rename -floop-fuse / -fexperimental-fuse-loops

sebpop · madhur13490 · commit cc3e9856f7f7 · 2025-07-29T21:50:01.000-07:00
diff --git a/clang/include/clang/Basic/CodeGenOptions.def b/clang/include/clang/Basic/CodeGenOptions.def
@@ -322,7 +322,7 @@ CODEGENOPT(TimeTrace         , 1, 0, Benign) ///< Set when -ftime-trace is enabl
 VALUE_CODEGENOPT(TimeTraceGranularity, 32, 500, Benign) ///< Minimum time granularity (in microseconds),
                                                         ///< traced by time profiler
 CODEGENOPT(InterchangeLoops  , 1, 0, Benign) ///< Run loop-interchange.
-CODEGENOPT(FuseLoops         , 1, 0, Benign) ///< Run loop-fuse.
+CODEGENOPT(FuseLoops         , 1, 0, Benign) ///< Run loop-fusion.
 CODEGENOPT(UnrollLoops       , 1, 0, Benign) ///< Control whether loops are unrolled.
 CODEGENOPT(RerollLoops       , 1, 0, Benign) ///< Control whether loops are rerolled.
 CODEGENOPT(NoUseJumpTables   , 1, 0, Benign) ///< Set when -fno-jump-tables is enabled.
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
@@ -4253,10 +4253,10 @@ def floop_interchange : Flag<["-"], "floop-interchange">, Group<f_Group>,
   HelpText<"Enable the loop interchange pass">, Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>;
 def fno_loop_interchange: Flag<["-"], "fno-loop-interchange">, Group<f_Group>,
   HelpText<"Disable the loop interchange pass">, Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>;
-def floop_fuse : Flag<["-"], "floop-fuse">, Group<f_Group>,
-  HelpText<"Enable the loop fuse pass">, Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>;
-def fno_loop_fuse: Flag<["-"], "fno-loop-fuse">, Group<f_Group>,
-  HelpText<"Disable the loop fuse pass">, Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>;
+def fexperimental_loop_fusion : Flag<["-"], "fexperimental-loop-fusion">, Group<f_Group>,
+  HelpText<"Enable the experimental loop fusion pass">, Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>;
+def fno_experimental_loop_fusion: Flag<["-"], "fno-experimental-loop-fusion">, Group<f_Group>,
+  HelpText<"Disable the experimental loop fusion pass">, Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>;
 def funroll_loops : Flag<["-"], "funroll-loops">, Group<f_Group>,
   HelpText<"Turn on loop unroller">, Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>;
 def fno_unroll_loops : Flag<["-"], "fno-unroll-loops">, Group<f_Group>,
diff --git a/clang/lib/CodeGen/BackendUtil.cpp b/clang/lib/CodeGen/BackendUtil.cpp
@@ -897,7 +897,7 @@ void EmitAssemblyHelper::RunOptimizationPipeline(
   PipelineTuningOptions PTO;
   PTO.LoopUnrolling = CodeGenOpts.UnrollLoops;
   PTO.LoopInterchange = CodeGenOpts.InterchangeLoops;
-  PTO.LoopFuse = CodeGenOpts.FuseLoops;
+  PTO.LoopFusion = CodeGenOpts.FuseLoops;
   // For historical reasons, loop interleaving is set to mirror setting for loop
   // unrolling.
   PTO.LoopInterleaving = CodeGenOpts.UnrollLoops;
@@ -1333,7 +1333,7 @@ runThinLTOBackend(CompilerInstance &CI, ModuleSummaryIndex *CombinedIndex,
   Conf.SampleProfile = std::move(SampleProfile);
   Conf.PTO.LoopUnrolling = CGOpts.UnrollLoops;
   Conf.PTO.LoopInterchange = CGOpts.InterchangeLoops;
-  Conf.PTO.LoopFuse = CGOpts.FuseLoops;
+  Conf.PTO.LoopFusion = CGOpts.FuseLoops;
   // For historical reasons, loop interleaving is set to mirror setting for loop
   // unrolling.
   Conf.PTO.LoopInterleaving = CGOpts.UnrollLoops;
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -6869,7 +6869,8 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
                   options::OPT_fno_unroll_loops);
   Args.AddLastArg(CmdArgs, options::OPT_floop_interchange,
                   options::OPT_fno_loop_interchange);
-  Args.AddLastArg(CmdArgs, options::OPT_floop_fuse, options::OPT_fno_loop_fuse);
+  Args.AddLastArg(CmdArgs, options::OPT_fexperimental_loop_fusion,
+                  options::OPT_fno_experimental_loop_fusion);
 
   Args.AddLastArg(CmdArgs, options::OPT_fstrict_flex_arrays_EQ);
 
diff --git a/clang/lib/Driver/ToolChains/CommonArgs.cpp b/clang/lib/Driver/ToolChains/CommonArgs.cpp
@@ -3265,7 +3265,7 @@ void tools::handleVectorizeSLPArgs(const ArgList &Args,
 
 void tools::handleInterchangeLoopsArgs(const ArgList &Args,
                                        ArgStringList &CmdArgs) {
-  // FIXME: Instead of relying on shouldEnableVectorizerAtOLevel, we may want to
+  // FIXME: instead of relying on shouldEnableVectorizerAtOLevel, we may want to
   // implement a separate function to infer loop interchange from opt level.
   // For now, enable loop-interchange at the same opt levels as loop-vectorize.
   bool EnableInterchange = shouldEnableVectorizerAtOLevel(Args, false);
diff --git a/clang/lib/Driver/ToolChains/Flang.cpp b/clang/lib/Driver/ToolChains/Flang.cpp
@@ -151,7 +151,8 @@ void Flang::addCodegenOptions(const ArgList &Args,
       !stackArrays->getOption().matches(options::OPT_fno_stack_arrays))
     CmdArgs.push_back("-fstack-arrays");
 
-  Args.AddLastArg(CmdArgs, options::OPT_floop_fuse, options::OPT_fno_loop_fuse);
+  Args.AddLastArg(CmdArgs, options::OPT_fexperimental_loop_fusion,
+                  options::OPT_fno_experimental_loop_fusion);
 
   handleInterchangeLoopsArgs(Args, CmdArgs);
   handleVectorizeLoopsArgs(Args, CmdArgs);
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -1672,9 +1672,9 @@ void CompilerInvocationBase::GenerateCodeGenArgs(const CodeGenOptions &Opts,
     GenerateArg(Consumer, OPT_fno_loop_interchange);
 
   if (Opts.FuseLoops)
-    GenerateArg(Consumer, OPT_floop_fuse);
+    GenerateArg(Consumer, OPT_fexperimental_loop_fusion);
   else
-    GenerateArg(Consumer, OPT_fno_loop_fuse);
+    GenerateArg(Consumer, OPT_fno_experimental_loop_fusion);
 
   if (!Opts.BinutilsVersion.empty())
     GenerateArg(Consumer, OPT_fbinutils_version_EQ, Opts.BinutilsVersion);
@@ -1996,7 +1996,8 @@ bool CompilerInvocation::ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args,
                    (Opts.OptimizationLevel > 1));
   Opts.InterchangeLoops =
       Args.hasFlag(OPT_floop_interchange, OPT_fno_loop_interchange, false);
-  Opts.FuseLoops = Args.hasFlag(OPT_floop_fuse, OPT_fno_loop_fuse, false);
+  Opts.FuseLoops = Args.hasFlag(OPT_fexperimental_loop_fusion,
+                                OPT_fno_experimental_loop_fusion, false);
   Opts.BinutilsVersion =
       std::string(Args.getLastArgValue(OPT_fbinutils_version_EQ));
 
diff --git a/clang/test/Driver/clang_f_opts.c b/clang/test/Driver/clang_f_opts.c
@@ -52,12 +52,12 @@
 // CHECK-INTERCHANGE-LOOPS: "-floop-interchange"
 // CHECK-NO-INTERCHANGE-LOOPS: "-fno-loop-interchange"
 
-// RUN: %clang -### -S -floop-fuse %s 2>&1 | FileCheck -check-prefix=CHECK-FUSE-LOOPS %s
-// RUN: %clang -### -S -fno-loop-fuse %s 2>&1 | FileCheck -check-prefix=CHECK-NO-FUSE-LOOPS %s
-// RUN: %clang -### -S -fno-loop-fuse -floop-fuse %s 2>&1 | FileCheck -check-prefix=CHECK-FUSE-LOOPS %s
-// RUN: %clang -### -S -floop-fuse -fno-loop-fuse %s 2>&1 | FileCheck -check-prefix=CHECK-NO-FUSE-LOOPS %s
-// CHECK-FUSE-LOOPS: "-floop-fuse"
-// CHECK-NO-FUSE-LOOPS: "-fno-loop-fuse"
+// RUN: %clang -### -S -fexperimental-loop-fusion %s 2>&1 | FileCheck -check-prefix=CHECK-FUSE-LOOPS %s
+// RUN: %clang -### -S -fno-experimental-loop-fusion %s 2>&1 | FileCheck -check-prefix=CHECK-NO-FUSE-LOOPS %s
+// RUN: %clang -### -S -fno-experimental-loop-fusion -fexperimental-loop-fusion %s 2>&1 | FileCheck -check-prefix=CHECK-FUSE-LOOPS %s
+// RUN: %clang -### -S -fexperimental-loop-fusion -fno-experimental-loop-fusion %s 2>&1 | FileCheck -check-prefix=CHECK-NO-FUSE-LOOPS %s
+// CHECK-FUSE-LOOPS: "-fexperimental-loop-fusion"
+// CHECK-NO-FUSE-LOOPS: "-fno-experimental-loop-fusion"
 
 // RUN: %clang -### -S -fprofile-sample-accurate %s 2>&1 | FileCheck -check-prefix=CHECK-PROFILE-SAMPLE-ACCURATE %s
 // CHECK-PROFILE-SAMPLE-ACCURATE: "-fprofile-sample-accurate"
diff --git a/flang/docs/ReleaseNotes.md b/flang/docs/ReleaseNotes.md
@@ -32,9 +32,7 @@ page](https://llvm.org/releases/).
 
 ## New Compiler Flags
 
-* -floop-interchange is now recognized by flang.
-* -floop-interchange is enabled by default at -O2 and above.
-* -floop-fuse is now recognized by flang.
+* -fexperimental-loop-fusion is now recognized by flang.
 
 ## Windows Support
 
diff --git a/flang/lib/Frontend/CompilerInvocation.cpp b/flang/lib/Frontend/CompilerInvocation.cpp
@@ -275,7 +275,7 @@ static void parseCodeGenArgs(Fortran::frontend::CodeGenOptions &opts,
   if (args.getLastArg(clang::driver::options::OPT_floop_interchange))
     opts.InterchangeLoops = 1;
 
-  if (args.getLastArg(clang::driver::options::OPT_floop_fuse))
+  if (args.getLastArg(clang::driver::options::OPT_fexperimental_loop_fusion))
     opts.FuseLoops = 1;
 
   if (args.getLastArg(clang::driver::options::OPT_vectorize_loops))
diff --git a/flang/lib/Frontend/FrontendActions.cpp b/flang/lib/Frontend/FrontendActions.cpp
@@ -951,7 +951,7 @@ void CodeGenAction::runOptimizationPipeline(llvm::raw_pwrite_stream &os) {
     si.getTimePasses().setOutStream(ci.getTimingStreamLLVM());
   pto.LoopUnrolling = opts.UnrollLoops;
   pto.LoopInterchange = opts.InterchangeLoops;
-  pto.LoopFuse = opts.FuseLoops;
+  pto.LoopFusion = opts.FuseLoops;
   pto.LoopInterleaving = opts.UnrollLoops;
   pto.LoopVectorization = opts.VectorizeLoop;
   pto.SLPVectorization = opts.VectorizeSLP;
diff --git a/flang/test/Driver/loop-fuse.f90 b/flang/test/Driver/loop-fuse.f90
@@ -1,15 +1,15 @@
-! RUN: %flang -### -S -floop-fuse %s 2>&1 | FileCheck -check-prefix=CHECK-LOOP-FUSE %s
-! RUN: %flang -### -S -fno-loop-fuse %s 2>&1 | FileCheck -check-prefix=CHECK-NO-LOOP-FUSE %s
+! RUN: %flang -### -S -fexperimental-loop-fusion %s 2>&1 | FileCheck -check-prefix=CHECK-LOOP-FUSE %s
+! RUN: %flang -### -S -fno-experimental-loop-fusion %s 2>&1 | FileCheck -check-prefix=CHECK-NO-LOOP-FUSE %s
 ! RUN: %flang -### -S -O0 %s 2>&1 | FileCheck -check-prefix=CHECK-NO-LOOP-FUSE %s
 ! RUN: %flang -### -S -O1 %s 2>&1 | FileCheck -check-prefix=CHECK-NO-LOOP-FUSE %s
 ! RUN: %flang -### -S -O2 %s 2>&1 | FileCheck -check-prefix=CHECK-NO-LOOP-FUSE %s
 ! RUN: %flang -### -S -O3 %s 2>&1 | FileCheck -check-prefix=CHECK-NO-LOOP-FUSE %s
 ! RUN: %flang -### -S -Os %s 2>&1 | FileCheck -check-prefix=CHECK-NO-LOOP-FUSE %s
 ! RUN: %flang -### -S -Oz %s 2>&1 | FileCheck -check-prefix=CHECK-NO-LOOP-FUSE %s
-! CHECK-LOOP-FUSE: "-floop-fuse"
-! CHECK-NO-LOOP-FUSE-NOT: "-floop-fuse"
-! RUN: %flang_fc1 -emit-llvm -O2 -floop-fuse -mllvm -print-pipeline-passes -o /dev/null %s 2>&1 | FileCheck -check-prefix=CHECK-LOOP-FUSE-PASS %s
-! RUN: %flang_fc1 -emit-llvm -O2 -fno-loop-fuse -mllvm -print-pipeline-passes -o /dev/null %s 2>&1 | FileCheck -check-prefix=CHECK-NO-LOOP-FUSE-PASS %s
+! CHECK-LOOP-FUSE: "-fexperimental-loop-fusion"
+! CHECK-NO-LOOP-FUSE-NOT: "-fexperimental-loop-fusion"
+! RUN: %flang_fc1 -emit-llvm -O2 -fexperimental-loop-fusion -mllvm -print-pipeline-passes -o /dev/null %s 2>&1 | FileCheck -check-prefix=CHECK-LOOP-FUSE-PASS %s
+! RUN: %flang_fc1 -emit-llvm -O2 -fno-experimental-loop-fusion -mllvm -print-pipeline-passes -o /dev/null %s 2>&1 | FileCheck -check-prefix=CHECK-NO-LOOP-FUSE-PASS %s
 ! CHECK-LOOP-FUSE-PASS: loop-fusion
 ! CHECK-NO-LOOP-FUSE-PASS-NOT: loop-fusion
 
diff --git a/llvm/include/llvm/Passes/PassBuilder.h b/llvm/include/llvm/Passes/PassBuilder.h
@@ -65,8 +65,8 @@ class PipelineTuningOptions {
   /// false.
   bool LoopInterchange;
 
-  /// Tuning option to enable/disable loop fuse. Its default value is false.
-  bool LoopFuse;
+  /// Tuning option to enable/disable loop fusion. Its default value is false.
+  bool LoopFusion;
 
   /// Tuning option to forget all SCEV loops in LoopUnroll. Its default value
   /// is that of the flag: `-forget-scev-loop-unroll`.
diff --git a/llvm/lib/Passes/PassBuilderPipelines.cpp b/llvm/lib/Passes/PassBuilderPipelines.cpp
@@ -205,9 +205,9 @@ static cl::opt<bool>
     EnableLoopInterchange("enable-loopinterchange", cl::init(false), cl::Hidden,
                           cl::desc("Enable the LoopInterchange Pass"));
 
-static cl::opt<bool> EnableLoopFuse("enable-loopfuse", cl::init(false),
-                                    cl::Hidden,
-                                    cl::desc("Enable the LoopFuse Pass"));
+static cl::opt<bool> EnableLoopFusion("enable-loopfusion", cl::init(false),
+                                      cl::Hidden,
+                                      cl::desc("Enable the LoopFusion Pass"));
 
 static cl::opt<bool> EnableUnrollAndJam("enable-unroll-and-jam",
                                         cl::init(false), cl::Hidden,
@@ -318,7 +318,7 @@ PipelineTuningOptions::PipelineTuningOptions() {
   SLPVectorization = false;
   LoopUnrolling = true;
   LoopInterchange = EnableLoopInterchange;
-  LoopFuse = EnableLoopFuse;
+  LoopFusion = EnableLoopFusion;
   ForgetAllSCEVInLoopUnroll = ForgetSCEVInLoopUnroll;
   LicmMssaOptCap = SetLicmMssaOptCap;
   LicmMssaNoAccForPromotionCap = SetLicmMssaNoAccForPromotionCap;
@@ -520,9 +520,6 @@ PassBuilder::buildO1FunctionSimplificationPipeline(OptimizationLevel Level,
 
   invokeLoopOptimizerEndEPCallbacks(LPM2, Level);
 
-  if (PTO.LoopFuse)
-    FPM.addPass(LoopFusePass());
-
   FPM.addPass(createFunctionToLoopPassAdaptor(std::move(LPM1),
                                               /*UseMemorySSA=*/true,
                                               /*UseBlockFrequencyInfo=*/true));
@@ -647,6 +644,9 @@ PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
   if (EnableConstraintElimination)
     FPM.addPass(ConstraintEliminationPass());
 
+  if (PTO.LoopFusion)
+    FPM.addPass(LoopFusePass());
+
   // Add the primary loop simplification pipeline.
   // FIXME: Currently this is split into two loop pass pipelines because we run
   // some function passes in between them. These can and should be removed
@@ -712,9 +712,6 @@ PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
 
   invokeLoopOptimizerEndEPCallbacks(LPM2, Level);
 
-  if (PTO.LoopFuse)
-    FPM.addPass(LoopFusePass());
-
   FPM.addPass(createFunctionToLoopPassAdaptor(std::move(LPM1),
                                               /*UseMemorySSA=*/true,
                                               /*UseBlockFrequencyInfo=*/true));
@@ -2127,6 +2124,7 @@ PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level,
     LPM.addPass(LoopFlattenPass());
   LPM.addPass(IndVarSimplifyPass());
   LPM.addPass(LoopDeletionPass());
+  // FIXME: Add loop interchange.
 
   // Unroll small loops and perform peeling.
   LPM.addPass(LoopFullUnrollPass(Level.getSpeedupLevel(),
@@ -2366,4 +2364,4 @@ AAManager PassBuilder::buildDefaultAAPipeline() {
 bool PassBuilder::isInstrumentedPGOUse() const {
   return (PGOOpt && PGOOpt->Action == PGOOptions::IRUse) ||
          !UseCtxProfile.empty();
-}
+}
