Skip to content

[MachineOutliner] Sort by Benefit to Cost Ratio #90264

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Jun 7, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions llvm/lib/CodeGen/MachineOutliner.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -828,10 +828,12 @@ bool MachineOutliner::outline(Module &M,
<< "\n");
bool OutlinedSomething = false;

// Sort by benefit. The most beneficial functions should be outlined first.
// Sort by priority where priority := getNotOutlinedCost / getOutliningCost.
// The function with highest priority should be outlined first.
stable_sort(FunctionList,
[](const OutlinedFunction &LHS, const OutlinedFunction &RHS) {
return LHS.getBenefit() > RHS.getBenefit();
return LHS.getNotOutlinedCost() * RHS.getOutliningCost() >
RHS.getNotOutlinedCost() * LHS.getOutliningCost();
});

// Walk over each function, outlining them as we go along. Functions are
Expand Down
96 changes: 96 additions & 0 deletions llvm/test/CodeGen/AArch64/machine-outliner-sort-per-priority.ll
Original file line number Diff line number Diff line change
@@ -0,0 +1,96 @@
; This tests the order in which functions are outlined in MachineOutliner
; There are TWO key OutlinedFunction in FunctionList
;
; ===================== First One =====================
; ```
; mov w0, #1
; mov w1, #2
; mov w2, #3
; mov w3, #4
; mov w4, #5
; ```
; It has:
; - `SequenceSize=20` and `OccurrenceCount=6`
; - each Candidate has `CallOverhead=12` and `FrameOverhead=4`
; - `NotOutlinedCost=20*6=120` and `OutliningCost=12*6+20+4=96`
; - `Benefit=120-96=24` and `Priority=120/96=1.25`
;
; ===================== Second One =====================
; ```
; mov w6, #6
; mov w7, #7
; b
; ```
; It has:
; - `SequenceSize=12` and `OccurrenceCount=4`
; - each Candidate has `CallOverhead=4` and `FrameOverhead=0`
; - `NotOutlinedCost=12*4=48` and `OutliningCost=4*4+12+0=28`
; - `Benefit=48-28=20` and `Priority=48/28=1.71`
;
; Note that the first one has higher benefit, but lower priority.
; Hence, when outlining per priority, the second one will be outlined first.

; RUN: llc %s -enable-machine-outliner=always -filetype=obj -o %t
; RUN: llvm-objdump -d %t | FileCheck %s --check-prefix=CHECK-SORT-BY-PRIORITY

; RUN: llc %s -enable-machine-outliner=always -outliner-benefit-threshold=22 -filetype=obj -o %t
; RUN: llvm-objdump -d %t | FileCheck %s --check-prefix=CHECK-THRESHOLD


target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
target triple = "arm64-apple-macosx14.0.0"

declare i32 @_Z3fooiiii(i32 noundef, i32 noundef, i32 noundef, i32 noundef, i32 noundef, i32 noundef, i32 noundef, i32 noundef)

define i32 @_Z2f1v() minsize {
%1 = tail call i32 @_Z3fooiiii(i32 noundef 1, i32 noundef 2, i32 noundef 3, i32 noundef 4, i32 noundef 5, i32 noundef 11, i32 noundef 6, i32 noundef 7)
ret i32 %1
}

define i32 @_Z2f2v() minsize {
%1 = tail call i32 @_Z3fooiiii(i32 noundef 1, i32 noundef 2, i32 noundef 3, i32 noundef 4, i32 noundef 5, i32 noundef 12, i32 noundef 6, i32 noundef 7)
ret i32 %1
}

define i32 @_Z2f3v() minsize {
%1 = tail call i32 @_Z3fooiiii(i32 noundef 1, i32 noundef 2, i32 noundef 3, i32 noundef 4, i32 noundef 5, i32 noundef 13, i32 noundef 6, i32 noundef 7)
ret i32 %1
}

define i32 @_Z2f4v() minsize {
%1 = tail call i32 @_Z3fooiiii(i32 noundef 1, i32 noundef 2, i32 noundef 3, i32 noundef 4, i32 noundef 5, i32 noundef 14, i32 noundef 6, i32 noundef 7)
ret i32 %1
}

define i32 @_Z2f5v() minsize {
%1 = tail call i32 @_Z3fooiiii(i32 noundef 1, i32 noundef 2, i32 noundef 3, i32 noundef 4, i32 noundef 5, i32 noundef 15, i32 noundef 8, i32 noundef 9)
ret i32 %1
}

define i32 @_Z2f6v() minsize {
%1 = tail call i32 @_Z3fooiiii(i32 noundef 1, i32 noundef 2, i32 noundef 3, i32 noundef 4, i32 noundef 5, i32 noundef 16, i32 noundef 9, i32 noundef 8)
ret i32 %1
}

; CHECK-SORT-BY-PRIORITY: <_OUTLINED_FUNCTION_0>:
; CHECK-SORT-BY-PRIORITY-NEXT: mov w6, #0x6
; CHECK-SORT-BY-PRIORITY-NEXT: mov w7, #0x7
; CHECK-SORT-BY-PRIORITY-NEXT: b

; CHECK-SORT-BY-PRIORITY: <_OUTLINED_FUNCTION_1>:
; CHECK-SORT-BY-PRIORITY-NEXT: mov w0, #0x1
; CHECK-SORT-BY-PRIORITY-NEXT: mov w1, #0x2
; CHECK-SORT-BY-PRIORITY-NEXT: mov w2, #0x3
; CHECK-SORT-BY-PRIORITY-NEXT: mov w3, #0x4
; CHECK-SORT-BY-PRIORITY-NEXT: mov w4, #0x5
; CHECK-SORT-BY-PRIORITY-NEXT: ret

; CHECK-THRESHOLD: <_OUTLINED_FUNCTION_0>:
; CHECK-THRESHOLD-NEXT: mov w0, #0x1
; CHECK-THRESHOLD-NEXT: mov w1, #0x2
; CHECK-THRESHOLD-NEXT: mov w2, #0x3
; CHECK-THRESHOLD-NEXT: mov w3, #0x4
; CHECK-THRESHOLD-NEXT: mov w4, #0x5
; CHECK-THRESHOLD-NEXT: ret

; CHECK-THRESHOLD-NOT: <_OUTLINED_FUNCTION_1>:
206 changes: 206 additions & 0 deletions llvm/test/CodeGen/AArch64/machine-outliner-sort-per-priority.mir
Original file line number Diff line number Diff line change
@@ -0,0 +1,206 @@
# The content of this test is modfied upon the output obtained from running
# `bin/llc -O2 -stop-before=machine-outliner <path_to_llvm_project>/llvm/test/CodeGen/AArch64/machine-outliner-sort-per-priority.ll -o -`
# RUN: llc -mtriple=aarch64 -run-pass=machine-outliner -verify-machineinstrs %s -o - | FileCheck %s

--- |
declare i32 @foo()

define void @f1() #0 { ret void }
define void @f2() #0 { ret void }
define void @f3() #0 { ret void }
define void @f4() #0 { ret void }
define void @f5() #0 { ret void }
define void @f6() #0 { ret void }

attributes #0 = { minsize }
...
---
# CHECK-LABEL: name: f1
# CHECK-LABEL: bb.0:
# CHECK-NEXT: liveins: $lr
# CHECK-NEXT: {{ $}}
# CHECK-NEXT: $x5 = ORRXrs $xzr, $lr, 0
# CHECK-NEXT: BL @OUTLINED_FUNCTION_1
# CHECK-NEXT: $lr = ORRXrs $xzr, $x5, 0
# CHECK-NEXT: $w5 = MOVZWi 11, 0
# CHECK-NEXT: TCRETURNdi @OUTLINED_FUNCTION_0
name: f1
tracksRegLiveness: true
frameInfo:
isCalleeSavedInfoValid: true
machineFunctionInfo:
hasRedZone: false
body: |
bb.0:
$w0 = MOVZWi 1, 0
$w1 = MOVZWi 2, 0
$w2 = MOVZWi 3, 0
$w3 = MOVZWi 4, 0
$w4 = MOVZWi 5, 0
$w5 = MOVZWi 11, 0
$w6 = MOVZWi 6, 0
$w7 = MOVZWi 7, 0
TCRETURNdi @foo, 0, csr_darwin_aarch64_aapcs, implicit $sp, implicit killed $w0, implicit killed $w1, implicit killed $w2, implicit killed $w3, implicit killed $w4, implicit killed $w5, implicit killed $w6, implicit killed $w7

...
---
# CHECK-LABEL: name: f2
# CHECK-LABEL: bb.0:
# CHECK-NEXT: liveins: $lr
# CHECK-NEXT: {{ $}}
# CHECK-NEXT: $x5 = ORRXrs $xzr, $lr, 0
# CHECK-NEXT: BL @OUTLINED_FUNCTION_1
# CHECK-NEXT: $lr = ORRXrs $xzr, $x5, 0
# CHECK-NEXT: $w5 = MOVZWi 12, 0
# CHECK-NEXT: TCRETURNdi @OUTLINED_FUNCTION_0
name: f2
tracksRegLiveness: true
frameInfo:
isCalleeSavedInfoValid: true
machineFunctionInfo:
hasRedZone: false
body: |
bb.0:
$w0 = MOVZWi 1, 0
$w1 = MOVZWi 2, 0
$w2 = MOVZWi 3, 0
$w3 = MOVZWi 4, 0
$w4 = MOVZWi 5, 0
$w5 = MOVZWi 12, 0
$w6 = MOVZWi 6, 0
$w7 = MOVZWi 7, 0
TCRETURNdi @foo, 0, csr_darwin_aarch64_aapcs, implicit $sp, implicit killed $w0, implicit killed $w1, implicit killed $w2, implicit killed $w3, implicit killed $w4, implicit killed $w5, implicit killed $w6, implicit killed $w7

...
---
# CHECK-LABEL: name: f3
# CHECK-LABEL: bb.0:
# CHECK-NEXT: liveins: $lr
# CHECK-NEXT: {{ $}}
# CHECK-NEXT: $x5 = ORRXrs $xzr, $lr, 0
# CHECK-NEXT: BL @OUTLINED_FUNCTION_1
# CHECK-NEXT: $lr = ORRXrs $xzr, $x5, 0
# CHECK-NEXT: $w5 = MOVZWi 13, 0
# CHECK-NEXT: TCRETURNdi @OUTLINED_FUNCTION_0
name: f3
tracksRegLiveness: true
frameInfo:
isCalleeSavedInfoValid: true
machineFunctionInfo:
hasRedZone: false
body: |
bb.0:
$w0 = MOVZWi 1, 0
$w1 = MOVZWi 2, 0
$w2 = MOVZWi 3, 0
$w3 = MOVZWi 4, 0
$w4 = MOVZWi 5, 0
$w5 = MOVZWi 13, 0
$w6 = MOVZWi 6, 0
$w7 = MOVZWi 7, 0
TCRETURNdi @foo, 0, csr_darwin_aarch64_aapcs, implicit $sp, implicit killed $w0, implicit killed $w1, implicit killed $w2, implicit killed $w3, implicit killed $w4, implicit killed $w5, implicit killed $w6, implicit killed $w7

...
---
# CHECK-LABEL: name: f4
# CHECK-LABEL: bb.0:
# CHECK-NEXT: liveins: $lr
# CHECK-NEXT: {{ $}}
# CHECK-NEXT: $x5 = ORRXrs $xzr, $lr, 0
# CHECK-NEXT: BL @OUTLINED_FUNCTION_1
# CHECK-NEXT: $lr = ORRXrs $xzr, $x5, 0
# CHECK-NEXT: $w5 = MOVZWi 14, 0
# CHECK-NEXT: TCRETURNdi @OUTLINED_FUNCTION_0
name: f4
tracksRegLiveness: true
frameInfo:
isCalleeSavedInfoValid: true
machineFunctionInfo:
hasRedZone: false
body: |
bb.0:
$w0 = MOVZWi 1, 0
$w1 = MOVZWi 2, 0
$w2 = MOVZWi 3, 0
$w3 = MOVZWi 4, 0
$w4 = MOVZWi 5, 0
$w5 = MOVZWi 14, 0
$w6 = MOVZWi 6, 0
$w7 = MOVZWi 7, 0
TCRETURNdi @foo, 0, csr_darwin_aarch64_aapcs, implicit $sp, implicit killed $w0, implicit killed $w1, implicit killed $w2, implicit killed $w3, implicit killed $w4, implicit killed $w5, implicit killed $w6, implicit killed $w7

...
---
# CHECK-LABEL: name: f5
# CHECK-LABEL: bb.0:
# CHECK-NEXT: liveins: $lr
# CHECK-NEXT: {{ $}}
# CHECK-NEXT: $x5 = ORRXrs $xzr, $lr, 0
# CHECK-NEXT: BL @OUTLINED_FUNCTION_1
# CHECK-NEXT: $lr = ORRXrs $xzr, $x5, 0
# CHECK-NOT: @OUTLINED_FUNCTION_0
name: f5
tracksRegLiveness: true
frameInfo:
isCalleeSavedInfoValid: true
machineFunctionInfo:
hasRedZone: false
body: |
bb.0:
$w0 = MOVZWi 1, 0
$w1 = MOVZWi 2, 0
$w2 = MOVZWi 3, 0
$w3 = MOVZWi 4, 0
$w4 = MOVZWi 5, 0
$w5 = MOVZWi 15, 0
$w6 = MOVZWi 8, 0
$w7 = MOVZWi 9, 0
TCRETURNdi @foo, 0, csr_darwin_aarch64_aapcs, implicit $sp, implicit killed $w0, implicit killed $w1, implicit killed $w2, implicit killed $w3, implicit killed $w4, implicit killed $w5, implicit killed $w6, implicit killed $w7

...
---
# CHECK-LABEL: name: f6
# CHECK-LABEL: bb.0:
# CHECK-NEXT: liveins: $lr
# CHECK-NEXT: {{ $}}
# CHECK-NEXT: $x5 = ORRXrs $xzr, $lr, 0
# CHECK-NEXT: BL @OUTLINED_FUNCTION_1
# CHECK-NEXT: $lr = ORRXrs $xzr, $x5, 0
# CHECK-NOT: @OUTLINED_FUNCTION_0
name: f6
tracksRegLiveness: true
frameInfo:
isCalleeSavedInfoValid: true
machineFunctionInfo:
hasRedZone: false
body: |
bb.0:
$w0 = MOVZWi 1, 0
$w1 = MOVZWi 2, 0
$w2 = MOVZWi 3, 0
$w3 = MOVZWi 4, 0
$w4 = MOVZWi 5, 0
$w5 = MOVZWi 16, 0
$w6 = MOVZWi 9, 0
$w7 = MOVZWi 8, 0
TCRETURNdi @foo, 0, csr_darwin_aarch64_aapcs, implicit $sp, implicit killed $w0, implicit killed $w1, implicit killed $w2, implicit killed $w3, implicit killed $w4, implicit killed $w5, implicit killed $w6, implicit killed $w7

...

# CHECK-LABEL: name: OUTLINED_FUNCTION_0
# CHECK-LABEL: bb.0:
# CHECK-NEXT: liveins: $x19, $x20, $x21, $x22, $x23, $x24, $x25, $x26, $x27, $x28, $lr, $d8, $d9, $d10, $d11, $d12, $d13, $d14, $d15, $w0, $w1, $w2, $w3, $w4, $w5
# CHECK-NEXT: {{ $}}
# CHECK-NEXT: $w6 = MOVZWi 6, 0
# CHECK-NEXT: $w7 = MOVZWi 7, 0

# CHECK-LABEL: name: OUTLINED_FUNCTION_1
# CHECK-LABEL: bb.0:
# CHECK-NEXT: liveins: $x19, $x20, $x21, $x22, $x23, $x24, $x25, $x26, $x27, $x28, $lr, $d8, $d9, $d10, $d11, $d12, $d13, $d14, $d15
# CHECK-NEXT: {{ $}}
# CHECK-NEXT: $w0 = MOVZWi 1, 0
# CHECK-NEXT: $w1 = MOVZWi 2, 0
# CHECK-NEXT: $w2 = MOVZWi 3, 0
# CHECK-NEXT: $w3 = MOVZWi 4, 0
# CHECK-NEXT: $w4 = MOVZWi 5, 0
# CHECK-NEXT: RET $lr
Loading
Loading