diff options
-rw-r--r-- | llvm/lib/CodeGen/AggressiveAntiDepBreaker.cpp | 6 | ||||
-rw-r--r-- | llvm/lib/CodeGen/AntiDepBreaker.h | 19 | ||||
-rw-r--r-- | llvm/lib/CodeGen/CriticalAntiDepBreaker.cpp | 6 | ||||
-rw-r--r-- | llvm/test/CodeGen/X86/post-ra-sched-with-debug.mir | 322 |
4 files changed, 345 insertions, 8 deletions
diff --git a/llvm/lib/CodeGen/AggressiveAntiDepBreaker.cpp b/llvm/lib/CodeGen/AggressiveAntiDepBreaker.cpp index 955524c2a67..3a57772cc7f 100644 --- a/llvm/lib/CodeGen/AggressiveAntiDepBreaker.cpp +++ b/llvm/lib/CodeGen/AggressiveAntiDepBreaker.cpp @@ -964,10 +964,8 @@ unsigned AggressiveAntiDepBreaker::BreakAntiDependencies( // sure to update that as well. const SUnit *SU = MISUnitMap[Q.second.Operand->getParent()]; if (!SU) continue; - for (DbgValueVector::iterator DVI = DbgValues.begin(), - DVE = DbgValues.end(); DVI != DVE; ++DVI) - if (DVI->second == Q.second.Operand->getParent()) - UpdateDbgValue(*DVI->first, AntiDepReg, NewReg); + UpdateDbgValues(DbgValues, Q.second.Operand->getParent(), + AntiDepReg, NewReg); } // We just went back in time and modified history; the diff --git a/llvm/lib/CodeGen/AntiDepBreaker.h b/llvm/lib/CodeGen/AntiDepBreaker.h index 04f7f419f5e..d14d93100ad 100644 --- a/llvm/lib/CodeGen/AntiDepBreaker.h +++ b/llvm/lib/CodeGen/AntiDepBreaker.h @@ -60,6 +60,25 @@ public: if (MI.getOperand(0).isReg() && MI.getOperand(0).getReg() == OldReg) MI.getOperand(0).setReg(NewReg); } + + /// Update all DBG_VALUE instructions that may be affected by the dependency + /// breaker's update of ParentMI to use NewReg. + void UpdateDbgValues(const DbgValueVector &DbgValues, MachineInstr *ParentMI, + unsigned OldReg, unsigned NewReg) { + // The following code is dependent on the order in which the DbgValues are + // constructed in ScheduleDAGInstrs::buildSchedGraph. + MachineInstr *PrevDbgMI = nullptr; + for (const auto &DV : make_range(DbgValues.crbegin(), DbgValues.crend())) { + MachineInstr *PrevMI = DV.second; + if ((PrevMI == ParentMI) || (PrevMI == PrevDbgMI)) { + MachineInstr *DbgMI = DV.first; + UpdateDbgValue(*DbgMI, OldReg, NewReg); + PrevDbgMI = DbgMI; + } else if (PrevDbgMI) { + break; // If no match and already found a DBG_VALUE, we're done. + } + } + } }; } diff --git a/llvm/lib/CodeGen/CriticalAntiDepBreaker.cpp b/llvm/lib/CodeGen/CriticalAntiDepBreaker.cpp index e1eeddf0816..b2d6652b075 100644 --- a/llvm/lib/CodeGen/CriticalAntiDepBreaker.cpp +++ b/llvm/lib/CodeGen/CriticalAntiDepBreaker.cpp @@ -648,10 +648,8 @@ BreakAntiDependencies(const std::vector<SUnit>& SUnits, // as well. const SUnit *SU = MISUnitMap[Q->second->getParent()]; if (!SU) continue; - for (DbgValueVector::iterator DVI = DbgValues.begin(), - DVE = DbgValues.end(); DVI != DVE; ++DVI) - if (DVI->second == Q->second->getParent()) - UpdateDbgValue(*DVI->first, AntiDepReg, NewReg); + UpdateDbgValues(DbgValues, Q->second->getParent(), + AntiDepReg, NewReg); } // We just went back in time and modified history; the diff --git a/llvm/test/CodeGen/X86/post-ra-sched-with-debug.mir b/llvm/test/CodeGen/X86/post-ra-sched-with-debug.mir new file mode 100644 index 00000000000..ba5c85922c7 --- /dev/null +++ b/llvm/test/CodeGen/X86/post-ra-sched-with-debug.mir @@ -0,0 +1,322 @@ +# RUN: llc -mtriple=x86_64-unknown-unknown -mcpu=btver2 -run-pass=post-RA-sched -o - %s | FileCheck %s + +# Test that multiple DBG_VALUE's following an instruction whose register needs +# to be changed during the post-RA scheduler pass are updated correctly. + +# Test case was derived from the output from the following command and +# the source code below: +# +# clang -S -emit-llvm -target x86_64 -march=btver2 -O2 -g -o - <srcfile> | +# llc -stop-before=post-RA-sched -o - +# +# Source code reduced from the original 8MB source file: +# +# struct a; +# class b { +# public: +# a *c = ap; +# unsigned *d() { return (unsigned *)c; } +# a *ap; +# }; +# enum { e = 2 }; +# template <typename f> f *g(f *h, f *i) { +# long j = long(i), k = -!h; +# return reinterpret_cast<f *>(long(h) | k & j); +# } +# class l { +# public: +# l(int); +# int m; +# }; +# unsigned *n; +# unsigned o; +# class p { +# public: +# int aa(); +# unsigned *q() { +# n = r.d(); +# return g(n, &o); +# } +# b r; +# }; +# class s : l { +# public: +# p t; +# s(int h) : l(h), ab(t), ac(~0 << h) { ae(); } +# p &ab; +# int ac; +# void ae() { +# const unsigned *v; +# const unsigned u = 0; +# v = ab.q(); +# const unsigned *x = g(v, &u); +# int w = x[m] & ac; +# while (w) { +# int z = (ab.aa() - 1) / e; +# if (m <= z) +# return; +# } +# } +# }; +# class ad { +# public: +# ~ad() { +# for (y();;) +# ; +# } +# class y { +# public: +# y() : af(0) {} +# s af; +# }; +# }; +# class ag { +# ad ah; +# }; +# enum ai {}; +# class aj { +# public: +# aj(unsigned(ai)); +# ag ak; +# }; +# struct al { +# static unsigned am(ai); +# }; +# template <int> struct an : al { static aj ao; }; +# template <> aj an<0>::ao(am); + +--- | + + %class.s = type <{ %class.l, [4 x i8], %class.p, %class.p*, i32, [4 x i8] }> + %class.l = type { i32 } + %class.p = type { %class.b } + %class.b = type { %struct.a*, %struct.a* } + %struct.a = type opaque + + @n = local_unnamed_addr global i32* null, align 8 + @o = global i32 0, align 4 + + define linkonce_odr void @_ZN1sC2Ei(%class.s*, i32) unnamed_addr #0 align 2 !dbg !4 { + %3 = alloca i32, align 4 + %4 = bitcast %class.s* %0 to %class.l* + tail call void @_ZN1lC2Ei(%class.l* %4, i32 %1) + %5 = getelementptr inbounds %class.s, %class.s* %0, i64 0, i32 2 + tail call void @llvm.dbg.value(metadata %class.p* %5, i64 0, metadata !10, metadata !17), !dbg !18 + tail call void @llvm.dbg.value(metadata %class.p* %5, i64 0, metadata !20, metadata !17), !dbg !27 + %6 = getelementptr inbounds %class.s, %class.s* %0, i64 0, i32 2, i32 0, i32 1 + %7 = bitcast %struct.a** %6 to i64* + %8 = load i64, i64* %7, align 8 + %9 = bitcast %class.p* %5 to i64* + store i64 %8, i64* %9, align 8 + %10 = getelementptr inbounds %class.s, %class.s* %0, i64 0, i32 3 + store %class.p* %5, %class.p** %10, align 8 + %11 = getelementptr inbounds %class.s, %class.s* %0, i64 0, i32 4 + %12 = shl i32 -1, %1 + store i32 %12, i32* %11, align 8 + store i32 0, i32* %3, align 4 + %13 = bitcast %class.p* %5 to i32** + %14 = load i32*, i32** %13, align 8 + store i32* %14, i32** @n, align 8 + %15 = icmp eq i32* %14, null + %16 = ptrtoint i32* %14 to i64 + %17 = select i1 %15, i64 ptrtoint (i32* @o to i64), i64 0 + %18 = or i64 %17, %16 + tail call void @llvm.dbg.value(metadata i32* %3, i64 0, metadata !29, metadata !35), !dbg !36 + tail call void @llvm.dbg.value(metadata i32* %3, i64 0, metadata !39, metadata !17), !dbg !44 + %19 = ptrtoint i32* %3 to i64 + call void @llvm.dbg.value(metadata i64 %19, i64 0, metadata !46, metadata !17), !dbg !48 + %20 = icmp eq i64 %18, 0 + %21 = select i1 %20, i64 %19, i64 0 + %22 = or i64 %21, %18 + %23 = inttoptr i64 %22 to i32* + %24 = bitcast %class.s* %0 to i32* + %25 = load i32, i32* %24, align 8 + %26 = sext i32 %25 to i64 + %27 = getelementptr inbounds i32, i32* %23, i64 %26 + %28 = load i32, i32* %27, align 4 + %29 = and i32 %12, %28 + %30 = icmp eq i32 %29, 0 + br i1 %30, label %47, label %31 + + ; <label>:31: ; preds = %2 + %32 = bitcast %class.s* %0 to i32* + %33 = call i32 @_ZN1p2aaEv(%class.p* %5) + %34 = add nsw i32 %33, -1 + %35 = sdiv i32 %34, 2 + %36 = load i32, i32* %32, align 8 + %37 = icmp sgt i32 %36, %35 + br i1 %37, label %38, label %47 + + ; <label>:38: ; preds = %31 + br label %39 + + ; <label>:39: ; preds = %39, %38 + %40 = bitcast %class.s* %0 to i32* + %sunkaddr = ptrtoint %class.s* %0 to i64 + %sunkaddr1 = add i64 %sunkaddr, 24 + %sunkaddr2 = inttoptr i64 %sunkaddr1 to %class.p** + %41 = load %class.p*, %class.p** %sunkaddr2, align 8 + %42 = call i32 @_ZN1p2aaEv(%class.p* %41) + %43 = add nsw i32 %42, -1 + %44 = sdiv i32 %43, 2 + %45 = load i32, i32* %40, align 8 + %46 = icmp sgt i32 %45, %44 + br i1 %46, label %39, label %47 + + ; <label>:47: ; preds = %39, %31, %2 + ret void + } + + declare void @_ZN1lC2Ei(%class.l*, i32) unnamed_addr #1 + + declare i32 @_ZN1p2aaEv(%class.p*) local_unnamed_addr #1 + + ; Function Attrs: nounwind readnone + declare void @llvm.dbg.value(metadata, i64, metadata, metadata) #2 + + !llvm.dbg.cu = !{!0} + !llvm.module.flags = !{!2, !3} + + !0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug) + !1 = !DIFile(filename: "test.cpp", directory: "") + !2 = !{i32 2, !"Dwarf Version", i32 4} + !3 = !{i32 2, !"Debug Info Version", i32 3} + !4 = distinct !DISubprogram(name: "s", linkageName: "_ZN1sC2Ei", scope: !5, file: !1, line: 32, type: !6, isLocal: false, isDefinition: true, scopeLine: 32, flags: DIFlagPrototyped, isOptimized: true, unit: !0) + !5 = distinct !DICompositeType(tag: DW_TAG_class_type, name: "s", file: !1, line: 29, size: 320, identifier: "_ZTS1s") + !6 = !DISubroutineType(types: !7) + !7 = !{null, !8, !9} + !8 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !5, size: 64, flags: DIFlagArtificial | DIFlagObjectPointer) + !9 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed) + !10 = !DILocalVariable(name: "this", arg: 1, scope: !11, type: !16, flags: DIFlagArtificial | DIFlagObjectPointer) + !11 = distinct !DISubprogram(name: "p", linkageName: "_ZN1pC2Ev", scope: !12, file: !1, line: 20, type: !13, isLocal: false, isDefinition: true, scopeLine: 20, flags: DIFlagArtificial | DIFlagPrototyped, isOptimized: true, unit: !0) + !12 = distinct !DICompositeType(tag: DW_TAG_class_type, name: "p", file: !1, line: 20, size: 128, identifier: "_ZTS1p") + !13 = !DISubroutineType(types: !14) + !14 = !{null, !15} + !15 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !12, size: 64, flags: DIFlagArtificial | DIFlagObjectPointer) + !16 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !12, size: 64) + !17 = !DIExpression() + !18 = !DILocation(line: 0, scope: !11, inlinedAt: !19) + !19 = distinct !DILocation(line: 32, column: 3, scope: !4) + !20 = !DILocalVariable(name: "this", arg: 1, scope: !21, type: !26, flags: DIFlagArtificial | DIFlagObjectPointer) + !21 = distinct !DISubprogram(name: "b", linkageName: "_ZN1bC2Ev", scope: !22, file: !1, line: 2, type: !23, isLocal: false, isDefinition: true, scopeLine: 2, flags: DIFlagArtificial | DIFlagPrototyped, isOptimized: true, unit: !0) + !22 = distinct !DICompositeType(tag: DW_TAG_class_type, name: "b", file: !1, line: 2, size: 128, identifier: "_ZTS1b") + !23 = !DISubroutineType(types: !24) + !24 = !{null, !25} + !25 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !22, size: 64, flags: DIFlagArtificial | DIFlagObjectPointer) + !26 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !22, size: 64) + !27 = !DILocation(line: 0, scope: !21, inlinedAt: !28) + !28 = distinct !DILocation(line: 20, column: 7, scope: !11, inlinedAt: !19) + !29 = !DILocalVariable(name: "u", scope: !30, file: !1, line: 37, type: !33) + !30 = distinct !DISubprogram(name: "ae", linkageName: "_ZN1s2aeEv", scope: !5, file: !1, line: 35, type: !31, isLocal: false, isDefinition: true, scopeLine: 35, flags: DIFlagPrototyped, isOptimized: true, unit: !0) + !31 = !DISubroutineType(types: !32) + !32 = !{null, !8} + !33 = !DIDerivedType(tag: DW_TAG_const_type, baseType: !34) + !34 = !DIBasicType(name: "unsigned int", size: 32, encoding: DW_ATE_unsigned) + !35 = !DIExpression(DW_OP_deref) + !36 = !DILocation(line: 37, column: 20, scope: !30, inlinedAt: !37) + !37 = distinct !DILocation(line: 32, column: 41, scope: !38) + !38 = distinct !DILexicalBlock(scope: !4, file: !1, line: 32, column: 39) + !39 = !DILocalVariable(name: "i", arg: 2, scope: !40, file: !1, line: 9, type: !43) + !40 = distinct !DISubprogram(name: "g<const unsigned int>", linkageName: "_Z1gIKjEPT_S2_S2_", scope: !1, file: !1, line: 9, type: !41, isLocal: false, isDefinition: true, scopeLine: 9, flags: DIFlagPrototyped, isOptimized: true, unit: !0) + !41 = !DISubroutineType(types: !42) + !42 = !{!43, !43, !43} + !43 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !33, size: 64) + !44 = !DILocation(line: 9, column: 37, scope: !40, inlinedAt: !45) + !45 = distinct !DILocation(line: 39, column: 25, scope: !30, inlinedAt: !37) + !46 = !DILocalVariable(name: "j", scope: !40, file: !1, line: 10, type: !47) + !47 = !DIBasicType(name: "long int", size: 64, encoding: DW_ATE_signed) + !48 = !DILocation(line: 10, column: 8, scope: !40, inlinedAt: !45) + +... +--- +name: _ZN1sC2Ei +tracksRegLiveness: true +liveins: + - { reg: '%rdi' } + - { reg: '%esi' } +fixedStack: + - { id: 0, type: spill-slot, offset: -32, size: 8, alignment: 16, callee-saved-register: '%rbx' } + - { id: 1, type: spill-slot, offset: -24, size: 8, alignment: 8, callee-saved-register: '%r14' } + - { id: 2, type: spill-slot, offset: -16, size: 8, alignment: 16 } +stack: + - { id: 0, offset: -36, size: 4, alignment: 4 } +body: | + bb.0: + successors: %bb.3, %bb.2 + liveins: %esi, %rdi, %r14, %rbx, %rbp + + ; CHECK: [[REGISTER:%r[a-z0-9]+]] = LEA64r {{%r[a-z0-9]+}}, 1, _, -20, _ + ; CHECK-NEXT: DBG_VALUE debug-use [[REGISTER]], debug-use _, !46, !17, debug-location !48 + ; CHECK-NEXT: DBG_VALUE debug-use [[REGISTER]], debug-use _, !39, !17, debug-location !44 + + frame-setup PUSH64r killed %rbp, implicit-def %rsp, implicit %rsp + CFI_INSTRUCTION def_cfa_offset 16 + CFI_INSTRUCTION offset %rbp, -16 + %rbp = frame-setup MOV64rr %rsp + CFI_INSTRUCTION def_cfa_register %rbp + frame-setup PUSH64r killed %r14, implicit-def %rsp, implicit %rsp + frame-setup PUSH64r killed %rbx, implicit-def %rsp, implicit %rsp + %rsp = frame-setup SUB64ri8 %rsp, 16, implicit-def dead %eflags + CFI_INSTRUCTION offset %rbx, -32 + CFI_INSTRUCTION offset %r14, -24 + %r14d = MOV32rr %esi + %rbx = MOV64rr %rdi + CALL64pcrel32 @_ZN1lC2Ei, csr_64, implicit %rsp, implicit %rdi, implicit %esi, implicit-def %rsp + %rdi = LEA64r %rbx, 1, _, 8, _ + DBG_VALUE debug-use %rdi, debug-use _, !20, !17, debug-location !27 + DBG_VALUE debug-use %rdi, debug-use _, !10, !17, debug-location !18 + %rax = MOV64rm %rbx, 1, _, 16, _ :: (load 8) + MOV64mr %rbx, 1, _, 8, _, killed %rax :: (store 8) + MOV64mr %rbx, 1, _, 24, _, %rdi :: (store 8) + %eax = MOV32ri -1 + %cl = MOV8rr %r14b, implicit killed %r14d + %eax = SHL32rCL killed %eax, implicit-def dead %eflags, implicit %cl + MOV32mr %rbx, 1, _, 32, _, %eax :: (store 4, align 8) + MOV32mi %rbp, 1, _, -20, _, 0 :: (store 4) + %rcx = MOV64rm %rbx, 1, _, 8, _ :: (load 8) + MOV64mr %rip, 1, _, @n, _, %rcx :: (store 8) + %edx = XOR32rr undef %edx, undef %edx, implicit-def dead %eflags, implicit-def %rdx + TEST64rr %rcx, %rcx, implicit-def %eflags + %esi = MOV32ri @o, implicit-def %rsi + %rsi = CMOVNE64rr killed %rsi, %rdx, implicit killed %eflags + %rsi = OR64rr killed %rsi, killed %rcx, implicit-def %eflags + %rcx = LEA64r %rbp, 1, _, -20, _ + DBG_VALUE debug-use %rcx, debug-use _, !46, !17, debug-location !48 + DBG_VALUE debug-use %rcx, debug-use _, !39, !17, debug-location !44 + DBG_VALUE %rbp, -20, !29, !17, debug-location !36 + %rcx = CMOVNE64rr killed %rcx, killed %rdx, implicit killed %eflags + %rcx = OR64rr killed %rcx, killed %rsi, implicit-def dead %eflags + %rdx = MOVSX64rm32 %rbx, 1, _, 0, _ :: (load 4, align 8) + TEST32rm killed %eax, killed %rcx, 4, killed %rdx, 0, _, implicit-def %eflags :: (load 4) + JNE_1 %bb.2, implicit %eflags + JMP_1 %bb.3 + + bb.1: + successors: %bb.2 + liveins: %rbx, %rbp + + %rdi = MOV64rm %rbx, 1, _, 24, _ :: (load 8) + + bb.2: + successors: %bb.1, %bb.3 + liveins: %rbx, %rbp, %rsp, %rdi + + CALL64pcrel32 @_ZN1p2aaEv, csr_64, implicit %rsp, implicit %rdi, implicit-def %rsp, implicit-def %eax + %eax = KILL %eax, implicit-def %rax + %ecx = LEA64_32r %rax, 1, _, -1, _, implicit-def %rcx + %ecx = SHR32ri %ecx, 31, implicit-def dead %eflags, implicit killed %rcx, implicit-def %rcx + %eax = LEA64_32r killed %rax, 1, killed %rcx, -1, _ + %eax = SAR32r1 killed %eax, implicit-def dead %eflags + CMP32mr %rbx, 1, _, 0, _, killed %eax, implicit-def %eflags :: (load 4, align 8), (load 4, align 8) + JG_1 %bb.1, implicit killed %eflags + + bb.3: + liveins: %rbp + + %rsp = ADD64ri8 %rsp, 16, implicit-def dead %eflags + %rbx = POP64r implicit-def %rsp, implicit %rsp + %r14 = POP64r implicit-def %rsp, implicit %rsp + %rbp = POP64r implicit-def %rsp, implicit %rsp + RETQ + +... |