[Mlir-commits] [mlir] [MLIR][XeGPU] Remove the transpose attribte from Gather/Scatter ops and Cleanup the documents (PR #145389)

[Chao Chen]

================
@@ -309,11 +310,23 @@ LogicalResult TensorDescType::verify(
     llvm::ArrayRef<int64_t> shape, mlir::Type elementType,
     mlir::Attribute encoding, mlir::Attribute layout) {
   size_t rank = shape.size();
-  // Low-precision types are packed in 32-bit units.
-  int32_t packingFactor = 32 / elementType.getIntOrFloatBitWidth();
   if (rank != 1 && rank != 2)
     return emitError() << "expected 1D or 2D tensor";
 
+  auto blockAttr = mlir::dyn_cast_if_present<BlockTensorDescAttr>(encoding);
+  if (blockAttr) {
+    MemorySpaceAttr memorySpaceAttr = blockAttr.getMemorySpace();
+    if (rank == 2 && memorySpaceAttr &&
+        memorySpaceAttr.getValue() == MemorySpace::SLM)
+      return emitError() << "SLM is not supported for 2D block tensor";
+  }
+
+  // for gather and scatter ops, Low-precision types are packed in 32-bit units.
+  unsigned bitWidth = elementType.getIntOrFloatBitWidth();
+  int packingFactor =
----------------
chencha3 wrote:

this is because chunk size is limited to 32-bit data type in PVC. so lower precision data will be loaded as 32-bit and then cast to lower precision. this limits the availability of chunk size. 

https://github.com/llvm/llvm-project/pull/145389