Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[SampleFDO] handle ProfileSampleAccurate when initializing function e…
…ntry count ProfileSampleAccurate is used to indicate the profile has exact match to the code to be optimized. Previously ProfileSampleAccurate is handled in ProfileSummaryInfo::isColdCallSite and ProfileSummaryInfo::isColdBlock. A better solution is to initialize function entry count to 0 when ProfileSampleAccurate is true, so we don't have to handle ProfileSampleAccurate in multiple places. Differential Revision: https://reviews.llvm.org/D55660 llvm-svn: 349088
- Loading branch information
Showing
6 changed files
with
103 additions
and
98 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
47 changes: 0 additions & 47 deletions
47
llvm/test/Transforms/Inline/inline-cold-callsite-samplepgo.ll
This file was deleted.
Oops, something went wrong.
31 changes: 31 additions & 0 deletions
31
llvm/test/Transforms/SampleProfile/inline-cold-callsite-samplepgo.ll
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,31 @@ | ||
; For SamplePGO, if -profile-sample-accurate is specified, cold callsite | ||
; heuristics should be honored if the caller has no profile. | ||
|
||
; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline.prof -inline -S -inline-cold-callsite-threshold=0 | FileCheck %s | ||
; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline.prof -profile-sample-accurate -inline -S -inline-cold-callsite-threshold=0 | FileCheck %s --check-prefix ACCURATE | ||
|
||
declare void @extern() | ||
define void @callee() { | ||
call void @extern() | ||
ret void | ||
} | ||
|
||
define void @caller(i32 %y1) { | ||
; CHECK-LABEL: @caller | ||
; CHECK-NOT: call void @callee | ||
; ACCURATE-LABEL: @caller | ||
; ACCURATE: call void @callee | ||
call void @callee() | ||
ret void | ||
} | ||
|
||
define void @caller_accurate(i32 %y1) #0 { | ||
; CHECK-LABEL: @caller_accurate | ||
; CHECK: call void @callee | ||
; ACCURATE-LABEL: @caller_accurate | ||
; ACCURATE: call void @callee | ||
call void @callee() | ||
ret void | ||
} | ||
|
||
attributes #0 = { "profile-sample-accurate" } |
52 changes: 52 additions & 0 deletions
52
llvm/test/Transforms/SampleProfile/section-accurate-samplepgo.ll
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,52 @@ | ||
; 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-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 ![[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: ![[UNKNOWN_ID]] = !{!"function_entry_count", i64 -1} | ||
; CHECK: ![[ZERO_ID]] = !{!"function_entry_count", i64 0} | ||
; CHECK: ![[COLD_ID]] = !{!"function_section_prefix", !".unlikely"} | ||
; 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} |