llvm-project/llvm/test/CodeGen/AArch64/loop-sink-limit.mir

179 lines
7.0 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple aarch64 -run-pass=machine-sink -sink-insts-to-avoid-spills \
# RUN: -machine-sink-loop-limit=1 -verify-machineinstrs %s -o - 2>&1 | \
# RUN: FileCheck %s --check-prefix=SINK1
#
# RUN: llc -mtriple aarch64 -run-pass=machine-sink -sink-insts-to-avoid-spills \
# RUN: -machine-sink-loop-limit=2 -verify-machineinstrs %s -o - 2>&1 | \
# RUN: FileCheck %s --check-prefix=SINK2
--- |
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64"
@A = external dso_local global [100 x i32], align 4
%struct.A = type { i32, i32, i32, i32, i32, i32 }
define i32 @do_sink_use_is_not_a_copy(i32 %n) {
entry:
%cmp63 = icmp sgt i32 %n, 0
br i1 %cmp63, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
%0 = load i32, i32* getelementptr inbounds ([100 x i32], [100 x i32]* @A, i64 0, i64 0), align 4
br label %for.body
for.cond.cleanup: ; preds = %for.body, %entry
%sum.0.lcssa = phi i32 [ %n, %entry ], [ %div, %for.body ]
ret i32 %sum.0.lcssa
for.body: ; preds = %for.body, %for.body.preheader
%lsr.iv = phi i32 [ %n, %for.body.preheader ], [ %lsr.iv.next, %for.body ]
%sum.065 = phi i32 [ %div, %for.body ], [ %n, %for.body.preheader ]
%div = sdiv i32 %sum.065, %0
%lsr.iv.next = add i32 %lsr.iv, -1
%exitcond.not = icmp eq i32 %lsr.iv.next, 0
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
...
---
name: do_sink_use_is_not_a_copy
alignment: 4
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
failedISel: false
tracksRegLiveness: true
hasWinCFI: false
registers:
- { id: 0, class: gpr32, preferred-register: '' }
- { id: 1, class: gpr32all, preferred-register: '' }
- { id: 2, class: gpr32sp, preferred-register: '' }
- { id: 3, class: gpr32, preferred-register: '' }
- { id: 4, class: gpr32all, preferred-register: '' }
- { id: 5, class: gpr32all, preferred-register: '' }
- { id: 6, class: gpr32common, preferred-register: '' }
- { id: 7, class: gpr32, preferred-register: '' }
- { id: 8, class: gpr64common, preferred-register: '' }
- { id: 9, class: gpr32, preferred-register: '' }
- { id: 10, class: gpr32, preferred-register: '' }
- { id: 11, class: gpr32, preferred-register: '' }
liveins:
- { reg: '$w0', virtual-reg: '%6' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 1
adjustsStack: false
hasCalls: false
stackProtector: ''
maxCallFrameSize: 0
cvBytesOfCalleeSavedRegisters: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
localFrameSize: 0
savePoint: ''
restorePoint: ''
fixedStack: []
stack: []
callSites: []
debugValueSubstitutions: []
constants: []
machineFunctionInfo: {}
body: |
; SINK1-LABEL: name: do_sink_use_is_not_a_copy
; SINK1: bb.0.entry:
; SINK1: successors: %bb.1(0x50000000), %bb.2(0x30000000)
; SINK1: liveins: $w0
; SINK1: [[COPY:%[0-9]+]]:gpr32common = COPY $w0
; SINK1: [[SUBSWri:%[0-9]+]]:gpr32 = SUBSWri [[COPY]], 1, 0, implicit-def $nzcv
; SINK1: Bcc 11, %bb.2, implicit $nzcv
; SINK1: B %bb.1
; SINK1: bb.1.for.body.preheader:
; SINK1: successors: %bb.3(0x80000000)
; SINK1: [[ADRP:%[0-9]+]]:gpr64common = ADRP target-flags(aarch64-page) @A
; SINK1: [[LDRWui:%[0-9]+]]:gpr32 = LDRWui killed [[ADRP]], target-flags(aarch64-pageoff, aarch64-nc) @A :: (dereferenceable load 4 from `i32* getelementptr inbounds ([100 x i32], [100 x i32]* @A, i64 0, i64 0)`)
; SINK1: B %bb.3
; SINK1: bb.2.for.cond.cleanup:
; SINK1: [[PHI:%[0-9]+]]:gpr32all = PHI [[COPY]], %bb.0, %4, %bb.3
; SINK1: $w0 = COPY [[PHI]]
; SINK1: RET_ReallyLR implicit $w0
; SINK1: bb.3.for.body:
; SINK1: successors: %bb.2(0x04000000), %bb.3(0x7c000000)
; SINK1: [[PHI1:%[0-9]+]]:gpr32sp = PHI [[COPY]], %bb.1, %5, %bb.3
; SINK1: [[PHI2:%[0-9]+]]:gpr32 = PHI [[COPY]], %bb.1, %4, %bb.3
; SINK1: [[SDIVWr:%[0-9]+]]:gpr32 = SDIVWr [[PHI2]], [[LDRWui]]
; SINK1: [[COPY1:%[0-9]+]]:gpr32all = COPY [[SDIVWr]]
; SINK1: [[SUBSWri1:%[0-9]+]]:gpr32 = SUBSWri [[PHI1]], 1, 0, implicit-def $nzcv
; SINK1: [[COPY2:%[0-9]+]]:gpr32all = COPY [[SUBSWri1]]
; SINK1: Bcc 0, %bb.2, implicit $nzcv
; SINK1: B %bb.3
; SINK2-LABEL: name: do_sink_use_is_not_a_copy
; SINK2: bb.0.entry:
; SINK2: successors: %bb.1(0x50000000), %bb.2(0x30000000)
; SINK2: liveins: $w0
; SINK2: [[COPY:%[0-9]+]]:gpr32common = COPY $w0
; SINK2: [[SUBSWri:%[0-9]+]]:gpr32 = SUBSWri [[COPY]], 1, 0, implicit-def $nzcv
; SINK2: Bcc 11, %bb.2, implicit $nzcv
; SINK2: B %bb.1
; SINK2: bb.1.for.body.preheader:
; SINK2: successors: %bb.3(0x80000000)
; SINK2: [[ADRP:%[0-9]+]]:gpr64common = ADRP target-flags(aarch64-page) @A
; SINK2: [[LDRWui:%[0-9]+]]:gpr32 = LDRWui killed [[ADRP]], target-flags(aarch64-pageoff, aarch64-nc) @A :: (dereferenceable load 4 from `i32* getelementptr inbounds ([100 x i32], [100 x i32]* @A, i64 0, i64 0)`)
; SINK2: B %bb.3
; SINK2: bb.2.for.cond.cleanup:
; SINK2: [[PHI:%[0-9]+]]:gpr32all = PHI [[COPY]], %bb.0, %4, %bb.3
; SINK2: $w0 = COPY [[PHI]]
; SINK2: RET_ReallyLR implicit $w0
; SINK2: bb.3.for.body:
; SINK2: successors: %bb.2(0x04000000), %bb.3(0x7c000000)
; SINK2: [[PHI1:%[0-9]+]]:gpr32sp = PHI [[COPY]], %bb.1, %5, %bb.3
; SINK2: [[PHI2:%[0-9]+]]:gpr32 = PHI [[COPY]], %bb.1, %4, %bb.3
; SINK2: [[SDIVWr:%[0-9]+]]:gpr32 = SDIVWr [[PHI2]], [[LDRWui]]
; SINK2: [[COPY1:%[0-9]+]]:gpr32all = COPY [[SDIVWr]]
; SINK2: [[SUBSWri1:%[0-9]+]]:gpr32 = SUBSWri [[PHI1]], 1, 0, implicit-def $nzcv
; SINK2: [[COPY2:%[0-9]+]]:gpr32all = COPY [[SUBSWri1]]
; SINK2: Bcc 0, %bb.2, implicit $nzcv
; SINK2: B %bb.3
bb.0.entry:
successors: %bb.1(0x50000000), %bb.2(0x30000000)
liveins: $w0
%6:gpr32common = COPY $w0
%7:gpr32 = SUBSWri %6, 1, 0, implicit-def $nzcv
Bcc 11, %bb.2, implicit $nzcv
B %bb.1
bb.1.for.body.preheader:
successors: %bb.3(0x80000000)
%8:gpr64common = ADRP target-flags(aarch64-page) @A
%9:gpr32 = LDRWui killed %8, target-flags(aarch64-pageoff, aarch64-nc) @A :: (dereferenceable load 4 from `i32* getelementptr inbounds ([100 x i32], [100 x i32]* @A, i64 0, i64 0)`)
B %bb.3
bb.2.for.cond.cleanup:
%1:gpr32all = PHI %6, %bb.0, %4, %bb.3
$w0 = COPY %1
RET_ReallyLR implicit $w0
bb.3.for.body:
successors: %bb.2(0x04000000), %bb.3(0x7c000000)
%2:gpr32sp = PHI %6, %bb.1, %5, %bb.3
%3:gpr32 = PHI %6, %bb.1, %4, %bb.3
%10:gpr32 = SDIVWr %3, %9
%4:gpr32all = COPY %10
%11:gpr32 = SUBSWri %2, 1, 0, implicit-def $nzcv
%5:gpr32all = COPY %11
Bcc 0, %bb.2, implicit $nzcv
B %bb.3
...