add -floop-fuse to clang and flang

clang/include/clang/Basic/CodeGenOptions.def

@@ -326,6 +326,7 @@ CODEGENOPT(TimeTrace         , 1, 0) ///< Set when -ftime-trace is enabled.
 VALUE_CODEGENOPT(TimeTraceGranularity, 32, 500) ///< Minimum time granularity (in microseconds),
                                                ///< traced by time profiler
 CODEGENOPT(InterchangeLoops  , 1, 0) ///< Run loop-interchange.
+CODEGENOPT(FuseLoops         , 1, 0) ///< Run loop-fuse.
 CODEGENOPT(UnrollLoops       , 1, 0) ///< Control whether loops are unrolled.
 CODEGENOPT(RerollLoops       , 1, 0) ///< Control whether loops are rerolled.
 CODEGENOPT(NoUseJumpTables   , 1, 0) ///< Set when -fno-jump-tables is enabled.

clang/include/clang/Driver/Options.td

@@ -4189,6 +4189,10 @@ 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<["-"], "fexperimental-fuse-loops">, Group<f_Group>,
+  HelpText<"Enable the loop fuse pass">, Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>;
+def fno_loop_fuse: Flag<["-"], "fno-experimental-fuse-loops">, Group<f_Group>,
+  HelpText<"Disable the loop fuse 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>,

clang/lib/CodeGen/BackendUtil.cpp

@@ -898,6 +898,7 @@ void EmitAssemblyHelper::RunOptimizationPipeline(
   PipelineTuningOptions PTO;
   PTO.LoopUnrolling = CodeGenOpts.UnrollLoops;
   PTO.LoopInterchange = CodeGenOpts.InterchangeLoops;
+  PTO.LoopFuse = CodeGenOpts.FuseLoops;
   // For historical reasons, loop interleaving is set to mirror setting for loop
   // unrolling.
   PTO.LoopInterleaving = CodeGenOpts.UnrollLoops;
@@ -1339,6 +1340,7 @@ 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;
   // For historical reasons, loop interleaving is set to mirror setting for loop
   // unrolling.
   Conf.PTO.LoopInterleaving = CGOpts.UnrollLoops;

clang/lib/Driver/ToolChains/Clang.cpp

@@ -7030,6 +7030,7 @@ 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_fstrict_flex_arrays_EQ);
 

clang/lib/Driver/ToolChains/CommonArgs.cpp

@@ -3157,7 +3157,7 @@ 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);

clang/lib/Driver/ToolChains/Flang.cpp

@@ -151,6 +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);
+
   handleInterchangeLoopsArgs(Args, CmdArgs);
   handleVectorizeLoopsArgs(Args, CmdArgs);
   handleVectorizeSLPArgs(Args, CmdArgs);

clang/lib/Frontend/CompilerInvocation.cpp

@@ -1648,6 +1648,11 @@ void CompilerInvocationBase::GenerateCodeGenArgs(const CodeGenOptions &Opts,
   else
     GenerateArg(Consumer, OPT_fno_loop_interchange);
 
+  if (Opts.FuseLoops)
+    GenerateArg(Consumer, OPT_floop_fuse);
+  else
+    GenerateArg(Consumer, OPT_fno_loop_fuse);
+
   if (!Opts.BinutilsVersion.empty())
     GenerateArg(Consumer, OPT_fbinutils_version_EQ, Opts.BinutilsVersion);
 
@@ -1963,6 +1968,7 @@ 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.BinutilsVersion =
       std::string(Args.getLastArgValue(OPT_fbinutils_version_EQ));
 

clang/test/Driver/clang_f_opts.c

@@ -52,6 +52,13 @@
 // CHECK-INTERCHANGE-LOOPS: "-floop-interchange"
 // CHECK-NO-INTERCHANGE-LOOPS: "-fno-loop-interchange"
 
+// RUN: %clang -### -S -fexperimental-fuse-loops %s 2>&1 | FileCheck -check-prefix=CHECK-FUSE-LOOPS %s
+// RUN: %clang -### -S -fno-experimental-fuse-loops %s 2>&1 | FileCheck -check-prefix=CHECK-NO-FUSE-LOOPS %s
+// RUN: %clang -### -S -fno-experimental-fuse-loops -fexperimental-fuse-loops %s 2>&1 | FileCheck -check-prefix=CHECK-FUSE-LOOPS %s
+// RUN: %clang -### -S -fexperimental-fuse-loops -fno-experimental-fuse-loops %s 2>&1 | FileCheck -check-prefix=CHECK-NO-FUSE-LOOPS %s
+// CHECK-FUSE-LOOPS: "-fexperimental-fuse-loops"
+// CHECK-NO-FUSE-LOOPS: "-fno-experimental-fuse-loops"
+
 // RUN: %clang -### -S -fprofile-sample-accurate %s 2>&1 | FileCheck -check-prefix=CHECK-PROFILE-SAMPLE-ACCURATE %s
 // CHECK-PROFILE-SAMPLE-ACCURATE: "-fprofile-sample-accurate"
 

flang/docs/ReleaseNotes.md

@@ -34,6 +34,7 @@ page](https://llvm.org/releases/).
 
 * -floop-interchange is now recognized by flang.
 * -floop-interchange is enabled by default at -O2 and above.
+* -fexperimental-fuse-loops is now recognized by flang.
 
 ## Windows Support
 

flang/include/flang/Frontend/CodeGenOptions.def

@@ -36,6 +36,7 @@ CODEGENOPT(StackArrays, 1, 0) ///< -fstack-arrays (enable the stack-arrays pass)
 CODEGENOPT(VectorizeLoop, 1, 0) ///< Enable loop vectorization.
 CODEGENOPT(VectorizeSLP, 1, 0) ///< Enable SLP vectorization.
 CODEGENOPT(InterchangeLoops, 1, 0) ///< Enable loop interchange.
+CODEGENOPT(FuseLoops, 1, 0)        ///< Enable loop fuse.
 CODEGENOPT(LoopVersioning, 1, 0) ///< Enable loop versioning.
 CODEGENOPT(UnrollLoops, 1, 0) ///< Enable loop unrolling
 CODEGENOPT(AliasAnalysis, 1, 0) ///< Enable alias analysis pass

flang/lib/Frontend/CompilerInvocation.cpp

@@ -273,6 +273,9 @@ 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))
+    opts.FuseLoops = 1;
+
   if (args.getLastArg(clang::driver::options::OPT_vectorize_loops))
     opts.VectorizeLoop = 1;
 

flang/lib/Frontend/FrontendActions.cpp

@@ -925,6 +925,7 @@ 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.LoopInterleaving = opts.UnrollLoops;
   pto.LoopVectorization = opts.VectorizeLoop;
   pto.SLPVectorization = opts.VectorizeSLP;

flang/test/Driver/loop-fuse.f90

@@ -0,0 +1,17 @@
+! RUN: %flang -### -S -fexperimental-fuse-loops %s 2>&1 | FileCheck -check-prefix=CHECK-LOOP-FUSE %s
+! RUN: %flang -### -S -fno-experimental-fuse-loops %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: "-fexperimental-fuse-loops"
+! CHECK-NO-LOOP-FUSE-NOT: "-fexperimental-fuse-loops"
+! RUN: %flang_fc1 -emit-llvm -O2 -fexperimental-fuse-loops -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-fuse-loops -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
+
+program test
+end program

llvm/include/llvm/Passes/PassBuilder.h

@@ -64,6 +64,9 @@ class PipelineTuningOptions {
   /// false.
   bool LoopInterchange;
 
+  /// Tuning option to enable/disable loop fuse. Its default value is false.
+  bool LoopFuse;
+
   /// Tuning option to forget all SCEV loops in LoopUnroll. Its default value
   /// is that of the flag: `-forget-scev-loop-unroll`.
   bool ForgetAllSCEVInLoopUnroll;

llvm/lib/Passes/PassBuilderPipelines.cpp

@@ -104,6 +104,7 @@
 #include "llvm/Transforms/Scalar/LoopDeletion.h"
 #include "llvm/Transforms/Scalar/LoopDistribute.h"
 #include "llvm/Transforms/Scalar/LoopFlatten.h"
+#include "llvm/Transforms/Scalar/LoopFuse.h"
 #include "llvm/Transforms/Scalar/LoopIdiomRecognize.h"
 #include "llvm/Transforms/Scalar/LoopInstSimplify.h"
 #include "llvm/Transforms/Scalar/LoopInterchange.h"
@@ -205,6 +206,10 @@ 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> EnableUnrollAndJam("enable-unroll-and-jam",
                                         cl::init(false), cl::Hidden,
                                         cl::desc("Enable Unroll And Jam Pass"));
@@ -314,6 +319,7 @@ PipelineTuningOptions::PipelineTuningOptions() {
   SLPVectorization = false;
   LoopUnrolling = true;
   LoopInterchange = EnableLoopInterchange;
+  LoopFuse = EnableLoopFuse;
   ForgetAllSCEVInLoopUnroll = ForgetSCEVInLoopUnroll;
   LicmMssaOptCap = SetLicmMssaOptCap;
   LicmMssaNoAccForPromotionCap = SetLicmMssaNoAccForPromotionCap;
@@ -518,6 +524,9 @@ PassBuilder::buildO1FunctionSimplificationPipeline(OptimizationLevel Level,
 
   invokeLoopOptimizerEndEPCallbacks(LPM2, Level);
 
+  if (PTO.LoopFuse)
+    FPM.addPass(LoopFusePass());
+
   FPM.addPass(createFunctionToLoopPassAdaptor(std::move(LPM1),
                                               /*UseMemorySSA=*/true,
                                               /*UseBlockFrequencyInfo=*/true));
@@ -709,6 +718,9 @@ PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
 
   invokeLoopOptimizerEndEPCallbacks(LPM2, Level);
 
+  if (PTO.LoopFuse)
+    FPM.addPass(LoopFusePass());
+
   FPM.addPass(createFunctionToLoopPassAdaptor(std::move(LPM1),
                                               /*UseMemorySSA=*/true,
                                               /*UseBlockFrequencyInfo=*/true));
@@ -2112,7 +2124,6 @@ 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(),