.. index:: pair: page; Verbose Message Catalogue .. _doxid-dev_guide_verbose_table: Verbose Message Catalogue ========================= The following catalogue lists verbose messages, explanations, and additional information for: primitive creation and dispatch checks for primitive implementations; and implementation failures that occur during engine/memory object creation. Primitive Creation/Dispatching ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ =============================================================================== =========================================================================================================================== ============================ ======================================================================================================================================================================================================================================================================================================================================================================================= VERBOSE MESSAGE SUBSTRING PRIMITIVE EXPLANATION =============================================================================== =========================================================================================================================== ============================ ======================================================================================================================================================================================================================================================================================================================================================================================= **Bad/Invalid Arguments** ``bad algorithm`` all Bad or invalid algorithm ``:ref:`dnnl::algorithm ``` selected for the current primitive implementation. The choice and availability of the algorithm depends on the specific implementation selected for the primitive. For example, oneDNN supports Winograd convolution only on GPU and AArch64 CPU systems. ``bad propagation kind`` all Incorrect propagation kind ``:ref:`dnnl::prop_kind ``` ( ``forward_training`` , ``backward_weights`` , ``backward_data`` , etc.) selected for the primitive. ``bad param

`` ``p`` - initialization parameter for ``:ref:`dnnl::primitive_desc ``` all Invalid parameter passed for the initialization of the primitive descriptor. **Example** : For the ``group_normalization`` primitive, this message is displayed when the value passed for the ``groups`` parameter does not evenly divide the number of channels for the source tensor. ``one of the mandatory arguments is nullptr`` all A NULL pointer argument exception for the primitive methods. ``bad flags`` all Bad or unsupported flags specified for the initialization of the primitive descriptor ``:ref:`dnnl::primitive_desc ``` . **Unsupported Arguments/Parameters** ``unsupported isa`` all Primitive implementation does not support the current ISA. This typically results in the dispatching to the next best supporting implementation for the ISA. ``unsupported datatype`` all Tensor data type is not supported for the current primitive implementation. Depending on the primitive, this may correspond to the source, weights, bias or destination tensors. ``unsupported datatype combination`` all Datatype combination for source, weights, bias or destination tensors is not supported for the current primitive implementation. ``unsupported attr`` all Bad or unsupported attributes ``:ref:`dnnl::primitive_attr ``` passed to the primitive descriptor for the current implementation. Since attributes are separately created from the corresponding primitive descriptor, the selected primitive implementation may not support the attribute configuration. ``unsupported post-ops`` all Unsupported post-ops configuration ``:ref:`dnnl::post_ops ``` passed on to the primitive descriptor. Similar to ``:ref:`dnnl::primitive_attr ``` , the selected implementation may not support the postop configuration during primitive creation. ``unsupported scales configuration`` all Unsupported scales configuration specified for the primitive attributes ``:ref:`dnnl::primitive_attr ``` . ``unsupported zero-point configuration`` all Unsupported zero-point configuration specified for the primitive attributes ``:ref:`dnnl::primitive_attr ``` . ``unsupported bias configuration`` compute-based primitives Unsupported bias data configuration specified for the descriptors. ``unsupported sparse md configuration`` all Current primitive implementation does not support sparse data operations. ``unsupported format tag`` all Unsupported format tag ``:ref:`dnnl::memory::format_tag ``` encountered during primitive operation. ``unsupported format tag for `` ``t`` - tensor all Unsupported format tag ``:ref:`dnnl::memory::format_tag ``` specified for tensor ``t`` during primitive operation. ``unsupported format kind`` all Unsupported format kind ``:ref:`dnnl::memory::format_kind ``` encountered during primitive operation. ``runtime dimension is not supported`` all Current implementation does not support processing runtime-specified shapes and strides using ``DNNL_RUNTIME_DIM_VAL`` . ``runtime dimension is inconsistent across tensors`` ``d`` - dimension all Runtime dimension specified using ``DNNL_RUNTIME_DIM_VAL`` is not consistent with every tensor in the primitive operation. ``unsupported md flags`` ``t`` - tensor all Unsupported flags specified for the memory descriptor for the tensor ``t`` . **Tensor Operations** ``tensor has no elements`` ``t`` - tensor all Empty tensor passed as data to the primitive. Depending on the primitive, this may correspond to the source, weights or destination tensors. `` has a bad number of dimensions `` ``t`` - tensor, ``ndims`` - number of tensor dimensions all Tensor data has bad or invalid number of dimensions for the current primitive operation. **Example** : The ``convolution`` primitive expects only 1D-, 2D- or 3D-spatial tensors for operations and prints this message for any other data with higher dimensions. ``bad dimensions :`` ``t`` - tensor, ``axis`` - axis all Tensor ```` has an invalid dimension along the specified axis. **Example** : The ``concat`` primitive prints this message when the destination tensor dimension along the concatenated axis does not match the sum of the dimensions of the concatenated tensors. ``dimension : is inconsistent with :`` ``t0, t1`` - tensors, ``a0, a1`` - tensor axes all Tensors ``t0, t1`` have inconsistent dimensions along axes ``a0`` and ``a1`` respectively. **Example** : This is encountered for the ``matmul`` primitive when the input matrices have mismatching dimensions. ``out-of-range dimensions for `` ``t`` - tensor all One of the dimensions of tensor ``t`` is beyond the maximum range that can be processed by the current implementation. ``tensors and have inconsistent number of dimensions`` ``t0, t1`` - tensors all Tensors ``t0, t1`` have inconsistent dimensions for primitive operation. ``tensors and have inconsistent number of dimensions (d0) and (d1)`` ``t0, t1`` - tensors all Tensors ``t0, t1`` have inconsistent dimensions ( ``d0`` , ``d1`` ) for primitive operation. ``tensors and have inconsistent datatypes`` ``t0, t1`` - tensors all Tensors ``t0, t1`` have inconsistent data types for primitive operation. ``invalid broadcast semantic on :`` ``t`` - tensor, ``d`` - dimension all Broadcasting semantic is not consistent with tensor ``t`` on dimension ``d`` . ``invalid datatype for `` ``t`` - tensor all Tensor ``t`` has a datatype that is invalid for the primitive operation. **Unsupported Combinations** ``sparse encoding is not supported on this isa`` all Current ISA does not support the primitive operation with sparse encoded tensors. ``datatype configuration not supported on this isa`` all Datatype combination for the primitive tensors is not supported for the current ISA. ``datatype and propagation kind mismatch`` all Tensor datatype is not supported for the current propagation kind ( ``:ref:`dnnl::impl::prop_kind ``` ) of the primitive. ``inconsistent and mds`` ``t0, t1`` - tensors all Tensors ``t0, t1`` have inconsistent memory descriptors ``:ref:`dnnl::memory::desc ``` for the primitive operation. ``memory formats for and tensors do not match`` ``t0, t1`` - tensors all Tensors ``t0, t1`` require similar `memory format `__ kinds for the primitive operation. **Implementation Heuristics/Features** ``unsupported feature for implementation: `` ``msg`` - feature description all Current implementation is skipped because it does not support the specified feature for the primitive operation. `` feature unavailable for device`` ``msg`` - feature description all Current implementation is skipped because the selected device does not support the specified feature for primitive operation. ``unsupported feature for padding: `` ``msg`` - feature description all Current implementation is skipped because of a padding inconsistency or unsupported feature related to padding. ``heuristic fail: `` ``h`` - implementation heuristic all Implementation skipped due to specified heuristic. ``blocking heuristic fail: `` ``h`` - implementation heuristic all Current implementation is skipped because of the specified inconsistency or implementation heuristic related to blocking. **Primitive-Specific Messages** ``heuristic fail for 1x1 convolution: `` ``h`` - implementation heuristic ``convolution`` Implementation skipped due to specified heuristic related to 1x1 convolution. `` offsets do not fit into

datatype`` ``o`` - { ``input`` , ``output`` }, ``dt`` - data type ``convolution`` I/O dimension offsets do not fit into the specified datatype range for the kernel implementation. ``failed shape restrictions`` ``convolution`` , ``gnorm`` Implementation skipped because the current data layout/shapes exceeds the range supported by the current implementation. ``alpha and beta parameters are not properly set`` ``eltwise`` Alpha and beta parameters are not properly set for the elementwise algorithm. ``large shapes fall back`` ``gemm`` Heuristic to skip current implementation for large tensor shapes for better performance. ``only trivial strides are supported`` ``gemm`` , ``rnn`` Current implementation for the primitive does not process non-trivial stride values. ``unsupported fpmath mode`` ``matmul`` `Floating-point math mode `__ is not supported by the current primitive implementation. ``small shapes fall back`` ``matmul`` Heuristic to skip current implementation for small tensor shapes for better performance. ``incompatible gemm format`` ``matmul`` , ``ip`` Specified GeMM format is incompatible with the current primitive implementation. ``unsupported tensor layout`` ``t`` - tensor ``reorder`` The data layout for the source/destination tensor is not supported by the current implementation. ``bad axis`` ``softmax`` , ``shuffle`` Bad or invalid axis specified for softmax/shuffle operation. ``unsupported architecture`` ``d`` - ``:ref:`dnnl::engine::kind ``` ``gemm`` Unsupported architecture for specified device-type. Typically encountered when current GPU device does not support the primitive. ``unsupported precomputed reductions configuration`` ``matmul`` Precomputed reductions for the parameter argument are not supported for the matmul operation. **Miscellaneous** ``failed to create nested primitive`` ``pm`` - ``:ref:`dnnl::primitive ``` all Descriptor initialization for the nested primitive implementation was unsuccessful. ``failed to create descriptor`` ``pm`` - ``:ref:`dnnl::primitive ``` , ``:ref:`dnnl::memory ``` all Descriptor initialization for the primitive or memory object was unsuccessful. ``bad accumulation mode`` all Bad or invalid `accumulation mode `__ specified for primitive attribute ``:ref:`dnnl::primitive_attr ``` . ``unsupported md flag`` ``t`` - tensor all Bad or unsupported flags specified for the memory descriptor ``:ref:`dnnl::memory::desc ``` . ``problem is not mathematically consistent`` all Parameters provided for primitive creation are not mathematically consistent with the formula for computation. **Example** : Negative dilation values for the convolution primitive. ``workspace mismatch between forward and backward primitive descriptors`` all Dispatch failure encountered when the backward and forward propagation primitives do not share the workspace memory. ``workspace initialization failed`` all `Workspace `__ descriptor initialization was unsuccessful during primitive creation. ``invalid datatype for `` ``t`` - tensor all The data type for the tensor/data processed by the primitive is invalid. **Example** : This is encountered when an undefined data type ``data_type::undef`` is specified for the accumulator. ``failed to run kernel deterministically`` all failed to run application in the `deterministic mode `__ . ``skipping or dispatching to another implementation`` all Printed when there is a failed heuristic that forces the implementation to be skipped in a favor of another one. ``failed to create kernel`` ``k`` - kernel name all Dispatch failure due to issues in kernel creation. =============================================================================== =========================================================================================================================== ============================ ======================================================================================================================================================================================================================================================================================================================================================================================= Engine Creation ~~~~~~~~~~~~~~~ =================================================================== ====================================================================================================================================================================== =============================== ==================================================================================================================================================================================================================== VERBOSE MESSAGE SUBSTRING ENGINE EXPLANATION =================================================================== ====================================================================================================================================================================== =============================== ==================================================================================================================================================================================================================== ``bad engine kind`` all Invalid value for ``:ref:`dnnl::engine::kind ``` encountered during engine creation. ``invalid device in environment: index `` ``d`` - ``:ref:`dnnl::engine::kind ``` , ``i`` - device index all Device of type ``:ref:`dnnl::engine::kind ``` and index ``i`` is invalid for the current environment. ``no device is available`` ``d`` - ``:ref:`dnnl::engine::kind ``` , ``k`` - ``dnnl::impl::runtime_kind`` all No device of type ``:ref:`dnnl::engine::kind ``` was found during engine creation. `` devices are available but device index was queried`` ``d`` - ``:ref:`dnnl::engine::kind ``` , ``n`` - number of ``d`` devices, ``i`` - queried device index all Queried index is out-of-range for device of type ``:ref:`dnnl::engine::kind ``` . ``device not found in the given context`` all Device mismatch with runtime context during engine creation. ``unsupported platform (expected got )`` ``d`` - ``:ref:`dnnl::engine::kind ``` , ``d0`` - queried platform, ``d1`` - available platform ``sycl`` , ``opencl`` , ``ze`` Unsupported device platform encountered during engine creation. ``failed to create engine with index `` ``d`` - ``:ref:`dnnl::engine::kind ``` , ``i`` - device index all Engine creation was unsuccessful for the specified device index and kind. ``unsupported backend`` ``d`` - ``:ref:`dnnl::engine::kind ``` ``sycl`` Unknown/unsupported backend encountered by the SYCL engine. ``profiling capabilities are not supported`` all Experimental profiling `ONEDNN_EXPERIMENTAL_PROFILING `__ is not enabled for the application. =================================================================== ====================================================================================================================================================================== =============================== ==================================================================================================================================================================================================================== Memory Creation and Related Operations ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ =========================================== ======================================================================================================================================================================== VERBOSE MESSAGE EXPLANATION =========================================== ======================================================================================================================================================================== ``bad arguments for memory descriptor`` Bad or unsupported values passed to the memory descriptor ``:ref:`dnnl::memory::desc ``` during memory object creation. ``invalid memory index`` An out-of-range value encountered for memory handle during data mapping. ``unsupported memory stride`` Memory descriptor initialization failed due to unsupported value for memory strides. ``scratchpad memory limit exceeded`` `Scratchpad `__ space is exhausted during GEMM kernel initialization. ``scratchpad initialization unsuccessful`` Dispatch failure to issue in scratch memory initialization. =========================================== ========================================================================================================================================================================