[Mlir-commits] [mlir] [MLIR][XeGPU] Add XeGPU scattered ops (PR #86594)

llvmlistbot at llvm.org llvmlistbot at llvm.org
Mon Mar 25 15:38:47 PDT 2024


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-mlir

Author: Chao Chen (chencha3)

<details>
<summary>Changes</summary>

This PR adds definitions of XeGPU scattered ops and some misc updates, including:
- Extended TensorDescAttr with scattered attribute
- Add scattered ops: CreateDescOp, PrefetchOp, LoadGatherOp, StoreScatterOp, UpdateOffsetOp
- Add a block op: UpdateNdOffsetOp

---

Patch is 47.64 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/86594.diff


7 Files Affected:

- (modified) mlir/include/mlir/Dialect/XeGPU/IR/XeGPU.h (+1) 
- (modified) mlir/include/mlir/Dialect/XeGPU/IR/XeGPUAttrs.td (+10-8) 
- (modified) mlir/include/mlir/Dialect/XeGPU/IR/XeGPUOps.td (+386-63) 
- (modified) mlir/include/mlir/Dialect/XeGPU/IR/XeGPUTypes.td (+20-1) 
- (modified) mlir/lib/Dialect/XeGPU/IR/XeGPUDialect.cpp (+21) 
- (modified) mlir/lib/Dialect/XeGPU/IR/XeGPUOps.cpp (+223-18) 
- (modified) mlir/test/Dialect/XeGPU/XeGPUOps.mlir (+62) 


``````````diff
diff --git a/mlir/include/mlir/Dialect/XeGPU/IR/XeGPU.h b/mlir/include/mlir/Dialect/XeGPU/IR/XeGPU.h
index 87aabdc015fea5..eca9255ff3974b 100644
--- a/mlir/include/mlir/Dialect/XeGPU/IR/XeGPU.h
+++ b/mlir/include/mlir/Dialect/XeGPU/IR/XeGPU.h
@@ -12,6 +12,7 @@
 #include "mlir/Bytecode/BytecodeOpInterface.h"
 #include "mlir/IR/BuiltinTypes.h"
 #include "mlir/IR/Dialect.h"
+#include "mlir/IR/TypeUtilities.h"
 #include "mlir/Interfaces/ShapedOpInterfaces.h"
 #include "mlir/Interfaces/SideEffectInterfaces.h"
 #include "mlir/Interfaces/ViewLikeInterface.h"
diff --git a/mlir/include/mlir/Dialect/XeGPU/IR/XeGPUAttrs.td b/mlir/include/mlir/Dialect/XeGPU/IR/XeGPUAttrs.td
index cd38549f1ccf43..5a05462b3579de 100644
--- a/mlir/include/mlir/Dialect/XeGPU/IR/XeGPUAttrs.td
+++ b/mlir/include/mlir/Dialect/XeGPU/IR/XeGPUAttrs.td
@@ -22,14 +22,16 @@ def XeGPU_TensorDescAttr: XeGPUAttr<"TensorDesc", "tdesc_attr"> {
   let parameters = (ins
     OptionalParameter<"MemoryScopeAttr">: $memory_scope,
     OptionalParameter<"IntegerAttr", "1">: $array_length,
-    OptionalParameter<"BoolAttr", "true">: $boundary_check
+    OptionalParameter<"BoolAttr", "true">: $boundary_check,
+    OptionalParameter<"BoolAttr", "false">: $scattered
   );
 
   let builders = [
     AttrBuilder<(ins
       CArg<"xegpu::MemoryScope", "xegpu::MemoryScope::Global">:$memory_scope,
       CArg<"int", "1">:$array_length,
-      CArg<"bool", "true">: $boundary_check
+      CArg<"bool", "true">: $boundary_check,
+      CArg<"bool", "false">: $scattered
     )>
   ];
 
@@ -41,14 +43,14 @@ def XeGPU_TensorDescAttr: XeGPUAttr<"TensorDesc", "tdesc_attr"> {
 //===----------------------------------------------------------------------===//
 def XeGPU_MemoryScopeGlobal: I32EnumAttrCase<"Global", 0, "global">;
 def XeGPU_MemoryScopeShared: I32EnumAttrCase<"SLM", 1, "slm">;
-def XeGPU_MemoryScope: I32EnumAttr<"MemoryScope", 
-      "The address space of the memory the tensor descritor is created for", 
+def XeGPU_MemoryScope: I32EnumAttr<"MemoryScope",
+      "The address space of the memory the tensor descritor is created for",
       [XeGPU_MemoryScopeGlobal, XeGPU_MemoryScopeShared]> {
   let genSpecializedAttr = 0;
   let cppNamespace = "::mlir::xegpu";
 }
 
-def XeGPU_MemoryScopeAttr: 
+def XeGPU_MemoryScopeAttr:
   EnumAttr<XeGPU_Dialect, XeGPU_MemoryScope, "memory_scope"> {
     let assemblyFormat = "$value";
 }
@@ -63,15 +65,15 @@ def XeGPU_CachePolicyInvalid:       I32EnumAttrCase<"READ_INVALIDATE", 3, "read_
 def XeGPU_CachePolicyWriteBack:     I32EnumAttrCase<"WRITE_BACK", 4, "write_back">;            // valid for write only
 def XeGPU_CachePolicyWriteThrough:  I32EnumAttrCase<"WRITE_THROUGH", 5, "write_through">;      // valid for write only
 
-def XeGPU_CachePolicyEnums : I32EnumAttr<"CachePolicy", "Cache policy", 
-  [XeGPU_CachePolicyCached, XeGPU_CachePolicyUncached, 
+def XeGPU_CachePolicyEnums : I32EnumAttr<"CachePolicy", "Cache policy",
+  [XeGPU_CachePolicyCached, XeGPU_CachePolicyUncached,
    XeGPU_CachePolicyStreaming, XeGPU_CachePolicyInvalid,
    XeGPU_CachePolicyWriteBack, XeGPU_CachePolicyWriteThrough]> {
   let genSpecializedAttr = 0;
   let cppNamespace = "::mlir::xegpu";
 }
 
-def XeGPU_CacheHintAttr 
+def XeGPU_CacheHintAttr
   : EnumAttr<XeGPU_Dialect, XeGPU_CachePolicyEnums, "cache_hint"> {
     let assemblyFormat = "`<` $value `>`";
 }
diff --git a/mlir/include/mlir/Dialect/XeGPU/IR/XeGPUOps.td b/mlir/include/mlir/Dialect/XeGPU/IR/XeGPUOps.td
index 93c56ad05b432c..0380ff83581517 100644
--- a/mlir/include/mlir/Dialect/XeGPU/IR/XeGPUOps.td
+++ b/mlir/include/mlir/Dialect/XeGPU/IR/XeGPUOps.td
@@ -46,36 +46,35 @@ class XeGPU_Op<string mnemonic, list<Trait> traits = []>:
 }
 
 
-def XeGPU_CreateNdDescOp: XeGPU_Op<"create_nd_tdesc", [Pure, ViewLikeOpInterface, 
+def XeGPU_CreateNdDescOp: XeGPU_Op<"create_nd_tdesc", [Pure, ViewLikeOpInterface,
                         AttrSizedOperandSegments, OffsetSizeAndStrideOpInterface]> {
 
   let summary = "Create nd-tensor descriptor operation";
   let description = [{
     The "create_nd_tdesc" operation creates a TensorDescType which represents
     a sub-view of a 2D memory region (It can be extended to support n-D memory
-    region if needed in future). Elements in the subview continuous in each 
-    dimention. It encodes the following important information for supporting 
+    region if needed in future). Elements in the subview continuous in each
+    dimention. It encodes the following important information for supporting
     Intel hardware features:
 
-    * source: an object representing (starting address/pointer of) a 2D memory region. 
+    * source: an object representing (starting address/pointer of) a 2D memory region.
         It can be either a 2D memref object, or simply a pointer represented by uint64_t type.
-        for the later case, the shape and layout information of the 2D memory region should 
-        be explicitly passed via `dynamic_shape` and `dynamic_strides` parameters.
-    * offsets: two index values represents offsets from the "source" at the each dimension 
+        for the later case, the shape and layout information of the 2D memory region should
+        be explicitly passed via `shape` and `strides` parameters.
+    * offsets: two index values represents offsets from the "source" at the each dimension
         at which the subview of the target memory will be created. It is encoded via two
-        variables, including "dynamic_offsets" and "static_offsets", such that it can
-        accept various forms, such as, operands (e.g., [%c0, %c]) and attributes (e.g., [2, 4])).
-    * shape: the shape information of the memory region pointed by the "source".  It is 
-        typically encoded via the MemRefType of the source, e.g., memref<4096x4096xf16>. 
-        But if "source" is simply a pointer represented as uint64_t type, or a memref 
-        type without shape information e.g., memref<?x?xf16>, the shape information has 
-        to be explicitly passed via the "dynamic_shape" argument. Currently "dynamic_shape" 
-        only accepts operands(e.g., [%c4096, %c4096]), not attributes(e.g., [4096, 4096]).
-    * strides: the strides of the memory region pointed by the "source". Similar to shape, 
-        it is typically encoded via the MemRefType of the source too. But if "source" is 
-        simply a pointer represented as uint64_t type, or a memref type without shape 
-        information e.g., memref<?x?xf16>, the strides information has to be explicitly 
-        passed via the "dynamic_strides" argument. And it currently only accepts operands two.
+        variables, including "offsets" and "const_offsets", such that it can
+        accept various forms, such as, operands (e.g., [%c0, %c]) and attributes (e.g., [2, 4]).
+    * shape: the shape information of the memory region pointed by the "source".  It is
+        typically encoded via the MemRefType of the source, e.g., memref<4096x4096xf16>.
+        But if "source" is simply a pointer represented as uint64_t type, or a memref
+        type without shape information e.g., memref<?x?xf16>, the shape information has
+        to be explicitly passed via the "shape" and "const_shape" arguments.
+    * strides: the strides of the memory region pointed by the "source". Similar to shape,
+        it is typically encoded via the MemRefType of the source too. But if "source" is
+        simply a pointer represented as uint64_t type, or a memref type without shape
+        information e.g., memref<?x?xf16>, the strides information has to be explicitly
+        passed via the "strides" and "const_strides" argument.
 
     Example 1 (suppose the tensor shape inferred by the compiler is 8x16):
     %0 = memref.alloc() : memref<1024x1024xf32>
@@ -96,10 +95,10 @@ def XeGPU_CreateNdDescOp: XeGPU_Op<"create_nd_tdesc", [Pure, ViewLikeOpInterface
     %1 = xegpu.create_nd_tdesc %0[%c0, %c0], [%h, %w], [%w, %c1]: ui64 -> TensorDesc<8x16xf32>
   }];
 
-  let arguments = (ins 
-    XeGPU_BaseAddrType: $source, 
-    Variadic<Index>: $offsets, 
-    Variadic<Index>: $shape, 
+  let arguments = (ins
+    XeGPU_BaseAddrType: $source,
+    Variadic<Index>: $offsets,
+    Variadic<Index>: $shape,
     Variadic<Index>: $strides,
     DenseI64ArrayAttr: $const_offsets,
     OptionalAttr<DenseI64ArrayAttr>: $const_shape,
@@ -118,12 +117,12 @@ def XeGPU_CreateNdDescOp: XeGPU_Op<"create_nd_tdesc", [Pure, ViewLikeOpInterface
   let hasVerifier = 1;
 
   let builders = [
-    OpBuilder<(ins "Type": $tdesc, "TypedValue<MemRefType>": $source, 
+    OpBuilder<(ins "Type": $tdesc, "TypedValue<MemRefType>": $source,
                    "llvm::ArrayRef<OpFoldResult>": $offsets)>,
 
-    OpBuilder<(ins "Type": $tdesc, "TypedValue<IntegerType> ": $source, 
+    OpBuilder<(ins "Type": $tdesc, "TypedValue<IntegerType> ": $source,
                    "llvm::ArrayRef<OpFoldResult>": $offsets,
-                   "llvm::ArrayRef<OpFoldResult>": $shape, 
+                   "llvm::ArrayRef<OpFoldResult>": $shape,
                    "llvm::ArrayRef<OpFoldResult>": $strides)>
   ];
 
@@ -158,41 +157,41 @@ def XeGPU_CreateNdDescOp: XeGPU_Op<"create_nd_tdesc", [Pure, ViewLikeOpInterface
     }
 
     /// wrapper for matching with OffsetSizeAndStrideOpInterface
-    /// If source is IntegerType or `const_shape` is filled, 
+    /// If source is IntegerType or `const_shape` is filled,
     /// it will return `const_shape`, such that mixes of `shape`
-    /// and `const_shape` will be used to represent the shape of 
+    /// and `const_shape` will be used to represent the shape of
     /// source operand. They overide static shape from source memref type.
     ArrayRef<int64_t> getStaticSizes() {
       auto attr = getConstShapeAttr();
       if (getSourceType().isa<IntegerType>() || attr)
         return attr;
-      
+
       auto memrefType = getSourceType().dyn_cast<MemRefType>();
       assert(memrefType && "Incorrect use of getStaticSizes");
       return memrefType.getShape();
     }
 
     /// wrapper for matching with OffsetSizeAndStrideOpInterface
-    /// If source is IntegerType or `const_strides` is filled, it 
+    /// If source is IntegerType or `const_strides` is filled, it
     /// will return `const_strides`, such that mixes of `strides`
-    /// and `const_strides` will be used to represent the strides of 
+    /// and `const_strides` will be used to represent the strides of
     /// source operand. They overide static strides from source memref type.
     ArrayRef<int64_t> getStaticStrides() {
       auto attr = getConstStridesAttr();
       if (getSourceType().isa<IntegerType>() || attr)
         return attr;
-      
+
       auto memrefType = getSourceType().dyn_cast<MemRefType>();
       assert(memrefType && "Incorrect use of getStaticStrides");
       auto [strides, offset] = getStridesAndOffset(memrefType);
-      // reuse the storage of ConstStridesAttr since strides from 
+      // reuse the storage of ConstStridesAttr since strides from
       // memref is not persistant
       setConstStrides(strides);
       attr = getConstStridesAttr();
       return attr;
     }
 
-    /// Return the expected rank of each of the`static_offsets`, 
+    /// Return the expected rank of each of the`static_offsets`,
     /// `static_shape` and `static_strides` attributes.
     std::array<unsigned, 3> getArrayAttrMaxRanks() {
       unsigned rank;
@@ -203,8 +202,8 @@ def XeGPU_CreateNdDescOp: XeGPU_Op<"create_nd_tdesc", [Pure, ViewLikeOpInterface
       }
       return {rank, rank, rank};
     }
-    
-    /// Return the number of leading operands before the `offsets`, 
+
+    /// Return the number of leading operands before the `offsets`,
     /// `shape` and `strides` operands.
     static unsigned getOffsetSizeAndStrideStartOperandIndex() { return 1; }
 
@@ -213,15 +212,15 @@ def XeGPU_CreateNdDescOp: XeGPU_Op<"create_nd_tdesc", [Pure, ViewLikeOpInterface
 }
 
 def XeGPU_PrefetchNdOp : XeGPU_Op<"prefetch_nd", []> {
-  let summary = "prefetches a nD block to cache";
+  let summary = "prefetches a n-D block to cache";
   let description = [{
-    It issues an instruction to prefetch the data from memory to each 
-    level of the cache based on their cache policy.
+    It issues an instruction to prefetch a block of data from continuous
+    memory regions to each level of the cache based on their cache policy.
 
     Example:
     ```
-      xegpu.prefetch_nd %tdesc {l1_hint = #xegpu.cache_hint<cached>, 
-                                l2_hint = #xegpu.cache_hint<cached>, 
+      xegpu.prefetch_nd %tdesc {l1_hint = #xegpu.cache_hint<cached>,
+                                l2_hint = #xegpu.cache_hint<cached>,
                                 l3_hint = #xegpu.cache_hint<cached>}
         : !xegpu.tensor_desc<8x16xf16>
     ```
@@ -232,34 +231,41 @@ def XeGPU_PrefetchNdOp : XeGPU_Op<"prefetch_nd", []> {
                        OptionalAttr<XeGPU_CacheHintAttr>: $l1_hint,
                        OptionalAttr<XeGPU_CacheHintAttr>: $l2_hint,
                        OptionalAttr<XeGPU_CacheHintAttr>: $l3_hint);
-                       
-  let extraClassDeclaration = extraBaseClassDeclaration;
+
+  let extraClassDeclaration = extraBaseClassDeclaration # [{
+    xegpu::TensorDescType getTensorDescType() {
+      return getTensorDesc().getType();
+    }
+  }];
 
   let assemblyFormat = "$TensorDesc prop-dict attr-dict `:` qualified(type($TensorDesc))";
+
+  let hasVerifier = 1;
 }
 
 
-def XeGPU_LoadNdOp : XeGPU_Op<"load_nd"> {
-  let summary = "loads a n-D block from memory (represented by TensorDesc)" 
+def XeGPU_LoadNdOp : XeGPU_Op<"load_nd", [AllElementTypesMatch<["value", "TensorDesc"]>,
+                                         AllElementCountsMatch<["value", "TensorDesc"]>]> {
+  let summary = "loads a n-D block from memory (represented by TensorDesc)"
                 "to registers (represented by vector)";
   let description = [{
-    LoadNdOp essentially mimics the hardware block read instruction to read 
-    a block of data from memory to register. It takes a set of optional cache 
-    hints for each level of cache, L1, L2 and L3. If hardware does not have a 
+    LoadNdOp essentially mimics the hardware block read instruction to read
+    a block of data from memory to register. It takes a set of optional cache
+    hints for each level of cache, L1, L2 and L3. If hardware does not have a
     correspoding cache, Corresponding cache hint attribute will be masked.
-    vnni transform is an hardware feature for Intel GPU, which is used to 
-    do data packing during the load for B operand of matrix operation, if 
-    the bit width of the data type is less then 32 bits, e.g., fp16. And 
+    vnni transform is an hardware feature for Intel GPU, which is used to
+    do data packing during the load for B operand of matrix operation, if
+    the bit width of the data type is less then 32 bits, e.g., fp16. And
     transpose is another Intel hardware feature, which will do transpose
-    operation when loading the data if the bit width of the data type is 
-    fp32 or fp64. It implies that vnni and transpose cannot exit at the 
+    operation when loading the data if the bit width of the data type is
+    fp32 or fp64. It implies that vnni and transpose cannot exit at the
     same time.
 
     Example:
     ```
       xegpu.load_nd %1 {transpose = [1, 0],
-                        l1_hint = #xegpu.cache_hint<cached>, 
-                        l2_hint = #xegpu.cache_hint<uncached>, 
+                        l1_hint = #xegpu.cache_hint<cached>,
+                        l2_hint = #xegpu.cache_hint<uncached>,
                         l3_hint = #xegpu.cache_hint<streaming>}
               : !xegpu.tensor_desc<8x16xf32> -> vector<16x8xf32>
     ```
@@ -290,20 +296,21 @@ def XeGPU_LoadNdOp : XeGPU_Op<"load_nd"> {
   let hasVerifier = 1;
 }
 
-def XeGPU_StoreNdOp : XeGPU_Op<"store_nd", []> {
+def XeGPU_StoreNdOp : XeGPU_Op<"store_nd", [AllShapesMatch<["value", "TensorDesc"]>,
+                                       AllElementTypesMatch<["value", "TensorDesc"]>]> {
   let summary = "stores a n-D block register region back to memory, currently only supports 2D";
 
   let description = [{
     StoreNdOp essentially mimics the hardware block write instruction io
-    write a block of data from register into the memory region as described 
-    by the TensorDesc. It takes a set of optional cache hints for each level 
-    of cache, L1, L2 and L3. If hardware does not have a correspoding cache, 
+    write a block of data from register into the memory region as described
+    by the TensorDesc. It takes a set of optional cache hints for each level
+    of cache, L1, L2 and L3. If hardware does not have a correspoding cache,
     Corresponding cache hint attribute will be masked.
 
     Example:
     ```
       xegpu.store_nd %3, %2 {l1_hint = #xegpu.cache_hint<uncached>,
-                             l2_hint = #xegpu.cache_hint<write_back>, 
+                             l2_hint = #xegpu.cache_hint<write_back>,
                              l3_hint = #xegpu.cache_hint<write_through>}
                              : vector<8x16xf16>, !xegpu.tensor_desc<8x16xf16>
     ```
@@ -317,11 +324,327 @@ def XeGPU_StoreNdOp : XeGPU_Op<"store_nd", []> {
                        OptionalAttr<XeGPU_CacheHintAttr>: $l2_hint,
                        OptionalAttr<XeGPU_CacheHintAttr>: $l3_hint);
 
-  let extraClassDeclaration = extraBaseClassDeclaration;
+  let extraClassDeclaration = extraBaseClassDeclaration # [{
+    VectorType getValueType() {
+      return llvm::dyn_cast<VectorType>(getValue().getType());
+    }
+
+    xegpu::TensorDescType getTensorDescType() {
+      return getTensorDesc().getType();
+    }
+  }];
 
-  let assemblyFormat = [{$value `,` $TensorDesc prop-dict attr-dict 
+  let assemblyFormat = [{$value `,` $TensorDesc prop-dict attr-dict
                         `:` type($value) `,` qualified(type($TensorDesc))}];
   let hasVerifier = 1;
 }
 
+def XeGPU_UpdateNdOffsetOp : XeGPU_Op<"update_nd_offset",
+                [AllTypesMatch<["TensorDesc", "result"]>]> {
+  let summary = "It updates the offsets for the TensorDesc.";
+  let description = [{The op updates the offset of the given TensorDesc.
+    The offsets are relative offset to the current position in the number
+    of elements. It will result in a same type TensorDesc as the input.
+
+  example:
+  ```
+    %2 = xegpu.update_nd_offset %1, [0, 16]: !xegpu.tensor_desc<8x16xf32>
+  ```
+  }];
+
+  let arguments = (ins
+    XeGPU_TensorDesc: $TensorDesc,
+    Variadic<Index>: $offsets,
+    DenseI64ArrayAttr: $const_offsets);
+
+  let results = (outs XeGPU_TensorDesc: $result);
+
+  let extraClassDeclaration = extraBaseClassDeclaration # [{
+    xegpu::TensorDescType getTensorDescType() {
+      return getTensorDesc().getType();
+    }
+
+    SmallVector<OpFoldResult> getMixedOffsets() {
+      Builder b(getContext());
+      return getMixedValues(getConstOffsets(), getOffsets(), b);
+    }
+
+    size_t getNumOffsets() {
+      return getMixedOffsets().size();
+    }
+
+    OpFoldResult getOffset(unsigned idx) {
+      assert(idx < getNumOffsets() && "Invalid out of bound access.");
+      return getMixedOffsets()[idx];
+    }
+  }];
+
+  let assemblyFormat = [{
+    $TensorDesc `,`
+    custom<DynamicIndexList>($offsets, $const_offsets)
+    attr-dict `:` qualified(type($result))
+  }];
+
+  let hasVerifier = 1;
+}
+
+def XeGPU_CreateDescOp: XeGPU_Op<"create_tdesc", [Pure, ViewLikeOpInterface]> {
+  let summary = "create scattered tensor descriptors (TensorDesc).";
+  let description = [{
+    "create_tdesc" is similar to "create_nd_tdesc" in terms that it creates
+    a Tensor Descriptor (TensorDescType) for a memory region. While "create_nd_tdesc"
+    is for creating continious subviews, "create_tdesc" is for creating non-continious
+    (scattered) subviews, allowing each work-item in a subgroup specifying their own offset.
+    It accepts the following parameters:
+
+    * source: a 1D memref or pointer (uint64_t) represents the flattened memory object.
+    * offsets: a array containing offsets of each access point. Its size
+      is fixed to the hardware supportted subgroup size, e.g., 16 on PVC,
+      implying each element in the array corresponds to a work-item (SIMT lane)
+      in the subgroup.
+    * chunk_size: [optional attribute] indicates number...
[truncated]

``````````

</details>


https://github.com/llvm/llvm-project/pull/86594


More information about the Mlir-commits mailing list