diff --git a/mlir/include/mlir/Interfaces/SideEffectInterfaceBase.td b/mlir/include/mlir/Interfaces/SideEffectInterfaceBase.td
--- a/mlir/include/mlir/Interfaces/SideEffectInterfaceBase.td
+++ b/mlir/include/mlir/Interfaces/SideEffectInterfaceBase.td
@@ -98,7 +98,7 @@
     static bool hasNoEffect(Operation *op) {
       if (auto interface = dyn_cast<}] # name # [{>(op))
         return interface.hasNoEffect();
-      return op->hasTrait<::mlir::OpTrait::HasRecursiveMemoryEffects>();
+      return !op->hasTrait<::mlir::OpTrait::HasRecursiveMemoryEffects>();
     }
 
     /// Collect all of the effect instances that operate on the provided value
diff --git a/mlir/lib/Dialect/GPU/Transforms/AsyncRegionRewriter.cpp b/mlir/lib/Dialect/GPU/Transforms/AsyncRegionRewriter.cpp
--- a/mlir/lib/Dialect/GPU/Transforms/AsyncRegionRewriter.cpp
+++ b/mlir/lib/Dialect/GPU/Transforms/AsyncRegionRewriter.cpp
@@ -340,13 +340,20 @@
 // inserts the necessary synchronization (as gpu.wait ops). Assumes sequential
 // execution semantics and that no GPU ops are asynchronous yet.
 void GpuAsyncRegionPass::runOnOperation() {
-  if (getOperation()->walk(ThreadTokenCallback(getContext())).wasInterrupted())
+  auto operation = getOperation();
+  if (operation->walk(ThreadTokenCallback(getContext())).wasInterrupted())
     return signalPassFailure();
 
   // Collect gpu.wait ops that we can move out of async.execute regions.
-  getOperation().getRegion().walk(DeferWaitCallback());
-  // Makes each !gpu.async.token returned from async.execute op have single use.
-  getOperation().getRegion().walk(SingleTokenUseCallback());
+  if (operation->getNumRegions() != 0) {
+    Region &region = operation.getRegion();
+    if (!region.empty()) {
+      region.walk(DeferWaitCallback());
+      // Makes each !gpu.async.token returned from async.execute op have single
+      // use.
+      region.walk(SingleTokenUseCallback());
+    }
+  }
 }
 
 std::unique_ptr<OperationPass<func::FuncOp>> mlir::createGpuAsyncRegionPass() {