centralize logic for materializing contiguous memory into bufferization

fix codegen symlinks overwrite
remove deprecated pim memcp_hd_batch op
This commit is contained in:
NiccoloN
2026-05-30 15:54:24 +02:00
parent 2d5b03c08f
commit ff36729140
29 changed files with 642 additions and 822 deletions
@@ -6,20 +6,6 @@
namespace onnx_mlir {
/**
* \brief Get the offset of the ExtractSliceOp based on its static offsets and
* its static tensor input.
*
* The static offsets represent the starting position of the slice in each
* dimension, while the static tensor input gives its dimension size.
*
* \param sliceOp The ExtractSliceOp for which the actual offset needs to be
* calculated.
* \param inputShape The ShapedType of the ExtractSliceOp's input tensor
* \return The actual offset of the ExtractSliceOp.
*/
size_t getSliceActualOffset(mlir::tensor::ExtractSliceOp& sliceOp, mlir::ShapedType& inputShape);
mlir::IntegerAttr getTensorSizeInBytesAttr(mlir::Builder& builder, mlir::Value value);
template <class T>