[mlir] Make GpuAsyncRegion pass depend on async dialect.

[csigg]

Summary

Do not cache gpu.async.token type so that the pass can be created before the GPU dialect is registered.

[csigg]

Fix.

mlir/include/mlir/Dialect/GPU/Passes.td

 def GpuKernelOutlining : Pass<"gpu-kernel-outlining", "ModuleOp"> {
   let summary = "Outline gpu.launch bodies to kernel functions";
   let constructor = "mlir::createGpuKernelOutliningPass()";
 }
 
 def GpuAsyncRegionPass : FunctionPass<"gpu-async-region"> {
   let summary = "Make GPU ops async";
   let constructor = "mlir::createGpuAsyncRegionPass()";
+  let dependentDialects = ["async::AsyncDialect"];
 }
 
 #endif // MLIR_DIALECT_GPU_PASSES

mlir/lib/Dialect/GPU/Transforms/AsyncRegionRewriter.cpp

private:
   LogicalResult rewriteAsyncOp(gpu::AsyncOpInterface asyncOp) {
     auto *op = asyncOp.getOperation();
     if (asyncOp.getAsyncToken())
       // TODO: Support ops that are already async.
       return op->emitOpError("is already async");
     if (op->getNumRegions() > 0)
       return op->emitOpError("regions are not supported");
 
+    auto tokenType = builder.getType<gpu::AsyncTokenType>();
+
     // If there is no current token, insert a `gpu.wait async` without
     // dependencies to create one.
     if (!currentToken)
       currentToken = createWaitOp(op->getLoc(), tokenType, {});
     asyncOp.addAsyncDependency(currentToken);
 
     // Clone the op to return a token in addition to the other results.
     SmallVector<Type, 1> resultTypes;
LogicalResult rewriteAsyncOp(gpu::AsyncOpInterface asyncOp) {
     return success();
   }
 
   Value createWaitOp(Location loc, Type resultType, ValueRange operands) {
     return builder.create<gpu::WaitOp>(loc, resultType, operands).asyncToken();
   }
 
   OpBuilder builder;
-  const Type tokenType = builder.getType<gpu::AsyncTokenType>();
+
   // The token that represents the current asynchronous dependency. It's valid
   // range starts with a `gpu.wait async` op, and ends with a `gpu.wait` op.
   // In between, each gpu::AsyncOpInterface depends on the current token and
   // produces the new one.
   Value currentToken = {};
 };
 
 // Callback for `async.execute` ops which tries to push the contained

mlir/lib/Dialect/GPU/Transforms/PassDetail.h

 //===- PassDetail.h - GPU Pass class details --------------------*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef DIALECT_GPU_TRANSFORMS_PASSDETAIL_H_
 #define DIALECT_GPU_TRANSFORMS_PASSDETAIL_H_
 
+#include "mlir/Dialect/Async/IR/Async.h"
 #include "mlir/Pass/Pass.h"
 
 namespace mlir {
 
 #define GEN_PASS_CLASSES
 #include "mlir/Dialect/GPU/Passes.h.inc"
 
 } // end namespace mlir
 
 #endif // DIALECT_GPU_TRANSFORMS_PASSDETAIL_H_