From: Rafael Auler Date: Thu, 5 Aug 2021 21:17:07 +0000 (-0700) Subject: Rebase: [Facebook] [MC] Introduce NeverAlign fragment type X-Git-Tag: upstream/15.0.7~2112 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=6d0528636ae54fba75938a79ae7a98dfcc949f72;p=platform%2Fupstream%2Fllvm.git Rebase: [Facebook] [MC] Introduce NeverAlign fragment type Summary: Introduce NeverAlign fragment type. The intended usage of this fragment is to insert it before a pair of macro-op fusion eligible instructions. NeverAlign fragment ensures that the next fragment (first instruction in the pair) does not end at a given alignment boundary by emitting a minimal size nop if necessary. In effect, it ensures that a pair of macro-fusible instructions is not split by a given alignment boundary, which is a precondition for macro-op fusion in modern Intel Cores (64B = cache line size, see Intel Architecture Optimization Reference Manual, 2.3.2.1 Legacy Decode Pipeline: Macro-Fusion). This patch introduces functionality used by BOLT when emitting code with MacroFusion alignment already in place. The use case is different from BoundaryAlign and instruction bundling: - BoundaryAlign can be extended to perform the desired alignment for the first instruction in the macro-op fusion pair (D101817). However, this approach has higher overhead due to reliance on relaxation as BoundaryAlign requires in the general case - see https://reviews.llvm.org/D97982#2710638. - Instruction bundling: the intent of NeverAlign fragment is to prevent the first instruction in a pair ending at a given alignment boundary, by inserting at most one minimum size nop. It's OK if either instruction crosses the cache line. Padding both instructions using bundles to not cross the alignment boundary would result in excessive padding. There's no straightforward way to request instruction bundling to avoid a given end alignment for the first instruction in the bundle. LLVM: https://reviews.llvm.org/D97982 Manual rebase conflict history: https://phabricator.intern.facebook.com/D30142613 Test Plan: sandcastle Reviewers: #llvm-bolt Subscribers: phabricatorlinter Differential Revision: https://phabricator.intern.facebook.com/D31361547 --- diff --git a/bolt/lib/Core/BinaryEmitter.cpp b/bolt/lib/Core/BinaryEmitter.cpp index 1001a3a..85595a5 100644 --- a/bolt/lib/Core/BinaryEmitter.cpp +++ b/bolt/lib/Core/BinaryEmitter.cpp @@ -453,6 +453,7 @@ void BinaryEmitter::emitFunctionBody(BinaryFunction &BF, bool EmitColdPart, // This assumes the second instruction in the macro-op pair will get // assigned to its own MCRelaxableFragment. Since all JCC instructions // are relaxable, we should be safe. + Streamer.emitNeverAlignCodeAtEnd(/*Alignment to avoid=*/64, *BC.STI); } if (!EmitCodeOnly && opts::UpdateDebugSections && BF.getDWARFUnit()) { diff --git a/llvm/include/llvm/MC/MCFragment.h b/llvm/include/llvm/MC/MCFragment.h index b6329b1..bbfb398 100644 --- a/llvm/include/llvm/MC/MCFragment.h +++ b/llvm/include/llvm/MC/MCFragment.h @@ -33,6 +33,7 @@ class MCFragment : public ilist_node_with_parent { public: enum FragmentType : uint8_t { FT_Align, + FT_NeverAlign, FT_Data, FT_CompactEncodedInst, FT_Fill, @@ -340,6 +341,27 @@ public: } }; +class MCNeverAlignFragment : public MCFragment { + /// The alignment the end of the next fragment should avoid. + unsigned Alignment; + + /// When emitting Nops some subtargets have specific nop encodings. + const MCSubtargetInfo &STI; + +public: + MCNeverAlignFragment(unsigned Alignment, const MCSubtargetInfo &STI, + MCSection *Sec = nullptr) + : MCFragment(FT_NeverAlign, false, Sec), Alignment(Alignment), STI(STI) {} + + unsigned getAlignment() const { return Alignment; } + + const MCSubtargetInfo &getSubtargetInfo() const { return STI; } + + static bool classof(const MCFragment *F) { + return F->getKind() == MCFragment::FT_NeverAlign; + } +}; + class MCFillFragment : public MCFragment { uint8_t ValueSize; /// Value to use for filling bytes. diff --git a/llvm/include/llvm/MC/MCObjectStreamer.h b/llvm/include/llvm/MC/MCObjectStreamer.h index 6536c81..d09defe 100644 --- a/llvm/include/llvm/MC/MCObjectStreamer.h +++ b/llvm/include/llvm/MC/MCObjectStreamer.h @@ -157,6 +157,8 @@ public: unsigned MaxBytesToEmit = 0) override; void emitCodeAlignment(unsigned ByteAlignment, const MCSubtargetInfo *STI, unsigned MaxBytesToEmit = 0) override; + void emitNeverAlignCodeAtEnd(unsigned ByteAlignment, + const MCSubtargetInfo &STI) override; void emitValueToOffset(const MCExpr *Offset, unsigned char Value, SMLoc Loc) override; void emitDwarfLocDirective(unsigned FileNo, unsigned Line, unsigned Column, diff --git a/llvm/include/llvm/MC/MCStreamer.h b/llvm/include/llvm/MC/MCStreamer.h index e71014b..a8ac7ff 100644 --- a/llvm/include/llvm/MC/MCStreamer.h +++ b/llvm/include/llvm/MC/MCStreamer.h @@ -872,6 +872,12 @@ public: const MCSubtargetInfo *STI, unsigned MaxBytesToEmit = 0); + /// If the end of the fragment following this NeverAlign fragment ever gets + /// aligned to \p ByteAlignment, this fragment emits a single nop before the + /// following fragment to break this end-alignment. + virtual void emitNeverAlignCodeAtEnd(unsigned ByteAlignment, + const MCSubtargetInfo &STI); + /// Emit some number of copies of \p Value until the byte offset \p /// Offset is reached. /// diff --git a/llvm/lib/MC/MCAssembler.cpp b/llvm/lib/MC/MCAssembler.cpp index a33d7ea..61c69c6 100644 --- a/llvm/lib/MC/MCAssembler.cpp +++ b/llvm/lib/MC/MCAssembler.cpp @@ -290,6 +290,43 @@ bool MCAssembler::evaluateFixup(const MCAsmLayout &Layout, return IsResolved; } +/// Check if the branch crosses the boundary. +/// +/// \param StartAddr start address of the fused/unfused branch. +/// \param Size size of the fused/unfused branch. +/// \param BoundaryAlignment alignment requirement of the branch. +/// \returns true if the branch cross the boundary. +static bool mayCrossBoundary(uint64_t StartAddr, uint64_t Size, + Align BoundaryAlignment) { + uint64_t EndAddr = StartAddr + Size; + return (StartAddr >> Log2(BoundaryAlignment)) != + ((EndAddr - 1) >> Log2(BoundaryAlignment)); +} + +/// Check if the branch is against the boundary. +/// +/// \param StartAddr start address of the fused/unfused branch. +/// \param Size size of the fused/unfused branch. +/// \param BoundaryAlignment alignment requirement of the branch. +/// \returns true if the branch is against the boundary. +static bool isAgainstBoundary(uint64_t StartAddr, uint64_t Size, + Align BoundaryAlignment) { + uint64_t EndAddr = StartAddr + Size; + return (EndAddr & (BoundaryAlignment.value() - 1)) == 0; +} + +/// Check if the branch needs padding. +/// +/// \param StartAddr start address of the fused/unfused branch. +/// \param Size size of the fused/unfused branch. +/// \param BoundaryAlignment alignment requirement of the branch. +/// \returns true if the branch needs padding. +static bool needPadding(uint64_t StartAddr, uint64_t Size, + Align BoundaryAlignment) { + return mayCrossBoundary(StartAddr, Size, BoundaryAlignment) || + isAgainstBoundary(StartAddr, Size, BoundaryAlignment); +} + uint64_t MCAssembler::computeFragmentSize(const MCAsmLayout &Layout, const MCFragment &F) const { assert(getBackendPtr() && "Requires assembler backend"); @@ -350,6 +387,41 @@ uint64_t MCAssembler::computeFragmentSize(const MCAsmLayout &Layout, return Size; } + case MCFragment::FT_NeverAlign: { + // Disclaimer: NeverAlign fragment size depends on the size of its immediate + // successor, but NeverAlign need not be a MCRelaxableFragment. + // NeverAlign fragment size is recomputed if the successor is relaxed: + // - If RelaxableFragment is relaxed, it gets invalidated by marking its + // predecessor as LastValidFragment. + // - This forces the assembler to call MCAsmLayout::layoutFragment on that + // relaxable fragment, which in turn will always ask the predecessor to + // compute its size (see "computeFragmentSize(prev)" in layoutFragment). + // + // In short, the simplest way to ensure that computeFragmentSize() is sane + // is to establish the following rule: it should never examine fragments + // after the current fragment in the section. If we logically need to + // examine any fragment after the current fragment, we need to do that using + // relaxation, inside MCAssembler::layoutSectionOnce. + const MCNeverAlignFragment &NAF = cast(F); + const MCFragment *NF = F.getNextNode(); + uint64_t Offset = Layout.getFragmentOffset(&NAF); + size_t NextFragSize = 0; + if (const auto *NextFrag = dyn_cast(NF)) { + NextFragSize = NextFrag->getContents().size(); + } else if (const auto *NextFrag = dyn_cast(NF)) { + NextFragSize = NextFrag->getContents().size(); + } else { + llvm_unreachable("Didn't find the expected fragment after NeverAlign"); + } + // Check if the next fragment ends at the alignment we want to avoid. + if (isAgainstBoundary(Offset, NextFragSize, Align(NAF.getAlignment()))) { + // Avoid this alignment by introducing minimum nop. + assert(getBackend().getMinimumNopSize() != NAF.getAlignment()); + return getBackend().getMinimumNopSize(); + } + return 0; + } + case MCFragment::FT_Org: { const MCOrgFragment &OF = cast(F); MCValue Value; @@ -574,6 +646,15 @@ static void writeFragment(raw_ostream &OS, const MCAssembler &Asm, break; } + case MCFragment::FT_NeverAlign: { + const MCNeverAlignFragment &NAF = cast(F); + if (!Asm.getBackend().writeNopData(OS, FragmentSize, + &NAF.getSubtargetInfo())) + report_fatal_error("unable to write nop sequence of " + + Twine(FragmentSize) + " bytes"); + break; + } + case MCFragment::FT_Data: ++stats::EmittedDataFragments; OS << cast(F).getContents(); @@ -1027,43 +1108,6 @@ bool MCAssembler::relaxLEB(MCAsmLayout &Layout, MCLEBFragment &LF) { return OldSize != LF.getContents().size(); } -/// Check if the branch crosses the boundary. -/// -/// \param StartAddr start address of the fused/unfused branch. -/// \param Size size of the fused/unfused branch. -/// \param BoundaryAlignment alignment requirement of the branch. -/// \returns true if the branch cross the boundary. -static bool mayCrossBoundary(uint64_t StartAddr, uint64_t Size, - Align BoundaryAlignment) { - uint64_t EndAddr = StartAddr + Size; - return (StartAddr >> Log2(BoundaryAlignment)) != - ((EndAddr - 1) >> Log2(BoundaryAlignment)); -} - -/// Check if the branch is against the boundary. -/// -/// \param StartAddr start address of the fused/unfused branch. -/// \param Size size of the fused/unfused branch. -/// \param BoundaryAlignment alignment requirement of the branch. -/// \returns true if the branch is against the boundary. -static bool isAgainstBoundary(uint64_t StartAddr, uint64_t Size, - Align BoundaryAlignment) { - uint64_t EndAddr = StartAddr + Size; - return (EndAddr & (BoundaryAlignment.value() - 1)) == 0; -} - -/// Check if the branch needs padding. -/// -/// \param StartAddr start address of the fused/unfused branch. -/// \param Size size of the fused/unfused branch. -/// \param BoundaryAlignment alignment requirement of the branch. -/// \returns true if the branch needs padding. -static bool needPadding(uint64_t StartAddr, uint64_t Size, - Align BoundaryAlignment) { - return mayCrossBoundary(StartAddr, Size, BoundaryAlignment) || - isAgainstBoundary(StartAddr, Size, BoundaryAlignment); -} - bool MCAssembler::relaxBoundaryAlign(MCAsmLayout &Layout, MCBoundaryAlignFragment &BF) { // BoundaryAlignFragment that doesn't need to align any fragment should not be diff --git a/llvm/lib/MC/MCFragment.cpp b/llvm/lib/MC/MCFragment.cpp index 4e6459c..5a143a4 100644 --- a/llvm/lib/MC/MCFragment.cpp +++ b/llvm/lib/MC/MCFragment.cpp @@ -274,6 +274,9 @@ void MCFragment::destroy() { case FT_Align: delete cast(this); return; + case FT_NeverAlign: + delete cast(this); + return; case FT_Data: delete cast(this); return; @@ -342,6 +345,9 @@ LLVM_DUMP_METHOD void MCFragment::dump() const { OS << "<"; switch (getKind()) { case MCFragment::FT_Align: OS << "MCAlignFragment"; break; + case MCFragment::FT_NeverAlign: + OS << "MCNeverAlignFragment"; + break; case MCFragment::FT_Data: OS << "MCDataFragment"; break; case MCFragment::FT_CompactEncodedInst: OS << "MCCompactEncodedInstFragment"; break; @@ -381,6 +387,12 @@ LLVM_DUMP_METHOD void MCFragment::dump() const { << " MaxBytesToEmit:" << AF->getMaxBytesToEmit() << ">"; break; } + case MCFragment::FT_NeverAlign: { + const MCNeverAlignFragment *NAF = cast(this); + OS << "\n "; + OS << " Alignment:" << NAF->getAlignment() << ">"; + break; + } case MCFragment::FT_Data: { const auto *DF = cast(this); OS << "\n "; diff --git a/llvm/lib/MC/MCObjectStreamer.cpp b/llvm/lib/MC/MCObjectStreamer.cpp index 0c4ed20..45dfab2 100644 --- a/llvm/lib/MC/MCObjectStreamer.cpp +++ b/llvm/lib/MC/MCObjectStreamer.cpp @@ -663,6 +663,11 @@ void MCObjectStreamer::emitCodeAlignment(unsigned ByteAlignment, cast(getCurrentFragment())->setEmitNops(true, STI); } +void MCObjectStreamer::emitNeverAlignCodeAtEnd(unsigned ByteAlignment, + const MCSubtargetInfo &STI) { + insert(new MCNeverAlignFragment(ByteAlignment, STI)); +} + void MCObjectStreamer::emitValueToOffset(const MCExpr *Offset, unsigned char Value, SMLoc Loc) { diff --git a/llvm/lib/MC/MCStreamer.cpp b/llvm/lib/MC/MCStreamer.cpp index a229d28..49ba240 100644 --- a/llvm/lib/MC/MCStreamer.cpp +++ b/llvm/lib/MC/MCStreamer.cpp @@ -1215,6 +1215,8 @@ void MCStreamer::emitValueToAlignment(unsigned ByteAlignment, int64_t Value, void MCStreamer::emitCodeAlignment(unsigned ByteAlignment, const MCSubtargetInfo *STI, unsigned MaxBytesToEmit) {} +void MCStreamer::emitNeverAlignCodeAtEnd(unsigned ByteAlignment, + const MCSubtargetInfo &STI) {} void MCStreamer::emitValueToOffset(const MCExpr *Offset, unsigned char Value, SMLoc Loc) {} void MCStreamer::emitBundleAlignMode(unsigned AlignPow2) {} diff --git a/llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp b/llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp index 871b23f..6e0c8c4 100644 --- a/llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp +++ b/llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp @@ -1145,6 +1145,7 @@ private: bool parseDirectiveArch(); bool parseDirectiveNops(SMLoc L); bool parseDirectiveEven(SMLoc L); + bool parseDirectiveAvoidEndAlign(SMLoc L); bool ParseDirectiveCode(StringRef IDVal, SMLoc L); /// CodeView FPO data directives. @@ -4633,6 +4634,8 @@ bool X86AsmParser::ParseDirective(AsmToken DirectiveID) { return false; } else if (IDVal == ".nops") return parseDirectiveNops(DirectiveID.getLoc()); + else if (IDVal == ".avoid_end_align") + return parseDirectiveAvoidEndAlign(DirectiveID.getLoc()); else if (IDVal == ".even") return parseDirectiveEven(DirectiveID.getLoc()); else if (IDVal == ".cv_fpo_proc") @@ -4727,6 +4730,27 @@ bool X86AsmParser::parseDirectiveEven(SMLoc L) { return false; } +/// Directive for NeverAlign fragment testing, not for general usage! +/// parseDirectiveAvoidEndAlign +/// ::= .avoid_end_align alignment +bool X86AsmParser::parseDirectiveAvoidEndAlign(SMLoc L) { + int64_t Alignment = 0; + SMLoc AlignmentLoc; + AlignmentLoc = getTok().getLoc(); + if (getParser().checkForValidSection() || + getParser().parseAbsoluteExpression(Alignment)) + return true; + + if (getParser().parseEOL("unexpected token in directive")) + return true; + + if (Alignment <= 0) + return Error(AlignmentLoc, "expected a positive alignment"); + + getParser().getStreamer().emitNeverAlignCodeAtEnd(Alignment, getSTI()); + return false; +} + /// ParseDirectiveCode /// ::= .code16 | .code32 | .code64 bool X86AsmParser::ParseDirectiveCode(StringRef IDVal, SMLoc L) { diff --git a/llvm/test/MC/X86/directive-avoid_end_align.s b/llvm/test/MC/X86/directive-avoid_end_align.s new file mode 100644 index 0000000..1d74840 --- /dev/null +++ b/llvm/test/MC/X86/directive-avoid_end_align.s @@ -0,0 +1,208 @@ +# RUN: llvm-mc -triple=x86_64 -filetype=obj %s | llvm-objdump --no-show-raw-insn -d - | FileCheck %s +# RUN: not llvm-mc -triple=x86_64 --defsym ERR=1 %s -o /dev/null 2>&1 | FileCheck %s --check-prefix=ERR + +# avoid_end_align has no effect since test doesn't end at alignment boundary: +.avoid_end_align 64 +# CHECK-NOT: nop + testl %eax, %eax +# CHECK: testl %eax, %eax + je .LBB0 + +.fill 58, 1, 0x00 +# NeverAlign followed by MCDataFragment: +# avoid_end_align inserts nop because `test` would end at alignment boundary: +.avoid_end_align 64 +# CHECK: 3e: nop + testl %eax, %eax +# CHECK-NEXT: 3f: testl %eax, %eax + je .LBB0 +# CHECK-NEXT: 41: je +.LBB0: + retq + +.p2align 6 +.L0: +.nops 57 + int3 +# NeverAlign followed by RelaxableFragment: +.avoid_end_align 64 +# CHECK: ba: nop + cmpl $(.L1-.L0), %eax +# CHECK-NEXT: bb: cmpl + je .L0 +# CHECK-NEXT: c1: je +.nops 65 +.L1: + +############################################################################### +# Experiment A: +# Check that NeverAlign doesn't introduce infinite loops in layout. +# Control: +# 1. NeverAlign fragment is not added, +# 2. Short formats of cmp and jcc are used (3 and 2 bytes respectively), +# 3. cmp and jcc are placed such that to be split by 64B alignment boundary. +# 4. jcc would be relaxed to a longer format if at least one byte is added +# between .L10 and je itself, e.g. by adding a NeverAlign padding byte, +# or relaxing cmp instruction. +# 5. cmp would be relaxed to a longer format if at least one byte is added +# between .L11 and .L12, e.g. due to relaxing jcc instruction. +.p2align 6 +# CHECK: 140: int3 +.fill 2, 1, 0xcc +.L10: +.nops 122 + int3 +# CHECK: 1bc: int3 +# no avoid_end_align here +# CHECK-NOT: nop + cmp $(.L12-.L11), %eax +# CHECK: 1bd: cmpl +.L11: + je .L10 +# CHECK-NEXT: 1c0: je +.nops 125 +.L12: + +# Experiment: +# Same setup as control, except NeverAlign fragment is added before cmp. +# Expected effect: +# 1. NeverAlign pads cmp+jcc by one byte since cmp and jcc are split by a 64B +# alignment boundary, +# 2. This extra byte forces jcc relaxation to a longer format (Control rule #4), +# 3. This results in an cmp relaxation (Control rule #5), +# 4. Which in turn makes NeverAlign fragment unnecessary as cmp and jcc +# are no longer split by an alignment boundary (cmp crosses the boundary). +# 5. NeverAlign padding is removed. +# 6. cmp and jcc instruction remain in relaxed form. +# 7. Relaxation converges, layout succeeds. +.p2align 6 +# CHECK: 240: int3 +.fill 2, 1, 0xcc +.L20: +.nops 122 + int3 +# CHECK: 2bc: int3 +.avoid_end_align 64 +# CHECK-NOT: nop + cmp $(.L22-.L21), %eax +# CHECK-NEXT: 2bd: cmpl +.L21: + je .L20 +# CHECK-NEXT: 2c3: je +.nops 125 +.L22: + +############################################################################### +# Experiment B: similar to exp A, but we check that once NeverAlign padding is +# removed from the layout (exp A, experiment step 5), the increased distance +# between the symbols L33 and L34 triggers the relaxation of instruction at +# label L32. +# +# Control 1: using a one-byte instruction at L33 (site of NeverAlign) leads to +# steps 2-3 of exp A, experiment: +# 2. This extra byte forces jcc relaxation to a longer format (Control rule #4), +# 3. This results in an cmp relaxation (Control rule #5), +# => short cmp under L32 +.p2align 6 +# CHECK: 380: int3 +.fill 2, 1, 0xcc +.L30: +.nops 122 + int3 +# CHECK: 3fc: int3 + hlt +#.avoid_end_align 64 +.L33: + cmp $(.L32-.L31), %eax +# CHECK: 3fe: cmpl +.L31: + je .L30 +# CHECK-NEXT: 404: je +.nops 114 +.p2align 1 + int3 + int3 +# CHECK: 47c: int3 +.L34: +.nops 9 +.L32: + cmp $(.L33-.L34), %eax +# CHECK: 487: cmp +# note that the size of cmp is 48a-487 == 3 bytes (distance is exactly -128) + int3 +# CHECK-NEXT: 48a: int3 + +# Control 2: leaving out a byte at L43 (site of NeverAlign), plus +# relaxed jcc and cmp leads to a relaxed cmp under L42 (-129 as cmp's immediate) +.p2align 6 +# CHECK: 4c0: int3 +.fill 2, 1, 0xcc +.L40: +.nops 122 + int3 +# CHECK: 53c: int3 +# int3 +#.avoid_end_align 64 +.L43: + cmp $(.L42-.L41+0x100), %eax +# CHECK: 53d: cmpl +.L41: + je .L40+0x100 +# CHECK-NEXT: 543: je +.nops 114 +.p2align 1 + int3 + int3 +# CHECK: 5bc: int3 +.L44: +.nops 9 +.L42: + cmp $(.L43-.L44), %eax +# CHECK: 5c7: cmp +# note that the size of cmp is 5cd-5c7 == 6 bytes (distance is exactly -129) + int3 +# CHECK-NEXT: 5cd: int3 + +# Experiment +# Checking if removing NeverAlign padding at L53 as a result of alignment and +# relaxation of cmp and jcc following it (see exp A), thus reproducing the case +# in Control 2 (getting a relaxed cmp under L52), is handled correctly. +.p2align 6 +# CHECK: 600: int3 +.fill 2, 1, 0xcc +.L50: +.nops 122 + int3 +# CHECK: 67c: int3 +.avoid_end_align 64 +.L53: +# CHECK-NOT: nop + cmp $(.L52-.L51), %eax +# CHECK-NEXT: 67d: cmpl +.L51: + je .L50 +# CHECK-NEXT: 683: je +.nops 114 +.p2align 1 + int3 + int3 +# CHECK: 6fc: int3 +.L54: +.nops 9 +.L52: + cmp $(.L53-.L54), %eax +# CHECK: 707: cmp +# note that the size of cmp is 70d-707 == 6 bytes (distance is exactly -129) + int3 +# CHECK-NEXT: 70d: int3 + +.ifdef ERR +# ERR: {{.*}}.s:[[#@LINE+1]]:17: error: unknown token in expression +.avoid_end_align +# ERR: {{.*}}.s:[[#@LINE+1]]:18: error: expected absolute expression +.avoid_end_align x +# ERR: {{.*}}.s:[[#@LINE+1]]:18: error: expected a positive alignment +.avoid_end_align 0 +# ERR: {{.*}}.s:[[#@LINE+1]]:20: error: unexpected token in directive +.avoid_end_align 64, 0 +.endif