Revert "[flang] Add basic -mtune support" (#96678)

Reverts #95043
llvm · Jun 25, 2024 · 8dd9494 · 8dd9494
1 parent ec2fb59
commit 8dd9494
Show file tree

Hide file tree

Showing 26 changed files with 14 additions and 160 deletions.
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
@@ -5421,7 +5421,6 @@ def module_file_info : Flag<["-"], "module-file-info">, Flags<[]>,
   HelpText<"Provide information about a particular module file">;
 def mthumb : Flag<["-"], "mthumb">, Group<m_Group>;
 def mtune_EQ : Joined<["-"], "mtune=">, Group<m_Group>,
-  Visibility<[ClangOption, FlangOption]>,
   HelpText<"Only supported on AArch64, PowerPC, RISC-V, SPARC, SystemZ, and X86">;
 def multi__module : Flag<["-"], "multi_module">;
 def multiply__defined__unused : Separate<["-"], "multiply_defined_unused">;
@@ -6738,6 +6737,9 @@ def emit_hlfir : Flag<["-"], "emit-hlfir">, Group<Action_Group>,
 
 let Visibility = [CC1Option, CC1AsOption] in {
 
+def tune_cpu : Separate<["-"], "tune-cpu">,
+  HelpText<"Tune for a specific cpu type">,
+  MarshallingInfoString<TargetOpts<"TuneCPU">>;
 def target_abi : Separate<["-"], "target-abi">,
   HelpText<"Target a particular ABI type">,
   MarshallingInfoString<TargetOpts<"ABI">>;
@@ -6764,9 +6766,6 @@ def darwin_target_variant_triple : Separate<["-"], "darwin-target-variant-triple
 
 let Visibility = [CC1Option, CC1AsOption, FC1Option] in {
 
-def tune_cpu : Separate<["-"], "tune-cpu">,
-  HelpText<"Tune for a specific cpu type">,
-  MarshallingInfoString<TargetOpts<"TuneCPU">>;
 def target_cpu : Separate<["-"], "target-cpu">,
   HelpText<"Target a specific cpu type">,
   MarshallingInfoString<TargetOpts<"CPU">>;

diff --git a/clang/lib/Driver/ToolChains/Flang.cpp b/clang/lib/Driver/ToolChains/Flang.cpp
@@ -15,7 +15,6 @@
 #include "llvm/Frontend/Debug/Options.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/Path.h"
-#include "llvm/TargetParser/Host.h"
 #include "llvm/TargetParser/RISCVISAInfo.h"
 #include "llvm/TargetParser/RISCVTargetParser.h"
 
@@ -412,13 +411,6 @@ void Flang::addTargetOptions(const ArgList &Args,
   }
 
   // TODO: Add target specific flags, ABI, mtune option etc.
-  if (const Arg *A = Args.getLastArg(options::OPT_mtune_EQ)) {
-    CmdArgs.push_back("-tune-cpu");
-    if (A->getValue() == StringRef{"native"})
-      CmdArgs.push_back(Args.MakeArgString(llvm::sys::getHostCPUName()));
-    else
-      CmdArgs.push_back(A->getValue());
-  }
 }
 
 void Flang::addOffloadOptions(Compilation &C, const InputInfoList &Inputs,
@@ -810,7 +802,7 @@ void Flang::ConstructJob(Compilation &C, const JobAction &JA,
   case CodeGenOptions::FramePointerKind::None:
     FPKeepKindStr = "-mframe-pointer=none";
     break;
-  case CodeGenOptions::FramePointerKind::Reserved:
+   case CodeGenOptions::FramePointerKind::Reserved:
     FPKeepKindStr = "-mframe-pointer=reserved";
     break;
   case CodeGenOptions::FramePointerKind::NonLeaf:

diff --git a/flang/include/flang/Frontend/TargetOptions.h b/flang/include/flang/Frontend/TargetOptions.h
@@ -32,9 +32,6 @@ class TargetOptions {
   /// If given, the name of the target CPU to generate code for.
   std::string cpu;
 
-  /// If given, the name of the target CPU to tune code for.
-  std::string cpuToTuneFor;
-
   /// The list of target specific features to enable or disable, as written on
   /// the command line.
   std::vector<std::string> featuresAsWritten;

diff --git a/flang/include/flang/Lower/Bridge.h b/flang/include/flang/Lower/Bridge.h
@@ -65,11 +65,11 @@ class LoweringBridge {
          const Fortran::lower::LoweringOptions &loweringOptions,
          const std::vector<Fortran::lower::EnvironmentDefault> &envDefaults,
          const Fortran::common::LanguageFeatureControl &languageFeatures,
-         const llvm::TargetMachine &targetMachine, llvm::StringRef tuneCPU) {
+         const llvm::TargetMachine &targetMachine) {
     return LoweringBridge(ctx, semanticsContext, defaultKinds, intrinsics,
                           targetCharacteristics, allCooked, triple, kindMap,
                           loweringOptions, envDefaults, languageFeatures,
-                          targetMachine, tuneCPU);
+                          targetMachine);
   }
 
   //===--------------------------------------------------------------------===//
@@ -148,7 +148,7 @@ class LoweringBridge {
       const Fortran::lower::LoweringOptions &loweringOptions,
       const std::vector<Fortran::lower::EnvironmentDefault> &envDefaults,
       const Fortran::common::LanguageFeatureControl &languageFeatures,
-      const llvm::TargetMachine &targetMachine, const llvm::StringRef tuneCPU);
+      const llvm::TargetMachine &targetMachine);
   LoweringBridge() = delete;
   LoweringBridge(const LoweringBridge &) = delete;
 

diff --git a/flang/include/flang/Optimizer/CodeGen/CGPasses.td b/flang/include/flang/Optimizer/CodeGen/CGPasses.td
@@ -31,8 +31,6 @@ def FIRToLLVMLowering : Pass<"fir-to-llvm-ir", "mlir::ModuleOp"> {
            "Override module's data layout.">,
     Option<"forcedTargetCPU", "target-cpu", "std::string", /*default=*/"",
            "Override module's target CPU.">,
-    Option<"forcedTuneCPU", "tune-cpu", "std::string", /*default=*/"",
-           "Override module's tune CPU.">,
     Option<"forcedTargetFeatures", "target-features", "std::string",
            /*default=*/"", "Override module's target features.">,
     Option<"applyTBAA", "apply-tbaa", "bool", /*default=*/"false",
@@ -70,8 +68,6 @@ def TargetRewritePass : Pass<"target-rewrite", "mlir::ModuleOp"> {
            "Override module's target triple.">,
     Option<"forcedTargetCPU", "target-cpu", "std::string", /*default=*/"",
            "Override module's target CPU.">,
-    Option<"forcedTuneCPU", "tune-cpu", "std::string", /*default=*/"",
-           "Override module's tune CPU.">,
     Option<"forcedTargetFeatures", "target-features", "std::string",
            /*default=*/"", "Override module's target features.">,
     Option<"noCharacterConversion", "no-character-conversion",

diff --git a/flang/include/flang/Optimizer/CodeGen/Target.h b/flang/include/flang/Optimizer/CodeGen/Target.h
@@ -76,29 +76,14 @@ class CodeGenSpecifics {
       llvm::StringRef targetCPU, mlir::LLVM::TargetFeaturesAttr targetFeatures,
       const mlir::DataLayout &dl);
 
-  static std::unique_ptr<CodeGenSpecifics>
-  get(mlir::MLIRContext *ctx, llvm::Triple &&trp, KindMapping &&kindMap,
-      llvm::StringRef targetCPU, mlir::LLVM::TargetFeaturesAttr targetFeatures,
-      const mlir::DataLayout &dl, llvm::StringRef tuneCPU);
-
   static TypeAndAttr getTypeAndAttr(mlir::Type t) { return TypeAndAttr{t, {}}; }
 
   CodeGenSpecifics(mlir::MLIRContext *ctx, llvm::Triple &&trp,
                    KindMapping &&kindMap, llvm::StringRef targetCPU,
                    mlir::LLVM::TargetFeaturesAttr targetFeatures,
                    const mlir::DataLayout &dl)
       : context{*ctx}, triple{std::move(trp)}, kindMap{std::move(kindMap)},
-        targetCPU{targetCPU}, targetFeatures{targetFeatures}, dataLayout{&dl},
-        tuneCPU{""} {}
-
-  CodeGenSpecifics(mlir::MLIRContext *ctx, llvm::Triple &&trp,
-                   KindMapping &&kindMap, llvm::StringRef targetCPU,
-                   mlir::LLVM::TargetFeaturesAttr targetFeatures,
-                   const mlir::DataLayout &dl, llvm::StringRef tuneCPU)
-      : context{*ctx}, triple{std::move(trp)}, kindMap{std::move(kindMap)},
-        targetCPU{targetCPU}, targetFeatures{targetFeatures}, dataLayout{&dl},
-        tuneCPU{tuneCPU} {}
-
+        targetCPU{targetCPU}, targetFeatures{targetFeatures}, dataLayout{&dl} {}
   CodeGenSpecifics() = delete;
   virtual ~CodeGenSpecifics() {}
 
@@ -180,7 +165,6 @@ class CodeGenSpecifics {
   virtual unsigned char getCIntTypeWidth() const = 0;
 
   llvm::StringRef getTargetCPU() const { return targetCPU; }
-  llvm::StringRef getTuneCPU() const { return tuneCPU; }
 
   mlir::LLVM::TargetFeaturesAttr getTargetFeatures() const {
     return targetFeatures;
@@ -198,7 +182,6 @@ class CodeGenSpecifics {
   llvm::StringRef targetCPU;
   mlir::LLVM::TargetFeaturesAttr targetFeatures;
   const mlir::DataLayout *dataLayout = nullptr;
-  llvm::StringRef tuneCPU;
 };
 
 } // namespace fir

diff --git a/flang/include/flang/Optimizer/Dialect/Support/FIRContext.h b/flang/include/flang/Optimizer/Dialect/Support/FIRContext.h
@@ -58,13 +58,6 @@ void setTargetCPU(mlir::ModuleOp mod, llvm::StringRef cpu);
 /// Get the target CPU string from the Module or return a null reference.
 llvm::StringRef getTargetCPU(mlir::ModuleOp mod);
 
-/// Set the tune CPU for the module. `cpu` must not be deallocated while
-/// module `mod` is still live.
-void setTuneCPU(mlir::ModuleOp mod, llvm::StringRef cpu);
-
-/// Get the tune CPU string from the Module or return a null reference.
-llvm::StringRef getTuneCPU(mlir::ModuleOp mod);
-
 /// Set the target features for the module.
 void setTargetFeatures(mlir::ModuleOp mod, llvm::StringRef features);
 

diff --git a/flang/include/flang/Optimizer/Transforms/Passes.td b/flang/include/flang/Optimizer/Transforms/Passes.td
@@ -411,9 +411,6 @@ def FunctionAttr : Pass<"function-attr", "mlir::func::FuncOp"> {
     Option<"unsafeFPMath", "unsafe-fp-math",
            "bool", /*default=*/"false",
            "Set the unsafe-fp-math attribute on functions in the module.">,
-    Option<"tuneCPU", "tune-cpu",
-           "llvm::StringRef", /*default=*/"llvm::StringRef{}",
-           "Set the tune-cpu attribute on functions in the module.">,
   ];
 }
 

diff --git a/flang/lib/Frontend/CompilerInvocation.cpp b/flang/lib/Frontend/CompilerInvocation.cpp
@@ -407,10 +407,6 @@ static void parseTargetArgs(TargetOptions &opts, llvm::opt::ArgList &args) {
           args.getLastArg(clang::driver::options::OPT_target_cpu))
     opts.cpu = a->getValue();
 
-  if (const llvm::opt::Arg *a =
-          args.getLastArg(clang::driver::options::OPT_tune_cpu))
-    opts.cpuToTuneFor = a->getValue();
-
   for (const llvm::opt::Arg *currentArg :
        args.filtered(clang::driver::options::OPT_target_feature))
     opts.featuresAsWritten.emplace_back(currentArg->getValue());

diff --git a/flang/lib/Frontend/FrontendActions.cpp b/flang/lib/Frontend/FrontendActions.cpp
@@ -297,8 +297,7 @@ bool CodeGenAction::beginSourceFileAction() {
       ci.getParsing().allCooked(), ci.getInvocation().getTargetOpts().triple,
       kindMap, ci.getInvocation().getLoweringOpts(),
       ci.getInvocation().getFrontendOpts().envDefaults,
-      ci.getInvocation().getFrontendOpts().features, targetMachine,
-      ci.getInvocation().getTargetOpts().cpuToTuneFor);
+      ci.getInvocation().getFrontendOpts().features, targetMachine);
 
   // Fetch module from lb, so we can set
   mlirModule = std::make_unique<mlir::ModuleOp>(lb.getModule());

diff --git a/flang/lib/Lower/Bridge.cpp b/flang/lib/Lower/Bridge.cpp
@@ -5929,7 +5929,7 @@ Fortran::lower::LoweringBridge::LoweringBridge(
     const Fortran::lower::LoweringOptions &loweringOptions,
     const std::vector<Fortran::lower::EnvironmentDefault> &envDefaults,
     const Fortran::common::LanguageFeatureControl &languageFeatures,
-    const llvm::TargetMachine &targetMachine, const llvm::StringRef tuneCPU)
+    const llvm::TargetMachine &targetMachine)
     : semanticsContext{semanticsContext}, defaultKinds{defaultKinds},
       intrinsics{intrinsics}, targetCharacteristics{targetCharacteristics},
       cooked{&cooked}, context{context}, kindMap{kindMap},
@@ -5986,7 +5986,6 @@ Fortran::lower::LoweringBridge::LoweringBridge(
   fir::setTargetTriple(*module.get(), triple);
   fir::setKindMapping(*module.get(), kindMap);
   fir::setTargetCPU(*module.get(), targetMachine.getTargetCPU());
-  fir::setTuneCPU(*module.get(), tuneCPU);
   fir::setTargetFeatures(*module.get(), targetMachine.getTargetFeatureString());
   fir::support::setMLIRDataLayout(*module.get(),
                                   targetMachine.createDataLayout());

diff --git a/flang/lib/Optimizer/CodeGen/CodeGen.cpp b/flang/lib/Optimizer/CodeGen/CodeGen.cpp
@@ -3618,9 +3618,6 @@ class FIRToLLVMLowering
     if (!forcedTargetCPU.empty())
       fir::setTargetCPU(mod, forcedTargetCPU);
 
-    if (!forcedTuneCPU.empty())
-      fir::setTuneCPU(mod, forcedTuneCPU);
-
     if (!forcedTargetFeatures.empty())
       fir::setTargetFeatures(mod, forcedTargetFeatures);
 
@@ -3717,8 +3714,7 @@ class FIRToLLVMLowering
       signalPassFailure();
     }
 
-    // Run pass to add comdats to functions that have weak linkage on relevant
-    // platforms
+    // Run pass to add comdats to functions that have weak linkage on relevant platforms
     if (fir::getTargetTriple(mod).supportsCOMDAT()) {
       mlir::OpPassManager comdatPM("builtin.module");
       comdatPM.addPass(mlir::LLVM::createLLVMAddComdats());

diff --git a/flang/lib/Optimizer/CodeGen/Target.cpp b/flang/lib/Optimizer/CodeGen/Target.cpp
@@ -1113,14 +1113,3 @@ fir::CodeGenSpecifics::get(mlir::MLIRContext *ctx, llvm::Triple &&trp,
   }
   TODO(mlir::UnknownLoc::get(ctx), "target not implemented");
 }
-
-std::unique_ptr<fir::CodeGenSpecifics> fir::CodeGenSpecifics::get(
-    mlir::MLIRContext *ctx, llvm::Triple &&trp, KindMapping &&kindMap,
-    llvm::StringRef targetCPU, mlir::LLVM::TargetFeaturesAttr targetFeatures,
-    const mlir::DataLayout &dl, llvm::StringRef tuneCPU) {
-  std::unique_ptr<fir::CodeGenSpecifics> CGS = fir::CodeGenSpecifics::get(
-      ctx, std::move(trp), std::move(kindMap), targetCPU, targetFeatures, dl);
-
-  CGS->tuneCPU = tuneCPU;
-  return CGS;
-}
diff --git a/flang/lib/Optimizer/CodeGen/TargetRewrite.cpp b/flang/lib/Optimizer/CodeGen/TargetRewrite.cpp
@@ -89,9 +89,6 @@ class TargetRewrite : public fir::impl::TargetRewritePassBase<TargetRewrite> {
     if (!forcedTargetCPU.empty())
       fir::setTargetCPU(mod, forcedTargetCPU);
 
-    if (!forcedTuneCPU.empty())
-      fir::setTuneCPU(mod, forcedTuneCPU);
-
     if (!forcedTargetFeatures.empty())
       fir::setTargetFeatures(mod, forcedTargetFeatures);
 
@@ -109,8 +106,7 @@ class TargetRewrite : public fir::impl::TargetRewritePassBase<TargetRewrite> {
 
     auto specifics = fir::CodeGenSpecifics::get(
         mod.getContext(), fir::getTargetTriple(mod), fir::getKindMapping(mod),
-        fir::getTargetCPU(mod), fir::getTargetFeatures(mod), *dl,
-        fir::getTuneCPU(mod));
+        fir::getTargetCPU(mod), fir::getTargetFeatures(mod), *dl);
 
     setMembers(specifics.get(), &rewriter, &*dl);
 
@@ -676,18 +672,12 @@ class TargetRewrite : public fir::impl::TargetRewritePassBase<TargetRewrite> {
     auto targetCPU = specifics->getTargetCPU();
     mlir::StringAttr targetCPUAttr =
         targetCPU.empty() ? nullptr : mlir::StringAttr::get(ctx, targetCPU);
-    auto tuneCPU = specifics->getTuneCPU();
-    mlir::StringAttr tuneCPUAttr =
-        tuneCPU.empty() ? nullptr : mlir::StringAttr::get(ctx, tuneCPU);
     auto targetFeaturesAttr = specifics->getTargetFeatures();
 
     for (auto fn : mod.getOps<mlir::func::FuncOp>()) {
       if (targetCPUAttr)
         fn->setAttr("target_cpu", targetCPUAttr);
 
-      if (tuneCPUAttr)
-        fn->setAttr("tune_cpu", tuneCPUAttr);
-
       if (targetFeaturesAttr)
         fn->setAttr("target_features", targetFeaturesAttr);
 

diff --git a/flang/lib/Optimizer/CodeGen/TypeConverter.cpp b/flang/lib/Optimizer/CodeGen/TypeConverter.cpp
@@ -35,8 +35,7 @@ LLVMTypeConverter::LLVMTypeConverter(mlir::ModuleOp module, bool applyTBAA,
       kindMapping(getKindMapping(module)),
       specifics(CodeGenSpecifics::get(
           module.getContext(), getTargetTriple(module), getKindMapping(module),
-          getTargetCPU(module), getTargetFeatures(module), dl,
-          getTuneCPU(module))),
+          getTargetCPU(module), getTargetFeatures(module), dl)),
       tbaaBuilder(std::make_unique<TBAABuilder>(module->getContext(), applyTBAA,
                                                 forceUnifiedTBAATree)),
       dataLayout{&dl} {

diff --git a/flang/lib/Optimizer/Dialect/Support/FIRContext.cpp b/flang/lib/Optimizer/Dialect/Support/FIRContext.cpp
@@ -77,24 +77,6 @@ llvm::StringRef fir::getTargetCPU(mlir::ModuleOp mod) {
   return {};
 }
 
-static constexpr const char *tuneCpuName = "fir.tune_cpu";
-
-void fir::setTuneCPU(mlir::ModuleOp mod, llvm::StringRef cpu) {
-  if (cpu.empty())
-    return;
-
-  auto *ctx = mod.getContext();
-
-  mod->setAttr(tuneCpuName, mlir::StringAttr::get(ctx, cpu));
-}
-
-llvm::StringRef fir::getTuneCPU(mlir::ModuleOp mod) {
-  if (auto attr = mod->getAttrOfType<mlir::StringAttr>(tuneCpuName))
-    return attr.getValue();
-
-  return {};
-}
-
 static constexpr const char *targetFeaturesName = "fir.target_features";
 
 void fir::setTargetFeatures(mlir::ModuleOp mod, llvm::StringRef features) {

diff --git a/flang/test/Driver/tune-cpu-fir.f90 b/flang/test/Driver/tune-cpu-fir.f90
diff --git a/flang/test/Lower/tune-cpu-llvm.f90 b/flang/test/Lower/tune-cpu-llvm.f90
diff --git a/flang/tools/bbc/bbc.cpp b/flang/tools/bbc/bbc.cpp
@@ -367,12 +367,11 @@ static mlir::LogicalResult convertFortranSourceToMLIR(
   loweringOptions.setLowerToHighLevelFIR(useHLFIR || emitHLFIR);
   loweringOptions.setNSWOnLoopVarInc(setNSW);
   std::vector<Fortran::lower::EnvironmentDefault> envDefaults = {};
-  constexpr const char *tuneCPU = "";
   auto burnside = Fortran::lower::LoweringBridge::create(
       ctx, semanticsContext, defKinds, semanticsContext.intrinsics(),
       semanticsContext.targetCharacteristics(), parsing.allCooked(),
       targetTriple, kindMap, loweringOptions, envDefaults,
-      semanticsContext.languageFeatures(), targetMachine, tuneCPU);
+      semanticsContext.languageFeatures(), targetMachine);
   mlir::ModuleOp mlirModule = burnside.getModule();
   if (enableOpenMP) {
     if (enableOpenMPGPU && !enableOpenMPDevice) {

diff --git a/flang/tools/tco/tco.cpp b/flang/tools/tco/tco.cpp
@@ -58,9 +58,6 @@ static cl::opt<std::string> targetTriple("target",
 static cl::opt<std::string>
     targetCPU("target-cpu", cl::desc("specify a target CPU"), cl::init(""));
 
-static cl::opt<std::string> tuneCPU("tune-cpu", cl::desc("specify a tune CPU"),
-                                    cl::init(""));
-
 static cl::opt<std::string>
     targetFeatures("target-features", cl::desc("specify the target features"),
                    cl::init(""));
@@ -116,7 +113,6 @@ compileFIR(const mlir::PassPipelineCLParser &passPipeline) {
   fir::setTargetTriple(*owningRef, targetTriple);
   fir::setKindMapping(*owningRef, kindMap);
   fir::setTargetCPU(*owningRef, targetCPU);
-  fir::setTuneCPU(*owningRef, tuneCPU);
   fir::setTargetFeatures(*owningRef, targetFeatures);
   // tco is a testing tool, so it will happily use the target independent
   // data layout if none is on the module.