[AutoFDO] Statistic for context sensitive profile guided inlining

Summary: AutoFDO compilation has two places that do inlining - the sample profile loader that does inlining with context sensitive profile, and the regular inliner as CGSCC pass. Ideally we want most inlining to come from sample profile loader as that is driven by context sensitive profile and also retains context sensitivity after inlining. However the reality is most of the inlining actually happens during regular inliner. To track the number of inline instances from sample profile loader and help move more inlining to sample profile loader, I'm adding statistics and optimization remarks for sample profile loader's inlining.

Reviewers: wmi, davidxl

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D70584

3 files changed, 109 insertions, 5 deletions

diff --git a/llvm/test/Transforms/SampleProfile/inline-coverage.ll b/llvm/test/Transforms/SampleProfile/inline-coverage.ll
index 7e189545190..134bbe8b80d 100644
--- a/llvm/test/Transforms/SampleProfile/inline-coverage.ll
+++ b/llvm/test/Transforms/SampleProfile/inline-coverage.ll
@@ -16,7 +16,7 @@
 ;    11      return sum > 0 ? 0 : 1;
 ;    12    }
 ;
-; CHECK: remark: coverage.cc:10:12: inlined hot callee '_Z3fool' into 'main'
+; CHECK: remark: coverage.cc:10:12: previous inlining reattempted for hotness: '_Z3fool' into 'main'
 ; CHECK: remark: coverage.cc:9:21: Applied 23478 samples from profile (offset: 2.1)
 ; CHECK: remark: coverage.cc:10:16: Applied 23478 samples from profile (offset: 3)
 ; CHECK: remark: coverage.cc:4:10: Applied 31878 samples from profile (offset: 1)
diff --git a/llvm/test/Transforms/SampleProfile/inline-stats.ll b/llvm/test/Transforms/SampleProfile/inline-stats.ll
new file mode 100644
index 00000000000..f928aed6a97
--- /dev/null
+++ b/llvm/test/Transforms/SampleProfile/inline-stats.ll
@@ -0,0 +1,104 @@
+; REQUIRES: asserts
+; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline.prof -stats -S 2>&1 | FileCheck %s
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline.prof -stats -S 2>&1 | FileCheck %s
+
+; Original C++ test case
+;
+; #include <stdio.h>
+;
+; int sum(int x, int y) {
+;   return x + y;
+; }
+;
+; int main() {
+;   int s, i = 0;
+;   while (i++ < 20000 * 20000)
+;     if (i != 100) s = sum(i, s); else s = 30;
+;   printf("sum is %d\n", s);
+;   return 0;
+; }
+;
+@.str = private unnamed_addr constant [11 x i8] c"sum is %d\0A\00", align 1
+define i32 @_Z3sumii(i32 %x, i32 %y) !dbg !6 {
+entry:
+  %x.addr = alloca i32, align 4
+  %y.addr = alloca i32, align 4
+  store i32 %x, i32* %x.addr, align 4
+  store i32 %y, i32* %y.addr, align 4
+  %tmp = load i32, i32* %x.addr, align 4, !dbg !8
+  %tmp1 = load i32, i32* %y.addr, align 4, !dbg !8
+  %add = add nsw i32 %tmp, %tmp1, !dbg !8
+  ret i32 %add, !dbg !8
+}
+define i32 @main() !dbg !9 {
+entry:
+  %retval = alloca i32, align 4
+  %s = alloca i32, align 4
+  %i = alloca i32, align 4
+  store i32 0, i32* %retval
+  store i32 0, i32* %i, align 4, !dbg !10
+  br label %while.cond, !dbg !11
+
+while.cond:                                       ; preds = %if.end, %entry
+  %tmp = load i32, i32* %i, align 4, !dbg !12
+  %inc = add nsw i32 %tmp, 1, !dbg !12
+  store i32 %inc, i32* %i, align 4, !dbg !12
+  %cmp = icmp slt i32 %tmp, 400000000, !dbg !12
+  br i1 %cmp, label %while.body, label %while.end, !dbg !12
+
+while.body:                                       ; preds = %while.cond
+  %tmp1 = load i32, i32* %i, align 4, !dbg !14
+  %cmp1 = icmp ne i32 %tmp1, 100, !dbg !14
+  br i1 %cmp1, label %if.then, label %if.else, !dbg !14
+
+if.then:                                          ; preds = %while.body
+  %tmp2 = load i32, i32* %i, align 4, !dbg !16
+  %tmp3 = load i32, i32* %s, align 4, !dbg !16
+  %call = call i32 @_Z3sumii(i32 %tmp2, i32 %tmp3), !dbg !16
+  store i32 %call, i32* %s, align 4, !dbg !16
+  br label %if.end, !dbg !16
+
+if.else:                                          ; preds = %while.body
+  store i32 30, i32* %s, align 4, !dbg !18
+  br label %if.end
+
+if.end:                                           ; preds = %if.else, %if.then
+  br label %while.cond, !dbg !20
+
+while.end:                                        ; preds = %while.cond
+  %tmp4 = load i32, i32* %s, align 4, !dbg !22
+  %call2 = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([11 x i8], [11 x i8]* @.str, i32 0, i32 0), i32 %tmp4), !dbg !22
+  ret i32 0, !dbg !23
+}
+declare i32 @printf(i8*, ...)
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4}
+!llvm.ident = !{!5}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "clang version 3.5 ", isOptimized: false, runtimeVersion: 0, emissionKind: NoDebug, enums: !2, retainedTypes: !2, globals: !2, imports: !2)
+!1 = !DIFile(filename: "calls.cc", directory: ".")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 1, !"Debug Info Version", i32 3}
+!5 = !{!"clang version 3.5 "}
+!6 = distinct !DISubprogram(name: "sum", scope: !1, file: !1, line: 3, type: !7, scopeLine: 3, virtualIndex: 6, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition, unit: !0, retainedNodes: !2)
+!7 = !DISubroutineType(types: !2)
+!8 = !DILocation(line: 4, scope: !6)
+!9 = distinct !DISubprogram(name: "main", scope: !1, file: !1, line: 7, type: !7, scopeLine: 7, virtualIndex: 6, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition, unit: !0, retainedNodes: !2)
+!10 = !DILocation(line: 8, scope: !9)
+!11 = !DILocation(line: 9, scope: !9)
+!12 = !DILocation(line: 9, scope: !13)
+!13 = !DILexicalBlockFile(scope: !9, file: !1, discriminator: 2)
+!14 = !DILocation(line: 10, scope: !15)
+!15 = distinct !DILexicalBlock(scope: !9, file: !1, line: 10)
+!16 = !DILocation(line: 10, scope: !17)
+!17 = !DILexicalBlockFile(scope: !15, file: !1, discriminator: 2)
+!18 = !DILocation(line: 10, scope: !19)
+!19 = !DILexicalBlockFile(scope: !15, file: !1, discriminator: 4)
+!20 = !DILocation(line: 10, scope: !21)
+!21 = !DILexicalBlockFile(scope: !15, file: !1, discriminator: 6)
+!22 = !DILocation(line: 11, scope: !9)
+!23 = !DILocation(line: 12, scope: !9)
+
+; CHECK: 1 sample-profile - Number of functions inlined with context sensitive profile
\ No newline at end of file
diff --git a/llvm/test/Transforms/SampleProfile/remarks.ll b/llvm/test/Transforms/SampleProfile/remarks.ll
index 3ecaa534296..89a4bbe46d0 100644
--- a/llvm/test/Transforms/SampleProfile/remarks.ll
+++ b/llvm/test/Transforms/SampleProfile/remarks.ll
@@ -21,7 +21,7 @@
 
 ; We are expecting foo() to be inlined in main() (almost all the cycles are
 ; spent inside foo).
-; CHECK: remark: remarks.cc:13:21: inlined hot callee '_Z3foov' into 'main'
+; CHECK: remark: remarks.cc:13:21: inlined callee '_Z3foov' into 'main'
 
 ; The back edge for the loop is the hottest edge in the loop subgraph.
 ; CHECK: remark: remarks.cc:6:9: most popular destination for conditional branches at remarks.cc:5:3
@@ -31,12 +31,12 @@
 
 ; Checking to see if YAML file is generated and contains remarks
 ;YAML:       --- !Passed
-;YAML-NEXT:  Pass:            sample-profile
-;YAML-NEXT:  Name:            HotInline
+;YAML-NEXT:  Pass:            sample-profile-inline
+;YAML-NEXT:  Name:            InlineSuccess
 ;YAML-NEXT:  DebugLoc:        { File: remarks.cc, Line: 13, Column: 21 }
 ;YAML-NEXT:  Function:        main
 ;YAML-NEXT:  Args:
-;YAML-NEXT:    - String:          'inlined hot callee '''
+;YAML-NEXT:    - String:          'inlined callee '''
 ;YAML-NEXT:    - Callee:          _Z3foov
 ;YAML-NEXT:      DebugLoc:        { File: remarks.cc, Line: 3, Column: 0 }
 ;YAML-NEXT:    - String:          ''' into '''