maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/Inline/inline-cold-callsite.ll

48 lines
1.2 KiB
LLVM
Raw Normal View History

[NewPM/Inliner] Reduce threshold for cold callsites in the non-PGO case Differential Revision: https://reviews.llvm.org/D34312 llvm-svn: 306484
2017-06-28 07:11:18 +08:00
Improve PGO support for the new inliner This adds the following to the new PM based inliner in PGO mode: * Use block frequency analysis to derive callsite's profile count and use that to adjust thresholds of hot and cold callsites. * Incrementally update the BFI of the caller after a callee gets inlined into it. This incremental update is only within an invocation of the run method - BFI is not preserved across calls to run. Update the function entry count of the callee after inlining it into a caller. * I've tuned the thresholds for the hot and cold callsites using a hacked up version of the old inliner that explicitly computes BFI on a set of internal benchmarks and spec. Once the new PM based pipeline stabilizes (IIRC Chandler mentioned there are known issues) I'll benchmark this again and adjust the thresholds if required. Inliner PGO support. Differential revision: https://reviews.llvm.org/D28331 llvm-svn: 292666
2017-01-21 06:44:04 +08:00
; RUN: opt < %s -passes='require<profile-summary>,cgscc(inline)' -inline-threshold=100 -inline-cold-callsite-threshold=0 -S | FileCheck %s
; This tests that a cold callsite gets the inline-cold-callsite-threshold
; and does not get inlined. Another callsite to an identical callee that
; is not cold gets inlined because cost is below the inline-threshold.
[NewPM/Inliner] Reduce threshold for cold callsites in the non-PGO case Differential Revision: https://reviews.llvm.org/D34312 llvm-svn: 306484
2017-06-28 07:11:18 +08:00
define void @callee() {
call void @extern()
Improve PGO support for the new inliner This adds the following to the new PM based inliner in PGO mode: * Use block frequency analysis to derive callsite's profile count and use that to adjust thresholds of hot and cold callsites. * Incrementally update the BFI of the caller after a callee gets inlined into it. This incremental update is only within an invocation of the run method - BFI is not preserved across calls to run. Update the function entry count of the callee after inlining it into a caller. * I've tuned the thresholds for the hot and cold callsites using a hacked up version of the old inliner that explicitly computes BFI on a set of internal benchmarks and spec. Once the new PM based pipeline stabilizes (IIRC Chandler mentioned there are known issues) I'll benchmark this again and adjust the thresholds if required. Inliner PGO support. Differential revision: https://reviews.llvm.org/D28331 llvm-svn: 292666
2017-01-21 06:44:04 +08:00
call void @extern()
[NewPM/Inliner] Reduce threshold for cold callsites in the non-PGO case Differential Revision: https://reviews.llvm.org/D34312 llvm-svn: 306484
2017-06-28 07:11:18 +08:00
ret void
Improve PGO support for the new inliner This adds the following to the new PM based inliner in PGO mode: * Use block frequency analysis to derive callsite's profile count and use that to adjust thresholds of hot and cold callsites. * Incrementally update the BFI of the caller after a callee gets inlined into it. This incremental update is only within an invocation of the run method - BFI is not preserved across calls to run. Update the function entry count of the callee after inlining it into a caller. * I've tuned the thresholds for the hot and cold callsites using a hacked up version of the old inliner that explicitly computes BFI on a set of internal benchmarks and spec. Once the new PM based pipeline stabilizes (IIRC Chandler mentioned there are known issues) I'll benchmark this again and adjust the thresholds if required. Inliner PGO support. Differential revision: https://reviews.llvm.org/D28331 llvm-svn: 292666
2017-01-21 06:44:04 +08:00
}
declare void @extern()
[NewPM/Inliner] Reduce threshold for cold callsites in the non-PGO case Differential Revision: https://reviews.llvm.org/D34312 llvm-svn: 306484
2017-06-28 07:11:18 +08:00
declare i1 @ext(i32)
; CHECK-LABEL: caller
define i32 @caller(i32 %n) {
entry:
%cmp4 = icmp sgt i32 %n, 0
br i1 %cmp4, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
ret i32 0
for.body:
%i.05 = phi i32 [ %inc, %for.inc ], [ 0, %entry ]
; CHECK: %call = tail call
%call = tail call zeroext i1 @ext(i32 %i.05)
; CHECK-NOT: call void @callee
; CHECK-NEXT: call void @extern
call void @callee()
br i1 %call, label %cold, label %for.inc, !prof !0
cold:
; CHECK: call void @callee
call void @callee()
br label %for.inc
for.inc:
%inc = add nuw nsw i32 %i.05, 1
%exitcond = icmp eq i32 %inc, %n
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}
Improve PGO support for the new inliner This adds the following to the new PM based inliner in PGO mode: * Use block frequency analysis to derive callsite's profile count and use that to adjust thresholds of hot and cold callsites. * Incrementally update the BFI of the caller after a callee gets inlined into it. This incremental update is only within an invocation of the run method - BFI is not preserved across calls to run. Update the function entry count of the callee after inlining it into a caller. * I've tuned the thresholds for the hot and cold callsites using a hacked up version of the old inliner that explicitly computes BFI on a set of internal benchmarks and spec. Once the new PM based pipeline stabilizes (IIRC Chandler mentioned there are known issues) I'll benchmark this again and adjust the thresholds if required. Inliner PGO support. Differential revision: https://reviews.llvm.org/D28331 llvm-svn: 292666
2017-01-21 06:44:04 +08:00
[NewPM/Inliner] Reduce threshold for cold callsites in the non-PGO case Differential Revision: https://reviews.llvm.org/D34312 llvm-svn: 306484
2017-06-28 07:11:18 +08:00
!0 = !{!"branch_weights", i32 1, i32 2000}