From b080b630b1a71c25ae2c704461c246476c177421 Mon Sep 17 00:00:00 2001 From: Justin Lebar Date: Wed, 25 Jan 2017 21:29:48 +0000 Subject: [CodeGen] [CUDA] Add the ability set default attrs on functions in linked modules. Summary: Now when you ask clang to link in a bitcode module, you can tell it to set attributes on that module's functions to match what we would have set if we'd emitted those functions ourselves. This is particularly important for fast-math attributes in CUDA compilations. Each CUDA compilation links in libdevice, a bitcode library provided by nvidia as part of the CUDA distribution. Without this patch, if we have a user-function F that is compiled with -ffast-math that calls a function G from libdevice, F will have the unsafe-fp-math=true (etc.) attributes, but G will have no attributes. Since F calls G, the inliner will merge G's attributes into F's. It considers the lack of an unsafe-fp-math=true attribute on G to be tantamount to unsafe-fp-math=false, so it "merges" these by setting unsafe-fp-math=false on F. This then continues up the call graph, until every function that (transitively) calls something in libdevice gets unsafe-fp-math=false set, thus disabling fastmath in almost all CUDA code. Reviewers: echristo Subscribers: hfinkel, llvm-commits, mehdi_amini Differential Revision: https://reviews.llvm.org/D28538 llvm-svn: 293097 --- clang/lib/Frontend/CompilerInvocation.cpp | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'clang/lib/Frontend/CompilerInvocation.cpp') diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp index 7576d6d..ee46f92 100644 --- a/clang/lib/Frontend/CompilerInvocation.cpp +++ b/clang/lib/Frontend/CompilerInvocation.cpp @@ -722,11 +722,16 @@ static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK, Opts.RelaxELFRelocations = Args.hasArg(OPT_mrelax_relocations); Opts.DebugCompilationDir = Args.getLastArgValue(OPT_fdebug_compilation_dir); for (auto A : Args.filtered(OPT_mlink_bitcode_file, OPT_mlink_cuda_bitcode)) { - unsigned LinkFlags = llvm::Linker::Flags::None; - if (A->getOption().matches(OPT_mlink_cuda_bitcode)) - LinkFlags = llvm::Linker::Flags::LinkOnlyNeeded | - llvm::Linker::Flags::InternalizeLinkedSymbols; - Opts.LinkBitcodeFiles.push_back(std::make_pair(LinkFlags, A->getValue())); + CodeGenOptions::BitcodeFileToLink F; + F.Filename = A->getValue(); + if (A->getOption().matches(OPT_mlink_cuda_bitcode)) { + F.LinkFlags = llvm::Linker::Flags::LinkOnlyNeeded | + llvm::Linker::Flags::InternalizeLinkedSymbols; + // When linking CUDA bitcode, propagate function attributes so that + // e.g. libdevice gets fast-math attrs if we're building with fast-math. + F.PropagateAttrs = true; + } + Opts.LinkBitcodeFiles.push_back(F); } Opts.SanitizeCoverageType = getLastArgIntValue(Args, OPT_fsanitize_coverage_type, 0, Diags); -- cgit v1.1