maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Bitcode/thinlto-function-summary-ca...

121 lines
4.0 KiB
LLVM
Raw Normal View History

Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
; Test to check the callgraph in summary when there is PGO
; RUN: opt -module-summary %s -o %t.o
; RUN: llvm-bcanalyzer -dump %t.o | FileCheck %s
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
; RUN: opt -module-summary %p/Inputs/thinlto-function-summary-callgraph-sample-profile-summary.ll -o %t2.o
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
; RUN: llvm-lto -thinlto -o %t3 %t.o %t2.o
; RUN: llvm-bcanalyzer -dump %t3.thinlto.bc | FileCheck %s --check-prefix=COMBINED
; CHECK: <SOURCE_FILENAME
; "hot_function"
; CHECK-NEXT: <FUNCTION op0=0 op1=12
; "hot1"
; CHECK-NEXT: <FUNCTION op0=12 op1=4
; "hot2"
; CHECK-NEXT: <FUNCTION op0=16 op1=4
; "hot3"
; CHECK-NEXT: <FUNCTION op0=20 op1=4
; "hot4"
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
; CHECK-NEXT: <FUNCTION op0=24 op1=5
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
; "cold"
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
; CHECK-NEXT: <FUNCTION op0=29 op1=5
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
; "none1"
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
; CHECK-NEXT: <FUNCTION op0=34 op1=5
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
; "none2"
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
; CHECK-NEXT: <FUNCTION op0=39 op1=5
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
; "none3"
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
; CHECK-NEXT: <FUNCTION op0=44 op1=5
; CHECK-NEXT: <FUNCTION op0=49 op1=5
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
; CHECK-LABEL: <GLOBALVAL_SUMMARY_BLOCK
; CHECK-NEXT: <VERSION
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
; CHECK-NEXT: <VALUE_GUID op0=26 op1=123/>
; op4=none1 op6=hot1 op8=cold1 op10=none2 op12=hot2 op14=cold2 op16=none3 op18=hot3 op20=cold3 op22=123
; CHECK-NEXT: <PERMODULE_PROFILE {{.*}} op4=7 op5=0 op6=1 op7=3 op8=4 op9=1 op10=8 op11=0 op12=2 op13=3 op14=5 op15=1 op16=9 op17=0 op18=3 op19=3 op20=6 op21=1 op22=26 op23=4/>
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
; CHECK-NEXT: </GLOBALVAL_SUMMARY_BLOCK>
; CHECK: <STRTAB_BLOCK
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
; CHECK-NEXT: blob data = 'hot_functionhot1hot2hot3cold1cold2cold3none1none2none3{{.*}}'
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
; COMBINED: <GLOBALVAL_SUMMARY_BLOCK
; COMBINED-NEXT: <VERSION
; COMBINED-NEXT: <VALUE_GUID
; COMBINED-NEXT: <VALUE_GUID
; COMBINED-NEXT: <VALUE_GUID
; COMBINED-NEXT: <VALUE_GUID
; COMBINED-NEXT: <VALUE_GUID
; COMBINED-NEXT: <VALUE_GUID
; COMBINED-NEXT: <VALUE_GUID
; COMBINED-NEXT: <VALUE_GUID
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
; COMBINED-NEXT: <VALUE_GUID
; COMBINED-NEXT: <VALUE_GUID
; COMBINED-NEXT: <COMBINED abbrevid=
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
; COMBINED-NEXT: <COMBINED abbrevid=
; COMBINED-NEXT: <COMBINED abbrevid=
; COMBINED-NEXT: <COMBINED abbrevid=
; COMBINED-NEXT: <COMBINED abbrevid=
; COMBINED-NEXT: <COMBINED abbrevid=
; COMBINED-NEXT: <COMBINED abbrevid=
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
; COMBINED-NEXT: <COMBINED abbrevid=
; COMBINED-NEXT: <COMBINED_PROFILE {{.*}} op5=[[NONE1:.*]] op6=0 op7=[[HOT1:.*]] op8=3 op9=[[COLD1:.*]] op10=1 op11=[[NONE2:.*]] op12=0 op13=[[HOT2:.*]] op14=3 op15=[[COLD2:.*]] op16=1 op17=[[NONE3:.*]] op18=0 op19=[[HOT3:.*]] op20=3 op21=[[COLD3:.*]] op22=1/>
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
; COMBINED_NEXT: <COMBINED abbrevid=
; COMBINED_NEXT: </GLOBALVAL_SUMMARY_BLOCK>
; ModuleID = 'thinlto-function-summary-callgraph.ll'
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
; This function have high profile count, so entry block is hot.
define void @hot_function(i1 %a, i1 %a2) !prof !20 {
entry:
call void @none1()
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
call void @hot1(), !prof !15
call void @cold1(), !prof !16
br i1 %a, label %Cold, label %Hot, !prof !41
Cold: ; 1/1000 goes here
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
call void @none2()
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
call void @hot2(), !prof !15
call void @cold2(), !prof !16
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
br label %exit
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
Hot: ; 999/1000 goes here
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
call void @none3()
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
call void @hot3(), !prof !15
call void @cold3(), !prof !16
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
br label %exit
exit:
ret void
}
declare void @hot1() #1
declare void @hot2() #1
declare void @hot3() #1
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
declare void @cold1() #1
declare void @cold2() #1
declare void @cold3() #1
Restrict call metadata based hotness detection to Sample PGO mode Summary: Don't use the metadata on call instructions for determining hotness unless we are in sample PGO mode, where it is needed because profile counts are not accurate. In instrumentation mode this is not necessary and does more harm than good when calls have VP metadata that hasn't been properly scaled after transformations or dropped after constant prop based devirtualization (both should be fixed, but we don't need to do this in the first place for instrumentation PGO). This required adjusting a number of tests to distinguish between sample and instrumentation PGO handling, and to add in profile summary metadata so that getProfileCount can get the summary. Reviewers: davidxl, danielcdh Subscribers: aemerson, rengolin, mehdi_amini, Prazek, llvm-commits Differential Revision: https://reviews.llvm.org/D32877 llvm-svn: 302844
2017-05-12 07:18:05 +08:00
declare void @none1() #1
declare void @none2() #1
declare void @none3() #1
!41 = !{!"branch_weights", i32 1, i32 1000}
!llvm.module.flags = !{!1}
!20 = !{!"function_entry_count", i64 110, i64 123}
!1 = !{i32 1, !"ProfileSummary", !2}
!2 = !{!3, !4, !5, !6, !7, !8, !9, !10}
!3 = !{!"ProfileFormat", !"SampleProfile"}
!4 = !{!"TotalCount", i64 10000}
!5 = !{!"MaxCount", i64 10}
!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}
!15 = !{!"branch_weights", i32 100}
Do not want to use BFI to get profile count for sample pgo Summary: For SamplePGO, we already record the callsite count in the call instruction itself. So we do not want to use BFI to get profile count as it is less accurate. Reviewers: tejohnson, davidxl, eraman Reviewed By: eraman Subscribers: sanjoy, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D36025 llvm-svn: 309964
2017-08-04 01:11:41 +08:00
!16 = !{!"branch_weights", i32 1}