[Mlir-commits] [mlir] [mlir][sparse] implement lowering rules for IterateOp. (PR #95286)

Aart Bik llvmlistbot at llvm.org
Mon Jun 17 10:22:49 PDT 2024


================
@@ -34,6 +34,20 @@ convertIterSpaceType(IterSpaceType itSp, SmallVectorImpl<Type> &fields) {
   return success();
 }
 
+static std::optional<LogicalResult>
+convertIteratorType(IteratorType itTp, SmallVectorImpl<Type> &fields) {
+  // The actually Iterator Values (that are updated every iteration).
+  auto idxTp = IndexType::get(itTp.getContext());
+  // TODO: handle batch dimension.
+  assert(itTp.getEncoding().getBatchLvlRank() == 0);
+  if (!itTp.isUnique()) {
+    // Segment high for non-unqiue iterator.
----------------
aartbik wrote:

non-unique (typo)

https://github.com/llvm/llvm-project/pull/95286


More information about the Mlir-commits mailing list