rename getLayoutAttr util

chencha3 · chencha3 · commit ad5d0a88a4f0 · 2025-08-21T17:58:25.000Z
diff --git a/mlir/include/mlir/Dialect/XeGPU/IR/XeGPUAttrs.td b/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">,
@@ -202,6 +205,15 @@ 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">,
@@ -388,6 +400,24 @@ 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 +518,42 @@ 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());
diff --git a/mlir/include/mlir/Dialect/XeGPU/IR/XeGPUDialect.td b/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]
diff --git a/mlir/include/mlir/Dialect/XeGPU/Utils/XeGPUUtils.h b/mlir/include/mlir/Dialect/XeGPU/Utils/XeGPUUtils.h
@@ -21,6 +21,7 @@ class ValueRange;
 class TypeConverter;
 
 namespace xegpu {
+class DistributeLayoutAttr;
 class LayoutAttr;
 class TensorDescType;
 } // namespace xegpu
@@ -60,46 +61,46 @@ 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
+/// 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 LayoutAttr is found.
-LayoutAttr getLayoutAttr(const Value value);
+/// Returns nullptr if no DistributeLayoutAttr is found.
+DistributeLayoutAttr getDistributeLayoutAttr(const Value value);
 
-/// Retrieves the LayoutAttr associated with a given OpOperand. It will
+/// 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.
-LayoutAttr getLayoutAttr(const OpOperand &opr);
+DistributeLayoutAttr getDistributeLayoutAttr(const OpOperand &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
+/// 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);
+void setLayoutAttr(const T &operandOrResult, const DistributeLayoutAttr layout);
 
-/// Set the LayoutAttr for each OpOperand and OpResult of the given operation.
+/// 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 setLayoutAttrs(Operation *op,
-                    function_ref<LayoutAttr(Value)> getLayoutImpl);
+                    function_ref<DistributeLayoutAttr(Value)> getLayoutImpl);
 
 /// Extract a set of small vectors from a value with a given shape using
 /// vector.extract_stride_slice
diff --git a/mlir/lib/Dialect/XeGPU/IR/XeGPUDialect.cpp b/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);
+      tryDistribute(instShape, attr.getLaneLayoutAsInt(), attr.getLaneDataAsInt(), false);
   return maybeLaneShape.has_value();
 }
 
diff --git a/mlir/lib/Dialect/XeGPU/Transforms/XeGPUBlocking.cpp b/mlir/lib/Dialect/XeGPU/Transforms/XeGPUBlocking.cpp
@@ -140,10 +140,10 @@ 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 +204,12 @@ 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 +220,8 @@ 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 +247,7 @@ 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::setLayoutAttrs(op, [](Value v) { return xegpu::getDistributeLayoutAttr(v); });
 
   auto getTileShapeAndCount = [](llvm::ArrayRef<int64_t> shape,
                                  xegpu::LayoutAttr layout) {
diff --git a/mlir/lib/Dialect/XeGPU/Transforms/XeGPUSubgroupDistribute.cpp b/mlir/lib/Dialect/XeGPU/Transforms/XeGPUSubgroupDistribute.cpp
@@ -841,7 +841,7 @@ void XeGPUSubgroupDistributePass::runOnOperation() {
       if (!isa<VectorType>(operand.get().getType()))
         continue;
 
-      xegpu::LayoutAttr layout = xegpu::getLayoutAttr(operand);
+      auto layout = dyn_cast<xegpu::LayoutAttr>(xegpu::getDistributeLayoutAttr(operand));
       if (!layout) {
         op->emitError("Could not find layout attribute for operand ")
             << operand.getOperandNumber() << " of operation " << op->getName();
@@ -882,7 +882,8 @@ void XeGPUSubgroupDistributePass::runOnOperation() {
     if (vecRank == 0)
       return AffineMap::get(val.getContext());
     // Get the layout of the vector type.
-    xegpu::LayoutAttr layout = xegpu::getLayoutAttr(val);
+    // TODO: support more layout types
+    auto layout = dyn_cast<xegpu::LayoutAttr>(xegpu::getDistributeLayoutAttr(val));
     // If no layout is specified, assume the inner most dimension is distributed
     // for now.
     if (!layout)
diff --git a/mlir/lib/Dialect/XeGPU/Transforms/XeGPUWgToSgDistribute.cpp b/mlir/lib/Dialect/XeGPU/Transforms/XeGPUWgToSgDistribute.cpp
@@ -406,7 +406,7 @@ struct WgToSgDpasOp : public OpConversionPattern<xegpu::DpasOp> {
     if (resultTy.getRank() != 2)
       return failure();
 
-    auto originalLayout = xegpu::getLayoutAttr(op.getResult());
+    auto originalLayout = xegpu::getDistributeLayoutAttr(op.getResult());
     if (!originalLayout)
       return failure();
 
@@ -470,8 +470,8 @@ struct WgToSgVectorBroadcastOp
     VectorType resultType = op.getResult().getType();
     ArrayRef<int64_t> wgShape = resultType.getShape();
 
-    xegpu::LayoutAttr layout = xegpu::getLayoutAttr(op.getResult());
-    if (!layout || !layout.getSgLayout())
+    xegpu::DistributeLayoutAttr layout = xegpu::getDistributeLayoutAttr(op.getResult());
+    if (!layout || !layout.isForWorkgroup())
       return failure();
 
     // TODO: Currently only supports cases where the source and result ranks
@@ -487,8 +487,8 @@ struct WgToSgVectorBroadcastOp
 
     // Check if the output layout is distributable
     SmallVector<int64_t> sgLayout;
-    if (auto sgLayoutAttr = layout.getSgLayout())
-      sgLayout = llvm::to_vector_of<int64_t>(sgLayoutAttr.asArrayRef());
+    if (auto maybeSgLayout = layout.getSgLayoutAsInt())
+      sgLayout = *maybeSgLayout;
     else
       return failure();
 
@@ -535,8 +535,8 @@ struct WgToSgElementwiseOp : public ConversionPattern {
 
     ArrayRef<int64_t> wgShape = resultType.getShape();
 
-    xegpu::LayoutAttr layout = xegpu::getLayoutAttr(op->getResult(0));
-    if (!layout || !layout.getSgLayout())
+    xegpu::DistributeLayoutAttr layout = xegpu::getDistributeLayoutAttr(op->getResult(0));
+    if (!layout || !layout.isForWorkgroup())
       return failure();
 
     SmallVector<int64_t> sgShape = getSgShapeAndCount(wgShape, layout).first;
@@ -737,8 +737,8 @@ struct WgToSgArithConstantOp : public OpConversionPattern<arith::ConstantOp> {
     if (!vecAttr || !vecAttr.isSplat() || !vecType)
       return failure();
 
-    xegpu::LayoutAttr layout = xegpu::getLayoutAttr(op.getResult());
-    if (!layout || !layout.getSgLayout())
+    xegpu::DistributeLayoutAttr layout = xegpu::getDistributeLayoutAttr(op.getResult());
+    if (!layout || !layout.isForWorkgroup())
       return failure();
 
     ArrayRef<int64_t> wgShape = vecType.getShape();
@@ -928,7 +928,7 @@ void XeGPUWgToSgDistributePass::runOnOperation() {
   });
 
   target.addDynamicallyLegalOp<xegpu::DpasOp>([=](xegpu::DpasOp op) -> bool {
-    auto layout = xegpu::getLayoutAttr(op.getResult());
+    auto layout = xegpu::getDistributeLayoutAttr(op.getResult());
     return isLegal(layout);
   });
 
@@ -947,12 +947,12 @@ void XeGPUWgToSgDistributePass::runOnOperation() {
         auto vecType = dyn_cast<VectorType>(op.getType());
         if (!vecType)
           return true;
-        return isLegal(xegpu::getLayoutAttr(op.getResult()));
+        return isLegal(xegpu::getDistributeLayoutAttr(op.getResult()));
       });
 
   target.addDynamicallyLegalOp<vector::BroadcastOp>(
       [=](vector::BroadcastOp op) -> bool {
-        return isLegal(xegpu::getLayoutAttr(op.getResult()));
+        return isLegal(xegpu::getDistributeLayoutAttr(op.getResult()));
       });
 
   target.addDynamicallyLegalOp<xegpu::ConvertLayoutOp>(
@@ -980,7 +980,7 @@ void XeGPUWgToSgDistributePass::runOnOperation() {
           }
         }
 
-        xegpu::LayoutAttr layout = xegpu::getLayoutAttr(op->getResult(0));
+        xegpu::DistributeLayoutAttr layout = xegpu::getDistributeLayoutAttr(op->getResult(0));
         return isLegal(layout);
       });
 
diff --git a/mlir/lib/Dialect/XeGPU/Utils/XeGPUUtils.cpp b/mlir/lib/Dialect/XeGPU/Utils/XeGPUUtils.cpp
