| # 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 a VPNOT is not added to a max sized VPT block. |
| |
| --- | |
| define dso_local void @inloop_vpnot(i16* nocapture readonly %a, i16* nocapture readonly %b, i16* nocapture readonly %c, i16* nocapture readonly %d, i32* nocapture %e, 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 |
| %start = call i32 @llvm.start.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 ], [ %start, %vector.ph ] |
| %lsr.iv.e = phi i32* [ %scevgep.e, %vector.body ], [ %e, %vector.ph ] |
| %lsr.iv.d = phi i16* [ %scevgep.d, %vector.body ], [ %d, %vector.ph ] |
| %lsr.iv.c = phi i16* [ %scevgep.c, %vector.body ], [ %c, %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 ], [ %tmp14, %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>* |
| %lsr.iv1820.c = bitcast i16* %lsr.iv.c to <4 x i16>* |
| %lsr.iv17.d = bitcast i16* %lsr.iv.d to <4 x i16>* |
| %lsr.cast.e = bitcast i32* %lsr.iv.e to <4 x i32>* |
| %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> |
| %wide.masked.load.c = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv1820.c, i32 2, <4 x i1> %tmp8, <4 x i16> undef) |
| %sext.load.c = sext <4 x i16> %wide.masked.load.c to <4 x i32> |
| %wide.masked.load.d = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %lsr.iv17.d, i32 2, <4 x i1> %tmp8, <4 x i16> undef) |
| %sext.load.d = sext <4 x i16> %wide.masked.load.d to <4 x i32> |
| %tmp12 = mul nsw <4 x i32> %tmp11, %tmp10 |
| %mul.2 = mul nsw <4 x i32> %sext.load.c, %sext.load.d |
| %tmp13 = add <4 x i32> %tmp12, %mul.2 |
| %tmp14 = add <4 x i32> %tmp13, %vec.phi |
| %vpnot = xor <4 x i1> %tmp8, <i1 true, i1 true, i1 true, i1 true> |
| call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp14, <4 x i32>* %lsr.cast.e, i32 4, <4 x i1> %vpnot) |
| %scevgep = getelementptr i16, i16* %lsr.iv, i32 4 |
| %scevgep19 = getelementptr i16, i16* %lsr.iv18, i32 4 |
| %scevgep.c = getelementptr i16, i16* %lsr.iv.c, i32 4 |
| %scevgep.d = getelementptr i16, i16* %lsr.iv.d, i32 4 |
| %scevgep.e = getelementptr i32, i32* %lsr.iv.e, i32 4 |
| %tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv1, i32 1) |
| %tmp16 = icmp ne i32 %tmp15, 0 |
| %lsr.iv.next = add nsw i32 %lsr.iv1, -1 |
| br i1 %tmp16, label %vector.body, label %for.cond.cleanup |
| |
| for.cond.cleanup: ; preds = %vector.body, %entry |
| ret void |
| } |
| declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32 immarg, <4 x i1>, <4 x i16>) #1 |
| declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>) #2 |
| declare i32 @llvm.start.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: inloop_vpnot |
| 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: '$r2', virtual-reg: '' } |
| - { reg: '$r3', virtual-reg: '' } |
| frameInfo: |
| isFrameAddressTaken: false |
| isReturnAddressTaken: false |
| hasStackMap: false |
| hasPatchPoint: false |
| stackSize: 16 |
| offsetAdjustment: 0 |
| maxAlignment: 4 |
| adjustsStack: false |
| hasCalls: false |
| stackProtector: '' |
| maxCallFrameSize: 0 |
| cvBytesOfCalleeSavedRegisters: 0 |
| hasOpaqueSPAdjustment: false |
| hasVAStart: false |
| hasMustTailInVarArgFunc: false |
| localFrameSize: 0 |
| savePoint: '' |
| restorePoint: '' |
| fixedStack: |
| - { id: 0, type: default, offset: 4, size: 4, alignment: 4, stack-id: default, |
| isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true, |
| debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } |
| - { id: 1, type: default, offset: 0, size: 4, alignment: 8, stack-id: default, |
| isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true, |
| debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } |
| 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: '' } |
| - { id: 2, name: '', type: spill-slot, offset: -12, size: 4, alignment: 4, |
| stack-id: default, callee-saved-register: '$r5', callee-saved-restored: true, |
| debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } |
| - { id: 3, name: '', type: spill-slot, offset: -16, size: 4, alignment: 4, |
| stack-id: default, callee-saved-register: '$r4', callee-saved-restored: true, |
| debug-info-variable: '', debug-info-expression: '', debug-info-location: '' } |
| callSites: [] |
| constants: [] |
| machineFunctionInfo: {} |
| body: | |
| ; CHECK-LABEL: name: inloop_vpnot |
| ; CHECK: bb.0.entry: |
| ; CHECK: successors: %bb.3(0x30000000), %bb.1(0x50000000) |
| ; CHECK: liveins: $lr, $r0, $r1, $r2, $r3, $r4, $r5, $r7 |
| ; CHECK: frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r4, killed $r5, killed $r7, killed $lr, implicit-def $sp, implicit $sp |
| ; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 16 |
| ; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4 |
| ; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8 |
| ; CHECK: frame-setup CFI_INSTRUCTION offset $r5, -12 |
| ; CHECK: frame-setup CFI_INSTRUCTION offset $r4, -16 |
| ; CHECK: renamable $r12 = t2LDRi12 $sp, 20, 14 /* CC::al */, $noreg :: (load (s32) from %fixed-stack.1) |
| ; CHECK: t2CMPri renamable $r12, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr |
| ; CHECK: tBcc %bb.3, 0 /* CC::eq */, killed $cpsr |
| ; CHECK: bb.1.vector.ph: |
| ; CHECK: successors: %bb.2(0x80000000) |
| ; CHECK: liveins: $r0, $r1, $r2, $r3, $r12 |
| ; CHECK: renamable $lr = t2ADDri renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg |
| ; CHECK: renamable $r4, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg |
| ; CHECK: renamable $lr = t2BICri killed renamable $lr, 3, 14 /* CC::al */, $noreg, $noreg |
| ; CHECK: renamable $r5 = tLDRspi $sp, 4, 14 /* CC::al */, $noreg :: (load (s32) from %fixed-stack.0, align 8) |
| ; CHECK: renamable $lr = t2SUBri killed renamable $lr, 4, 14 /* CC::al */, $noreg, $noreg |
| ; CHECK: renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0 |
| ; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $lr, 19, 14 /* CC::al */, $noreg, $noreg |
| ; CHECK: $r4 = tMOVr killed $lr, 14 /* CC::al */, $noreg |
| ; CHECK: bb.2.vector.body: |
| ; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000) |
| ; CHECK: liveins: $q0, $r0, $r1, $r2, $r3, $r4, $r5, $r12 |
| ; CHECK: renamable $vpr = MVE_VCTP32 renamable $r12, 0, $noreg |
| ; CHECK: MVE_VPST 4, implicit $vpr |
| ; CHECK: renamable $r3, renamable $q1 = MVE_VLDRHS32_post killed renamable $r3, 8, 1, renamable $vpr :: (load (s64) from %ir.lsr.iv17.d, align 2) |
| ; CHECK: renamable $r2, renamable $q2 = MVE_VLDRHS32_post killed renamable $r2, 8, 1, renamable $vpr :: (load (s64) from %ir.lsr.iv1820.c, align 2) |
| ; CHECK: renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 |
| ; CHECK: MVE_VPST 4, implicit $vpr |
| ; CHECK: renamable $r0, renamable $q2 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load (s64) from %ir.lsr.iv17, align 2) |
| ; CHECK: renamable $r1, renamable $q3 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, renamable $vpr :: (load (s64) from %ir.lsr.iv1820, align 2) |
| ; CHECK: $lr = tMOVr $r4, 14 /* CC::al */, $noreg |
| ; CHECK: renamable $r4, dead $cpsr = nsw tSUBi8 killed $r4, 1, 14 /* CC::al */, $noreg |
| ; CHECK: renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg |
| ; CHECK: MVE_VPST 2, implicit $vpr |
| ; CHECK: renamable $q2 = nsw MVE_VMULi32 killed renamable $q3, killed renamable $q2, 0, $noreg, undef renamable $q2 |
| ; CHECK: renamable $q1 = MVE_VADDi32 killed renamable $q2, killed renamable $q1, 0, renamable $vpr, undef renamable $q1 |
| ; CHECK: renamable $q0 = MVE_VADDi32 killed renamable $q1, killed renamable $q0, 0, renamable $vpr, undef renamable $q0 |
| ; CHECK: renamable $r5 = MVE_VSTRWU32_post renamable $q0, killed renamable $r5, 16, 1, renamable $vpr :: (store (s128) into %ir.lsr.cast.e, align 4) |
| ; CHECK: dead renamable $vpr = MVE_VPNOT killed renamable $vpr, 0, $noreg |
| ; CHECK: dead $lr = t2LEUpdate killed renamable $lr, %bb.2 |
| ; CHECK: bb.3.for.cond.cleanup: |
| ; CHECK: tPOP_RET 14 /* CC::al */, $noreg, def $r4, def $r5, def $r7, def $pc |
| bb.0.entry: |
| successors: %bb.3(0x30000000), %bb.1(0x50000000) |
| liveins: $r0, $r1, $r2, $r3, $r4, $r5, $r7, $lr |
| |
| frame-setup tPUSH 14, $noreg, killed $r4, killed $r5, killed $r7, killed $lr, implicit-def $sp, implicit $sp |
| frame-setup CFI_INSTRUCTION def_cfa_offset 16 |
| frame-setup CFI_INSTRUCTION offset $lr, -4 |
| frame-setup CFI_INSTRUCTION offset $r7, -8 |
| frame-setup CFI_INSTRUCTION offset $r5, -12 |
| frame-setup CFI_INSTRUCTION offset $r4, -16 |
| renamable $r12 = t2LDRi12 $sp, 20, 14, $noreg :: (load (s32) from %fixed-stack.0) |
| t2CMPri renamable $r12, 0, 14, $noreg, implicit-def $cpsr |
| tBcc %bb.3, 0, killed $cpsr |
| |
| bb.1.vector.ph: |
| successors: %bb.2(0x80000000) |
| liveins: $r0, $r1, $r2, $r3, $r12 |
| |
| renamable $lr = t2ADDri renamable $r12, 3, 14, $noreg, $noreg |
| renamable $r4, dead $cpsr = tMOVi8 1, 14, $noreg |
| renamable $lr = t2BICri killed renamable $lr, 3, 14, $noreg, $noreg |
| renamable $r5 = tLDRspi $sp, 4, 14, $noreg :: (load (s32) from %fixed-stack.1, align 8) |
| renamable $lr = t2SUBri killed renamable $lr, 4, 14, $noreg, $noreg |
| renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0 |
| renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $lr, 19, 14, $noreg, $noreg |
| $lr = t2DoLoopStart renamable $lr |
| $r4 = tMOVr killed $lr, 14, $noreg |
| |
| bb.2.vector.body: |
| successors: %bb.2(0x7c000000), %bb.3(0x04000000) |
| liveins: $q0, $r0, $r1, $r2, $r3, $r4, $r5, $r12 |
| |
| renamable $vpr = MVE_VCTP32 renamable $r12, 0, $noreg |
| MVE_VPST 4, implicit $vpr |
| renamable $r3, renamable $q1 = MVE_VLDRHS32_post killed renamable $r3, 8, 1, renamable $vpr :: (load (s64) from %ir.lsr.iv17.d, align 2) |
| renamable $r2, renamable $q2 = MVE_VLDRHS32_post killed renamable $r2, 8, 1, renamable $vpr :: (load (s64) from %ir.lsr.iv1820.c, align 2) |
| renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1 |
| MVE_VPST 4, implicit $vpr |
| renamable $r0, renamable $q2 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load (s64) from %ir.lsr.iv17, align 2) |
| renamable $r1, renamable $q3 = MVE_VLDRHS32_post killed renamable $r1, 8, 1, renamable $vpr :: (load (s64) from %ir.lsr.iv1820, align 2) |
| $lr = tMOVr $r4, 14, $noreg |
| renamable $r4, dead $cpsr = nsw tSUBi8 killed $r4, 1, 14, $noreg |
| renamable $r12 = t2SUBri killed renamable $r12, 4, 14, $noreg, $noreg |
| MVE_VPST 2, implicit $vpr |
| renamable $q2 = nsw MVE_VMULi32 killed renamable $q3, killed renamable $q2, 0, $noreg, undef renamable $q2 |
| renamable $q1 = MVE_VADDi32 killed renamable $q2, killed renamable $q1, 0, renamable $vpr, undef renamable $q1 |
| renamable $q0 = MVE_VADDi32 killed renamable $q1, killed renamable $q0, 0, renamable $vpr, undef renamable $q0 |
| renamable $r5 = MVE_VSTRWU32_post renamable $q0, killed renamable $r5, 16, 1, renamable $vpr :: (store (s128) into %ir.lsr.cast.e, align 4) |
| renamable $vpr = MVE_VPNOT renamable $vpr, 0, $noreg |
| renamable $lr = t2LoopDec killed renamable $lr, 1 |
| t2LoopEnd killed renamable $lr, %bb.2, implicit-def dead $cpsr |
| tB %bb.3, 14, $noreg |
| |
| bb.3.for.cond.cleanup: |
| tPOP_RET 14, $noreg, def $r4, def $r5, def $r7, def $pc |
| |
| ... |
