| # RUN: llc -mtriple=armv8.1m.main -mattr=+lob -run-pass=arm-low-overhead-loops --verify-machineinstrs %s -o - | FileCheck %s |
| # CHECK: for.body: |
| # CHECK-NOT: t2DLS |
| # CHECK-NOT: t2LEUpdate |
| |
| --- | |
| ; ModuleID = 'massive.ll' |
| source_filename = "massive.ll" |
| target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64" |
| target triple = "thumbv8.1m.main" |
| |
| define dso_local arm_aapcscc void @massive(i32* nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %c, i32 %N) { |
| entry: |
| %cmp8 = icmp eq i32 %N, 0 |
| br i1 %cmp8, label %for.cond.cleanup, label %for.body.preheader |
| |
| for.body.preheader: ; preds = %entry |
| %scevgep = getelementptr i32, i32* %a, i32 -1 |
| %scevgep4 = getelementptr i32, i32* %c, i32 -1 |
| %scevgep8 = getelementptr i32, i32* %b, i32 -1 |
| call void @llvm.set.loop.iterations.i32(i32 %N) |
| br label %for.body |
| |
| for.cond.cleanup: ; preds = %for.body, %entry |
| ret void |
| |
| for.body: ; preds = %for.body, %for.body.preheader |
| %lsr.iv9 = phi i32* [ %scevgep8, %for.body.preheader ], [ %scevgep10, %for.body ] |
| %lsr.iv5 = phi i32* [ %scevgep4, %for.body.preheader ], [ %scevgep6, %for.body ] |
| %lsr.iv1 = phi i32* [ %scevgep, %for.body.preheader ], [ %scevgep2, %for.body ] |
| %0 = phi i32 [ %N, %for.body.preheader ], [ %3, %for.body ] |
| %size = call i32 @llvm.arm.space(i32 4096, i32 undef) |
| %scevgep3 = getelementptr i32, i32* %lsr.iv9, i32 1 |
| %1 = load i32, i32* %scevgep3, align 4 |
| %scevgep7 = getelementptr i32, i32* %lsr.iv5, i32 1 |
| %2 = load i32, i32* %scevgep7, align 4 |
| %mul = mul nsw i32 %2, %1 |
| %scevgep11 = getelementptr i32, i32* %lsr.iv1, i32 1 |
| store i32 %mul, i32* %scevgep11, align 4 |
| %scevgep2 = getelementptr i32, i32* %lsr.iv1, i32 1 |
| %scevgep6 = getelementptr i32, i32* %lsr.iv5, i32 1 |
| %scevgep10 = getelementptr i32, i32* %lsr.iv9, i32 1 |
| %3 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %0, i32 1) |
| %4 = icmp ne i32 %3, 0 |
| br i1 %4, label %for.body, label %for.cond.cleanup |
| } |
| |
| ; Function Attrs: nounwind |
| declare i32 @llvm.arm.space(i32 immarg, i32) #0 |
| |
| ; Function Attrs: noduplicate nounwind |
| declare void @llvm.set.loop.iterations.i32(i32) #1 |
| |
| ; Function Attrs: noduplicate nounwind |
| declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #1 |
| |
| ; Function Attrs: nounwind |
| declare void @llvm.stackprotector(i8*, i8**) #0 |
| |
| attributes #0 = { nounwind } |
| attributes #1 = { noduplicate nounwind } |
| |
| ... |
| --- |
| name: massive |
| 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: 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: | |
| bb.0.entry: |
| successors: %bb.1(0x80000000) |
| liveins: $r0, $r1, $r2, $r3, $r7, $lr |
| |
| 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 |
| tCMPi8 $r3, 0, 14, $noreg, implicit-def $cpsr |
| t2IT 0, 8, implicit-def $itstate |
| tPOP_RET 0, killed $cpsr, def $r7, def $pc, implicit killed $itstate |
| renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 4, 14, $noreg |
| renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg |
| renamable $r0, dead $cpsr = tSUBi8 killed renamable $r0, 4, 14, $noreg |
| $lr = tMOVr $r3, 14, $noreg |
| t2DoLoopStart killed $r3 |
| |
| bb.1.for.body: |
| successors: %bb.1(0x7c000000), %bb.2(0x04000000) |
| liveins: $lr, $r0, $r1, $r2 |
| |
| dead renamable $r3 = SPACE 4096, undef renamable $r0 |
| renamable $r12, renamable $r1 = t2LDR_PRE killed renamable $r1, 4, 14, $noreg :: (load 4 from %ir.scevgep3) |
| renamable $r3, renamable $r2 = t2LDR_PRE killed renamable $r2, 4, 14, $noreg :: (load 4 from %ir.scevgep7) |
| renamable $r3 = nsw t2MUL killed renamable $r3, killed renamable $r12, 14, $noreg |
| early-clobber renamable $r0 = t2STR_PRE killed renamable $r3, killed renamable $r0, 4, 14, $noreg :: (store 4 into %ir.scevgep11) |
| renamable $lr = t2LoopDec killed renamable $lr, 1 |
| t2LoopEnd renamable $lr, %bb.1, implicit-def dead $cpsr |
| tB %bb.2, 14, $noreg |
| |
| bb.2.for.cond.cleanup: |
| tPOP_RET 14, $noreg, def $r7, def $pc |
| |
| ... |