maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/Thumb2/LowOverheadLoops/invariant-qreg.mir

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

474 lines
24 KiB
Plaintext
Raw Normal View History

[ARM][MVE] Validate tail predication values Iterate through the loop and check that the observable values produced are the same whether tail predication happens or not. We want to find out if the tail-predicated version of this loop will produce the same values as the loop in its original form. For this to be true, the newly inserted implicit predication must not change the the (observable) results. We're doing this because many instructions in the loop will not be predicated and so the conversion from VPT predication to tail predication can result in different values being produced, because of falsely predicated lanes not being updated in the converted form. A masked load, whether through VPT or tail predication, will write zeros to any of the falsely predicated bytes. So, from the loads, we know that the false lanes are zeroed and here we're trying to track that those false lanes remain zero, or where they change, the differences are masked away by their user(s). All MVE loads and stores have to be predicated, so we know that any load operands, or stored results are equivalent already. Other explicitly predicated instructions will perform the same operation in the original loop and the tail-predicated form too. Because of this, we can insert loads, stores and other predicated instructions into our KnownFalseZeros set and build from there. Differential Revision: https://reviews.llvm.org/D75452
2020-03-10 17:58:29 +08:00
# 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 <4 x i32> @invariant_use_store(i16* nocapture readonly %a, i32* %c, i32 %N, <4 x i32> %pass) {
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 %exit, 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.iv20 = phi i32* [ %scevgep20, %vector.body ], [ %c, %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.store = bitcast i32* %lsr.iv20 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>
%tmp12 = mul nsw <4 x i32> %pass, %tmp10
%tmp13 = add <4 x i32> %tmp12, %vec.phi
call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp13, <4 x i32>* %lsr.store, i32 4, <4 x i1> %tmp8)
%scevgep = getelementptr i16, i16* %lsr.iv, i32 4
%scevgep20 = getelementptr i32, i32* %lsr.iv20, 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 %exit
exit: ; preds = %vector.body, %entry
ret <4 x i32> %pass
}
define dso_local i32 @invariant_mul_use_reduce(i16* nocapture readonly %a, i32* %c, i32 %N, <4 x i32> %pass) {
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 %exit, 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.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
%tmp7 = phi i32 [ %N, %vector.ph ], [ %tmp9, %vector.body ]
%lsr.iv17 = bitcast i16* %lsr.iv 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>
%tmp12 = mul nsw <4 x i32> %pass, %tmp10
%tmp13 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %tmp12)
%scevgep = getelementptr i16, i16* %lsr.iv, 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 %exit
exit: ; preds = %vector.body, %entry
%res = phi i32 [ 0, %entry ], [ %tmp13, %vector.body ]
ret i32 %res
}
define dso_local i32 @invariant_add_use_reduce(i16* nocapture readonly %a, i32* %c, i32 %N, <4 x i32> %pass) {
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 %exit, 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.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
%tmp7 = phi i32 [ %N, %vector.ph ], [ %tmp9, %vector.body ]
%lsr.iv17 = bitcast i16* %lsr.iv 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>
%tmp12 = add nsw <4 x i32> %pass, %tmp10
%tmp13 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %tmp12)
%scevgep = getelementptr i16, i16* %lsr.iv, 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 %exit
exit: ; preds = %vector.body, %entry
%res = phi i32 [ 0, %entry ], [ %tmp13, %vector.body ]
ret i32 %res
}
declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>)
declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32 immarg, <4 x i1>, <4 x i16>)
declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>)
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: invariant_use_store
alignment: 2
tracksRegLiveness: true
registers: []
liveins:
- { reg: '$r0', virtual-reg: '' }
- { reg: '$r1', virtual-reg: '' }
- { reg: '$r2', virtual-reg: '' }
frameInfo:
stackSize: 8
offsetAdjustment: 0
maxAlignment: 8
fixedStack:
- { id: 0, type: default, offset: 0, size: 16, alignment: 8, stack-id: default,
isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
stack:
- { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$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: '' }
callSites: []
constants: []
machineFunctionInfo: {}
body: |
; CHECK-LABEL: name: invariant_use_store
; CHECK: bb.0.entry:
; CHECK: successors: %bb.3(0x30000000), %bb.1(0x50000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r7
; CHECK: frame-setup tPUSH 14 /* CC::al */, $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 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
; CHECK: renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
; CHECK: tCBZ $r2, %bb.3
; CHECK: bb.1.vector.ph:
; CHECK: successors: %bb.2(0x80000000)
; CHECK: liveins: $q0, $r0, $r1, $r2
; CHECK: renamable $q1 = MVE_VMOVimmi32 0, 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, $r0, $r1
; CHECK: renamable $r0, renamable $q2 = MVE_VLDRHS32_post killed renamable $r0, 8, 0, $noreg :: (load 8 from %ir.lsr.iv17, align 2)
; CHECK: renamable $q2 = nsw MVE_VMULi32 renamable $q0, killed renamable $q2, 0, $noreg, undef renamable $q2
; CHECK: renamable $q1 = MVE_VADDi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1
; CHECK: renamable $r1 = MVE_VSTRWU32_post renamable $q1, killed renamable $r1, 16, 0, killed $noreg :: (store 16 into %ir.lsr.store, align 4)
; CHECK: $lr = MVE_LETP killed renamable $lr, %bb.2
; CHECK: bb.3.exit:
; CHECK: liveins: $q0
; CHECK: renamable $r0, renamable $r1 = VMOVRRD renamable $d0, 14 /* CC::al */, $noreg
; CHECK: renamable $r2, renamable $r3 = VMOVRRD killed renamable $d1, 14 /* CC::al */, $noreg, implicit killed $q0
; CHECK: tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0, implicit killed $r1, implicit killed $r2, implicit killed $r3
bb.0.entry:
successors: %bb.3(0x30000000), %bb.1(0x50000000)
liveins: $r0, $r1, $r2, $r7, $lr
frame-setup tPUSH 14 /* CC::al */, $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 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
tCBZ $r2, %bb.3
bb.1.vector.ph:
successors: %bb.2(0x80000000)
liveins: $q0, $r0, $r1, $r2
renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1
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 $r12 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
t2DoLoopStart renamable $r12
$r3 = tMOVr killed $r12, 14 /* CC::al */, $noreg
bb.2.vector.body:
successors: %bb.2(0x7c000000), %bb.3(0x04000000)
liveins: $q0, $q1, $r0, $r1, $r2, $r3
renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
MVE_VPST 8, implicit $vpr
renamable $r0, renamable $q2 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2)
$lr = tMOVr $r3, 14 /* CC::al */, $noreg
renamable $q2 = nsw MVE_VMULi32 renamable $q0, killed renamable $q2, 0, $noreg, undef renamable $q2
renamable $r3, dead $cpsr = nsw tSUBi8 killed $r3, 1, 14 /* CC::al */, $noreg
renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
renamable $q1 = MVE_VADDi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1
renamable $lr = t2LoopDec killed renamable $lr, 1
MVE_VPST 8, implicit $vpr
renamable $r1 = MVE_VSTRWU32_post renamable $q1, killed renamable $r1, 16, 1, killed renamable $vpr :: (store 16 into %ir.lsr.store, align 4)
t2LoopEnd killed renamable $lr, %bb.2, implicit-def dead $cpsr
tB %bb.3, 14 /* CC::al */, $noreg
bb.3.exit:
liveins: $q0
renamable $r0, renamable $r1 = VMOVRRD renamable $d0, 14 /* CC::al */, $noreg
renamable $r2, renamable $r3 = VMOVRRD killed renamable $d1, 14 /* CC::al */, $noreg, implicit $q0
tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0, implicit killed $r1, implicit killed $r2, implicit killed $r3
...
---
name: invariant_mul_use_reduce
alignment: 2
tracksRegLiveness: true
registers: []
liveins:
- { reg: '$r0', virtual-reg: '' }
- { reg: '$r2', virtual-reg: '' }
frameInfo:
stackSize: 8
offsetAdjustment: 0
maxAlignment: 8
fixedStack:
- { id: 0, type: default, offset: 0, size: 16, alignment: 8, stack-id: default,
isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
stack:
- { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$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: '' }
callSites: []
constants: []
machineFunctionInfo: {}
body: |
; CHECK-LABEL: name: invariant_mul_use_reduce
; CHECK: bb.0.entry:
; CHECK: successors: %bb.4(0x30000000), %bb.1(0x50000000)
; CHECK: liveins: $lr, $r0, $r2, $r7
; CHECK: frame-setup tPUSH 14 /* CC::al */, $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: tCBZ $r2, %bb.4
; CHECK: bb.1.vector.ph:
; CHECK: successors: %bb.2(0x80000000)
; CHECK: liveins: $r0, $r2
; CHECK: renamable $r1, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
; CHECK: renamable $r1 = t2BICri killed renamable $r1, 3, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 4, 14 /* CC::al */, $noreg
; CHECK: renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r1, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r1 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
; CHECK: renamable $q0 = MVE_VLDRWU32 killed renamable $r1, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
; CHECK: dead $lr = t2DLS renamable $r3
; CHECK: $r1 = tMOVr killed $r3, 14 /* CC::al */, $noreg
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $q0, $r0, $r1, $r2
; CHECK: renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
; CHECK: $lr = tMOVr $r1, 14 /* CC::al */, $noreg
; CHECK: renamable $r1, dead $cpsr = nsw tSUBi8 killed $r1, 1, 14 /* CC::al */, $noreg
; CHECK: renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
; CHECK: MVE_VPST 8, implicit $vpr
; CHECK: renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2)
; CHECK: renamable $r12 = MVE_VMLADAVu32 renamable $q0, killed renamable $q1, 0, $noreg
; CHECK: dead $lr = t2LEUpdate killed renamable $lr, %bb.2
; CHECK: bb.3.exit:
; CHECK: liveins: $r12
; CHECK: $r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
; CHECK: tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
; CHECK: bb.4:
; CHECK: renamable $r12 = t2MOVi 0, 14 /* CC::al */, $noreg, $noreg
; CHECK: $r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
; CHECK: tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
bb.0.entry:
successors: %bb.4(0x30000000), %bb.1(0x50000000)
liveins: $r0, $r2, $r7, $lr
frame-setup tPUSH 14 /* CC::al */, $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
tCBZ $r2, %bb.4
bb.1.vector.ph:
successors: %bb.2(0x80000000)
liveins: $r0, $r2
renamable $r1, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
renamable $r1 = t2BICri killed renamable $r1, 3, 14 /* CC::al */, $noreg, $noreg
renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 4, 14 /* CC::al */, $noreg
renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r1, 19, 14 /* CC::al */, $noreg, $noreg
renamable $r1 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
renamable $q0 = MVE_VLDRWU32 killed renamable $r1, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
t2DoLoopStart renamable $r3
$r1 = tMOVr killed $r3, 14 /* CC::al */, $noreg
bb.2.vector.body:
successors: %bb.2(0x7c000000), %bb.3(0x04000000)
liveins: $q0, $r0, $r1, $r2
renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
$lr = tMOVr $r1, 14 /* CC::al */, $noreg
renamable $r1, dead $cpsr = nsw tSUBi8 killed $r1, 1, 14 /* CC::al */, $noreg
renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
MVE_VPST 8, implicit $vpr
renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2)
renamable $r12 = MVE_VMLADAVu32 renamable $q0, killed renamable $q1, 0, $noreg
renamable $lr = t2LoopDec killed renamable $lr, 1
t2LoopEnd killed renamable $lr, %bb.2, implicit-def dead $cpsr
tB %bb.3, 14 /* CC::al */, $noreg
bb.3.exit:
liveins: $r12
$r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
bb.4:
renamable $r12 = t2MOVi 0, 14 /* CC::al */, $noreg, $noreg
$r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
...
---
name: invariant_add_use_reduce
alignment: 2
tracksRegLiveness: true
registers: []
liveins:
- { reg: '$r0', virtual-reg: '' }
- { reg: '$r2', virtual-reg: '' }
frameInfo:
stackSize: 8
offsetAdjustment: 0
maxAlignment: 8
fixedStack:
- { id: 0, type: default, offset: 0, size: 16, alignment: 8, stack-id: default,
isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
stack:
- { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$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: '' }
callSites: []
constants: []
machineFunctionInfo: {}
body: |
; CHECK-LABEL: name: invariant_add_use_reduce
; CHECK: bb.0.entry:
; CHECK: successors: %bb.4(0x30000000), %bb.1(0x50000000)
; CHECK: liveins: $lr, $r0, $r2, $r7
; CHECK: frame-setup tPUSH 14 /* CC::al */, $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: tCBZ $r2, %bb.4
; CHECK: bb.1.vector.ph:
; CHECK: successors: %bb.2(0x80000000)
; CHECK: liveins: $r0, $r2
; CHECK: renamable $r1, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
; CHECK: renamable $r1 = t2BICri killed renamable $r1, 3, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 4, 14 /* CC::al */, $noreg
; CHECK: renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r1, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r1 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
; CHECK: renamable $q0 = MVE_VLDRWU32 killed renamable $r1, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
; CHECK: dead $lr = t2DLS renamable $r3
; CHECK: $r1 = tMOVr killed $r3, 14 /* CC::al */, $noreg
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $q0, $r0, $r1, $r2
; CHECK: renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
; CHECK: MVE_VPST 8, implicit $vpr
; CHECK: renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2)
; CHECK: $lr = tMOVr $r1, 14 /* CC::al */, $noreg
; CHECK: renamable $q1 = nsw MVE_VADDi32 renamable $q0, killed renamable $q1, 0, $noreg, undef renamable $q1
; CHECK: renamable $r1, dead $cpsr = nsw tSUBi8 killed $r1, 1, 14 /* CC::al */, $noreg
; CHECK: renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
; CHECK: renamable $r12 = MVE_VADDVu32no_acc killed renamable $q1, 0, $noreg
; CHECK: dead $lr = t2LEUpdate killed renamable $lr, %bb.2
; CHECK: bb.3.exit:
; CHECK: liveins: $r12
; CHECK: $r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
; CHECK: tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
; CHECK: bb.4:
; CHECK: renamable $r12 = t2MOVi 0, 14 /* CC::al */, $noreg, $noreg
; CHECK: $r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
; CHECK: tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
bb.0.entry:
successors: %bb.4(0x30000000), %bb.1(0x50000000)
liveins: $r0, $r2, $r7, $lr
frame-setup tPUSH 14 /* CC::al */, $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
tCBZ $r2, %bb.4
bb.1.vector.ph:
successors: %bb.2(0x80000000)
liveins: $r0, $r2
renamable $r1, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
renamable $r1 = t2BICri killed renamable $r1, 3, 14 /* CC::al */, $noreg, $noreg
renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 4, 14 /* CC::al */, $noreg
renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r1, 19, 14 /* CC::al */, $noreg, $noreg
renamable $r1 = tADDrSPi $sp, 2, 14 /* CC::al */, $noreg
renamable $q0 = MVE_VLDRWU32 killed renamable $r1, 0, 0, $noreg :: (load 16 from %fixed-stack.0, align 8)
t2DoLoopStart renamable $r3
$r1 = tMOVr killed $r3, 14 /* CC::al */, $noreg
bb.2.vector.body:
successors: %bb.2(0x7c000000), %bb.3(0x04000000)
liveins: $q0, $r0, $r1, $r2
renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
MVE_VPST 8, implicit $vpr
renamable $r0, renamable $q1 = MVE_VLDRHS32_post killed renamable $r0, 8, 1, killed renamable $vpr :: (load 8 from %ir.lsr.iv17, align 2)
$lr = tMOVr $r1, 14 /* CC::al */, $noreg
renamable $q1 = nsw MVE_VADDi32 renamable $q0, killed renamable $q1, 0, $noreg, undef renamable $q1
renamable $r1, dead $cpsr = nsw tSUBi8 killed $r1, 1, 14 /* CC::al */, $noreg
renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
renamable $r12 = MVE_VADDVu32no_acc killed renamable $q1, 0, $noreg
renamable $lr = t2LoopDec killed renamable $lr, 1
t2LoopEnd killed renamable $lr, %bb.2, implicit-def dead $cpsr
tB %bb.3, 14 /* CC::al */, $noreg
bb.3.exit:
liveins: $r12
$r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
bb.4:
renamable $r12 = t2MOVi 0, 14 /* CC::al */, $noreg, $noreg
$r0 = tMOVr killed $r12, 14 /* CC::al */, $noreg
tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc, implicit killed $r0
...