.2.vector.body: successors: %bb.2(0x7c000000), %bb.3(0x04000000) liveins: $lr, $q0, $q1, $q2, $r0, $r1, $r2 renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg MVE_VPST 2, implicit $vpr renamable $vpr = MVE_VCMPu32 renamable $q1, renamable $q0, 8, 1, killed renamable $vpr renamable $r1, renamable $q3 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv35, align 4) renamable $r0 = MVE_VSTRWU32_post killed renamable $q3, killed renamable $r0, 16, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv12, align 4) renamable $q0 = MVE_VADDi32 killed renamable $q0, renamable $q2, 0, $noreg, undef renamable $q0 renamable $lr = t2LoopDec killed renamable $lr, 1 t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr tB %bb.3, 14 /* CC::al */, $noreg bb.3.for.cond.cleanup: frame-destroy tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc bb.4 (align 16): CONSTPOOL_ENTRY 0, %const.0, 16 ...