add the -mrecip driver flag and process its options (3rd try)

The 1st and 2nd tries to land this (r238055, r238851) were reverted due to
bot failures caused by the LLVM part of the patch. That was hopefully fixed 
after r239001.

This is the front-end counterpart to D8982.

The -mrecip option interface is based on maintaining compatibility with gcc:
https://gcc.gnu.org/onlinedocs/gcc-4.9.2/gcc/i386-and-x86-64-Options.html#index-mrecip_003dopt-1627
https://gcc.gnu.org/onlinedocs/gcc-4.9.2/gcc/RS_002f6000-and-PowerPC-Options.html#index-mrecip-2289

...while adding more functionality (allowing users to specify the number of refinement steps for each
estimate type).

Differential Revision: http://reviews.llvm.org/D8989

llvm-svn: 239536

3 files changed, 137 insertions, 1 deletions

diff --git a/clang/lib/CodeGen/BackendUtil.cpp b/clang/lib/CodeGen/BackendUtil.cpp
index cb077e64863..905ea617ae8 100644
--- a/clang/lib/CodeGen/BackendUtil.cpp
+++ b/clang/lib/CodeGen/BackendUtil.cpp
@@ -478,6 +478,9 @@ TargetMachine *EmitAssemblyHelper::CreateTargetMachine(bool MustCreateTM) {
 
   llvm::TargetOptions Options;
 
+  if (!TargetOpts.Reciprocals.empty())
+    Options.Reciprocals = TargetRecip(TargetOpts.Reciprocals);
+
   Options.ThreadModel =
     llvm::StringSwitch<llvm::ThreadModel::Model>(CodeGenOpts.ThreadModel)
       .Case("posix", llvm::ThreadModel::POSIX)
diff --git a/clang/lib/Driver/Tools.cpp b/clang/lib/Driver/Tools.cpp
index 43d6ce9bbbb..144c74de921 100644
--- a/clang/lib/Driver/Tools.cpp
+++ b/clang/lib/Driver/Tools.cpp
@@ -1550,6 +1550,137 @@ static void AddGoldPlugin(const ToolChain &ToolChain, const ArgList &Args,
     CmdArgs.push_back(Args.MakeArgString(Twine("-plugin-opt=mcpu=") + CPU));
 }
 
+/// This is a helper function for validating the optional refinement step
+/// parameter in reciprocal argument strings. Return false if there is an error
+/// parsing the refinement step. Otherwise, return true and set the Position
+/// of the refinement step in the input string.
+static bool getRefinementStep(const StringRef &In, const Driver &D,
+                                const Arg &A, size_t &Position) {
+  const char RefinementStepToken = ':';
+  Position = In.find(RefinementStepToken);
+  if (Position != StringRef::npos) {
+    StringRef Option = A.getOption().getName();
+    StringRef RefStep = In.substr(Position + 1);
+    // Allow exactly one numeric character for the additional refinement
+    // step parameter. This is reasonable for all currently-supported
+    // operations and architectures because we would expect that a larger value
+    // of refinement steps would cause the estimate "optimization" to
+    // under-perform the native operation. Also, if the estimate does not
+    // converge quickly, it probably will not ever converge, so further
+    // refinement steps will not produce a better answer.
+    if (RefStep.size() != 1) {
+      D.Diag(diag::err_drv_invalid_value) << Option << RefStep;
+      return false;
+    }
+    char RefStepChar = RefStep[0];
+    if (RefStepChar < '0' || RefStepChar > '9') {
+      D.Diag(diag::err_drv_invalid_value) << Option << RefStep;
+      return false;
+    }
+  }
+  return true;
+}
+
+/// The -mrecip flag requires processing of many optional parameters.
+static void ParseMRecip(const Driver &D, const ArgList &Args,
+                        ArgStringList &OutStrings) {
+  StringRef DisabledPrefixIn = "!";
+  StringRef DisabledPrefixOut = "!";
+  StringRef EnabledPrefixOut = "";
+  StringRef Out = "-mrecip=";
+
+  Arg *A = Args.getLastArg(options::OPT_mrecip, options::OPT_mrecip_EQ);
+  if (!A)
+    return;
+
+  unsigned NumOptions = A->getNumValues();
+  if (NumOptions == 0) {
+    // No option is the same as "all".
+    OutStrings.push_back(Args.MakeArgString(Out + "all"));
+    return;
+  }
+
+  // Pass through "all", "none", or "default" with an optional refinement step.
+  if (NumOptions == 1) {
+    StringRef Val = A->getValue(0);
+    size_t RefStepLoc;
+    if (!getRefinementStep(Val, D, *A, RefStepLoc))
+      return;
+    StringRef ValBase = Val.slice(0, RefStepLoc);
+    if (ValBase == "all" || ValBase == "none" || ValBase == "default") {
+      OutStrings.push_back(Args.MakeArgString(Out + Val));
+      return;
+    }
+  }
+
+  // Each reciprocal type may be enabled or disabled individually.
+  // Check each input value for validity, concatenate them all back together,
+  // and pass through.
+
+  llvm::StringMap<bool> OptionStrings;
+  OptionStrings.insert(std::make_pair("divd",       false));
+  OptionStrings.insert(std::make_pair("divf",       false));
+  OptionStrings.insert(std::make_pair("vec-divd",   false));
+  OptionStrings.insert(std::make_pair("vec-divf",   false));
+  OptionStrings.insert(std::make_pair("sqrtd",      false));
+  OptionStrings.insert(std::make_pair("sqrtf",      false));
+  OptionStrings.insert(std::make_pair("vec-sqrtd",  false));
+  OptionStrings.insert(std::make_pair("vec-sqrtf",  false));
+
+  for (unsigned i = 0; i != NumOptions; ++i) {
+    StringRef Val = A->getValue(i);
+
+    bool IsDisabled = Val.startswith(DisabledPrefixIn);
+    // Ignore the disablement token for string matching.
+    if (IsDisabled)
+      Val = Val.substr(1);
+
+    size_t RefStep;
+    if (!getRefinementStep(Val, D, *A, RefStep))
+      return;
+
+    StringRef ValBase = Val.slice(0, RefStep);
+    llvm::StringMap<bool>::iterator OptionIter = OptionStrings.find(ValBase);
+    if (OptionIter == OptionStrings.end()) {
+      // Try again specifying float suffix.
+      OptionIter = OptionStrings.find(ValBase.str() + 'f');
+      if (OptionIter == OptionStrings.end()) {
+        // The input name did not match any known option string.
+        D.Diag(diag::err_drv_unknown_argument) << Val;
+        return;
+      }
+      // The option was specified without a float or double suffix.
+      // Make sure that the double entry was not already specified.
+      // The float entry will be checked below.
+      if (OptionStrings[ValBase.str() + 'd']) {
+        D.Diag(diag::err_drv_invalid_value) << A->getOption().getName() << Val;
+        return;
+      }
+    }
+    
+    if (OptionIter->second == true) {
+      // Duplicate option specified.
+      D.Diag(diag::err_drv_invalid_value) << A->getOption().getName() << Val;
+      return;
+    }
+
+    // Mark the matched option as found. Do not allow duplicate specifiers.
+    OptionIter->second = true;
+
+    // If the precision was not specified, also mark the double entry as found.
+    if (ValBase.back() != 'f' && ValBase.back() != 'd')
+      OptionStrings[ValBase.str() + 'd'] = true;
+
+    // Build the output string.
+    StringRef Prefix = IsDisabled ? DisabledPrefixOut : EnabledPrefixOut;
+    Out = Args.MakeArgString(Out + Prefix + Val);
+    if (i != NumOptions - 1)
+      Out = Args.MakeArgString(Out + ",");
+  }
+
+  OutStrings.push_back(Args.MakeArgString(Out));
+}
+
 static void getX86TargetFeatures(const Driver &D, const llvm::Triple &Triple,
                                  const ArgList &Args,
                                  std::vector<const char *> &Features) {
@@ -3155,6 +3286,8 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
       CmdArgs.push_back(Args.MakeArgString("-ffp-contract=fast"));
     }
   }
+  
+  ParseMRecip(getToolChain().getDriver(), Args, CmdArgs);
 
   // We separately look for the '-ffast-math' and '-ffinite-math-only' flags,
   // and if we find them, tell the frontend to provide the appropriate
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index 3238a6408c1..19fe848109a 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -1805,7 +1805,7 @@ static void ParseTargetArgs(TargetOptions &Opts, ArgList &Args) {
   Opts.FeaturesAsWritten = Args.getAllArgValues(OPT_target_feature);
   Opts.LinkerVersion = Args.getLastArgValue(OPT_target_linker_version);
   Opts.Triple = llvm::Triple::normalize(Args.getLastArgValue(OPT_triple));
-
+  Opts.Reciprocals = Args.getAllArgValues(OPT_mrecip_EQ);
   // Use the default target triple if unspecified.
   if (Opts.Triple.empty())
     Opts.Triple = llvm::sys::getDefaultTargetTriple();