[SampleFDO] Add compression support for any section in ExtBinary profile format

Previously ExtBinary profile format only supports compression using zlib for
profile symbol list. In this patch, we extend the compression support to any
section. User can select some or all of the sections to compress. In an
experiment, for a 45M profile in ExtBinary format, compressing name table
reduced its size to 24M, and compressing all the sections reduced its size
to 11M.

Differential Revision: https://reviews.llvm.org/D68253

llvm-svn: 373914

5 files changed, 141 insertions, 2 deletions

diff --git a/llvm/test/Transforms/SampleProfile/compressed-profile-symbol-list.ll b/llvm/test/Transforms/SampleProfile/compressed-profile-symbol-list.ll
index 66265677229..6ac62c1701b 100644
--- a/llvm/test/Transforms/SampleProfile/compressed-profile-symbol-list.ll
+++ b/llvm/test/Transforms/SampleProfile/compressed-profile-symbol-list.ll
@@ -1,5 +1,5 @@
 ; REQUIRES: zlib
 ; Append inline.prof with profile symbol list and save it after compression.
-; RUN: llvm-profdata merge --sample --prof-sym-list=%S/Inputs/profile-symbol-list.text --compress-prof-sym-list=true --extbinary %S/Inputs/inline.prof --output=%t.profdata
+; RUN: llvm-profdata merge --sample --prof-sym-list=%S/Inputs/profile-symbol-list.text --compress-all-sections=true --extbinary %S/Inputs/inline.prof --output=%t.profdata
 ; RUN: opt < %S/Inputs/profile-symbol-list.ll -sample-profile -profile-accurate-for-symsinlist -sample-profile-file=%t.profdata -S | FileCheck %S/Inputs/profile-symbol-list.ll
 ; RUN: opt < %S/Inputs/profile-symbol-list.ll -passes=sample-profile -profile-accurate-for-symsinlist -sample-profile-file=%t.profdata -S | FileCheck %S/Inputs/profile-symbol-list.ll
diff --git a/llvm/test/Transforms/SampleProfile/profile-format-compress.ll b/llvm/test/Transforms/SampleProfile/profile-format-compress.ll
new file mode 100644
index 00000000000..be4eae3cddc
--- /dev/null
+++ b/llvm/test/Transforms/SampleProfile/profile-format-compress.ll
@@ -0,0 +1,123 @@
+; REQUIRES: zlib
+; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline.prof -S | FileCheck %s
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline.prof -S | FileCheck %s
+; RUN: llvm-profdata merge -sample -extbinary -compress-all-sections %S/Inputs/inline.prof -o %t.compress.extbinary.afdo
+; RUN: opt < %s -sample-profile -sample-profile-file=%t.compress.extbinary.afdo -S | FileCheck %s
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t.compress.extbinary.afdo -S | 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
+
+; Check sample-profile phase using compressed extbinary format profile
+; will annotate the IR with exactly the same result as using text format.
+; CHECK: br i1 %cmp, label %while.body, label %while.end{{.*}} !prof ![[IDX1:[0-9]*]]
+; CHECK: br i1 %cmp1, label %if.then, label %if.else{{.*}} !prof ![[IDX2:[0-9]*]]
+; CHECK: call i32 (i8*, ...) @printf{{.*}} !prof ![[IDX3:[0-9]*]]
+; CHECK: = !{!"TotalCount", i64 26781}
+; CHECK: = !{!"MaxCount", i64 5553}
+; CHECK: ![[IDX1]] = !{!"branch_weights", i32 5392, i32 163}
+; CHECK: ![[IDX2]] = !{!"branch_weights", i32 5280, i32 113}
+; CHECK: ![[IDX3]] = !{!"branch_weights", i32 1}
+
+; Function Attrs: nounwind uwtable
+define i32 @_Z3sumii(i32 %x, i32 %y) !dbg !4 {
+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
+  %0 = load i32, i32* %x.addr, align 4, !dbg !11
+  %1 = load i32, i32* %y.addr, align 4, !dbg !11
+  %add = add nsw i32 %0, %1, !dbg !11
+  ret i32 %add, !dbg !11
+}
+
+; Function Attrs: uwtable
+define i32 @main() !dbg !7 {
+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 !12
+  br label %while.cond, !dbg !13
+
+while.cond:                                       ; preds = %if.end, %entry
+  %0 = load i32, i32* %i, align 4, !dbg !14
+  %inc = add nsw i32 %0, 1, !dbg !14
+  store i32 %inc, i32* %i, align 4, !dbg !14
+  %cmp = icmp slt i32 %0, 400000000, !dbg !14
+  br i1 %cmp, label %while.body, label %while.end, !dbg !14
+
+while.body:                                       ; preds = %while.cond
+  %1 = load i32, i32* %i, align 4, !dbg !16
+  %cmp1 = icmp ne i32 %1, 100, !dbg !16
+  br i1 %cmp1, label %if.then, label %if.else, !dbg !16
+
+
+if.then:                                          ; preds = %while.body
+  %2 = load i32, i32* %i, align 4, !dbg !18
+  %3 = load i32, i32* %s, align 4, !dbg !18
+  %call = call i32 @_Z3sumii(i32 %2, i32 %3), !dbg !18
+  store i32 %call, i32* %s, align 4, !dbg !18
+  br label %if.end, !dbg !18
+
+if.else:                                          ; preds = %while.body
+  store i32 30, i32* %s, align 4, !dbg !20
+  br label %if.end
+
+if.end:                                           ; preds = %if.else, %if.then
+  br label %while.cond, !dbg !22
+
+while.end:                                        ; preds = %while.cond
+  %4 = load i32, i32* %s, align 4, !dbg !24
+  %call2 = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([11 x i8], [11 x i8]* @.str, i32 0, i32 0), i32 %4), !dbg !24
+  ret i32 0, !dbg !25
+}
+
+declare i32 @printf(i8*, ...) #2
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!8, !9}
+!llvm.ident = !{!10}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, producer: "clang version 3.5 ", isOptimized: false, emissionKind: NoDebug, file: !1, enums: !2, retainedTypes: !2, globals: !2, imports: !2)
+!1 = !DIFile(filename: "calls.cc", directory: ".")
+!2 = !{}
+!4 = distinct !DISubprogram(name: "sum", line: 3, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 3, file: !1, scope: !5, type: !6, retainedNodes: !2)
+!5 = !DIFile(filename: "calls.cc", directory: ".")
+!6 = !DISubroutineType(types: !2)
+!7 = distinct !DISubprogram(name: "main", line: 7, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 7, file: !1, scope: !5, type: !6, retainedNodes: !2)
+!8 = !{i32 2, !"Dwarf Version", i32 4}
+!9 = !{i32 1, !"Debug Info Version", i32 3}
+!10 = !{!"clang version 3.5 "}
+!11 = !DILocation(line: 4, scope: !4)
+!12 = !DILocation(line: 8, scope: !7)
+!13 = !DILocation(line: 9, scope: !7)
+!14 = !DILocation(line: 9, scope: !15)
+!15 = !DILexicalBlockFile(discriminator: 2, file: !1, scope: !7)
+!16 = !DILocation(line: 10, scope: !17)
+!17 = distinct !DILexicalBlock(line: 10, column: 0, file: !1, scope: !7)
+!18 = !DILocation(line: 10, scope: !19)
+!19 = !DILexicalBlockFile(discriminator: 2, file: !1, scope: !17)
+!20 = !DILocation(line: 10, scope: !21)
+!21 = !DILexicalBlockFile(discriminator: 4, file: !1, scope: !17)
+!22 = !DILocation(line: 10, scope: !23)
+!23 = !DILexicalBlockFile(discriminator: 6, file: !1, scope: !17)
+!24 = !DILocation(line: 11, scope: !7)
+!25 = !DILocation(line: 12, scope: !7)
diff --git a/llvm/test/Transforms/SampleProfile/uncompressed-profile-symbol-list.ll b/llvm/test/Transforms/SampleProfile/uncompressed-profile-symbol-list.ll
index abe562d7ebb..5eaf4b279d7 100644
--- a/llvm/test/Transforms/SampleProfile/uncompressed-profile-symbol-list.ll
+++ b/llvm/test/Transforms/SampleProfile/uncompressed-profile-symbol-list.ll
@@ -1,4 +1,4 @@
 ; Append inline.prof with profile symbol list and save it without compression.
-; RUN: llvm-profdata merge --sample --prof-sym-list=%S/Inputs/profile-symbol-list.text --compress-prof-sym-list=false --extbinary %S/Inputs/inline.prof --output=%t.profdata
+; RUN: llvm-profdata merge --sample --prof-sym-list=%S/Inputs/profile-symbol-list.text --compress-all-sections=false --extbinary %S/Inputs/inline.prof --output=%t.profdata
 ; RUN: opt < %S/Inputs/profile-symbol-list.ll -sample-profile -profile-accurate-for-symsinlist -sample-profile-file=%t.profdata -S | FileCheck %S/Inputs/profile-symbol-list.ll
 ; RUN: opt < %S/Inputs/profile-symbol-list.ll -passes=sample-profile -profile-accurate-for-symsinlist -sample-profile-file=%t.profdata -S | FileCheck %S/Inputs/profile-symbol-list.ll
diff --git a/llvm/test/tools/llvm-profdata/profile-symbol-list-compress.test b/llvm/test/tools/llvm-profdata/profile-symbol-list-compress.test
new file mode 100644
index 00000000000..66b0543d7a4
--- /dev/null
+++ b/llvm/test/tools/llvm-profdata/profile-symbol-list-compress.test
@@ -0,0 +1,6 @@
+REQUIRES: zlib
+; RUN: llvm-profdata merge -sample -extbinary -compress-all-sections -prof-sym-list=%S/Inputs/profile-symbol-list-1.text %S/Inputs/sample-profile.proftext -o %t.1.output
+; RUN: llvm-profdata merge -sample -extbinary -compress-all-sections -prof-sym-list=%S/Inputs/profile-symbol-list-2.text %S/Inputs/sample-profile.proftext -o %t.2.output
+; RUN: llvm-profdata merge -sample -extbinary -compress-all-sections %t.1.output %t.2.output -o %t.3.output
+; RUN: llvm-profdata show -sample -show-prof-sym-list %t.3.output > %t.4.output
+; RUN: diff %S/Inputs/profile-symbol-list.expected %t.4.output
diff --git a/llvm/test/tools/llvm-profdata/roundtrip-compress.test b/llvm/test/tools/llvm-profdata/roundtrip-compress.test
new file mode 100644
index 00000000000..7e495b6d951
--- /dev/null
+++ b/llvm/test/tools/llvm-profdata/roundtrip-compress.test
@@ -0,0 +1,10 @@
+REQUIRES: zlib
+# Round trip from text --> compressed extbinary --> text
+RUN: llvm-profdata merge --sample --extbinary -compress-all-sections -output=%t.1.profdata %S/Inputs/sample-profile.proftext
+RUN: llvm-profdata merge --sample --text -output=%t.1.proftext %t.1.profdata
+RUN: diff %t.1.proftext %S/Inputs/sample-profile.proftext
+# Round trip from text --> binary --> compressed extbinary --> text
+RUN: llvm-profdata merge --sample --binary -output=%t.2.profdata %S/Inputs/sample-profile.proftext
+RUN: llvm-profdata merge --sample --extbinary -compress-all-sections -output=%t.3.profdata %t.2.profdata
+RUN: llvm-profdata merge --sample --text -output=%t.2.proftext %t.3.profdata
+RUN: diff %t.2.proftext %S/Inputs/sample-profile.proftext