[mlir] Async: Add numWorkerThreads argument to createAsyncParallelForPass

Add an option to pass the number of worker threads to select the number of async regions for parallel for transformation.
```
std::unique_ptr<OperationPass<FuncOp>> createAsyncParallelForPass(int numWorkerThreads);
```

Reviewed By: mehdi_amini

Differential Revision: https://reviews.llvm.org/D92835

mlir/include/mlir/Dialect/Async/Passes.h

@@ -19,6 +19,9 @@ namespace mlir {
 
 std::unique_ptr<OperationPass<FuncOp>> createAsyncParallelForPass();
 
+std::unique_ptr<OperationPass<FuncOp>>
+createAsyncParallelForPass(int numWorkerThreads);
+
 std::unique_ptr<OperationPass<FuncOp>> createAsyncRefCountingPass();
 
 std::unique_ptr<OperationPass<FuncOp>> createAsyncRefCountingOptimizationPass();

mlir/lib/Dialect/Async/Transforms/AsyncParallelFor.cpp

@@ -96,6 +96,10 @@ private:
 struct AsyncParallelForPass
     : public AsyncParallelForBase<AsyncParallelForPass> {
   AsyncParallelForPass() = default;
+  AsyncParallelForPass(int numWorkerThreads) {
+    assert(numWorkerThreads >= 1);
+    numConcurrentAsyncExecute = numWorkerThreads;
+  }
   void runOnFunction() override;
 };
 
@@ -276,3 +280,8 @@ void AsyncParallelForPass::runOnFunction() {
 std::unique_ptr<OperationPass<FuncOp>> mlir::createAsyncParallelForPass() {
   return std::make_unique<AsyncParallelForPass>();
 }
+
+std::unique_ptr<OperationPass<FuncOp>>
+mlir::createAsyncParallelForPass(int numWorkerThreads) {
+  return std::make_unique<AsyncParallelForPass>(numWorkerThreads);
+}