[Mlir-commits] [mlir] [MLIR][OpenMP] Skip host omp ops when compiling for the target device (PR #85239)

[Jan Leyonberg]

================
@@ -2922,6 +2922,178 @@ convertDeclareTargetAttr(Operation *op, mlir::omp::DeclareTargetAttr attribute,
   return success();
 }
 
+static bool isInternalTargetDeviceOp(Operation *op) {
+  // Assumes no reverse offloading
+  if (op->getParentOfType<omp::TargetOp>())
+    return true;
+
+  auto parentFn = op->getParentOfType<LLVM::LLVMFuncOp>();
+  if (auto declareTargetIface =
+          llvm::dyn_cast<mlir::omp::DeclareTargetInterface>(
+              parentFn.getOperation()))
+    if (declareTargetIface.isDeclareTarget() &&
+        declareTargetIface.getDeclareTargetDeviceType() !=
+            mlir::omp::DeclareTargetDeviceType::host)
+      return true;
+
+  return false;
+}
+
+/// Given an OpenMP MLIR operation, create the corresponding LLVM IR
+/// (including OpenMP runtime calls).
+static LogicalResult
+convertCommonOperation(Operation *op, llvm::IRBuilderBase &builder,
+                       LLVM::ModuleTranslation &moduleTranslation) {
+
+  llvm::OpenMPIRBuilder *ompBuilder = moduleTranslation.getOpenMPBuilder();
+
+  return llvm::TypeSwitch<Operation *, LogicalResult>(op)
+      .Case([&](omp::BarrierOp) {
+        ompBuilder->createBarrier(builder.saveIP(), llvm::omp::OMPD_barrier);
+        return success();
+      })
+      .Case([&](omp::TaskwaitOp) {
+        ompBuilder->createTaskwait(builder.saveIP());
+        return success();
+      })
+      .Case([&](omp::TaskyieldOp) {
+        ompBuilder->createTaskyield(builder.saveIP());
+        return success();
+      })
+      .Case([&](omp::FlushOp) {
+        // No support in Openmp runtime function (__kmpc_flush) to accept
+        // the argument list.
+        // OpenMP standard states the following:
+        //  "An implementation may implement a flush with a list by ignoring
+        //   the list, and treating it the same as a flush without a list."
+        //
+        // The argument list is discarded so that, flush with a list is treated
+        // same as a flush without a list.
+        ompBuilder->createFlush(builder.saveIP());
+        return success();
+      })
+      .Case([&](omp::ParallelOp op) {
+        return convertOmpParallel(op, builder, moduleTranslation);
+      })
+      .Case([&](omp::ReductionOp reductionOp) {
+        return convertOmpReductionOp(reductionOp, builder, moduleTranslation);
+      })
+      .Case([&](omp::MasterOp) {
+        return convertOmpMaster(*op, builder, moduleTranslation);
+      })
+      .Case([&](omp::CriticalOp) {
+        return convertOmpCritical(*op, builder, moduleTranslation);
+      })
+      .Case([&](omp::OrderedRegionOp) {
+        return convertOmpOrderedRegion(*op, builder, moduleTranslation);
+      })
+      .Case([&](omp::OrderedOp) {
+        return convertOmpOrdered(*op, builder, moduleTranslation);
+      })
+      .Case([&](omp::WsLoopOp) {
+        return convertOmpWsLoop(*op, builder, moduleTranslation);
+      })
+      .Case([&](omp::SimdLoopOp) {
+        return convertOmpSimdLoop(*op, builder, moduleTranslation);
+      })
+      .Case([&](omp::AtomicReadOp) {
+        return convertOmpAtomicRead(*op, builder, moduleTranslation);
+      })
+      .Case([&](omp::AtomicWriteOp) {
+        return convertOmpAtomicWrite(*op, builder, moduleTranslation);
+      })
+      .Case([&](omp::AtomicUpdateOp op) {
+        return convertOmpAtomicUpdate(op, builder, moduleTranslation);
+      })
+      .Case([&](omp::AtomicCaptureOp op) {
+        return convertOmpAtomicCapture(op, builder, moduleTranslation);
+      })
+      .Case([&](omp::SectionsOp) {
+        return convertOmpSections(*op, builder, moduleTranslation);
+      })
+      .Case([&](omp::SingleOp op) {
+        return convertOmpSingle(op, builder, moduleTranslation);
+      })
+      .Case([&](omp::TeamsOp op) {
+        return convertOmpTeams(op, builder, moduleTranslation);
+      })
+      .Case([&](omp::TaskOp op) {
+        return convertOmpTaskOp(op, builder, moduleTranslation);
+      })
+      .Case([&](omp::TaskGroupOp op) {
+        return convertOmpTaskgroupOp(op, builder, moduleTranslation);
+      })
+      .Case<omp::YieldOp, omp::TerminatorOp, omp::ReductionDeclareOp,
+            omp::CriticalDeclareOp>([](auto op) {
+        // `yield` and `terminator` can be just omitted. The block structure
+        // was created in the region that handles their parent operation.
+        // `reduction.declare` will be used by reductions and is not
+        // converted directly, skip it.
+        // `critical.declare` is only used to declare names of critical
+        // sections which will be used by `critical` ops and hence can be
+        // ignored for lowering. The OpenMP IRBuilder will create unique
+        // name for critical section names.
+        return success();
+      })
+      .Case([&](omp::ThreadprivateOp) {
+        return convertOmpThreadprivate(*op, builder, moduleTranslation);
+      })
+      .Case<omp::DataOp, omp::EnterDataOp, omp::ExitDataOp, omp::UpdateDataOp>(
+          [&](auto op) {
+            return convertOmpTargetData(op, builder, moduleTranslation);
+          })
+      .Case([&](omp::TargetOp) {
+        return convertOmpTarget(*op, builder, moduleTranslation);
+      })
+      .Case<omp::MapInfoOp, omp::DataBoundsOp, omp::PrivateClauseOp>(
+          [&](auto op) {
+            // No-op, should be handled by relevant owning operations e.g.
+            // TargetOp, EnterDataOp, ExitDataOp, DataOp etc. and then
+            // discarded
+            return success();
+          })
+      .Default([&](Operation *inst) {
+        return inst->emitError("unsupported OpenMP operation: ")
+               << inst->getName();
+      });
+}
+
+static LogicalResult
+convertInternalTargetOp(Operation *op, llvm::IRBuilderBase &builder,
+                        LLVM::ModuleTranslation &moduleTranslation) {
+  return convertCommonOperation(op, builder, moduleTranslation);
+}
+
+static LogicalResult
+convertTopLevelTargetOp(Operation *op, llvm::IRBuilderBase &builder,
+                        LLVM::ModuleTranslation &moduleTranslation) {
+  return llvm::TypeSwitch<Operation *, LogicalResult>(op)
+      .Case<omp::DataOp, omp::EnterDataOp, omp::ExitDataOp, omp::UpdateDataOp>(
+          [&](auto op) {
+            return convertOmpTargetData(op, builder, moduleTranslation);
+          })
+      .Case([&](omp::TargetOp) {
+        return convertOmpTarget(*op, builder, moduleTranslation);
+      })
+      // Skip omp ops that are not legal top level ops for the target device
----------------
jsjodin wrote:

> Thinking about it a bit more, maybe it's not too difficult to support these cases. For those host ops that might contain a target region nested (immediately or not), we could just call `op.walk<omp::TargetOp>(...)` and trigger lowering for these target ops. The only problem this could have (I'm not sure, though) is that some arguments of that `omp.target` operation might not have been lowered to LLVM IR by then, since we would have skipped parent regions.

I think we are okay since omp.target is isolated from above, so I believe there shouldn't be any values that need to be translated (codegen seems to work for the omp.task { omp.target {}} case. I'm not sure if it is possible for the top level target data ops to have this issue.

https://github.com/llvm/llvm-project/pull/85239