Encode duplication factor from loop vectorization and loop unrolling to discriminator.
Summary:
This patch starts the implementation as discuss in the following RFC: http://lists.llvm.org/pipermail/llvm-dev/2016-October/106532.html
When optimization duplicates code that will scale down the execution count of a basic block, we will record the duplication factor as part of discriminator so that the offline process tool can find the duplication factor and collect the accurate execution frequency of the corresponding source code. Two important optimization that fall into this category is loop vectorization and loop unroll. This patch records the duplication factor for these 2 optimizations.
The recording will be guarded by a flag encode-duplication-in-discriminators, which is off by default.
Reviewers: probinson, aprantl, davidxl, hfinkel, echristo
Reviewed By: hfinkel
Subscribers: mehdi_amini, anemet, mzolotukhin, llvm-commits
Differential Revision: https://reviews.llvm.org/D26420
llvm-svn: 294782
diff --git a/llvm/test/Transforms/AddDiscriminators/basic.ll b/llvm/test/Transforms/AddDiscriminators/basic.ll
index 801eda2..a781c0d 100644
--- a/llvm/test/Transforms/AddDiscriminators/basic.ll
+++ b/llvm/test/Transforms/AddDiscriminators/basic.ll
@@ -58,5 +58,5 @@
; CHECK: ![[FOO:[0-9]+]] = distinct !DISubprogram(name: "foo"
; CHECK: ![[BLOCK:[0-9]+]] = distinct !DILexicalBlock(scope: ![[FOO]],{{.*}} line: 3)
; CHECK: ![[THEN]] = !DILocation(line: 3, scope: ![[BLOCKFILE:[0-9]+]])
-; CHECK: ![[BLOCKFILE]] = !DILexicalBlockFile(scope: ![[BLOCK]],{{.*}} discriminator: 1)
+; CHECK: ![[BLOCKFILE]] = !DILexicalBlockFile(scope: ![[BLOCK]],{{.*}} discriminator: 2)
; CHECK: ![[END]] = !DILocation(line: 4, scope: ![[FOO]])
diff --git a/llvm/test/Transforms/AddDiscriminators/call-nested.ll b/llvm/test/Transforms/AddDiscriminators/call-nested.ll
index 481d6f2..4d5145a 100644
--- a/llvm/test/Transforms/AddDiscriminators/call-nested.ll
+++ b/llvm/test/Transforms/AddDiscriminators/call-nested.ll
@@ -47,4 +47,4 @@
!14 = !DILocation(line: 4, column: 3, scope: !4)
; CHECK: ![[CALL2]] = !DILocation(line: 4, column: 10, scope: ![[CALL2BLOCK:[0-9]+]])
-; CHECK: ![[CALL2BLOCK]] = !DILexicalBlockFile({{.*}} discriminator: 1)
+; CHECK: ![[CALL2BLOCK]] = !DILexicalBlockFile({{.*}} discriminator: 2)
diff --git a/llvm/test/Transforms/AddDiscriminators/call.ll b/llvm/test/Transforms/AddDiscriminators/call.ll
index 847a6ad..5365d68 100644
--- a/llvm/test/Transforms/AddDiscriminators/call.ll
+++ b/llvm/test/Transforms/AddDiscriminators/call.ll
@@ -5,7 +5,7 @@
; #1 void bar();
; #2
; #3 void foo() {
-; #4 bar();bar()/*discriminator 1*/;bar()/*discriminator 2*/;
+; #4 bar();bar()/*discriminator 2*/;bar()/*discriminator 4*/;
; #5 }
; Function Attrs: uwtable
@@ -49,6 +49,6 @@
!13 = !DILocation(line: 5, column: 1, scope: !4)
; CHECK: ![[CALL1]] = !DILocation(line: 4, column: 9, scope: ![[CALL1BLOCK:[0-9]+]])
-; CHECK: ![[CALL1BLOCK]] = !DILexicalBlockFile({{.*}} discriminator: 1)
+; CHECK: ![[CALL1BLOCK]] = !DILexicalBlockFile({{.*}} discriminator: 2)
; CHECK: ![[CALL2]] = !DILocation(line: 4, column: 15, scope: ![[CALL2BLOCK:[0-9]+]])
-; CHECK: ![[CALL2BLOCK]] = !DILexicalBlockFile({{.*}} discriminator: 2)
+; CHECK: ![[CALL2BLOCK]] = !DILexicalBlockFile({{.*}} discriminator: 4)
diff --git a/llvm/test/Transforms/AddDiscriminators/diamond.ll b/llvm/test/Transforms/AddDiscriminators/diamond.ll
index b3afe72..307e95f 100644
--- a/llvm/test/Transforms/AddDiscriminators/diamond.ll
+++ b/llvm/test/Transforms/AddDiscriminators/diamond.ll
@@ -10,7 +10,7 @@
; #6 }
; bar(5): discriminator 0
-; bar(3): discriminator 1
+; bar(3): discriminator 2
; Function Attrs: uwtable
define void @_Z3fooi(i32 %i) #0 !dbg !4 {
@@ -69,4 +69,4 @@
!20 = !DILocation(line: 6, column: 1, scope: !4)
; CHECK: ![[ELSE]] = !DILocation(line: 5, column: 18, scope: ![[ELSEBLOCK:[0-9]+]])
-; CHECK: ![[ELSEBLOCK]] = !DILexicalBlockFile({{.*}} discriminator: 1)
+; CHECK: ![[ELSEBLOCK]] = !DILexicalBlockFile({{.*}} discriminator: 2)
diff --git a/llvm/test/Transforms/AddDiscriminators/first-only.ll b/llvm/test/Transforms/AddDiscriminators/first-only.ll
index 1bd8dae..dd2117a 100644
--- a/llvm/test/Transforms/AddDiscriminators/first-only.ll
+++ b/llvm/test/Transforms/AddDiscriminators/first-only.ll
@@ -69,7 +69,7 @@
!12 = !DILocation(line: 3, scope: !13)
!13 = distinct !DILexicalBlock(line: 3, column: 0, file: !1, scope: !11)
-; CHECK: !DILexicalBlockFile(scope: ![[BLOCK2:[0-9]+]],{{.*}} discriminator: 1)
+; CHECK: !DILexicalBlockFile(scope: ![[BLOCK2:[0-9]+]],{{.*}} discriminator: 2)
!14 = !DILocation(line: 4, scope: !13)
; CHECK: ![[BLOCK2]] = distinct !DILexicalBlock(scope: ![[BLOCK1]],{{.*}} line: 3)
diff --git a/llvm/test/Transforms/AddDiscriminators/inlined.ll b/llvm/test/Transforms/AddDiscriminators/inlined.ll
index 2e8ea97..226e903 100644
--- a/llvm/test/Transforms/AddDiscriminators/inlined.ll
+++ b/llvm/test/Transforms/AddDiscriminators/inlined.ll
@@ -62,8 +62,8 @@
!12 = distinct !DISubprogram(name: "g", scope: !1, file: !1, line: 1, type: !8, isLocal: false, isDefinition: true, scopeLine: 1, isOptimized: true, unit: !0, variables: !2)
!13 = distinct !DILocation(line: 1, column: 17, scope: !14)
; CHECK: ![[BF:.*]] = !DILexicalBlockFile(scope: ![[LB1:[0-9]+]],
-; CHECK-SAME: discriminator: 1)
-!14 = !DILexicalBlockFile(scope: !15, file: !1, discriminator: 1)
+; CHECK-SAME: discriminator: 2)
+!14 = !DILexicalBlockFile(scope: !15, file: !1, discriminator: 2)
; CHECK: ![[LB1]] = distinct !DILexicalBlock(scope: ![[LB2:[0-9]+]],
; CHECK-SAME: line: 1, column: 16)
!15 = distinct !DILexicalBlock(scope: !16, file: !1, line: 1, column: 16)
diff --git a/llvm/test/Transforms/AddDiscriminators/multiple.ll b/llvm/test/Transforms/AddDiscriminators/multiple.ll
index 387689c..b4c353c 100644
--- a/llvm/test/Transforms/AddDiscriminators/multiple.ll
+++ b/llvm/test/Transforms/AddDiscriminators/multiple.ll
@@ -67,6 +67,6 @@
!12 = !DILocation(line: 4, scope: !4)
; CHECK: ![[THEN]] = !DILocation(line: 3, scope: ![[THENBLOCK:[0-9]+]])
-; CHECK: ![[THENBLOCK]] = !DILexicalBlockFile(scope: ![[SCOPE:[0-9]+]],{{.*}} discriminator: 1)
+; CHECK: ![[THENBLOCK]] = !DILexicalBlockFile(scope: ![[SCOPE:[0-9]+]],{{.*}} discriminator: 2)
; CHECK: ![[ELSE]] = !DILocation(line: 3, scope: ![[ELSEBLOCK:[0-9]+]])
-; CHECK: ![[ELSEBLOCK]] = !DILexicalBlockFile(scope: ![[SCOPE]],{{.*}} discriminator: 2)
+; CHECK: ![[ELSEBLOCK]] = !DILexicalBlockFile(scope: ![[SCOPE]],{{.*}} discriminator: 4)
diff --git a/llvm/test/Transforms/AddDiscriminators/oneline.ll b/llvm/test/Transforms/AddDiscriminators/oneline.ll
index aa52ae4..724574a 100644
--- a/llvm/test/Transforms/AddDiscriminators/oneline.ll
+++ b/llvm/test/Transforms/AddDiscriminators/oneline.ll
@@ -7,9 +7,9 @@
; #3 }
; i == 3: discriminator 0
-; i == 5: discriminator 1
-; return 100: discriminator 2
-; return 99: discriminator 3
+; i == 5: discriminator 2
+; return 100: discriminator 4
+; return 99: discriminator 6
define i32 @_Z3fooi(i32 %i) #0 !dbg !4 {
%1 = alloca i32, align 4
@@ -91,11 +91,11 @@
; CHECK: ![[F:.*]] = distinct !DISubprogram(name: "foo",
; CHECK: ![[IF:.*]] = distinct !DILexicalBlock(scope: ![[F]],{{.*}}line: 2, column: 7)
; CHECK: ![[THEN1]] = !DILocation(line: 2, column: 17, scope: ![[THENBLOCK:[0-9]+]])
-; CHECK: ![[THENBLOCK]] = !DILexicalBlockFile(scope: ![[IF]],{{.*}} discriminator: 1)
+; CHECK: ![[THENBLOCK]] = !DILexicalBlockFile(scope: ![[IF]],{{.*}} discriminator: 2)
; CHECK: ![[THEN2]] = !DILocation(line: 2, column: 19, scope: ![[THENBLOCK]])
; CHECK: ![[THEN3]] = !DILocation(line: 2, column: 7, scope: ![[BRBLOCK:[0-9]+]])
-; CHECK: ![[BRBLOCK]] = !DILexicalBlockFile(scope: ![[F]],{{.*}} discriminator: 1)
+; CHECK: ![[BRBLOCK]] = !DILexicalBlockFile(scope: ![[F]],{{.*}} discriminator: 2)
; CHECK: ![[ELSE]] = !DILocation(line: 2, column: 25, scope: ![[ELSEBLOCK:[0-9]+]])
-; CHECK: ![[ELSEBLOCK]] = !DILexicalBlockFile(scope: ![[IF]],{{.*}} discriminator: 2)
+; CHECK: ![[ELSEBLOCK]] = !DILexicalBlockFile(scope: ![[IF]],{{.*}} discriminator: 4)
; CHECK: ![[COMBINE]] = !DILocation(line: 2, column: 42, scope: ![[COMBINEBLOCK:[0-9]+]])
-; CHECK: ![[COMBINEBLOCK]] = !DILexicalBlockFile(scope: ![[IF]],{{.*}} discriminator: 3)
+; CHECK: ![[COMBINEBLOCK]] = !DILexicalBlockFile(scope: ![[IF]],{{.*}} discriminator: 6)
diff --git a/llvm/test/Transforms/LoopVectorize/discriminator.ll b/llvm/test/Transforms/LoopVectorize/discriminator.ll
new file mode 100644
index 0000000..b7d3458
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/discriminator.ll
@@ -0,0 +1,70 @@
+; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 < %s | FileCheck --check-prefix=LOOPVEC_4_1 %s
+; RUN: opt -S -loop-vectorize -force-vector-width=2 -force-vector-interleave=3 < %s | FileCheck --check-prefix=LOOPVEC_2_3 %s
+; RUN: opt -S -loop-unroll -unroll-count=5 < %s | FileCheck --check-prefix=LOOPUNROLL_5 %s
+; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-interleave=4 -loop-unroll -unroll-count=2 < %s | FileCheck --check-prefix=LOOPVEC_UNROLL %s
+
+; Test if vectorization/unroll factor is recorded in discriminator.
+;
+; Original source code:
+; 1 int *a;
+; 2 int *b;
+; 3
+; 4 void foo() {
+; 5 for (int i = 0; i < 4096; i++)
+; 6 a[i] += b[i];
+; 7 }
+
+@a = local_unnamed_addr global i32* null, align 8
+@b = local_unnamed_addr global i32* null, align 8
+
+define void @_Z3foov() local_unnamed_addr #0 !dbg !6 {
+ %1 = load i32*, i32** @b, align 8, !dbg !8, !tbaa !9
+ %2 = load i32*, i32** @a, align 8, !dbg !13, !tbaa !9
+ br label %3, !dbg !14
+
+; <label>:3: ; preds = %3, %0
+ %indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %3 ]
+ %4 = getelementptr inbounds i32, i32* %1, i64 %indvars.iv, !dbg !8
+ %5 = load i32, i32* %4, align 4, !dbg !8, !tbaa !15
+ %6 = getelementptr inbounds i32, i32* %2, i64 %indvars.iv, !dbg !13
+ %7 = load i32, i32* %6, align 4, !dbg !17, !tbaa !15
+ %8 = add nsw i32 %7, %5, !dbg !17
+ store i32 %8, i32* %6, align 4, !dbg !17, !tbaa !15
+ %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !18
+ %exitcond = icmp eq i64 %indvars.iv.next, 4096, !dbg !19
+ br i1 %exitcond, label %9, label %3, !dbg !14, !llvm.loop !20
+
+; <label>:9: ; preds = %3
+ ret void, !dbg !21
+}
+
+;LOOPVEC_4_1: discriminator: 17
+;LOOPVEC_2_3: discriminator: 25
+;LOOPUNROLL_5: discriminator: 21
+; When unrolling after loop vectorize, both vec_body and remainder loop
+; are unrolled.
+;LOOPVEC_UNROLL: discriminator: 385
+;LOOPVEC_UNROLL: discriminator: 9
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, debugInfoForProfiling: true)
+!1 = !DIFile(filename: "a.cc", directory: "/")
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!6 = distinct !DISubprogram(name: "foo", scope: !1, file: !1, line: 4, unit: !0)
+!8 = !DILocation(line: 6, column: 13, scope: !6)
+!9 = !{!10, !10, i64 0}
+!10 = !{!"any pointer", !11, i64 0}
+!11 = !{!"omnipotent char", !12, i64 0}
+!12 = !{!"Simple C++ TBAA"}
+!13 = !DILocation(line: 6, column: 5, scope: !6)
+!14 = !DILocation(line: 5, column: 3, scope: !6)
+!15 = !{!16, !16, i64 0}
+!16 = !{!"int", !11, i64 0}
+!17 = !DILocation(line: 6, column: 10, scope: !6)
+!18 = !DILocation(line: 5, column: 30, scope: !6)
+!19 = !DILocation(line: 5, column: 21, scope: !6)
+!20 = distinct !{!20, !14}
+!21 = !DILocation(line: 7, column: 1, scope: !6)