[Mlir-commits] [mlir] [mlir] Let GPU ID bounds work on any FunctionOpInterfaces (PR #95166)

[Krzysztof Drewniak]

================
@@ -73,12 +85,16 @@ static std::optional<uint64_t> getKnownLaunchDim(Op op, LaunchDims type) {
       return value.getZExtValue();
   }
 
-  if (auto func = op->template getParentOfType<GPUFuncOp>()) {
+  if (auto func = op->template getParentOfType<FunctionOpInterface>()) {
     switch (type) {
     case LaunchDims::Block:
-      return llvm::transformOptional(func.getKnownBlockSize(dim), zext);
+      return llvm::transformOptional(
+          getKnownLaunchAttr(func, GPUFuncOp::getKnownBlockSizeAttrName(), dim),
+          zext);
     case LaunchDims::Grid:
-      return llvm::transformOptional(func.getKnownGridSize(dim), zext);
+      return llvm::transformOptional(
+          getKnownLaunchAttr(func, GPUFuncOp::getKnownGridSizeAttrName(), dim),
+          zext);
----------------
krzysz00 wrote:

That being said, you've got a point about the problems with discardable attributes, so how about ... we do both?

Known block/grid sizes would be an optional inherent attribute of `gpu.func`, and attempts to retrieve that data would go looking for those values if available. However, when the parent of the `gpu.*_id` or `gpu.*_dim` is some other kind of function, the data in question would live in `gpu.known_*_sizes`, a discardable attribute.

https://github.com/llvm/llvm-project/pull/95166