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...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

166 lines
7.6 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
[ThinLTO] Print module summary index to assembly Summary: Implements AsmWriter support for printing the module summary index to assembly with the format discussed in the RFC "LLVM Assembly format for ThinLTO Summary". Implements just enough of the parsing support to recognize and ignore the summary entries. As agreed in the RFC thread, this will be the behavior when assembling the IR. A follow on change will implement parsing/assembling of the summary entries for use by tools that currently build the summary index from bitcode. Reviewers: dexonsmith, pcc Subscribers: inglorion, eraman, steven_wu, dblaikie, llvm-commits Differential Revision: https://reviews.llvm.org/D46699 llvm-svn: 333335
2018-05-26 10:34:13 +08:00
; RUN: llvm-dis %t.o
; RUN: cat %t.o.ll | FileCheck %s --check-prefix=DIS
; Make sure the assembler doesn't error when parsing the summary
; RUN: llvm-as %t.o.ll
[ThinLTO] Parse module summary index from assembly Summary: Adds assembly parsing support for the module summary index (follow on to r333335 which added the assembly writing support). I added support to llvm-as to invoke the index parsing, so that it can create either a bitcode file with a Module and a per-module index, or a combined index without a Module. I will send follow on patches soon to do the following: - add support to tools such as llvm-lto2 to parse the per-module indexes from assembly instead of bitcode when testing the thin link. - verification support. Depends on D47844 and D47842. Reviewers: pcc, dexonsmith, mehdi_amini Subscribers: inglorion, eraman, steven_wu, llvm-commits Differential Revision: https://reviews.llvm.org/D47905 llvm-svn: 335602
2018-06-26 21:56:49 +08:00
; Check assembled summary.
; RUN: llvm-dis %t.o.bc -o - | FileCheck %s --check-prefix=DIS
[ThinLTO] Print module summary index to assembly Summary: Implements AsmWriter support for printing the module summary index to assembly with the format discussed in the RFC "LLVM Assembly format for ThinLTO Summary". Implements just enough of the parsing support to recognize and ignore the summary entries. As agreed in the RFC thread, this will be the behavior when assembling the IR. A follow on change will implement parsing/assembling of the summary entries for use by tools that currently build the summary index from bitcode. Reviewers: dexonsmith, pcc Subscribers: inglorion, eraman, steven_wu, dblaikie, llvm-commits Differential Revision: https://reviews.llvm.org/D46699 llvm-svn: 333335
2018-05-26 10:34:13 +08:00
[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
; 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
[ThinLTO] Print module summary index to assembly Summary: Implements AsmWriter support for printing the module summary index to assembly with the format discussed in the RFC "LLVM Assembly format for ThinLTO Summary". Implements just enough of the parsing support to recognize and ignore the summary entries. As agreed in the RFC thread, this will be the behavior when assembling the IR. A follow on change will implement parsing/assembling of the summary entries for use by tools that currently build the summary index from bitcode. Reviewers: dexonsmith, pcc Subscribers: inglorion, eraman, steven_wu, dblaikie, llvm-commits Differential Revision: https://reviews.llvm.org/D46699 llvm-svn: 333335
2018-05-26 10:34:13 +08:00
; RUN: llvm-dis %t3.thinlto.bc
; RUN: cat %t3.thinlto.ll | FileCheck %s --check-prefix=COMBINED-DIS
[ThinLTO] Parse module summary index from assembly Summary: Adds assembly parsing support for the module summary index (follow on to r333335 which added the assembly writing support). I added support to llvm-as to invoke the index parsing, so that it can create either a bitcode file with a Module and a per-module index, or a combined index without a Module. I will send follow on patches soon to do the following: - add support to tools such as llvm-lto2 to parse the per-module indexes from assembly instead of bitcode when testing the thin link. - verification support. Depends on D47844 and D47842. Reviewers: pcc, dexonsmith, mehdi_amini Subscribers: inglorion, eraman, steven_wu, llvm-commits Differential Revision: https://reviews.llvm.org/D47905 llvm-svn: 335602
2018-06-26 21:56:49 +08:00
; Round trip it through llvm-as
; RUN: cat %t3.thinlto.ll | llvm-as -o - | llvm-dis -o - | FileCheck %s --check-prefix=COMBINED-DIS
[ThinLTO] Print module summary index to assembly Summary: Implements AsmWriter support for printing the module summary index to assembly with the format discussed in the RFC "LLVM Assembly format for ThinLTO Summary". Implements just enough of the parsing support to recognize and ignore the summary entries. As agreed in the RFC thread, this will be the behavior when assembling the IR. A follow on change will implement parsing/assembling of the summary entries for use by tools that currently build the summary index from bitcode. Reviewers: dexonsmith, pcc Subscribers: inglorion, eraman, steven_wu, dblaikie, llvm-commits Differential Revision: https://reviews.llvm.org/D46699 llvm-svn: 333335
2018-05-26 10:34:13 +08:00
; Make sure the assembler doesn't error when parsing the combined summary
; RUN: llvm-as %t3.thinlto.ll -o %t3.thinlto.o
[ThinLTO] Parse module summary index from assembly Summary: Adds assembly parsing support for the module summary index (follow on to r333335 which added the assembly writing support). I added support to llvm-as to invoke the index parsing, so that it can create either a bitcode file with a Module and a per-module index, or a combined index without a Module. I will send follow on patches soon to do the following: - add support to tools such as llvm-lto2 to parse the per-module indexes from assembly instead of bitcode when testing the thin link. - verification support. Depends on D47844 and D47842. Reviewers: pcc, dexonsmith, mehdi_amini Subscribers: inglorion, eraman, steven_wu, llvm-commits Differential Revision: https://reviews.llvm.org/D47905 llvm-svn: 335602
2018-06-26 21:56:49 +08:00
; Check assembled combined summary.
; RUN: llvm-dis %t3.thinlto.o -o - | FileCheck %s --check-prefix=COMBINED-DIS
[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
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
[LTO] Record whether LTOUnit splitting is enabled in index Summary: Records in the module summary index whether the bitcode was compiled with the option necessary to enable splitting the LTO unit (e.g. -fsanitize=cfi, -fwhole-program-vtables, or -fsplit-lto-unit). The information is passed down to the ModuleSummaryIndex builder via a new module flag "EnableSplitLTOUnit", which is propagated onto a flag on the summary index. This is then used during the LTO link to check whether all linked summaries were built with the same value of this flag. If not, an error is issued when we detect a situation requiring whole program visibility of the class hierarchy. This is the case when both of the following conditions are met: 1) We are performing LowerTypeTests or Whole Program Devirtualization. 2) There are type tests or type checked loads in the code. Note I have also changed the ThinLTOBitcodeWriter to also gate the module splitting on the value of this flag. Reviewers: pcc Subscribers: ormris, mehdi_amini, Prazek, inglorion, eraman, steven_wu, dexonsmith, arphaman, dang, llvm-commits Differential Revision: https://reviews.llvm.org/D53890 llvm-svn: 350948
2019-01-12 02:31:57 +08:00
; CHECK-NEXT: <FLAGS
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] Attempt to recommit r365188 after alignment fix llvm-svn: 365215
2019-07-05 23:25:05 +08:00
; CHECK-NEXT: <PERMODULE_PROFILE {{.*}} op7=1 op8=3 op9=5 op10=1 op11=2 op12=3 op13=4 op14=1 op15=6 op16=2 op17=3 op18=3 op19=7 op20=2 op21=8 op22=2 op23=25 op24=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
[ThinLTO] Serialize WithGlobalValueDeadStripping index flag for distributed backends Summary: A recent fix to drop dead symbols (r323633) did not work for ThinLTO distributed backends because we lose the WithGlobalValueDeadStripping set on the index during the thin link. This patch adds a new flags record to the bitcode format for the index, and serializes this flag for the combined index (it would always be 0 for the per-module index generated by the compile step, so no need to serialize the new flags record there until/unless we add another flag that applies to the per-module indexes). Generally this flag should always be set for the distributed backends, which are necessarily performed after the thin link. However, if we were to simply set this flag on the index applied to the distributed backends (invoked via clang), we would lose the ability to disable dead stripping via -compute-dead=false for debugging purposes. Reviewers: grimar, pcc Subscribers: mehdi_amini, inglorion, eraman, llvm-commits Differential Revision: https://reviews.llvm.org/D42799 llvm-svn: 324444
2018-02-07 12:05:59 +08:00
; COMBINED-NEXT: <FLAGS
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] Attempt to recommit r365188 after alignment fix llvm-svn: 365215
2019-07-05 23:25:05 +08:00
; COMBINED-NEXT: <COMBINED_PROFILE {{.*}} op9=[[HOT1:.*]] op10=3 op11=[[COLD:.*]] op12=1 op13=[[HOT2:.*]] op14=3 op15=[[NONE1:.*]] op16=2 op17=[[HOT3:.*]] op18=3 op19=[[NONE2:.*]] op20=2 op21=[[NONE3:.*]] op22=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}
[ThinLTO] Print module summary index to assembly Summary: Implements AsmWriter support for printing the module summary index to assembly with the format discussed in the RFC "LLVM Assembly format for ThinLTO Summary". Implements just enough of the parsing support to recognize and ignore the summary entries. As agreed in the RFC thread, this will be the behavior when assembling the IR. A follow on change will implement parsing/assembling of the summary entries for use by tools that currently build the summary index from bitcode. Reviewers: dexonsmith, pcc Subscribers: inglorion, eraman, steven_wu, dblaikie, llvm-commits Differential Revision: https://reviews.llvm.org/D46699 llvm-svn: 333335
2018-05-26 10:34:13 +08:00
[ThinLTO] Parse module summary index from assembly Summary: Adds assembly parsing support for the module summary index (follow on to r333335 which added the assembly writing support). I added support to llvm-as to invoke the index parsing, so that it can create either a bitcode file with a Module and a per-module index, or a combined index without a Module. I will send follow on patches soon to do the following: - add support to tools such as llvm-lto2 to parse the per-module indexes from assembly instead of bitcode when testing the thin link. - verification support. Depends on D47844 and D47842. Reviewers: pcc, dexonsmith, mehdi_amini Subscribers: inglorion, eraman, steven_wu, llvm-commits Differential Revision: https://reviews.llvm.org/D47905 llvm-svn: 335602
2018-06-26 21:56:49 +08:00
; DIS: ^0 = module: (path: "{{.*}}thinlto-function-summary-callgraph-profile-summary.ll.tmp.o{{.*}}", hash: (0, 0, 0, 0, 0))
[ThinLTO] Print module summary index to assembly Summary: Implements AsmWriter support for printing the module summary index to assembly with the format discussed in the RFC "LLVM Assembly format for ThinLTO Summary". Implements just enough of the parsing support to recognize and ignore the summary entries. As agreed in the RFC thread, this will be the behavior when assembling the IR. A follow on change will implement parsing/assembling of the summary entries for use by tools that currently build the summary index from bitcode. Reviewers: dexonsmith, pcc Subscribers: inglorion, eraman, steven_wu, dblaikie, llvm-commits Differential Revision: https://reviews.llvm.org/D46699 llvm-svn: 333335
2018-05-26 10:34:13 +08:00
; DIS: ^1 = gv: (guid: 123)
; DIS: ^2 = gv: (name: "none2") ; guid = 3741006263754194003
; DIS: ^3 = gv: (name: "hot3") ; guid = 5026609803865204483
; DIS: ^4 = gv: (name: "hot2") ; guid = 8117347573235780485
; DIS: ^5 = gv: (name: "hot1") ; guid = 9453975128311291976
; DIS: ^6 = gv: (name: "cold") ; guid = 11668175513417606517
; DIS: ^7 = gv: (name: "hot4") ; guid = 13161834114071272798
; DIS: ^8 = gv: (name: "none3") ; guid = 16213681105727317812
[ThinLTO] Auto-hide prevailing linkonce_odr only when all copies eligible Summary: We hit undefined references building with ThinLTO when one source file contained explicit instantiations of a template method (weak_odr) but there were also implicit instantiations in another file (linkonce_odr), and the latter was the prevailing copy. In this case the symbol was marked hidden when the prevailing linkonce_odr copy was promoted to weak_odr. It led to unsats when the resulting shared library was linked with other code that contained a reference (expecting to be resolved due to the explicit instantiation). Add a CanAutoHide flag to the GV summary to allow the thin link to identify when all copies are eligible for auto-hiding (because they were all originally linkonce_odr global unnamed addr), and only do the auto-hide in that case. Most of the changes here are due to plumbing the new flag through the bitcode and llvm assembly, and resulting test changes. I augmented the existing auto-hide test to check for this situation. Reviewers: pcc Subscribers: mehdi_amini, inglorion, eraman, dexonsmith, arphaman, dang, llvm-commits, steven_wu, wmi Tags: #llvm Differential Revision: https://reviews.llvm.org/D59709 llvm-svn: 360466
2019-05-11 04:08:24 +08:00
; DIS: ^9 = gv: (name: "hot_function", summaries: (function: (module: ^0, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), insts: 16, calls: ((callee: ^5, hotness: hot), (callee: ^6, hotness: cold), (callee: ^4, hotness: hot), (callee: ^7, hotness: cold), (callee: ^10, hotness: none), (callee: ^3, hotness: hot), (callee: ^2, hotness: none), (callee: ^8, hotness: none), (callee: ^1, hotness: critical))))) ; guid = 17381606045411660303
[ThinLTO] Print module summary index to assembly Summary: Implements AsmWriter support for printing the module summary index to assembly with the format discussed in the RFC "LLVM Assembly format for ThinLTO Summary". Implements just enough of the parsing support to recognize and ignore the summary entries. As agreed in the RFC thread, this will be the behavior when assembling the IR. A follow on change will implement parsing/assembling of the summary entries for use by tools that currently build the summary index from bitcode. Reviewers: dexonsmith, pcc Subscribers: inglorion, eraman, steven_wu, dblaikie, llvm-commits Differential Revision: https://reviews.llvm.org/D46699 llvm-svn: 333335
2018-05-26 10:34:13 +08:00
; DIS: ^10 = gv: (name: "none1") ; guid = 17712061229457633252
[ThinLTO] Fix a few more test match issues Fix a few more bot failures due to r333335: - don't match path other than file name, since the delimiter is different for Windows - The summary IDs in thinlto-function-summary-refgraph.ll may vary and therefore can't be matched exactly, because the ordering depends on the iteration order of the index map which is keyed by GUID. The GUID for private values will depend on the path. llvm-svn: 333338
2018-05-26 11:50:29 +08:00
; COMBINED-DIS: ^0 = module: (path: "{{.*}}thinlto-function-summary-callgraph-profile-summary.ll.tmp.o", hash: (0, 0, 0, 0, 0))
; COMBINED-DIS: ^1 = module: (path: "{{.*}}thinlto-function-summary-callgraph-profile-summary.ll.tmp2.o", hash: (0, 0, 0, 0, 0))
[ThinLTO] Auto-hide prevailing linkonce_odr only when all copies eligible Summary: We hit undefined references building with ThinLTO when one source file contained explicit instantiations of a template method (weak_odr) but there were also implicit instantiations in another file (linkonce_odr), and the latter was the prevailing copy. In this case the symbol was marked hidden when the prevailing linkonce_odr copy was promoted to weak_odr. It led to unsats when the resulting shared library was linked with other code that contained a reference (expecting to be resolved due to the explicit instantiation). Add a CanAutoHide flag to the GV summary to allow the thin link to identify when all copies are eligible for auto-hiding (because they were all originally linkonce_odr global unnamed addr), and only do the auto-hide in that case. Most of the changes here are due to plumbing the new flag through the bitcode and llvm assembly, and resulting test changes. I augmented the existing auto-hide test to check for this situation. Reviewers: pcc Subscribers: mehdi_amini, inglorion, eraman, dexonsmith, arphaman, dang, llvm-commits, steven_wu, wmi Tags: #llvm Differential Revision: https://reviews.llvm.org/D59709 llvm-svn: 360466
2019-05-11 04:08:24 +08:00
; COMBINED-DIS: ^2 = gv: (guid: 3741006263754194003, summaries: (function: (module: ^1, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), insts: 1)))
; COMBINED-DIS: ^3 = gv: (guid: 5026609803865204483, summaries: (function: (module: ^1, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), insts: 1)))
; COMBINED-DIS: ^4 = gv: (guid: 8117347573235780485, summaries: (function: (module: ^1, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), insts: 1)))
; COMBINED-DIS: ^5 = gv: (guid: 9453975128311291976, summaries: (function: (module: ^1, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), insts: 1)))
; COMBINED-DIS: ^6 = gv: (guid: 11668175513417606517, summaries: (function: (module: ^1, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), insts: 1)))
; COMBINED-DIS: ^7 = gv: (guid: 16213681105727317812, summaries: (function: (module: ^1, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), insts: 1)))
; COMBINED-DIS: ^8 = gv: (guid: 17381606045411660303, summaries: (function: (module: ^0, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), insts: 16, calls: ((callee: ^5, hotness: hot), (callee: ^6, hotness: cold), (callee: ^4, hotness: hot), (callee: ^9, hotness: none), (callee: ^3, hotness: hot), (callee: ^2, hotness: none), (callee: ^7, hotness: none)))))
; COMBINED-DIS: ^9 = gv: (guid: 17712061229457633252, summaries: (function: (module: ^1, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), insts: 1)))