diff --git a/llvm/lib/Transforms/IPO/SampleProfile.cpp b/llvm/lib/Transforms/IPO/SampleProfile.cpp --- a/llvm/lib/Transforms/IPO/SampleProfile.cpp +++ b/llvm/lib/Transforms/IPO/SampleProfile.cpp @@ -74,6 +74,7 @@ #include "llvm/Transforms/Instrumentation.h" #include "llvm/Transforms/Utils/CallPromotionUtils.h" #include "llvm/Transforms/Utils/Cloning.h" +#include "llvm/Transforms/Utils/MisExpect.h" #include "llvm/Transforms/Utils/SampleProfileLoaderBaseImpl.h" #include "llvm/Transforms/Utils/SampleProfileLoaderBaseUtil.h" #include @@ -1704,10 +1705,7 @@ } } - // FIXME: Re-enable for sample profiling after investigating why the sum - // of branch weights can be 0 - // - // misexpect::checkExpectAnnotations(*TI, Weights, /*IsFrontend=*/false); + misexpect::checkExpectAnnotations(*TI, Weights, /*IsFrontend=*/false); uint64_t TempWeight; // Only set weights if there is at least one non-zero weight. diff --git a/llvm/lib/Transforms/Utils/MisExpect.cpp b/llvm/lib/Transforms/Utils/MisExpect.cpp --- a/llvm/lib/Transforms/Utils/MisExpect.cpp +++ b/llvm/lib/Transforms/Utils/MisExpect.cpp @@ -163,6 +163,8 @@ // We cannot calculate branch probability if either of these invariants aren't // met. However, MisExpect diagnostics should not prevent code from compiling, // so we simply forgo emitting diagnostics here, and return early. + // assert((TotalBranchWeight >= LikelyBranchWeight) && (TotalBranchWeight > 0) + // && "TotalBranchWeight is less than the Likely branch weight"); if ((TotalBranchWeight == 0) || (TotalBranchWeight <= LikelyBranchWeight)) return; diff --git a/llvm/test/Transforms/SampleProfile/Inputs/misexpect.prof b/llvm/test/Transforms/SampleProfile/Inputs/misexpect.prof new file mode 100644 --- /dev/null +++ b/llvm/test/Transforms/SampleProfile/Inputs/misexpect.prof @@ -0,0 +1,10 @@ +main:15680:2500 + 1: 2500 + 4: 1000 + 5: 1000 + 6: 800 + 7: 500 + 9: 10226 + 10: 2243 + 16: 0 + 18: 0 diff --git a/llvm/test/Transforms/SampleProfile/misexpect-zero.ll b/llvm/test/Transforms/SampleProfile/misexpect-zero.ll new file mode 100644 --- /dev/null +++ b/llvm/test/Transforms/SampleProfile/misexpect-zero.ll @@ -0,0 +1,85 @@ +; Ensure MisExpect does not crash when given branches with zero weights + +; RUN: opt < %s -passes="sample-profile" -sample-profile-file=%S/Inputs/misexpect.prof -pgo-warn-misexpect -S 2>&1 | FileCheck %s + +define i32 @main() #0 !dbg !36 { + ; CHECK-LABEL: @main( +; CHECK-NEXT: for.cond: +; CHECK-NEXT: %0 = load i32, i32* null, align 4, !dbg !44 +; CHECK-NEXT: br i1 false, label %for.body, label %for.end, !prof !49 +; CHECK: for.body: +; CHECK-NEXT: ret i32 0 +; CHECK: for.end: +; CHECK-NEXT: ret i32 0 +; NOT: warning: +for.cond: + %0 = load i32, i32* null, align 4, !dbg !43 + br i1 false, label %for.body, label %for.end, !prof !48 + +for.body: ; preds = %for.cond + ret i32 0 + +for.end: ; preds = %for.cond + ret i32 0 +} + +; Function Attrs: nocallback nofree nosync nounwind readnone speculatable willreturn +declare void @llvm.dbg.declare(metadata, metadata, metadata) #1 + +attributes #0 = { "use-sample-profile" } +attributes #1 = { nocallback nofree nosync nounwind readnone speculatable willreturn } + +!llvm.dbg.cu = !{!0} +!llvm.module.flags = !{!5, !6, !7} + +!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "clang version 3.8.0 (trunk 248211) (llvm/trunk 248217)", isOptimized: false, runtimeVersion: 0, emissionKind: NoDebug, enums: !2, retainedTypes: !3) +!1 = !DIFile(filename: "test.cc", directory: "/ssd/llvm_commit") +!2 = !{} +!3 = !{!4} +!4 = !DIBasicType(name: "double", size: 64, align: 64, encoding: DW_ATE_float) +!5 = !{i32 2, !"Dwarf Version", i32 4} +!6 = !{i32 2, !"Debug Info Version", i32 3} +!7 = !{i32 1, !"ProfileSummary", !8} +!8 = !{!9, !10, !11, !12, !13, !14, !15, !16, !17, !18} +!9 = !{!"ProfileFormat", !"SampleProfile"} +!10 = !{!"TotalCount", i64 0} +!11 = !{!"MaxCount", i64 0} +!12 = !{!"MaxInternalCount", i64 0} +!13 = !{!"MaxFunctionCount", i64 0} +!14 = !{!"NumCounts", i64 9} +!15 = !{!"NumFunctions", i64 1} +!16 = !{!"IsPartialProfile", i64 0} +!17 = !{!"PartialProfileRatio", double 0.000000e+00} +!18 = !{!"DetailedSummary", !19} +!19 = !{!20, !21, !22, !23, !24, !25, !26, !27, !28, !29, !30, !31, !32, !33, !34, !35} +!20 = !{i32 10000, i64 0, i32 0} +!21 = !{i32 100000, i64 0, i32 0} +!22 = !{i32 200000, i64 0, i32 0} +!23 = !{i32 300000, i64 0, i32 0} +!24 = !{i32 400000, i64 0, i32 0} +!25 = !{i32 500000, i64 0, i32 0} +!26 = !{i32 600000, i64 0, i32 0} +!27 = !{i32 700000, i64 0, i32 0} +!28 = !{i32 800000, i64 0, i32 0} +!29 = !{i32 900000, i64 0, i32 0} +!30 = !{i32 950000, i64 0, i32 0} +!31 = !{i32 990000, i64 0, i32 0} +!32 = !{i32 999000, i64 0, i32 0} +!33 = !{i32 999900, i64 0, i32 0} +!34 = !{i32 999990, i64 0, i32 0} +!35 = !{i32 999999, i64 0, i32 0} +!36 = distinct !DISubprogram(name: "main", scope: !1, file: !1, line: 4, type: !37, scopeLine: 4, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition, unit: !0, retainedNodes: !2) +!37 = !DISubroutineType(types: !38) +!38 = !{!39, !39, !40} +!39 = !DIBasicType(name: "int", size: 32, align: 32, encoding: DW_ATE_signed) +!40 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !41, size: 64, align: 64) +!41 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !42, size: 64, align: 64) +!42 = !DIBasicType(name: "char", size: 8, align: 8, encoding: DW_ATE_signed_char) +!43 = !DILocation(line: 11, column: 22, scope: !44) +!44 = distinct !DILexicalBlock(scope: !45, file: !1, line: 11, column: 6) +!45 = distinct !DILexicalBlock(scope: !46, file: !1, line: 11, column: 6) +!46 = distinct !DILexicalBlock(scope: !47, file: !1, line: 9, column: 21) +!47 = distinct !DILexicalBlock(scope: !36, file: !1, line: 9, column: 8) +; These branch weights shouldn't be removed by these passes +; CHECK: !{{[0-9]+}} = !{!"branch_weights", i32 0, i32 0} +!48 = !{!"branch_weights", i32 0, i32 0} diff --git a/llvm/test/Transforms/SampleProfile/misexpect.ll b/llvm/test/Transforms/SampleProfile/misexpect.ll new file mode 100644 --- /dev/null +++ b/llvm/test/Transforms/SampleProfile/misexpect.ll @@ -0,0 +1,250 @@ +; Test that misexpect diagnostics are issued in sample profiling +; RUN: opt < %s -passes="function(lower-expect),sample-profile" -sample-profile-file=%S/Inputs/misexpect.prof -pgo-warn-misexpect -S 2>&1 | FileCheck %s --check-prefix=WARNING + +; Test that if expect intrinsics are not lowered, then no diagnostics are issued +; RUN: opt < %s -passes="sample-profile" -sample-profile-file=%S/Inputs/misexpect.prof -pgo-warn-misexpect -S 2>&1 | FileCheck %s --check-prefix=NONE + +; Original C++ code for this test case: +; +; #include +; #include + +; int main(int argc, char *argv[]) { +; if (argc < 2) +; return 1; +; double result; +; int limit = atoi(argv[1]); +; if (limit > 100) { +; double s = 23.041968 * atoi(argv[2]); +; for (int u = 0; u < limit; u++) { +; double x = s; +; s = x + 3.049 + (double)u; +; s -= s + 3.94 / x * 0.32; +; } +; result = s; +; } else { +; result = atoi(argv[2]); +; } +; printf("result is %lf\n", result); +; return 0; +; } + +; WARNING-DAG: warning: test.cc:9:14: 20.06% +; WARNING-DAG: warning: test.cc:11:24: 92.74% + +; NONE-NOT: warning: test.cc:9:14: 20.06% +; NONE-NOT: warning: test.cc:11:24: 92.74% + +@.str = private unnamed_addr constant [15 x i8] c"result is %lf\0A\00", align 1 + +; Function Attrs: uwtable +define i32 @main(i32 %argc, i8** %argv) #0 !dbg !6 { + +entry: + %retval = alloca i32, align 4 + %argc.addr = alloca i32, align 4 + %argv.addr = alloca i8**, align 8 + %result = alloca double, align 8 + %limit = alloca i32, align 4 + %s = alloca double, align 8 + %u = alloca i32, align 4 + %x = alloca double, align 8 + store i32 0, i32* %retval, align 4 + store i32 %argc, i32* %argc.addr, align 4 + call void @llvm.dbg.declare(metadata i32* %argc.addr, metadata !16, metadata !17), !dbg !18 + store i8** %argv, i8*** %argv.addr, align 8 + call void @llvm.dbg.declare(metadata i8*** %argv.addr, metadata !19, metadata !17), !dbg !20 + %0 = load i32, i32* %argc.addr, align 4, !dbg !21 + %cmp = icmp slt i32 %0, 2, !dbg !23 + br i1 %cmp, label %if.then, label %if.end, !dbg !24 + +if.then: ; preds = %entry + store i32 1, i32* %retval, align 4, !dbg !25 + br label %return, !dbg !25 + +if.end: ; preds = %entry + call void @llvm.dbg.declare(metadata double* %result, metadata !26, metadata !17), !dbg !27 + call void @llvm.dbg.declare(metadata i32* %limit, metadata !28, metadata !17), !dbg !29 + %1 = load i8**, i8*** %argv.addr, align 8, !dbg !30 + %arrayidx = getelementptr inbounds i8*, i8** %1, i64 1, !dbg !30 + %2 = load i8*, i8** %arrayidx, align 8, !dbg !30 + %call = call i32 @atoi(i8* %2) #4, !dbg !31 + store i32 %call, i32* %limit, align 4, !dbg !29 + %3 = load i32, i32* %limit, align 4, !dbg !32 + %exp = call i32 @llvm.expect.i32(i32 %3, i32 0) + %tobool = icmp ne i32 %exp, 0, !dbg !34 + br i1 %tobool, label %if.then.2, label %if.else, !dbg !35 + +if.then.2: ; preds = %if.end + call void @llvm.dbg.declare(metadata double* %s, metadata !36, metadata !17), !dbg !38 + %4 = load i8**, i8*** %argv.addr, align 8, !dbg !39 + %arrayidx3 = getelementptr inbounds i8*, i8** %4, i64 2, !dbg !39 + %5 = load i8*, i8** %arrayidx3, align 8, !dbg !39 + %call4 = call i32 @atoi(i8* %5) #4, !dbg !40 + %conv = sitofp i32 %call4 to double, !dbg !40 + %mul = fmul double 0x40370ABE6A337A81, %conv, !dbg !41 + store double %mul, double* %s, align 8, !dbg !38 + call void @llvm.dbg.declare(metadata i32* %u, metadata !42, metadata !17), !dbg !44 + store i32 0, i32* %u, align 4, !dbg !44 + br label %for.cond, !dbg !45 + +for.cond: ; preds = %for.inc, %if.then.2 + %6 = load i32, i32* %u, align 4, !dbg !46 + %7 = load i32, i32* %limit, align 4, !dbg !48 + %expval = call i32 @llvm.expect.i32(i32 %6, i32 1) + %cmp5 = icmp ne i32 %expval, 0, !dbg !49 + br i1 %cmp5, label %for.body, label %for.end, !dbg !50 + +for.body: ; preds = %for.cond + call void @llvm.dbg.declare(metadata double* %x, metadata !51, metadata !17), !dbg !53 + %8 = load double, double* %s, align 8, !dbg !54 + store double %8, double* %x, align 8, !dbg !53 + %9 = load double, double* %x, align 8, !dbg !55 + %add = fadd double %9, 3.049000e+00, !dbg !56 + %10 = load i32, i32* %u, align 4, !dbg !57 + %conv6 = sitofp i32 %10 to double, !dbg !57 + %add7 = fadd double %add, %conv6, !dbg !58 + store double %add7, double* %s, align 8, !dbg !59 + %11 = load double, double* %s, align 8, !dbg !60 + %12 = load double, double* %x, align 8, !dbg !61 + %div = fdiv double 3.940000e+00, %12, !dbg !62 + %mul8 = fmul double %div, 3.200000e-01, !dbg !63 + %add9 = fadd double %11, %mul8, !dbg !64 + %13 = load double, double* %s, align 8, !dbg !65 + %sub = fsub double %13, %add9, !dbg !65 + store double %sub, double* %s, align 8, !dbg !65 + br label %for.inc, !dbg !66 + +for.inc: ; preds = %for.body + %14 = load i32, i32* %u, align 4, !dbg !67 + %inc = add nsw i32 %14, 1, !dbg !67 + store i32 %inc, i32* %u, align 4, !dbg !67 + br label %for.cond, !dbg !68 + +for.end: ; preds = %for.cond + %15 = load double, double* %s, align 8, !dbg !69 + store double %15, double* %result, align 8, !dbg !70 + br label %if.end.13, !dbg !71 + +if.else: ; preds = %if.end + %16 = load i8**, i8*** %argv.addr, align 8, !dbg !72 + %arrayidx10 = getelementptr inbounds i8*, i8** %16, i64 2, !dbg !72 + %17 = load i8*, i8** %arrayidx10, align 8, !dbg !72 + %call11 = call i32 @atoi(i8* %17) #4, !dbg !74 + %conv12 = sitofp i32 %call11 to double, !dbg !74 + store double %conv12, double* %result, align 8, !dbg !75 + br label %if.end.13 + +if.end.13: ; preds = %if.else, %for.end + %18 = load double, double* %result, align 8, !dbg !76 + %call14 = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([15 x i8], [15 x i8]* @.str, i32 0, i32 0), double %18), !dbg !77 + store i32 0, i32* %retval, align 4, !dbg !78 + br label %return, !dbg !78 + +return: ; preds = %if.end.13, %if.then + %19 = load i32, i32* %retval, align 4, !dbg !79 + ret i32 %19, !dbg !79 +} + +; Function Attrs: nounwind readnone +declare void @llvm.dbg.declare(metadata, metadata, metadata) #1 + +; Function Attrs: nounwind readonly +declare i32 @atoi(i8*) #2 + +declare i32 @printf(i8*, ...) #3 + +; Function Attrs: nounwind readnone willreturn +declare i32 @llvm.expect.i32(i32, i32) #5 + + +attributes #0 = { uwtable "disable-tail-calls"="false" "less-precise-fpmad"="false" "frame-pointer"="all" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" "use-sample-profile" } +attributes #1 = { nounwind readnone } +attributes #2 = { nounwind readonly "disable-tail-calls"="false" "less-precise-fpmad"="false" "frame-pointer"="all" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" } +attributes #3 = { "disable-tail-calls"="false" "less-precise-fpmad"="false" "frame-pointer"="all" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" } +attributes #4 = { nounwind readonly } +attributes #5 = { nounwind readnone willreturn } + +!llvm.dbg.cu = !{!0} +!llvm.module.flags = !{!13, !14} +!llvm.ident = !{!15} + +!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "clang version 3.8.0 (trunk 248211) (llvm/trunk 248217)", isOptimized: false, runtimeVersion: 0, emissionKind: NoDebug, enums: !2, retainedTypes: !3) +!1 = !DIFile(filename: "test.cc", directory: "/ssd/llvm_commit") +!2 = !{} +!3 = !{!4} +!4 = !DIBasicType(name: "double", size: 64, align: 64, encoding: DW_ATE_float) +!6 = distinct !DISubprogram(name: "main", scope: !1, file: !1, line: 4, type: !7, isLocal: false, isDefinition: true, scopeLine: 4, flags: DIFlagPrototyped, isOptimized: false, unit: !0, retainedNodes: !2) +!7 = !DISubroutineType(types: !8) +!8 = !{!9, !9, !10} +!9 = !DIBasicType(name: "int", size: 32, align: 32, encoding: DW_ATE_signed) +!10 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !11, size: 64, align: 64) +!11 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !12, size: 64, align: 64) +!12 = !DIBasicType(name: "char", size: 8, align: 8, encoding: DW_ATE_signed_char) +!13 = !{i32 2, !"Dwarf Version", i32 4} +!14 = !{i32 2, !"Debug Info Version", i32 3} +!15 = !{!"clang version 3.8.0 (trunk 248211) (llvm/trunk 248217)"} +!16 = !DILocalVariable(name: "argc", arg: 1, scope: !6, file: !1, line: 4, type: !9) +!17 = !DIExpression() +!18 = !DILocation(line: 4, column: 15, scope: !6) +!19 = !DILocalVariable(name: "argv", arg: 2, scope: !6, file: !1, line: 4, type: !10) +!20 = !DILocation(line: 4, column: 27, scope: !6) +!21 = !DILocation(line: 5, column: 8, scope: !22) +!22 = distinct !DILexicalBlock(scope: !6, file: !1, line: 5, column: 8) +!23 = !DILocation(line: 5, column: 13, scope: !22) +!24 = !DILocation(line: 5, column: 8, scope: !6) +!25 = !DILocation(line: 6, column: 6, scope: !22) +!26 = !DILocalVariable(name: "result", scope: !6, file: !1, line: 7, type: !4) +!27 = !DILocation(line: 7, column: 11, scope: !6) +!28 = !DILocalVariable(name: "limit", scope: !6, file: !1, line: 8, type: !9) +!29 = !DILocation(line: 8, column: 8, scope: !6) +!30 = !DILocation(line: 8, column: 21, scope: !6) +!31 = !DILocation(line: 8, column: 16, scope: !6) +!32 = !DILocation(line: 9, column: 8, scope: !33) +!33 = distinct !DILexicalBlock(scope: !6, file: !1, line: 9, column: 8) +!34 = !DILocation(line: 9, column: 14, scope: !33) +!35 = !DILocation(line: 9, column: 8, scope: !6) +!36 = !DILocalVariable(name: "s", scope: !37, file: !1, line: 10, type: !4) +!37 = distinct !DILexicalBlock(scope: !33, file: !1, line: 9, column: 21) +!38 = !DILocation(line: 10, column: 13, scope: !37) +!39 = !DILocation(line: 10, column: 34, scope: !37) +!40 = !DILocation(line: 10, column: 29, scope: !37) +!41 = !DILocation(line: 10, column: 27, scope: !37) +!42 = !DILocalVariable(name: "u", scope: !43, file: !1, line: 11, type: !9) +!43 = distinct !DILexicalBlock(scope: !37, file: !1, line: 11, column: 6) +!44 = !DILocation(line: 11, column: 15, scope: !43) +!45 = !DILocation(line: 11, column: 11, scope: !43) +!46 = !DILocation(line: 11, column: 22, scope: !47) +!47 = distinct !DILexicalBlock(scope: !43, file: !1, line: 11, column: 6) +!48 = !DILocation(line: 11, column: 26, scope: !47) +!49 = !DILocation(line: 11, column: 24, scope: !47) +!50 = !DILocation(line: 11, column: 6, scope: !43) +!51 = !DILocalVariable(name: "x", scope: !52, file: !1, line: 12, type: !4) +!52 = distinct !DILexicalBlock(scope: !47, file: !1, line: 11, column: 38) +!53 = !DILocation(line: 12, column: 15, scope: !52) +!54 = !DILocation(line: 12, column: 19, scope: !52) +!55 = !DILocation(line: 13, column: 12, scope: !52) +!56 = !DILocation(line: 13, column: 14, scope: !52) +!57 = !DILocation(line: 13, column: 32, scope: !52) +!58 = !DILocation(line: 13, column: 22, scope: !52) +!59 = !DILocation(line: 13, column: 10, scope: !52) +!60 = !DILocation(line: 14, column: 13, scope: !52) +!61 = !DILocation(line: 14, column: 24, scope: !52) +!62 = !DILocation(line: 14, column: 22, scope: !52) +!63 = !DILocation(line: 14, column: 26, scope: !52) +!64 = !DILocation(line: 14, column: 15, scope: !52) +!65 = !DILocation(line: 14, column: 10, scope: !52) +!66 = !DILocation(line: 15, column: 6, scope: !52) +!67 = !DILocation(line: 11, column: 34, scope: !47) +!68 = !DILocation(line: 11, column: 6, scope: !47) +!69 = !DILocation(line: 16, column: 15, scope: !37) +!70 = !DILocation(line: 16, column: 13, scope: !37) +!71 = !DILocation(line: 17, column: 4, scope: !37) +!72 = !DILocation(line: 18, column: 20, scope: !73) +!73 = distinct !DILexicalBlock(scope: !33, file: !1, line: 17, column: 11) +!74 = !DILocation(line: 18, column: 15, scope: !73) +!75 = !DILocation(line: 18, column: 13, scope: !73) +!76 = !DILocation(line: 20, column: 30, scope: !6) +!77 = !DILocation(line: 20, column: 4, scope: !6) +!78 = !DILocation(line: 21, column: 4, scope: !6) +!79 = !DILocation(line: 22, column: 2, scope: !6)