Skip to main content
Back to top
Ctrl
+
K
Building and Linking
Build from Source
Build Options
Linking to the Library
Programming Model
Basic Concepts
Getting started
Memory Format Propagation
Inference and Training Aspects
Inference
Int8 Inference
Bfloat16 Training
Primitive Attributes
Primitive Attributes: floating-point math mode
Primitive Attributes: accumulation mode
Primitive Attributes: rounding mode
Primitive Attributes: deterministic
Primitive Attributes: Quantization
Primitive Attributes: Post-ops
Primitive Attributes: Scratchpad
Data Types
Reorder between CPU and GPU engines
API
Interoperability with DPC++ and OpenCL
OpenCL Interoperability
DPC++ Interoperability
Supported Primitives
Convolution
Inner Product
Matrix Multiplication
RNN
Batch Normalization
Binary
Concat
Eltwise
Group Normalization
Layer Normalization
Local Response Normalization (LRN)
Pooling
PReLU
Resampling
Shuffle
Softmax
Sum
Reorder
Reduction
Graph Extension
Programming Model
Basic Concepts
Low Precision
Supported Operations
Abs
AbsBackward
Add
AvgPool
AvgPoolBackward
BatchNormForwardTraining
BatchNormInference
BatchNormTrainingBackward
BiasAdd
BiasAddBackward
Clamp
ClampBackward
Concat
Convolution
ConvolutionBackwardData
ConvolutionBackwardWeights
ConvTranspose
ConvTransposeBackwardData
ConvTransposeBackwardWeights
Dequantize
Divide
DynamicDequantize
DynamicQuantize
Elu
EluBackward
End
Exp
GroupNorm
GELU
GELUBackward
HardSigmoid
HardSigmoidBackward
HardSwish
HardSwishBackward
Interpolate
InterpolateBackward
LayerNorm
LayerNormBackward
LeakyReLU
Log
LogSoftmax
LogSoftmaxBackward
MatMul
Maximum
MaxPool
MaxPoolBackward
Minimum
Mish
MishBackward
Multiply
Pow
PReLU
PReLUBackward
Quantize
Reciprocal
ReduceL1
ReduceL2
ReduceMax
ReduceMean
ReduceMin
ReduceProd
ReduceSum
ReLU
ReLUBackward
Reorder
Round
Select
Sigmoid
SigmoidBackward
SoftMax
SoftMaxBackward
SoftPlus
SoftPlusBackward
Sqrt
SqrtBackward
Square
SquaredDifference
StaticReshape
StaticTranspose
Subtract
Tanh
TanhBackward
TypeCast
Wildcard
Fusion Patterns
Gated Multi-Layer Perceptron (Gated-MLP)
Grouped Query Attention (GQA)
SDPA with Compressed Key and Value
Scaled Dot-Product Attention (SDPA)
Graph Dump
Constant Tensor Cache
Examples
Performance Profiling and Inspection
Verbose Mode
Configuring oneDNN for Benchmarking
Benchmarking Performance
Profiling oneDNN Performance
Inspecting JIT Code
Performance Profiling Example
CPU Dispatcher Control
CPU ISA Hints
Verbose Message Catalogue
Advanced Topics
Transitioning from Intel MKL-DNN to oneDNN
Understanding Memory Formats
Nuances of int8 Computations
Primitive Cache
Persistent Cache
Using oneDNN with Threadpool-Based Threading
Experimental features
Ukernels
Basic Concepts
Batch-Reduce General Matrix Multiplication
Data transformation
BRGeMM ukernel example
oneDNN API
Primitives
Common
enum dnnl_alg_kind_t
enum dnnl_normalization_flags_t
enum dnnl_primitive_kind_t
enum dnnl_prop_kind_t
enum dnnl_query_t
enum dnnl::normalization_flags
enum dnnl::query
struct dnnl_exec_arg_t
struct dnnl_primitive
struct dnnl_primitive_desc
struct dnnl::primitive
struct dnnl::primitive_desc
struct dnnl::primitive_desc_base
Attributes
enum dnnl::algorithm
enum dnnl_rounding_mode_t
enum dnnl_scratchpad_mode_t
enum dnnl::prop_kind
enum dnnl::rounding_mode
enum dnnl::scratchpad_mode
struct dnnl_post_ops
struct dnnl_primitive_attr
struct dnnl::post_ops
struct dnnl::primitive_attr
Reorder
struct dnnl::reorder
Concat
struct dnnl::concat
Sum
struct dnnl::sum
Binary
struct dnnl::binary
Convolution
struct dnnl::convolution_backward_data
struct dnnl::convolution_backward_weights
struct dnnl::convolution_forward
Deconvolution
struct dnnl::deconvolution_backward_data
struct dnnl::deconvolution_backward_weights
struct dnnl::deconvolution_forward
Shuffle
struct dnnl::shuffle_backward
struct dnnl::shuffle_forward
Eltwise
struct dnnl::eltwise_backward
struct dnnl::eltwise_forward
Softmax
struct dnnl::softmax_backward
struct dnnl::softmax_forward
Pooling
struct dnnl::pooling_backward
struct dnnl::pooling_forward
PReLU
struct dnnl::prelu_backward
struct dnnl::prelu_forward
LRN
struct dnnl::lrn_backward
struct dnnl::lrn_forward
Batch Normalization
struct dnnl::batch_normalization_backward
struct dnnl::batch_normalization_forward
Group Normalization
struct dnnl::group_normalization_backward
struct dnnl::group_normalization_forward
Layer Normalization
struct dnnl::layer_normalization_backward
struct dnnl::layer_normalization_forward
Inner Product
struct dnnl::inner_product_backward_data
struct dnnl::inner_product_backward_weights
struct dnnl::inner_product_forward
RNN
enum dnnl_rnn_direction_t
enum dnnl_rnn_flags_t
enum dnnl::rnn_direction
enum dnnl::rnn_flags
struct dnnl::augru_backward
struct dnnl::augru_forward
struct dnnl::gru_backward
struct dnnl::gru_forward
struct dnnl::lbr_augru_backward
struct dnnl::lbr_augru_forward
struct dnnl::lbr_gru_backward
struct dnnl::lbr_gru_forward
struct dnnl::lstm_backward
struct dnnl::lstm_forward
struct dnnl::rnn_primitive_desc_base
struct dnnl::vanilla_rnn_backward
struct dnnl::vanilla_rnn_forward
Matrix Multiplication
struct dnnl::matmul
Resampling
struct dnnl::resampling_backward
struct dnnl::resampling_forward
Reduction
struct dnnl::reduction
Primitive Cache
Profiling
enum dnnl::profiling_data_kind
BLAS functions
Common API
Engine
enum dnnl_engine_kind_t
struct dnnl_engine
struct dnnl::engine
Stream
enum dnnl_stream_flags_t
struct dnnl_stream
struct dnnl::stream
Floating-point Math Mode
enum dnnl_fpmath_mode_t
enum dnnl::fpmath_mode
Service
enum dnnl::cpu_isa
enum dnnl::cpu_isa_hints
enum dnnl_cpu_isa_hints_t
enum dnnl_cpu_isa_t
enum dnnl::status
struct dnnl_version_t
Utilities
enum dnnl_status_t
struct dnnl::error
template struct dnnl::handle
template struct dnnl::handle_traits
Accumulation Mode
enum dnnl::accumulation_mode
enum dnnl_accumulation_mode_t
Data types
enum dnnl_data_type_t
Memory
enum dnnl_format_kind_t
enum dnnl_format_tag_t
enum dnnl_profiling_data_kind_t
enum dnnl_sparse_encoding_t
struct dnnl_memory
struct dnnl_memory_desc
struct dnnl::memory
Graph API
Allocator
class dnnl::graph::allocator
Engine
Logical Tensor
enum dnnl_graph_layout_type_t
enum dnnl_graph_tensor_property_t
struct dnnl_graph_logical_tensor_t
class dnnl::graph::logical_tensor
Tensor
class dnnl::graph::tensor
Op
enum dnnl_graph_op_attr_t
enum dnnl_graph_op_kind_t
class dnnl::graph::op
Partition
enum dnnl_graph_partition_policy_t
class dnnl::graph::partition
Compiled Partition
struct dnnl_graph_inplace_pair_t
class dnnl::graph::compiled_partition
Graph
class dnnl::graph::graph
Compiled Partition Cache
Constant Tensor Cache
Runtime interoperability API
OpenCL interoperability API
SYCL interoperability API
namespace dnnl::graph
Runtime interoperability API
OpenCL interoperability API
namespace dnnl::ocl_interop
enum dnnl_ocl_interop_memory_kind_t
SYCL interoperability API
namespace dnnl::sycl_interop
enum dnnl_sycl_interop_memory_kind_t
Threadpool interoperability API
namespace dnnl::threadpool_interop
Ukernels
BRGeMM ukernel
struct dnnl::ukernel::brgemm
struct dnnl_brgemm
struct dnnl_transform
namespace dnnl::ukernel
enum dnnl_pack_type_t
struct dnnl_ukernel_attr_params
namespace dnnl
namespace oneapi
Repository
Open issue
.rst
.pdf
struct dnnl_transform
struct dnnl_transform
#
An opaque structure to describe a transform routine.
