[Mlir-commits] [mlir] [Flang][OpenMP][MLIR] Initial array section mapping MLIR -> LLVM-IR lowering utilising omp.bounds (PR #68689)

[Kiran Chandramohan]

================
@@ -2001,61 +2100,204 @@ static bool targetOpSupported(Operation &opInst) {
 }
 
 static void
-handleDeclareTargetMapVar(llvm::ArrayRef<Value> mapOperands,
+handleDeclareTargetMapVar(MapInfoData &mapData,
                           LLVM::ModuleTranslation &moduleTranslation,
                           llvm::IRBuilderBase &builder) {
-  for (const mlir::Value &mapOp : mapOperands) {
-    auto mapInfoOp =
-        mlir::dyn_cast<mlir::omp::MapInfoOp>(mapOp.getDefiningOp());
-    llvm::Value *mapOpValue =
-        moduleTranslation.lookupValue(mapInfoOp.getVarPtr());
-    if (auto *declareTarget = getRefPtrIfDeclareTarget(mapInfoOp.getVarPtr(),
-                                                       moduleTranslation)) {
-      // The user's iterator will get invalidated if we modify an element,
+  for (size_t i = 0; i < mapData.MapClause.size(); ++i) {
+    // In the case of declare target mapped variables, the basePointer is
+    // the reference pointer generated by the convertDeclareTargetAttr
+    // method. Whereas the kernelValue is the original variable, so for
+    // the device we must replace all uses of this original global variable
+    // (stored in kernelValue) with the reference pointer (stored in
+    // basePointer for declare target mapped variables), as for device the
+    // data is mapped into this reference pointer and should be loaded
+    // from it, the original variable is discarded. On host both exist and
+    // metadata is generated (elsewhere in the convertDeclareTargetAttr)
+    // function to link the two variables in the runtime and then both the
+    // reference pointer and the pointer are assigned in the kernel argument
+    // structure for the host.
+    if (mapData.IsDeclareTarget[i]) {
+      // The users iterator will get invalidated if we modify an element,
       // so we populate this vector of uses to alter each user on an individual
       // basis to emit its own load (rather than one load for all).
       llvm::SmallVector<llvm::User *> userVec;
-      for (llvm::User *user : mapOpValue->users())
+      for (llvm::User *user : mapData.OriginalValue[i]->users())
         userVec.push_back(user);
 
       for (llvm::User *user : userVec) {
         if (auto *insn = dyn_cast<llvm::Instruction>(user)) {
-          auto *load = builder.CreateLoad(
-              moduleTranslation.convertType(mapInfoOp.getVarPtr().getType()),
-              declareTarget);
+          auto *load = builder.CreateLoad(mapData.BasePointers[i]->getType(),
+                                          mapData.BasePointers[i]);
           load->moveBefore(insn);
-          user->replaceUsesOfWith(mapOpValue, load);
+          user->replaceUsesOfWith(mapData.OriginalValue[i], load);
         }
       }
     }
   }
 }
 
+// This currently implements a very light version of Clang's
+// EmitParmDecl's handling of direct argument handling as well
+// as a portion of the argument access generation based on
+// capture types found at the end of emitOutlinedFunctionPrologue
+// in Clang. The indirect path handling of EmitParmDecl's may be
+// required for future work, but a direct 1-to-1 copy doesn't seem
+// possible as the logic is rather scattered throughout Clang's
+// lowering and perhaps we wish to deviate slightly.
 static llvm::IRBuilderBase::InsertPoint
-createDeviceArgumentAccessor(llvm::Argument &arg, llvm::Value *input,
-                             llvm::Value *&retVal, llvm::IRBuilderBase &builder,
+createDeviceArgumentAccessor(MapInfoData &mapData, llvm::Argument &arg,
+                             llvm::Value *input, llvm::Value *&retVal,
+                             llvm::IRBuilderBase &builder,
                              llvm::OpenMPIRBuilder &ompBuilder,
                              LLVM::ModuleTranslation &moduleTranslation,
                              llvm::IRBuilderBase::InsertPoint allocaIP,
                              llvm::IRBuilderBase::InsertPoint codeGenIP) {
   builder.restoreIP(allocaIP);
 
-  llvm::Value *addr =
+  mlir::omp::VariableCaptureKind capture =
+      mlir::omp::VariableCaptureKind::ByRef;
+  llvm::Type *inputType = input->getType();
+
+  // Find the associated MapInfoData entry for the current input
+  for (size_t i = 0; i < mapData.MapClause.size(); ++i)
+    if (mapData.OriginalValue[i] == input) {
+      if (auto mapOp = mlir::dyn_cast_if_present<mlir::omp::MapInfoOp>(
+              mapData.MapClause[i])) {
+        capture = mapOp.getMapCaptureType().value_or(
----------------
kiranchandramohan wrote:

Ok. And this is specifically doing this for `input`. This function will be easier to read with a description based on the following three inputs/outpts.
```
llvm::Argument &arg,
llvm::Value *input
llvm::Value *&retVal
```

https://github.com/llvm/llvm-project/pull/68689