better MaterializeMergeSchedule.cpp with %lane indexed batch computes

support for tensors of index values
2026-05-22 21:52:28 +02:00
parent 495186503c
commit c77ffa9c56
20 changed files with 398 additions and 300 deletions
@@ -325,9 +325,9 @@ LogicalResult raptor::SpatialToPimPass::allocateAndInitializeCoreLocalVariables(
  auto insertMemCopyHostToDev = [&](Value inputTensor, int64_t elementsOffset) {
    auto tensorType = cast<ShapedType>(inputTensor.getType());
    Type elementType = tensorType.getElementType();
-    if (!elementType.isIntOrFloat())
+    if (!hasByteSizedElementType(elementType))
      return;
-    size_t elementByteSize = elementType.getIntOrFloatBitWidth() / 8;
+    size_t elementByteSize = getElementTypeSizeInBytes(elementType);
    rewriter.setInsertionPointAfter(inputTensor.getDefiningOp());

    auto deviceTensor = tensor::EmptyOp::create(rewriter, loc, tensorType.getShape(), elementType);