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...

122 lines
3.8 KiB
LLVM
Raw Normal View History

[thinlto] Basic thinlto fdo heuristic Summary: This patch improves thinlto importer by importing 3x larger functions that are called from hot block. I compared performance with the trunk on spec, and there were about 2% on povray and 3.33% on milc. These results seems to be consistant and match the results Teresa got with her simple heuristic. Some benchmarks got slower but I think they are just noisy (mcf, xalancbmki, omnetpp)- running the benchmarks again with more iterations to confirm. Geomean of all benchmarks including the noisy ones were about +0.02%. I see much better improvement on google branch with Easwaran patch for pgo callsite inlining (the inliner actually inline those big functions) Over all I see +0.5% improvement, and I get +8.65% on povray. So I guess we will see much bigger change when Easwaran patch will land (it depends on new pass manager), but it is still worth putting this to trunk before it. Implementation details changes: - Removed CallsiteCount. - ProfileCount got replaced by Hotness - hot-import-multiplier is set to 3.0 for now, didn't have time to tune it up, but I see that we get most of the interesting functions with 3, so there is no much performance difference with higher, and binary size doesn't grow as much as with 10.0. Reviewers: eraman, mehdi_amini, tejohnson Subscribers: mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D24638 llvm-svn: 282437
2016-09-27 04:37:32 +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
; RUN: opt -module-summary %p/Inputs/thinlto-function-summary-callgraph-profile-summary.ll -o %t2.o
; RUN: llvm-lto -thinlto -o %t3 %t.o %t2.o
; RUN: llvm-bcanalyzer -dump %t3.thinlto.bc | FileCheck %s --check-prefix=COMBINED
Bitcode: Add a string table to the bitcode format. Add a top-level STRTAB block containing a string table blob, and start storing strings for module codes FUNCTION, GLOBALVAR, ALIAS, IFUNC and COMDAT in the string table. This change allows us to share names between globals and comdats as well as between modules, and improves the efficiency of loading bitcode files by no longer using a bit encoding for symbol names. Once we start writing the irsymtab to the bitcode file we will also be able to share strings between it and the module. On my machine, link time for Chromium for Linux with ThinLTO decreases by about 7% for no-op incremental builds or about 1% for full builds. Total bitcode file size decreases by about 3%. As discussed on llvm-dev: http://lists.llvm.org/pipermail/llvm-dev/2017-April/111732.html Differential Revision: https://reviews.llvm.org/D31838 llvm-svn: 300464
2017-04-18 01:51:36 +08:00
; 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"
; CHECK-NEXT: <FUNCTION op0=24 op1=4
; "cold"
; CHECK-NEXT: <FUNCTION op0=28 op1=4
; "none1"
; CHECK-NEXT: <FUNCTION op0=32 op1=5
; "none2"
; CHECK-NEXT: <FUNCTION op0=37 op1=5
; "none3"
; CHECK-NEXT: <FUNCTION op0=42 op1=5
[thinlto] Basic thinlto fdo heuristic Summary: This patch improves thinlto importer by importing 3x larger functions that are called from hot block. I compared performance with the trunk on spec, and there were about 2% on povray and 3.33% on milc. These results seems to be consistant and match the results Teresa got with her simple heuristic. Some benchmarks got slower but I think they are just noisy (mcf, xalancbmki, omnetpp)- running the benchmarks again with more iterations to confirm. Geomean of all benchmarks including the noisy ones were about +0.02%. I see much better improvement on google branch with Easwaran patch for pgo callsite inlining (the inliner actually inline those big functions) Over all I see +0.5% improvement, and I get +8.65% on povray. So I guess we will see much bigger change when Easwaran patch will land (it depends on new pass manager), but it is still worth putting this to trunk before it. Implementation details changes: - Removed CallsiteCount. - ProfileCount got replaced by Hotness - hot-import-multiplier is set to 3.0 for now, didn't have time to tune it up, but I see that we get most of the interesting functions with 3, so there is no much performance difference with higher, and binary size doesn't grow as much as with 10.0. Reviewers: eraman, mehdi_amini, tejohnson Subscribers: mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D24638 llvm-svn: 282437
2016-09-27 04:37:32 +08:00
; CHECK-LABEL: <GLOBALVAL_SUMMARY_BLOCK
; CHECK-NEXT: <VERSION
Bitcode: Add a string table to the bitcode format. Add a top-level STRTAB block containing a string table blob, and start storing strings for module codes FUNCTION, GLOBALVAR, ALIAS, IFUNC and COMDAT in the string table. This change allows us to share names between globals and comdats as well as between modules, and improves the efficiency of loading bitcode files by no longer using a bit encoding for symbol names. Once we start writing the irsymtab to the bitcode file we will also be able to share strings between it and the module. On my machine, link time for Chromium for Linux with ThinLTO decreases by about 7% for no-op incremental builds or about 1% for full builds. Total bitcode file size decreases by about 3%. As discussed on llvm-dev: http://lists.llvm.org/pipermail/llvm-dev/2017-April/111732.html Differential Revision: https://reviews.llvm.org/D31838 llvm-svn: 300464
2017-04-18 01:51:36 +08:00
; CHECK-NEXT: <VALUE_GUID op0=25 op1=123/>
; op4=hot1 op6=cold op8=hot2 op10=hot4 op12=none1 op14=hot3 op16=none2 op18=none3 op20=123
[ThinLTO] Add FunctionAttrs to ThinLTO index Adds function attributes to index: ReadNone, ReadOnly, NoRecurse, NoAlias. This attributes will be used for future ThinLTO optimizations that will propagate function attributes across modules. llvm-svn: 310061
2017-08-05 00:00:58 +08:00
; CHECK-NEXT: <PERMODULE_PROFILE {{.*}} op5=1 op6=3 op7=5 op8=1 op9=2 op10=3 op11=4 op12=1 op13=6 op14=2 op15=3 op16=3 op17=7 op18=2 op19=8 op20=2 op21=25 op22=4/>
[thinlto] Basic thinlto fdo heuristic Summary: This patch improves thinlto importer by importing 3x larger functions that are called from hot block. I compared performance with the trunk on spec, and there were about 2% on povray and 3.33% on milc. These results seems to be consistant and match the results Teresa got with her simple heuristic. Some benchmarks got slower but I think they are just noisy (mcf, xalancbmki, omnetpp)- running the benchmarks again with more iterations to confirm. Geomean of all benchmarks including the noisy ones were about +0.02%. I see much better improvement on google branch with Easwaran patch for pgo callsite inlining (the inliner actually inline those big functions) Over all I see +0.5% improvement, and I get +8.65% on povray. So I guess we will see much bigger change when Easwaran patch will land (it depends on new pass manager), but it is still worth putting this to trunk before it. Implementation details changes: - Removed CallsiteCount. - ProfileCount got replaced by Hotness - hot-import-multiplier is set to 3.0 for now, didn't have time to tune it up, but I see that we get most of the interesting functions with 3, so there is no much performance difference with higher, and binary size doesn't grow as much as with 10.0. Reviewers: eraman, mehdi_amini, tejohnson Subscribers: mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D24638 llvm-svn: 282437
2016-09-27 04:37:32 +08:00
; CHECK-NEXT: </GLOBALVAL_SUMMARY_BLOCK>
Bitcode: Add a string table to the bitcode format. Add a top-level STRTAB block containing a string table blob, and start storing strings for module codes FUNCTION, GLOBALVAR, ALIAS, IFUNC and COMDAT in the string table. This change allows us to share names between globals and comdats as well as between modules, and improves the efficiency of loading bitcode files by no longer using a bit encoding for symbol names. Once we start writing the irsymtab to the bitcode file we will also be able to share strings between it and the module. On my machine, link time for Chromium for Linux with ThinLTO decreases by about 7% for no-op incremental builds or about 1% for full builds. Total bitcode file size decreases by about 3%. As discussed on llvm-dev: http://lists.llvm.org/pipermail/llvm-dev/2017-April/111732.html Differential Revision: https://reviews.llvm.org/D31838 llvm-svn: 300464
2017-04-18 01:51:36 +08:00
; CHECK: <STRTAB_BLOCK
Bitcode: Write the irsymtab to disk. Differential Revision: https://reviews.llvm.org/D33973 llvm-svn: 306487
2017-06-28 07:50:11 +08:00
; CHECK-NEXT: blob data = 'hot_functionhot1hot2hot3hot4coldnone1none2none3{{.*}}'
[thinlto] Basic thinlto fdo heuristic Summary: This patch improves thinlto importer by importing 3x larger functions that are called from hot block. I compared performance with the trunk on spec, and there were about 2% on povray and 3.33% on milc. These results seems to be consistant and match the results Teresa got with her simple heuristic. Some benchmarks got slower but I think they are just noisy (mcf, xalancbmki, omnetpp)- running the benchmarks again with more iterations to confirm. Geomean of all benchmarks including the noisy ones were about +0.02%. I see much better improvement on google branch with Easwaran patch for pgo callsite inlining (the inliner actually inline those big functions) Over all I see +0.5% improvement, and I get +8.65% on povray. So I guess we will see much bigger change when Easwaran patch will land (it depends on new pass manager), but it is still worth putting this to trunk before it. Implementation details changes: - Removed CallsiteCount. - ProfileCount got replaced by Hotness - hot-import-multiplier is set to 3.0 for now, didn't have time to tune it up, but I see that we get most of the interesting functions with 3, so there is no much performance difference with higher, and binary size doesn't grow as much as with 10.0. Reviewers: eraman, mehdi_amini, tejohnson Subscribers: mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D24638 llvm-svn: 282437
2016-09-27 04:37:32 +08:00
; COMBINED: <GLOBALVAL_SUMMARY_BLOCK
; COMBINED-NEXT: <VERSION
Bitcode: Add a string table to the bitcode format. Add a top-level STRTAB block containing a string table blob, and start storing strings for module codes FUNCTION, GLOBALVAR, ALIAS, IFUNC and COMDAT in the string table. This change allows us to share names between globals and comdats as well as between modules, and improves the efficiency of loading bitcode files by no longer using a bit encoding for symbol names. Once we start writing the irsymtab to the bitcode file we will also be able to share strings between it and the module. On my machine, link time for Chromium for Linux with ThinLTO decreases by about 7% for no-op incremental builds or about 1% for full builds. Total bitcode file size decreases by about 3%. As discussed on llvm-dev: http://lists.llvm.org/pipermail/llvm-dev/2017-April/111732.html Differential Revision: https://reviews.llvm.org/D31838 llvm-svn: 300464
2017-04-18 01:51:36 +08:00
; 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
[thinlto] Basic thinlto fdo heuristic Summary: This patch improves thinlto importer by importing 3x larger functions that are called from hot block. I compared performance with the trunk on spec, and there were about 2% on povray and 3.33% on milc. These results seems to be consistant and match the results Teresa got with her simple heuristic. Some benchmarks got slower but I think they are just noisy (mcf, xalancbmki, omnetpp)- running the benchmarks again with more iterations to confirm. Geomean of all benchmarks including the noisy ones were about +0.02%. I see much better improvement on google branch with Easwaran patch for pgo callsite inlining (the inliner actually inline those big functions) Over all I see +0.5% improvement, and I get +8.65% on povray. So I guess we will see much bigger change when Easwaran patch will land (it depends on new pass manager), but it is still worth putting this to trunk before it. Implementation details changes: - Removed CallsiteCount. - ProfileCount got replaced by Hotness - hot-import-multiplier is set to 3.0 for now, didn't have time to tune it up, but I see that we get most of the interesting functions with 3, so there is no much performance difference with higher, and binary size doesn't grow as much as with 10.0. Reviewers: eraman, mehdi_amini, tejohnson Subscribers: mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D24638 llvm-svn: 282437
2016-09-27 04:37:32 +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=
[ThinLTO] Add FunctionAttrs to ThinLTO index Adds function attributes to index: ReadNone, ReadOnly, NoRecurse, NoAlias. This attributes will be used for future ThinLTO optimizations that will propagate function attributes across modules. llvm-svn: 310061
2017-08-05 00:00:58 +08:00
; COMBINED-NEXT: <COMBINED_PROFILE {{.*}} op6=[[HOT1:.*]] op7=3 op8=[[COLD:.*]] op9=1 op10=[[HOT2:.*]] op11=3 op12=[[NONE1:.*]] op13=2 op14=[[HOT3:.*]] op15=3 op16=[[NONE2:.*]] op17=2 op18=[[NONE3:.*]] op19=2/>
[thinlto] Basic thinlto fdo heuristic Summary: This patch improves thinlto importer by importing 3x larger functions that are called from hot block. I compared performance with the trunk on spec, and there were about 2% on povray and 3.33% on milc. These results seems to be consistant and match the results Teresa got with her simple heuristic. Some benchmarks got slower but I think they are just noisy (mcf, xalancbmki, omnetpp)- running the benchmarks again with more iterations to confirm. Geomean of all benchmarks including the noisy ones were about +0.02%. I see much better improvement on google branch with Easwaran patch for pgo callsite inlining (the inliner actually inline those big functions) Over all I see +0.5% improvement, and I get +8.65% on povray. So I guess we will see much bigger change when Easwaran patch will land (it depends on new pass manager), but it is still worth putting this to trunk before it. Implementation details changes: - Removed CallsiteCount. - ProfileCount got replaced by Hotness - hot-import-multiplier is set to 3.0 for now, didn't have time to tune it up, but I see that we get most of the interesting functions with 3, so there is no much performance difference with higher, and binary size doesn't grow as much as with 10.0. Reviewers: eraman, mehdi_amini, tejohnson Subscribers: mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D24638 llvm-svn: 282437
2016-09-27 04:37:32 +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 @hot1()
br i1 %a, label %Cold, label %Hot, !prof !41
Cold: ; 1/1000 goes here
call void @cold()
call void @hot2()
Use ProfileSummary:getProfileCount to get ScaledCount for ModuleSummary Summary: ModuleSummary should use the standard interface of ProfileSummary::getProfileCount. Reviewers: eraman, tejohnson Reviewed By: tejohnson Subscribers: tejohnson, mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D31154 llvm-svn: 298404
2017-03-22 01:22:35 +08:00
call void @hot4(), !prof !15
[thinlto] Basic thinlto fdo heuristic Summary: This patch improves thinlto importer by importing 3x larger functions that are called from hot block. I compared performance with the trunk on spec, and there were about 2% on povray and 3.33% on milc. These results seems to be consistant and match the results Teresa got with her simple heuristic. Some benchmarks got slower but I think they are just noisy (mcf, xalancbmki, omnetpp)- running the benchmarks again with more iterations to confirm. Geomean of all benchmarks including the noisy ones were about +0.02%. I see much better improvement on google branch with Easwaran patch for pgo callsite inlining (the inliner actually inline those big functions) Over all I see +0.5% improvement, and I get +8.65% on povray. So I guess we will see much bigger change when Easwaran patch will land (it depends on new pass manager), but it is still worth putting this to trunk before it. Implementation details changes: - Removed CallsiteCount. - ProfileCount got replaced by Hotness - hot-import-multiplier is set to 3.0 for now, didn't have time to tune it up, but I see that we get most of the interesting functions with 3, so there is no much performance difference with higher, and binary size doesn't grow as much as with 10.0. Reviewers: eraman, mehdi_amini, tejohnson Subscribers: mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D24638 llvm-svn: 282437
2016-09-27 04:37:32 +08:00
call void @none1()
br label %exit
Hot: ; 999/1000 goes here
call void @hot2()
call void @hot3()
br i1 %a2, label %None1, label %None2, !prof !42
None1: ; half goes here
call void @none1()
call void @none2()
br label %exit
None2: ; half goes here
call void @none3()
br label %exit
exit:
ret void
}
declare void @hot1() #1
declare void @hot2() #1
declare void @hot3() #1
Use ProfileSummary:getProfileCount to get ScaledCount for ModuleSummary Summary: ModuleSummary should use the standard interface of ProfileSummary::getProfileCount. Reviewers: eraman, tejohnson Reviewed By: tejohnson Subscribers: tejohnson, mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D31154 llvm-svn: 298404
2017-03-22 01:22:35 +08:00
declare void @hot4() #1
[thinlto] Basic thinlto fdo heuristic Summary: This patch improves thinlto importer by importing 3x larger functions that are called from hot block. I compared performance with the trunk on spec, and there were about 2% on povray and 3.33% on milc. These results seems to be consistant and match the results Teresa got with her simple heuristic. Some benchmarks got slower but I think they are just noisy (mcf, xalancbmki, omnetpp)- running the benchmarks again with more iterations to confirm. Geomean of all benchmarks including the noisy ones were about +0.02%. I see much better improvement on google branch with Easwaran patch for pgo callsite inlining (the inliner actually inline those big functions) Over all I see +0.5% improvement, and I get +8.65% on povray. So I guess we will see much bigger change when Easwaran patch will land (it depends on new pass manager), but it is still worth putting this to trunk before it. Implementation details changes: - Removed CallsiteCount. - ProfileCount got replaced by Hotness - hot-import-multiplier is set to 3.0 for now, didn't have time to tune it up, but I see that we get most of the interesting functions with 3, so there is no much performance difference with higher, and binary size doesn't grow as much as with 10.0. Reviewers: eraman, mehdi_amini, tejohnson Subscribers: mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D24638 llvm-svn: 282437
2016-09-27 04:37:32 +08:00
declare void @cold() #1
declare void @none1() #1
declare void @none2() #1
declare void @none3() #1
!41 = !{!"branch_weights", i32 1, i32 1000}
!42 = !{!"branch_weights", i32 1, i32 1}
!llvm.module.flags = !{!1}
Add function importing info from samplepgo profile to the module summary. Summary: For SamplePGO, the profile may contain cross-module inline stacks. As we need to make sure the profile annotation happens when all the hot inline stacks are expanded, we need to pass this info to the module importer so that it can import proper functions if necessary. This patch implemented this feature by emitting cross-module targets as part of function entry metadata. In the module-summary phase, the metadata is used to build call edges that points to functions need to be imported. Reviewers: mehdi_amini, tejohnson Reviewed By: tejohnson Subscribers: davidxl, llvm-commits Differential Revision: https://reviews.llvm.org/D30053 llvm-svn: 296498
2017-03-01 02:09:44 +08:00
!20 = !{!"function_entry_count", i64 110, i64 123}
[thinlto] Basic thinlto fdo heuristic Summary: This patch improves thinlto importer by importing 3x larger functions that are called from hot block. I compared performance with the trunk on spec, and there were about 2% on povray and 3.33% on milc. These results seems to be consistant and match the results Teresa got with her simple heuristic. Some benchmarks got slower but I think they are just noisy (mcf, xalancbmki, omnetpp)- running the benchmarks again with more iterations to confirm. Geomean of all benchmarks including the noisy ones were about +0.02%. I see much better improvement on google branch with Easwaran patch for pgo callsite inlining (the inliner actually inline those big functions) Over all I see +0.5% improvement, and I get +8.65% on povray. So I guess we will see much bigger change when Easwaran patch will land (it depends on new pass manager), but it is still worth putting this to trunk before it. Implementation details changes: - Removed CallsiteCount. - ProfileCount got replaced by Hotness - hot-import-multiplier is set to 3.0 for now, didn't have time to tune it up, but I see that we get most of the interesting functions with 3, so there is no much performance difference with higher, and binary size doesn't grow as much as with 10.0. Reviewers: eraman, mehdi_amini, tejohnson Subscribers: mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D24638 llvm-svn: 282437
2016-09-27 04:37:32 +08:00
!1 = !{i32 1, !"ProfileSummary", !2}
!2 = !{!3, !4, !5, !6, !7, !8, !9, !10}
!3 = !{!"ProfileFormat", !"InstrProf"}
!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}
Use ProfileSummary:getProfileCount to get ScaledCount for ModuleSummary Summary: ModuleSummary should use the standard interface of ProfileSummary::getProfileCount. Reviewers: eraman, tejohnson Reviewed By: tejohnson Subscribers: tejohnson, mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D31154 llvm-svn: 298404
2017-03-22 01:22:35 +08:00
!15 = !{!"branch_weights", i32 100}