diff --git a/clang/lib/Driver/ToolChains/Darwin.cpp b/clang/lib/Driver/ToolChains/Darwin.cpp --- a/clang/lib/Driver/ToolChains/Darwin.cpp +++ b/clang/lib/Driver/ToolChains/Darwin.cpp @@ -542,6 +542,12 @@ CmdArgs.push_back(Args.MakeArgString("-lto-stats-file=" + StatsFile.str())); } + // Forward -fno-unroll-loops to the linker in LTO. + if (Args.hasArg(options::OPT_fno_unroll_loops)) { + CmdArgs.push_back("-mllvm"); + CmdArgs.push_back(Args.MakeArgString("-lto-no-unroll-loops")); + } + // It seems that the 'e' option is completely ignored for dynamic executables // (the default), and with static executables, the last one wins, as expected. Args.AddAllArgs(CmdArgs, {options::OPT_d_Flag, options::OPT_s, options::OPT_t, diff --git a/clang/test/Driver/darwin-ld-lto-fno-unroll-loops.c b/clang/test/Driver/darwin-ld-lto-fno-unroll-loops.c new file mode 100644 --- /dev/null +++ b/clang/test/Driver/darwin-ld-lto-fno-unroll-loops.c @@ -0,0 +1,17 @@ +// REQUIRES: system-darwin + +// RUN: mkdir -p %t/bin +// RUN: mkdir -p %t/lib +// RUN: touch %t/lib/libLTO.dylib + +// Check that ld gets "-lto-no-unroll-loops" when -fno-unroll-loops is passed. +// +// RUN: %clang -target x86_64-apple-darwin10 %s -fno-unroll-loops -flto=full -### 2>&1 | \ +// RUN: FileCheck --check-prefix=NOUNROLL %s + +// NOUNROLL: "-mllvm" "-lto-no-unroll-loops" +// +// RUN: %clang -target x86_64-apple-darwin10 %s -flto=full -### 2>&1 | \ +// RUN: FileCheck --check-prefix=UNROLL %s + +// UNROLL-NOT: -lto-no-unroll-loops diff --git a/llvm/lib/LTO/LTOCodeGenerator.cpp b/llvm/lib/LTO/LTOCodeGenerator.cpp --- a/llvm/lib/LTO/LTOCodeGenerator.cpp +++ b/llvm/lib/LTO/LTOCodeGenerator.cpp @@ -109,6 +109,10 @@ cl::Hidden); } +cl::opt LTONoUnrollLoops("lto-no-unroll-loops", + cl::desc("Disable unrolling during LTO."), + cl::Hidden, cl::init(false)); + LTOCodeGenerator::LTOCodeGenerator(LLVMContext &Context) : Context(Context), MergedModule(new Module("ld-temp.o", Context)), TheLinker(new Linker(*MergedModule)) { @@ -570,6 +574,7 @@ Triple TargetTriple(TargetMach->getTargetTriple()); PassManagerBuilder PMB; + PMB.DisableUnrollLoops = LTONoUnrollLoops; PMB.DisableGVNLoadPRE = DisableGVNLoadPRE; PMB.LoopVectorize = !DisableVectorization; PMB.SLPVectorize = !DisableVectorization; diff --git a/llvm/test/tools/llvm-lto/fno-unroll-loops-option.ll b/llvm/test/tools/llvm-lto/fno-unroll-loops-option.ll new file mode 100644 --- /dev/null +++ b/llvm/test/tools/llvm-lto/fno-unroll-loops-option.ll @@ -0,0 +1,34 @@ +; REQUIRES: asserts + +; RUN: llvm-as < %s > %t1.bc + +; Build with unrolling disabled (-lto-no-unroll-loops). +; RUN: llvm-lto %t1.bc -o %t.nounroll.o -lto-no-unroll-loops --exported-symbol=foo -save-merged-module +; RUN: llvm-dis -o - %t.nounroll.o.merged.bc | FileCheck --check-prefix=NOUNROLL %s + +; NOUNROLL: br label %loop +; NOUNROLL: br i1 %ec, label %exit, label %loop + +; Build with unrolling enabled (by not passing -lto-no-unroll-loops). All +; branches should be gone. +; RUN: llvm-lto %t1.bc -o %t.nounroll.o --exported-symbol=foo -save-merged-module +; RUN: llvm-dis -o - %t.nounroll.o.merged.bc | FileCheck --check-prefix=UNROLL %s + +; UNROLL-NOT: br + +define void @foo(i32* %ptr) { + +entry: + br label %loop + +loop: + %iv = phi i32 [ 0, %entry], [ %iv.next, %loop ] + %iv.ptr = getelementptr i32, i32* %ptr, i32 %iv + store i32 %iv, i32* %iv.ptr + %iv.next = add i32 %iv, 1 + %ec = icmp eq i32 %iv.next, 10 + br i1 %ec, label %exit, label %loop + +exit: + ret void +}