diff --git a/lld/MachO/Driver.cpp b/lld/MachO/Driver.cpp --- a/lld/MachO/Driver.cpp +++ b/lld/MachO/Driver.cpp @@ -804,6 +804,9 @@ parseClangOption(saver.save("-mcpu=" + StringRef(arg->getValue())), arg->getSpelling()); + for (auto *arg : args.filtered(OPT_mllvm)) + parseClangOption(arg->getValue(), arg->getSpelling()); + initLLVM(); compileBitcodeFiles(); replaceCommonSymbols(); diff --git a/lld/MachO/LTO.cpp b/lld/MachO/LTO.cpp --- a/lld/MachO/LTO.cpp +++ b/lld/MachO/LTO.cpp @@ -28,6 +28,7 @@ lto::Config c; c.Options = initTargetOptionsFromCodeGenFlags(); c.CPU = getCPUStr(); + c.MAttrs = getMAttrs(); return c; } diff --git a/lld/MachO/Options.td b/lld/MachO/Options.td --- a/lld/MachO/Options.td +++ b/lld/MachO/Options.td @@ -876,7 +876,6 @@ Group; def mllvm : Separate<["-"], "mllvm">, HelpText<"Options to pass to LLVM">, - Flags<[HelpHidden]>, Group; def mcpu : Separate<["-"], "mcpu">, HelpText<"Processor family target for LTO code generation">, diff --git a/lld/test/MachO/mattrs.ll b/lld/test/MachO/mattrs.ll new file mode 100644 --- /dev/null +++ b/lld/test/MachO/mattrs.ll @@ -0,0 +1,35 @@ +; REQUIRES: x86 +; RUN: llvm-as %s -o %t.o + +;; Verify that LTO behavior can be tweaked using -mattr. + +; RUN: %lld -mcpu haswell -mllvm -mattr=+fma %t.o -o %t.dylib -dylib +; RUN: llvm-objdump -d --section="__text" --no-leading-addr --no-show-raw-insn %t.dylib | FileCheck %s --check-prefix=FMA + +; RUN: %lld -mcpu haswell -mllvm -mattr=-fma %t.o -o %t.dylib -dylib +; RUN: llvm-objdump -d --section="__text" --no-leading-addr --no-show-raw-insn %t.dylib | FileCheck %s --check-prefix=NO-FMA + +; FMA: <_foo>: +; FMA-NEXT: vrcpss %xmm0, %xmm0, %xmm1 +; FMA-NEXT: vfmsub213ss 7(%rip), %xmm1, %xmm0 # 2d4 +; FMA-NEXT: vfnmadd132ss %xmm1, %xmm1, %xmm0 +; FMA-NEXT: retq + +; NO-FMA: <_foo>: +; NO-FMA-NEXT: vrcpss %xmm0, %xmm0, %xmm1 +; NO-FMA-NEXT: vmulss %xmm1, %xmm0, %xmm0 +; NO-FMA-NEXT: vmovss 16(%rip), %xmm2 # 2e0 +; NO-FMA-NEXT: vsubss %xmm0, %xmm2, %xmm0 +; NO-FMA-NEXT: vmulss %xmm0, %xmm1, %xmm0 +; NO-FMA-NEXT: vaddss %xmm0, %xmm1, %xmm0 +; NO-FMA-NEXT: retq + +target triple = "x86_64-apple-darwin" +target datalayout = "e-m:o-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128" + +define float @foo(float %x) #0 { + %div = fdiv fast float 1.0, %x + ret float %div +} + +attributes #0 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf,vec-divf" }