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/SampleProfile/cov-zero-samples.ll

148 lines
7.4 KiB
LLVM
Raw Normal View History

[OptDiag] Updating Remarks in SampleProfile Updating remark API to newer OptimizationDiagnosticInfo API. This allows remarks to show up in diagnostic yaml file, and enables use of opt-viewer tool. Hotness information for remarks (L505 and L751) do not display hotness information, most likely due to profile information not being propagated yet. Unsure if this is the desired outcome. Patch by Tarun Rajendran. Differential Revision: https://reviews.llvm.org/D36127 llvm-svn: 310763
2017-08-12 05:12:04 +08:00
; RUN: opt < %s -instcombine -sample-profile -sample-profile-file=%S/Inputs/cov-zero-samples.prof -sample-profile-check-record-coverage=100 -pass-remarks=sample-profile -pass-remarks-analysis=sample-profile -o /dev/null 2>&1 | FileCheck %s
; RUN: opt < %s -passes="function(instcombine),sample-profile" -sample-profile-file=%S/Inputs/cov-zero-samples.prof -sample-profile-check-record-coverage=100 -pass-remarks=sample-profile -pass-remarks-analysis=sample-profile -o /dev/null 2>&1 | FileCheck %s
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
;
Perform InstructioinCombiningPass before SampleProfile pass. Summary: SampleProfile pass needs to be performed after InstructionCombiningPass, which helps eliminate un-inlinable function calls. Reviewers: davidxl, dnovillo Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D17742 llvm-svn: 262419
2016-03-02 06:53:02 +08:00
; CHECK: remark: cov-zero-samples.cc:9:29: Applied 404065 samples from profile (offset: 2.1)
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
; CHECK: remark: cov-zero-samples.cc:10:9: Applied 443089 samples from profile (offset: 3)
; CHECK: remark: cov-zero-samples.cc:10:36: Applied 0 samples from profile (offset: 3.1)
; CHECK: remark: cov-zero-samples.cc:11:12: Applied 404066 samples from profile (offset: 4)
; CHECK: remark: cov-zero-samples.cc:13:25: Applied 0 samples from profile (offset: 6)
; CHECK: remark: cov-zero-samples.cc:14:3: Applied 0 samples from profile (offset: 7)
; CHECK: remark: cov-zero-samples.cc:10:9: most popular destination for conditional branches at cov-zero-samples.cc:9:3
; CHECK: remark: cov-zero-samples.cc:11:12: most popular destination for conditional branches at cov-zero-samples.cc:10:9
;
; Coverage for this profile should be 100%
; CHECK-NOT: warning: cov-zero-samples.cc:1:
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
source_filename = "test/Transforms/SampleProfile/cov-zero-samples.ll"
@N = global i64 8000000000, align 8, !dbg !0
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
@.str = private unnamed_addr constant [11 x i8] c"sum is %d\0A\00", align 1
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
define i32 @_Z12never_calledi(i32 %i) !dbg !11 {
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
entry:
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
ret i32 0, !dbg !15
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
}
; Function Attrs: nounwind readnone
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
declare void @llvm.dbg.declare(metadata, metadata, metadata) #0
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
define i32 @main() !dbg !17 {
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
entry:
%retval = alloca i32, align 4
%sum = alloca i32, align 4
%i = alloca i64, align 8
store i32 0, i32* %retval, align 4
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
call void @llvm.dbg.declare(metadata i32* %sum, metadata !20, metadata !21), !dbg !22
store i32 0, i32* %sum, align 4, !dbg !22
call void @llvm.dbg.declare(metadata i64* %i, metadata !23, metadata !21), !dbg !25
store i64 0, i64* %i, align 8, !dbg !25
br label %for.cond, !dbg !26
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
for.cond: ; preds = %for.inc, %entry
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
%0 = load i64, i64* %i, align 8, !dbg !27
%1 = load volatile i64, i64* @N, align 8, !dbg !30
%cmp = icmp slt i64 %0, %1, !dbg !31
br i1 %cmp, label %for.body, label %for.end, !dbg !32
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
for.body: ; preds = %for.cond
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
%2 = load i64, i64* %i, align 8, !dbg !33
%3 = load volatile i64, i64* @N, align 8, !dbg !36
%cmp1 = icmp sgt i64 %2, %3, !dbg !37
br i1 %cmp1, label %if.then, label %if.end, !dbg !38
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
if.then: ; preds = %for.body
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
%4 = load i64, i64* %i, align 8, !dbg !39
%conv = trunc i64 %4 to i32, !dbg !39
%call = call i32 @_Z12never_calledi(i32 %conv), !dbg !41
%5 = load i32, i32* %sum, align 4, !dbg !42
%add = add nsw i32 %5, %call, !dbg !42
store i32 %add, i32* %sum, align 4, !dbg !42
br label %if.end, !dbg !43
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
if.end: ; preds = %if.then, %for.body
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
%6 = load i64, i64* %i, align 8, !dbg !44
%div = sdiv i64 %6, 239, !dbg !45
%7 = load i32, i32* %sum, align 4, !dbg !46
%conv2 = sext i32 %7 to i64, !dbg !46
%mul = mul nsw i64 %conv2, %div, !dbg !46
%conv3 = trunc i64 %mul to i32, !dbg !46
store i32 %conv3, i32* %sum, align 4, !dbg !46
br label %for.inc, !dbg !47
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
for.inc: ; preds = %if.end
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
%8 = load i64, i64* %i, align 8, !dbg !48
%inc = add nsw i64 %8, 1, !dbg !48
store i64 %inc, i64* %i, align 8, !dbg !48
br label %for.cond, !dbg !50
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
for.end: ; preds = %for.cond
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
%9 = load i32, i32* %sum, align 4, !dbg !51
%call4 = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([11 x i8], [11 x i8]* @.str, i32 0, i32 0), i32 %9), !dbg !52
ret i32 0, !dbg !53
SamplePGO - Do not count never-executed inlined functions when computing coverage. If a function was originally inlined but not actually hot at runtime, its samples will not be counted inside the parent function. This throws off the coverage calculation because it expects to find more used records than it should. Fixed by ignoring functions that will not be inlined into the parent. Currently, this is inlined functions with 0 samples. In subsequent patches, I'll change this to mean "cold" functions. llvm-svn: 253716
2015-11-21 05:46:38 +08:00
}
declare i32 @printf(i8*, ...)
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
attributes #0 = { nounwind readnone }
!llvm.dbg.cu = !{!2}
!llvm.module.flags = !{!8, !9}
!llvm.ident = !{!10}
Canonicalize the representation of empty an expression in DIGlobalVariableExpression This change simplifies code that has to deal with DIGlobalVariableExpression and mirrors how we treat DIExpressions in debug info intrinsics. Before this change there were two ways of representing empty expressions on globals, a nullptr and an empty !DIExpression(). If someone needs to upgrade out-of-tree testcases: perl -pi -e 's/(!DIGlobalVariableExpression\(var: ![0-9]*)\)/\1, expr: !DIExpression())/g' <MYTEST.ll> will catch 95%. llvm-svn: 312144
2017-08-31 02:06:51 +08:00
!0 = !DIGlobalVariableExpression(var: !1, expr: !DIExpression())
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
!1 = !DIGlobalVariable(name: "N", scope: !2, file: !3, line: 3, type: !6, isLocal: false, isDefinition: true)
!2 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !3, producer: "clang version 3.8.0 (trunk 253667) (llvm/trunk 253670)", isOptimized: false, runtimeVersion: 0, emissionKind: NoDebug, enums: !4, globals: !5)
!3 = !DIFile(filename: "cov-zero-samples.cc", directory: ".")
!4 = !{}
!5 = !{!0}
!6 = !DIDerivedType(tag: DW_TAG_volatile_type, baseType: !7)
!7 = !DIBasicType(name: "long long int", size: 64, align: 64, encoding: DW_ATE_signed)
!8 = !{i32 2, !"Dwarf Version", i32 4}
!9 = !{i32 2, !"Debug Info Version", i32 3}
!10 = !{!"clang version 3.8.0 (trunk 253667) (llvm/trunk 253670)"}
[DebugInfo] Add DILabel metadata and intrinsic llvm.dbg.label. In order to set breakpoints on labels and list source code around labels, we need collect debug information for labels, i.e., label name, the function label belong, line number in the file, and the address label located. In order to keep these information in LLVM IR and to allow backend to generate debug information correctly. We create a new kind of metadata for labels, DILabel. The format of DILabel is !DILabel(scope: !1, name: "foo", file: !2, line: 3) We hope to keep debug information as much as possible even the code is optimized. So, we create a new kind of intrinsic for label metadata to avoid the metadata is eliminated with basic block. The intrinsic will keep existing if we keep it from optimized out. The format of the intrinsic is llvm.dbg.label(metadata !1) It has only one argument, that is the DILabel metadata. The intrinsic will follow the label immediately. Backend could get the label metadata through the intrinsic's parameter. We also create DIBuilder API for labels to be used by Frontend. Frontend could use createLabel() to allocate DILabel objects, and use insertLabel() to insert llvm.dbg.label intrinsic in LLVM IR. Differential Revision: https://reviews.llvm.org/D45024 Patch by Hsiangkai Wang. llvm-svn: 331841
2018-05-09 10:40:45 +08:00
!11 = distinct !DISubprogram(name: "never_called", linkageName: "_Z12never_calledi", scope: !3, file: !3, line: 5, type: !12, isLocal: false, isDefinition: true, scopeLine: 5, flags: DIFlagPrototyped, isOptimized: false, unit: !2, retainedNodes: !4)
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
!12 = !DISubroutineType(types: !13)
!13 = !{!14, !14}
!14 = !DIBasicType(name: "int", size: 32, align: 32, encoding: DW_ATE_signed)
!15 = !DILocation(line: 5, column: 27, scope: !16)
Use base discriminator in sample pgo profile matching. Summary: The discriminator has been encoded, and only the base discriminator should be used during profile matching. Reviewers: dblaikie, davidxl Reviewed By: dblaikie, davidxl Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D30218 llvm-svn: 295999
2017-02-24 02:27:45 +08:00
!16 = !DILexicalBlockFile(scope: !11, file: !3, discriminator: 6)
[DebugInfo] Add DILabel metadata and intrinsic llvm.dbg.label. In order to set breakpoints on labels and list source code around labels, we need collect debug information for labels, i.e., label name, the function label belong, line number in the file, and the address label located. In order to keep these information in LLVM IR and to allow backend to generate debug information correctly. We create a new kind of metadata for labels, DILabel. The format of DILabel is !DILabel(scope: !1, name: "foo", file: !2, line: 3) We hope to keep debug information as much as possible even the code is optimized. So, we create a new kind of intrinsic for label metadata to avoid the metadata is eliminated with basic block. The intrinsic will keep existing if we keep it from optimized out. The format of the intrinsic is llvm.dbg.label(metadata !1) It has only one argument, that is the DILabel metadata. The intrinsic will follow the label immediately. Backend could get the label metadata through the intrinsic's parameter. We also create DIBuilder API for labels to be used by Frontend. Frontend could use createLabel() to allocate DILabel objects, and use insertLabel() to insert llvm.dbg.label intrinsic in LLVM IR. Differential Revision: https://reviews.llvm.org/D45024 Patch by Hsiangkai Wang. llvm-svn: 331841
2018-05-09 10:40:45 +08:00
!17 = distinct !DISubprogram(name: "main", scope: !3, file: !3, line: 7, type: !18, isLocal: false, isDefinition: true, scopeLine: 7, flags: DIFlagPrototyped, isOptimized: false, unit: !2, retainedNodes: !4)
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
!18 = !DISubroutineType(types: !19)
!19 = !{!14}
!20 = !DILocalVariable(name: "sum", scope: !17, file: !3, line: 8, type: !14)
!21 = !DIExpression()
!22 = !DILocation(line: 8, column: 7, scope: !17)
!23 = !DILocalVariable(name: "i", scope: !24, file: !3, line: 9, type: !7)
!24 = distinct !DILexicalBlock(scope: !17, file: !3, line: 9, column: 3)
!25 = !DILocation(line: 9, column: 18, scope: !24)
!26 = !DILocation(line: 9, column: 8, scope: !24)
!27 = !DILocation(line: 9, column: 25, scope: !28)
Use base discriminator in sample pgo profile matching. Summary: The discriminator has been encoded, and only the base discriminator should be used during profile matching. Reviewers: dblaikie, davidxl Reviewed By: dblaikie, davidxl Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D30218 llvm-svn: 295999
2017-02-24 02:27:45 +08:00
!28 = !DILexicalBlockFile(scope: !29, file: !3, discriminator: 2)
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
!29 = distinct !DILexicalBlock(scope: !24, file: !3, line: 9, column: 3)
!30 = !DILocation(line: 9, column: 29, scope: !28)
!31 = !DILocation(line: 9, column: 27, scope: !28)
!32 = !DILocation(line: 9, column: 3, scope: !28)
!33 = !DILocation(line: 10, column: 9, scope: !34)
!34 = distinct !DILexicalBlock(scope: !35, file: !3, line: 10, column: 9)
!35 = distinct !DILexicalBlock(scope: !29, file: !3, line: 9, column: 37)
!36 = !DILocation(line: 10, column: 13, scope: !34)
!37 = !DILocation(line: 10, column: 11, scope: !34)
!38 = !DILocation(line: 10, column: 9, scope: !35)
!39 = !DILocation(line: 10, column: 36, scope: !40)
Use base discriminator in sample pgo profile matching. Summary: The discriminator has been encoded, and only the base discriminator should be used during profile matching. Reviewers: dblaikie, davidxl Reviewed By: dblaikie, davidxl Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D30218 llvm-svn: 295999
2017-02-24 02:27:45 +08:00
!40 = !DILexicalBlockFile(scope: !34, file: !3, discriminator: 2)
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
!41 = !DILocation(line: 10, column: 23, scope: !40)
!42 = !DILocation(line: 10, column: 20, scope: !40)
!43 = !DILocation(line: 10, column: 16, scope: !40)
!44 = !DILocation(line: 11, column: 12, scope: !35)
!45 = !DILocation(line: 11, column: 14, scope: !35)
!46 = !DILocation(line: 11, column: 9, scope: !35)
!47 = !DILocation(line: 12, column: 3, scope: !35)
!48 = !DILocation(line: 9, column: 33, scope: !49)
Use base discriminator in sample pgo profile matching. Summary: The discriminator has been encoded, and only the base discriminator should be used during profile matching. Reviewers: dblaikie, davidxl Reviewed By: dblaikie, davidxl Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D30218 llvm-svn: 295999
2017-02-24 02:27:45 +08:00
!49 = !DILexicalBlockFile(scope: !29, file: !3, discriminator: 4)
Renumber testcase metadata nodes after r290153. This patch renumbers the metadata nodes in debug info testcases after https://reviews.llvm.org/D26769. This is a separate patch because it causes so much churn. This was implemented with a python script that pipes the testcases through llvm-as - | llvm-dis - and then goes through the original and new output side-by side to insert all comments at a close-enough location. Differential Revision: https://reviews.llvm.org/D27765 llvm-svn: 290292
2016-12-22 08:45:21 +08:00
!50 = !DILocation(line: 9, column: 3, scope: !49)
!51 = !DILocation(line: 13, column: 25, scope: !17)
!52 = !DILocation(line: 13, column: 3, scope: !17)
!53 = !DILocation(line: 14, column: 3, scope: !17)