From d9830eb79fdc42368d370abeab9a3b56c08e3963 Mon Sep 17 00:00:00 2001 From: Piotr Padlewski Date: Mon, 26 Sep 2016 20:37:32 +0000 Subject: [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 --- ...o-function-summary-callgraph-profile-summary.ll | 98 ++++++++++++++++++++++ 1 file changed, 98 insertions(+) create mode 100644 llvm/test/Bitcode/thinlto-function-summary-callgraph-profile-summary.ll (limited to 'llvm/test/Bitcode/thinlto-function-summary-callgraph-profile-summary.ll') diff --git a/llvm/test/Bitcode/thinlto-function-summary-callgraph-profile-summary.ll b/llvm/test/Bitcode/thinlto-function-summary-callgraph-profile-summary.ll new file mode 100644 index 00000000000..fd12d3f99f6 --- /dev/null +++ b/llvm/test/Bitcode/thinlto-function-summary-callgraph-profile-summary.ll @@ -0,0 +1,98 @@ +; 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 + + +; CHECK-LABEL: +; CHECK-NEXT: +; CHECK-LABEL: + +; COMBINED: +; COMBINED_NEXT: + + +; 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() + 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 +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} +!20 = !{!"function_entry_count", i64 110} + +!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} -- cgit v1.2.3