diff options
| author | Hiroshi Yamauchi <yamauchi@google.com> | 2019-04-15 16:49:00 +0000 |
|---|---|---|
| committer | Hiroshi Yamauchi <yamauchi@google.com> | 2019-04-15 16:49:00 +0000 |
| commit | 09e539fcaebb6362795d352cdcf4a818cf4d0d6a (patch) | |
| tree | a91b7d07d85c67b737db8e49e3f62f95dd512898 /llvm/test/Transforms/LoopUnroll | |
| parent | 64041d7b90714aa6f0542c64ec5bb327beecfc58 (diff) | |
| download | bcm5719-llvm-09e539fcaebb6362795d352cdcf4a818cf4d0d6a.tar.gz bcm5719-llvm-09e539fcaebb6362795d352cdcf4a818cf4d0d6a.zip | |
[PGO] Profile guided code size optimization.
Summary:
Enable some of the existing size optimizations for cold code under PGO.
A ~5% code size saving in big internal app under PGO.
The way it gets BFI/PSI is discussed in the RFC thread
http://lists.llvm.org/pipermail/llvm-dev/2019-March/130894.html
Note it doesn't currently touch loop passes.
Reviewers: davidxl, eraman
Reviewed By: eraman
Subscribers: mgorny, javed.absar, smeenai, mehdi_amini, eraman, zzheng, steven_wu, dexonsmith, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59514
llvm-svn: 358422
Diffstat (limited to 'llvm/test/Transforms/LoopUnroll')
| -rw-r--r-- | llvm/test/Transforms/LoopUnroll/unroll-opt-attribute.ll | 46 |
1 files changed, 46 insertions, 0 deletions
diff --git a/llvm/test/Transforms/LoopUnroll/unroll-opt-attribute.ll b/llvm/test/Transforms/LoopUnroll/unroll-opt-attribute.ll index f4a76c71368..2f0eb756fb6 100644 --- a/llvm/test/Transforms/LoopUnroll/unroll-opt-attribute.ll +++ b/llvm/test/Transforms/LoopUnroll/unroll-opt-attribute.ll @@ -1,5 +1,7 @@ ; RUN: opt < %s -S -loop-unroll -unroll-count=4 | FileCheck -check-prefix=CHECK_COUNT4 %s
; RUN: opt < %s -S -loop-unroll | FileCheck -check-prefix=CHECK_NOCOUNT %s
+; RUN: opt < %s -S -passes='require<profile-summary>,function(unroll)' -pgso | FileCheck -check-prefix=PGSO %s
+; RUN: opt < %s -S -passes='require<profile-summary>,function(unroll)' -pgso=false | FileCheck -check-prefix=NPGSO %s
;///////////////////// TEST 1 //////////////////////////////
@@ -128,3 +130,47 @@ for.end: ; preds = %for.body ; CHECK_NOCOUNT-LABEL: @Test4
; CHECK_NOCOUNT: phi
; CHECK_NOCOUNT: icmp
+
+;///////////////////// TEST 5 //////////////////////////////
+
+; This test shows that with PGO, this loop is cold and not unrolled.
+
+define i32 @Test5() !prof !14 {
+entry:
+ br label %for.body
+
+for.body: ; preds = %for.body, %entry
+ %i.05 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
+ %arrayidx = getelementptr inbounds [24 x i32], [24 x i32]* @tab, i32 0, i32 %i.05
+ store i32 %i.05, i32* %arrayidx, align 4
+ %inc = add nuw nsw i32 %i.05, 1
+ %exitcond = icmp eq i32 %inc, 24
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body
+ ret i32 42
+}
+
+; PGSO-LABEL: @Test5
+; PGSO: phi
+; PGSO: icmp
+; NPGSO-LABEL: @Test5
+; NPGSO-NOT: phi
+; NPGSO-NOT: icmp
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 1, !"ProfileSummary", !1}
+!1 = !{!2, !3, !4, !5, !6, !7, !8, !9}
+!2 = !{!"ProfileFormat", !"InstrProf"}
+!3 = !{!"TotalCount", i64 10000}
+!4 = !{!"MaxCount", i64 10}
+!5 = !{!"MaxInternalCount", i64 1}
+!6 = !{!"MaxFunctionCount", i64 1000}
+!7 = !{!"NumCounts", i64 3}
+!8 = !{!"NumFunctions", i64 3}
+!9 = !{!"DetailedSummary", !10}
+!10 = !{!11, !12, !13}
+!11 = !{i32 10000, i64 100, i32 1}
+!12 = !{i32 999000, i64 100, i32 1}
+!13 = !{i32 999999, i64 1, i32 2}
+!14 = !{!"function_entry_count", i64 0}
|
