[mlir][XeGPU] Update utils for LayoutAttr and SliceAttr support

mlir/include/mlir/Dialect/XeGPU/IR/XeGPUAttrs.td

@@ -185,6 +185,9 @@ def DistributeLayoutAttr: AttrInterface<"DistributeLayoutAttr"> {
     InterfaceMethod<"Check the availability of workgroup level layouts",
                     "bool",
                     "isForWorkgroup">,
+    InterfaceMethod<"Check the availability of subgroup level layouts",
+                    "bool",
+                    "isForSubgroup">,
     InterfaceMethod<"Get the rank of attribute",
                     "int64_t",
                     "getRank">,
@@ -202,9 +205,21 @@ def DistributeLayoutAttr: AttrInterface<"DistributeLayoutAttr"> {
     InterfaceMethod<"Get the SgData field of the attribute as integer array",
                     "std::optional<SmallVector<int64_t>>",
                     "getSgDataAsInt">,
+    InterfaceMethod<"Get the InstData field of the attribute as integer array",
+                    "std::optional<SmallVector<int64_t>>",
+                    "getInstDataAsInt">,
+    InterfaceMethod<"Get the LaneLayout field of the attribute as integer array",
+                    "std::optional<SmallVector<int64_t>>",
+                    "getLaneLayoutAsInt">,
+    InterfaceMethod<"Get the LaneData field of the attribute as integer array",
+                    "std::optional<SmallVector<int64_t>>",
+                    "getLaneDataAsInt">,
     InterfaceMethod<"Derive a new layout by dropping sgLayout and sgData",
                     "xegpu::DistributeLayoutAttr",
                     "dropSgLayoutAndData">,
+    InterfaceMethod<"Derive a new layout by dropping InstData",
+                    "xegpu::DistributeLayoutAttr",
+                    "dropInstData">,
     InterfaceMethod<[{Delinearizes a linear subgroup ID into its multidimensional
                       indices based on the effective subgroup layout.}],
                     "FailureOr<SmallVector<Value>>",
@@ -388,6 +403,24 @@ def XeGPU_LayoutAttr : XeGPUAttr<"Layout", "layout", [DistributeLayoutAttr]> {
       return std::nullopt;
     }
 
+    std::optional<SmallVector<int64_t>> getInstDataAsInt() const {
+      if (DenseI32ArrayAttr inst = getInstData())
+        return llvm::to_vector_of<int64_t>(inst.asArrayRef());
+      return std::nullopt;
+    }
+
+    std::optional<SmallVector<int64_t>> getLaneLayoutAsInt() const {
+      if (DenseI32ArrayAttr layout = getLaneLayout())
+        return llvm::to_vector_of<int64_t>(layout.asArrayRef());
+      return std::nullopt;
+    }
+
+    std::optional<SmallVector<int64_t>> getLaneDataAsInt() const {
+      if (DenseI32ArrayAttr data = getLaneData())
+        return llvm::to_vector_of<int64_t>(data.asArrayRef());
+      return std::nullopt;
+    }
+
     /// Delinearizes a linear subgroup ID into its multidimensional indices
     /// based on the effective subgroup layout.
     FailureOr<SmallVector<Value>>
@@ -488,6 +521,42 @@ def XeGPU_SliceAttr : XeGPUAttr<"Slice", "slice", [DistributeLayoutAttr]> {
       return std::nullopt;
     }
 
+    /// Returns the InstData of the attribute, computed by applying
+    /// the slice dimensions to the underlying LayoutAttr.
+    std::optional<SmallVector<int64_t>> getInstDataAsInt() const {
+      SliceAttr attr = flatten();
+      auto parent = dyn_cast<LayoutAttr>(attr.getParent());
+      if (auto inst = parent.getInstDataAsInt()) {
+        ArrayRef<int64_t> dims = attr.getDims().asArrayRef();
+        return XeGPUDialect::slice(llvm::ArrayRef<int64_t>(*inst), dims);
+      }
+      return std::nullopt;
+    }
+
+    /// Returns the LaneLayout of the attribute, computed by applying
+    /// the slice dimensions to the underlying LayoutAttr.
+    std::optional<SmallVector<int64_t>> getLaneLayoutAsInt() const {
+      SliceAttr attr = flatten();
+      auto parent = dyn_cast<LayoutAttr>(attr.getParent());
+      if (auto layout = parent.getLaneLayoutAsInt()) {
+        ArrayRef<int64_t> dims = attr.getDims().asArrayRef();
+        return XeGPUDialect::slice(llvm::ArrayRef<int64_t>(*layout), dims);
+      }
+      return std::nullopt;
+    }
+
+    /// Returns the LaneData of the attribute, computed by applying
+    /// the slice dimensions to the underlying LayoutAttr.
+    std::optional<SmallVector<int64_t>> getLaneDataAsInt() const {
+      SliceAttr attr = flatten();
+      auto parent = dyn_cast<LayoutAttr>(attr.getParent());
+      if (auto data = parent.getLaneDataAsInt()) {
+        ArrayRef<int64_t> dims = attr.getDims().asArrayRef();
+        return XeGPUDialect::slice(llvm::ArrayRef<int64_t>(*data), dims);
+      }
+      return std::nullopt;
+    }
+
     SliceAttr dropSgLayoutAndData() {
       SliceAttr attr = flatten();
       auto parent = dyn_cast<LayoutAttr>(attr.getParent());

mlir/include/mlir/Dialect/XeGPU/IR/XeGPUDialect.td

@@ -40,7 +40,7 @@ def XeGPU_Dialect : Dialect {
     let extraClassDeclaration = [{
       /// Checks if the given shape can be evenly distributed based on the layout
       /// and data factors provided by the LayoutAttr.
-      static bool isEvenlyDistributable(llvm::ArrayRef<int64_t> shape, xegpu::LayoutAttr attr);
+      static bool isEvenlyDistributable(llvm::ArrayRef<int64_t> shape, xegpu::DistributeLayoutAttr attr);
 
       /// drops/slices the shape in the specified dims, and return the rest. e.g.,
       /// for shape = [32, 64, 8], dims = [0, 2], it will return [64]

mlir/include/mlir/Dialect/XeGPU/IR/XeGPUOps.td

@@ -1162,8 +1162,8 @@ def XeGPU_ConvertLayoutOp: XeGPU_Op<"convert_layout", [Pure, AllTypesMatch<["sou
       the IR is lowered to WI level because that is the end result of all distributions.
     }];
     let arguments = (ins XeGPU_VectorType: $source,
-                         XeGPU_LayoutAttr: $input_layout,
-                         XeGPU_LayoutAttr: $target_layout);
+                         DistributeLayoutAttr: $input_layout,
+                         DistributeLayoutAttr: $target_layout);
     let results = (outs XeGPU_VectorType: $result);
     let assemblyFormat = [{
         $source prop-dict attr-dict `:` type($source)

mlir/include/mlir/Dialect/XeGPU/Utils/XeGPUUtils.h

@@ -9,6 +9,7 @@
 #ifndef MLIR_DIALECT_XEGPU_UTILS_XEGPUUTILS_H_
 #define MLIR_DIALECT_XEGPU_UTILS_XEGPUUTILS_H_
 
+#include "mlir/Dialect/XeGPU/IR/XeGPU.h"
 #include "mlir/IR/BuiltinTypes.h"
 #include "mlir/IR/OpDefinition.h"
 namespace mlir {
@@ -21,6 +22,7 @@ class ValueRange;
 class TypeConverter;
 
 namespace xegpu {
+class DistributeLayoutAttr;
 class LayoutAttr;
 class TensorDescType;
 } // namespace xegpu
@@ -60,46 +62,58 @@ FailureOr<VectorType> getDistributedVectorType(xegpu::TensorDescType tdescTy);
 FailureOr<VectorType> getDistributedVectorType(VectorType originalType,
                                                LayoutAttr layout);
 
-/// Return the attribute name for the OpOperand to attach LayoutAttr
+/// Return the attribute name for the OpOperand to attach DistributeLayoutAttr
 std::string getLayoutName(const OpOperand &operand);
 
-/// Return the attribute name for the OpResult to attach LayoutAttr
+/// Return the attribute name for the OpResult to attach DistributeLayoutAttr
 std::string getLayoutName(const OpResult result);
 
-/// Retrieves the LayoutAttr associated with a given Value. For TensorDescType
-/// values, the LayoutAttr is extracted from the TensorDescType itself. For
-/// other values, it is obtained from the attributes of the defining operation.
-/// Returns nullptr if no LayoutAttr is found.
-LayoutAttr getLayoutAttr(const Value value);
+/// Retrieves the DistributeLayoutAttr associated with a given Value. For
+/// TensorDescType values, the DistributeLayoutAttr is extracted from the
+/// TensorDescType itself. For other values, it is obtained from the attributes
+/// of the defining operation. Returns nullptr if no DistributeLayoutAttr is
+/// found.
+DistributeLayoutAttr getDistributeLayoutAttr(const Value value);
 
-/// Retrieves the LayoutAttr associated with a given OpOperand. It will
-/// first check the operand_layout_{id} of the owner operation. If not found,
-/// it will check the operand itself and its defining op.
-LayoutAttr getLayoutAttr(const OpOperand &opr);
+template <typename AttrTy>
+AttrTy getDistributeLayoutAttrOfType(const Value value) {
+  return dyn_cast_if_present<AttrTy>(getDistributeLayoutAttr(value));
+}
+
+/// Retrieves the DistributeLayoutAttr associated with a given OpOperand. It
+/// will first check the operand_layout_{id} of the owner operation. If not
+/// found, it will check the operand itself and its defining op.
+DistributeLayoutAttr getDistributeLayoutAttr(const OpOperand &opr);
+
+template <typename AttrTy>
+AttrTy getDistributeLayoutAttrOfType(const OpOperand &opr) {
+  return dyn_cast_if_present<AttrTy>(getDistributeLayoutAttr(opr));
+}
 
 /// Removes the LayoutAttr for a given OpOperand or OpResult if it exists.
 template <typename T,
           typename = std::enable_if_t<std::is_same_v<T, OpOperand> ||
                                       std::is_same_v<T, OpResult>>>
 void removeLayoutAttr(const T &operandOrResult);
 
-/// Removes the LayoutAttr for each OpOperand and OpResult of the given
-/// operation if they exist. If the operation contains regions, it is also
+/// Removes the DistributeLayoutAttr for each OpOperand and OpResult of the
+/// given operation if they exist. If the operation contains regions, it is also
 /// applied recursively to the contained operations
 void removeLayoutAttrs(Operation *op);
 
-/// Sets the LayoutAttr for a given OpOperand or OpResult by attaching
+/// Sets the DistributeLayoutAttr for a given OpOperand or OpResult by attaching
 /// it to the owner's dictionary attributes
 template <typename T,
           typename = std::enable_if_t<std::is_same_v<T, OpOperand> ||
                                       std::is_same_v<T, OpResult>>>
-void setLayoutAttr(const T &operandOrResult, const LayoutAttr layout);
-
-/// Set the LayoutAttr for each OpOperand and OpResult of the given operation.
-/// If the operation contains regions, it is also applied recursively to the
-/// contained operations
-void setLayoutAttrs(Operation *op,
-                    function_ref<LayoutAttr(Value)> getLayoutImpl);
+void setDistributeLayoutAttr(const T &operandOrResult,
+                             const DistributeLayoutAttr layout);
+
+/// Set the DistributeLayoutAttr for each OpOperand and OpResult of the given
+/// operation. If the operation contains regions, it is also applied recursively
+/// to the contained operations
+void setDistributeLayoutAttrs(
+    Operation *op, function_ref<DistributeLayoutAttr(Value)> getLayoutImpl);
 
 /// Extract a set of small vectors from a value with a given shape using
 /// vector.extract_stride_slice

mlir/lib/Dialect/XeGPU/IR/XeGPUDialect.cpp

@@ -91,7 +91,7 @@ genOffsetsComputingInsts(OpBuilder &builder, Location loc,
 // Checks if the given shape can be evenly distributed based on the layout
 // and data factors provided by the LayoutAttr.
 bool XeGPUDialect::isEvenlyDistributable(llvm::ArrayRef<int64_t> shape,
-                                         xegpu::LayoutAttr attr) {
+                                         xegpu::DistributeLayoutAttr attr) {
   assert(attr && "Layout attribute is missing.");
 
   // Checks whether the given shape can be evenly distributed using the
@@ -104,52 +104,51 @@ bool XeGPUDialect::isEvenlyDistributable(llvm::ArrayRef<int64_t> shape,
   // smaller than `layout[i] * data[i]`, allowing multiple compute units to
   // share the data.
   auto tryDistribute = [&](llvm::ArrayRef<int64_t> shape,
-                           DenseI32ArrayAttr layout, DenseI32ArrayAttr data,
+                           std::optional<SmallVector<int64_t>> layout,
+                           std::optional<SmallVector<int64_t>> data,
                            bool rr = true) -> optional<SmallVector<int64_t>> {
     llvm::SmallVector<int64_t> newShape(shape);
     if (layout) {
-      auto vec = llvm::to_vector_of<int64_t>(layout.asArrayRef());
-      if (vec.size() != shape.size())
+      if ((*layout).size() != shape.size())
         return std::nullopt;
-      auto ratio = computeShapeRatio(shape, vec);
+      auto ratio = computeShapeRatio(shape, *layout);
       if (!ratio.has_value())
         return std::nullopt;
       newShape = ratio.value();
     }
 
     if (data) {
-      auto vec = llvm::to_vector_of<int64_t>(data.asArrayRef());
-      if (vec.size() != shape.size())
+      if ((*data).size() != shape.size())
         return std::nullopt;
-      auto ratio = computeShapeRatio(newShape, vec);
+      auto ratio = computeShapeRatio(newShape, *data);
       if (!ratio.has_value() && rr)
-        ratio = computeShapeRatio(vec, newShape);
+        ratio = computeShapeRatio(*data, newShape);
       if (!ratio.has_value())
         return std::nullopt;
 
       // if data is not null, we always return it for next phase.
-      newShape = vec;
+      newShape = *data;
     }
     return newShape;
   };
 
   // check the sgLayout and sgData
   auto maybeSgShape =
-      tryDistribute(shape, attr.getSgLayout(), attr.getSgData());
+      tryDistribute(shape, attr.getSgLayoutAsInt(), attr.getSgDataAsInt());
   if (!maybeSgShape)
     return false;
   auto sgShape = maybeSgShape.value();
 
   // check InstData, it neither have layout nor need round-robin
   auto maybeInstShape =
-      tryDistribute(sgShape, nullptr, attr.getInstData(), false);
+      tryDistribute(sgShape, std::nullopt, attr.getInstDataAsInt(), false);
   if (!maybeInstShape)
     return false;
   auto instShape = maybeInstShape.value();
 
   // check LaneLayout and LaneData
-  auto maybeLaneShape =
-      tryDistribute(instShape, attr.getLaneLayout(), attr.getLaneData(), false);
+  auto maybeLaneShape = tryDistribute(instShape, attr.getLaneLayoutAsInt(),
+                                      attr.getLaneDataAsInt(), false);
   return maybeLaneShape.has_value();
 }
 

mlir/lib/Dialect/XeGPU/Transforms/XeGPUBlocking.cpp

@@ -84,9 +84,9 @@ struct ConvertLayoutOpPattern
   using OpRewritePattern::OpRewritePattern;
   LogicalResult matchAndRewrite(xegpu::ConvertLayoutOp op,
                                 PatternRewriter &rewriter) const override {
-    xegpu::LayoutAttr input_layout = op.getInputLayoutAttr();
-    xegpu::LayoutAttr target_layout = op.getTargetLayoutAttr();
-    if (!input_layout.getInstData() || !target_layout.getInstData())
+    xegpu::DistributeLayoutAttr input_layout = op.getInputLayoutAttr();
+    xegpu::DistributeLayoutAttr target_layout = op.getTargetLayoutAttr();
+    if (!input_layout.getInstDataAsInt() || !target_layout.getInstDataAsInt())
       return rewriter.notifyMatchFailure(op, "Not a target ConvertLayoutOp.");
 
     input_layout = input_layout.dropInstData();
@@ -140,10 +140,11 @@ XeGPUBlockingPass::getTileShape(const T &operandOrResult) const {
   else
     value = (Value)operandOrResult;
 
-  xegpu::LayoutAttr layout = xegpu::getLayoutAttr(operandOrResult);
+  xegpu::DistributeLayoutAttr layout =
+      xegpu::getDistributeLayoutAttr(operandOrResult);
   if (layout && layout.isForSubgroup()) {
-    if (auto inst_data = layout.getInstData())
-      return llvm::to_vector_of<int64_t>(inst_data.asArrayRef());
+    if (auto inst_data = layout.getInstDataAsInt())
+      return inst_data.value();
 
     if (auto type = dyn_cast<ShapedType>(value.getType()))
       return llvm::to_vector(type.getShape());
@@ -204,12 +205,14 @@ bool XeGPUBlockingPass::needsUnroll(Operation *op) const {
   // skip the op if any of its operands or results has workgroup level layouts
   bool hasWgLayoutOperands =
       llvm::any_of(op->getOpOperands(), [](OpOperand &opr) {
-        xegpu::LayoutAttr layout = xegpu::getLayoutAttr(opr);
+        xegpu::DistributeLayoutAttr layout =
+            xegpu::getDistributeLayoutAttr(opr);
         return layout && layout.isForWorkgroup();
       });
   bool hasWgLayoutResults =
       llvm::any_of(op->getOpResults(), [](OpResult result) {
-        xegpu::LayoutAttr layout = xegpu::getLayoutAttr(result);
+        xegpu::DistributeLayoutAttr layout =
+            xegpu::getDistributeLayoutAttr(result);
         return layout && layout.isForWorkgroup();
       });
   if (hasWgLayoutOperands || hasWgLayoutResults) {
@@ -220,8 +223,8 @@ bool XeGPUBlockingPass::needsUnroll(Operation *op) const {
   auto isUnrollable = [](Value value, ArrayRef<int64_t> tileShape) {
     Type valTy = value.getType();
     if (auto tdescTy = dyn_cast<xegpu::TensorDescType>(valTy)) {
-      xegpu::LayoutAttr layout = tdescTy.getLayoutAttr();
-      return layout && layout.getInstData();
+      xegpu::DistributeLayoutAttr layout = tdescTy.getLayoutAttr();
+      return layout && layout.getInstDataAsInt();
     }
     auto shapedType = dyn_cast<ShapedType>(valTy);
     return shapedType && !llvm::equal(tileShape, shapedType.getShape());
@@ -247,7 +250,8 @@ void XeGPUBlockingPass::runOnOperation() {
   // Preserve the LayoutAttr for each operand to the owner's DictionaryAttr.
   // This ensures that the LayoutAttr remains accessible even if the defining
   // operation is replaced.
-  xegpu::setLayoutAttrs(op, [](Value v) { return xegpu::getLayoutAttr(v); });
+  xegpu::setDistributeLayoutAttrs(
+      op, [](Value v) { return xegpu::getDistributeLayoutAttr(v); });
 
   auto getTileShapeAndCount = [](llvm::ArrayRef<int64_t> shape,
                                  xegpu::LayoutAttr layout) {
@@ -377,7 +381,7 @@ void XeGPUBlockingPass::runOnOperation() {
       if (auto layout = op->getAttrOfType<xegpu::LayoutAttr>(name)) {
         op->removeAttr(name);
         if (!isa<LoopLikeOpInterface>(op))
-          xegpu::setLayoutAttr(result, layout.dropInstData());
+          xegpu::setDistributeLayoutAttr(result, layout.dropInstData());
       }
     }
 

mlir/lib/Dialect/XeGPU/Transforms/XeGPUPropagateLayout.cpp

@@ -718,7 +718,7 @@ static LogicalResult updateOp(mlir::OpBuilder &builder, mlir::Operation *op,
     }
     // If the result is a vector type, add a temporary layout attribute to the
     // op.
-    xegpu::setLayoutAttr(result, layout);
+    xegpu::setDistributeLayoutAttr(result, layout);
   }
   return success();
 }
@@ -800,7 +800,7 @@ updateControlFlowOps(mlir::OpBuilder &builder,
       // If the type is a vector type and this region argument is an OpResult,
       // set the layout attribute on the OpResult.
       if (auto result = dyn_cast<OpResult>(successorInput))
-        xegpu::setLayoutAttr(result, successorOperandLayout);
+        xegpu::setDistributeLayoutAttr(result, successorOperandLayout);
     }
   }
   return success();