[Mlir-commits] [mlir] [MLIR][XeGPU][VectorToXeGPU] Lower vector.load/store/transfer_read/transfer_write to new offsets syntax (PR #162095)

[Adam Siemieniuk]

================
@@ -97,57 +97,49 @@ static LogicalResult transferPreconditions(PatternRewriter &rewriter,
   return success();
 }
 
-static xegpu::CreateNdDescOp
-createNdDescriptor(PatternRewriter &rewriter, Location loc,
-                   xegpu::TensorDescType descType, TypedValue<MemRefType> src,
-                   Operation::operand_range offsets) {
+static xegpu::CreateNdDescOp createNdDescriptor(PatternRewriter &rewriter,
+                                                Location loc,
+                                                xegpu::TensorDescType descType,
+                                                TypedValue<MemRefType> src) {
   MemRefType srcTy = src.getType();
   auto [strides, offset] = srcTy.getStridesAndOffset();
 
   xegpu::CreateNdDescOp ndDesc;
-  if (srcTy.hasStaticShape()) {
-    ndDesc = xegpu::CreateNdDescOp::create(rewriter, loc, descType, src,
-                                           getAsOpFoldResult(offsets));
-  } else {
+  if (srcTy.hasStaticShape())
+    ndDesc = xegpu::CreateNdDescOp::create(rewriter, loc, descType, src);
----------------
adam-smnk wrote:

nit: braces to match else

https://github.com/llvm/llvm-project/pull/162095