aa2ddfc73d
them in a special text section. For sampleFDO, because the optimized build uses profile generated from previous release, previously we couldn't tell a function without profile was truely cold or just newly created so we had to treat them conservatively and put them in .text section instead of .text.unlikely. The result was when we persuing the best performance by locking .text.hot and .text in memory, we wasted a lot of memory to keep cold functions inside. In https://reviews.llvm.org/D66374, we introduced profile symbol list to discriminate functions being cold versus functions being newly added. This mechanism works quite well for regular use cases in AutoFDO. However, in some case, we can only have a partial profile when optimizing a target. The partial profile may be an aggregated profile collected from many targets. The profile symbol list method used for regular sampleFDO profile is not applicable to partial profile use case because it may be too large and introduce many false positives. To solve the problem for partial profile use case, we provide an option called --profile-unknown-in-special-section. For functions without profile, we will still treat them conservatively in compiler optimizations -- for example, treat them as warm instead of cold in inliner. When we use profile info to add section prefix for functions, we will discriminate functions known to be not cold versus functions without profile (being unknown), and we will put functions being unknown in a special text section called .text.unknown. Runtime system will have the flexibility to decide where to put the special section in order to achieve a balance between performance and memory saving. Differential Revision: https://reviews.llvm.org/D62540
58 lines
2.5 KiB
LLVM
58 lines
2.5 KiB
LLVM
; REQUIRES: x86-registered-target
|
|
; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline.prof -codegenprepare -S | FileCheck %s
|
|
; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline.prof -codegenprepare -profile-unknown-in-special-section -partial-profile -S | FileCheck %s --check-prefix UNKNOWN
|
|
; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline.prof -codegenprepare -profile-sample-accurate -S | FileCheck %s --check-prefix ACCURATE
|
|
|
|
target triple = "x86_64-pc-linux-gnu"
|
|
|
|
; The test checks that function without profile gets unlikely section prefix
|
|
; if -profile-sample-accurate is specified or the function has the
|
|
; profile-sample-accurate attribute.
|
|
|
|
declare void @hot_func()
|
|
|
|
; CHECK-NOT: foo_not_in_profile{{.*}}!section_prefix
|
|
; CHECK: foo_not_in_profile{{.*}}!prof ![[NOPROFILE_ID:[0-9]+]]
|
|
; UNKNOWN: foo_not_in_profile{{.*}}!prof ![[NOPROFILE_ID:[0-9]+]] !section_prefix ![[UNKNOWN_ID:[0-9]+]]
|
|
; ACCURATE: foo_not_in_profile{{.*}}!prof ![[ZERO_ID:[0-9]+]] !section_prefix ![[COLD_ID:[0-9]+]]
|
|
; The function not appearing in profile is cold when -profile-sample-accurate
|
|
; is on.
|
|
define void @foo_not_in_profile() {
|
|
call void @hot_func()
|
|
ret void
|
|
}
|
|
|
|
; CHECK: bar_not_in_profile{{.*}}!prof ![[ZERO_ID:[0-9]+]] !section_prefix ![[COLD_ID:[0-9]+]]
|
|
; ACCURATE: bar_not_in_profile{{.*}}!prof ![[ZERO_ID:[0-9]+]] !section_prefix ![[COLD_ID:[0-9]+]]
|
|
; The function not appearing in profile is cold when the func has
|
|
; profile-sample-accurate attribute.
|
|
define void @bar_not_in_profile() #0 {
|
|
call void @hot_func()
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "profile-sample-accurate" }
|
|
|
|
; CHECK: ![[NOPROFILE_ID]] = !{!"function_entry_count", i64 -1}
|
|
; CHECK: ![[ZERO_ID]] = !{!"function_entry_count", i64 0}
|
|
; CHECK: ![[COLD_ID]] = !{!"function_section_prefix", !".unlikely"}
|
|
; UNKNOWN: ![[NOPROFILE_ID]] = !{!"function_entry_count", i64 -1}
|
|
; UNKNOWN: ![[UNKNOWN_ID]] = !{!"function_section_prefix", !".unknown"}
|
|
; ACCURATE: ![[ZERO_ID]] = !{!"function_entry_count", i64 0}
|
|
; ACCURATE: ![[COLD_ID]] = !{!"function_section_prefix", !".unlikely"}
|
|
!llvm.module.flags = !{!1}
|
|
!1 = !{i32 1, !"ProfileSummary", !2}
|
|
!2 = !{!3, !4, !5, !6, !7, !8, !9, !10}
|
|
!3 = !{!"ProfileFormat", !"SampleProfile"}
|
|
!4 = !{!"TotalCount", i64 10000}
|
|
!5 = !{!"MaxCount", i64 1000}
|
|
!6 = !{!"MaxInternalCount", i64 1}
|
|
!7 = !{!"MaxFunctionCount", i64 1000}
|
|
!8 = !{!"NumCounts", i64 3}
|
|
!9 = !{!"NumFunctions", i64 3}
|
|
!10 = !{!"DetailedSummary", !11}
|
|
!11 = !{!12, !13, !14}
|
|
!12 = !{i32 10000, i64 100, i32 1}
|
|
!13 = !{i32 999000, i64 100, i32 1}
|
|
!14 = !{i32 999999, i64 1, i32 2}
|