[flang] Lower omp.workshare to other omp constructs

Change to workshare loop wrapper op

Move single op declaration

Schedule pass properly

Correctly handle nested nested loop nests to be parallelized by workshare

Leave comments for shouldUseWorkshareLowering

Use copyprivate to scatter val from omp.single

TODO still need to implement copy function
TODO transitive check for usage outside of omp.single not imiplemented yet

Transitively check for users outisde of single op

TODO need to implement copy func
TODO need to hoist allocas outside of single regions

Add tests

Hoist allocas

More tests

Emit body for copy func

Test the tmp storing logic

Clean up trivially dead ops

Only handle single-block regions for now

Fix tests for custom assembly for loop wrapper

Only run the lower workshare pass if openmp is enabled

Implement some missing functionality

Fix tests

Fix test

Iterate backwards to find all trivially dead ops

Add expalanation comment for createCopyFun

Update test

Author: ivanradanov

flang/include/flang/Optimizer/OpenMP/Passes.h

@@ -25,6 +25,11 @@ namespace flangomp {
 #define GEN_PASS_REGISTRATION
 #include "flang/Optimizer/OpenMP/Passes.h.inc"
 
+/// Impelements the logic specified in the 2.8.3  workshare Construct section of
+/// the OpenMP standard which specifies what statements or constructs shall be
+/// divided into units of work.
+bool shouldUseWorkshareLowering(mlir::Operation *op);
+
 } // namespace flangomp
 
 #endif // FORTRAN_OPTIMIZER_OPENMP_PASSES_H

flang/include/flang/Optimizer/OpenMP/Passes.td

@@ -37,4 +37,9 @@ def FunctionFiltering : Pass<"omp-function-filtering"> {
   ];
 }
 
+// Needs to be scheduled on Module as we create functions in it
+def LowerWorkshare : Pass<"lower-workshare", "::mlir::ModuleOp"> {
+  let summary = "Lower workshare construct";
+}
+
 #endif //FORTRAN_OPTIMIZER_OPENMP_PASSES

flang/include/flang/Tools/CLOptions.inc

@@ -337,7 +337,7 @@ inline void createDefaultFIROptimizerPassPipeline(
 /// \param optLevel - optimization level used for creating FIR optimization
 ///   passes pipeline
 inline void createHLFIRToFIRPassPipeline(
-    mlir::PassManager &pm, llvm::OptimizationLevel optLevel = defaultOptLevel) {
+    mlir::PassManager &pm, bool enableOpenMP, llvm::OptimizationLevel optLevel = defaultOptLevel) {
   if (optLevel.isOptimizingForSpeed()) {
     addCanonicalizerPassWithoutRegionSimplification(pm);
     addNestedPassToAllTopLevelOperations(
@@ -354,6 +354,8 @@ inline void createHLFIRToFIRPassPipeline(
   pm.addPass(hlfir::createLowerHLFIRIntrinsics());
   pm.addPass(hlfir::createBufferizeHLFIR());
   pm.addPass(hlfir::createConvertHLFIRtoFIR());
+  if (enableOpenMP)
+    pm.addPass(flangomp::createLowerWorkshare());
 }
 
 /// Create a pass pipeline for handling certain OpenMP transformations needed
@@ -425,7 +427,7 @@ inline void createDefaultFIRCodeGenPassPipeline(mlir::PassManager &pm,
 ///   passes pipeline
 inline void createMLIRToLLVMPassPipeline(mlir::PassManager &pm,
     MLIRToLLVMPassPipelineConfig &config, llvm::StringRef inputFilename = {}) {
-  fir::createHLFIRToFIRPassPipeline(pm, config.OptLevel);
+  fir::createHLFIRToFIRPassPipeline(pm, config.EnableOpenMP, config.OptLevel);
 
   // Add default optimizer pass pipeline.
   fir::createDefaultFIROptimizerPassPipeline(pm, config);

flang/include/flang/Tools/CrossToolHelpers.h

@@ -123,6 +123,7 @@ struct MLIRToLLVMPassPipelineConfig : public FlangEPCallBacks {
       false; ///< Set no-signed-zeros-fp-math attribute for functions.
   bool UnsafeFPMath = false; ///< Set unsafe-fp-math attribute for functions.
   bool NSWOnLoopVarInc = false; ///< Add nsw flag to loop variable increments.
+  bool EnableOpenMP = false; ///< Enable OpenMP lowering.
 };
 
 struct OffloadModuleOpts {

flang/lib/Frontend/FrontendActions.cpp

@@ -711,7 +711,11 @@ void CodeGenAction::lowerHLFIRToFIR() {
   pm.enableVerifier(/*verifyPasses=*/true);
 
   // Create the pass pipeline
-  fir::createHLFIRToFIRPassPipeline(pm, level);
+  fir::createHLFIRToFIRPassPipeline(
+      pm,
+      ci.getInvocation().getFrontendOpts().features.IsEnabled(
+          Fortran::common::LanguageFeature::OpenMP),
+      level);
   (void)mlir::applyPassManagerCLOptions(pm);
 
   if (!mlir::succeeded(pm.run(*mlirModule))) {
@@ -824,6 +828,10 @@ void CodeGenAction::generateLLVMIR() {
     config.VScaleMax = vsr->second;
   }
 
+  if (ci.getInvocation().getFrontendOpts().features.IsEnabled(
+          Fortran::common::LanguageFeature::OpenMP))
+    config.EnableOpenMP = true;
+
   if (ci.getInvocation().getLoweringOpts().getNSWOnLoopVarInc())
     config.NSWOnLoopVarInc = true;
 

flang/lib/Optimizer/OpenMP/CMakeLists.txt

@@ -4,6 +4,7 @@ add_flang_library(FlangOpenMPTransforms
   FunctionFiltering.cpp
   MapInfoFinalization.cpp
   MarkDeclareTarget.cpp
+  LowerWorkshare.cpp
 
   DEPENDS
   FIRDialect