Intel® oneAPI Deep Neural Network Developer Guide and Reference
enum dnnl::query
Overview
Primitive descriptor query specification. More…
#include <dnnl.hpp>
enum query
{
undef = dnnl_query_undef,
engine = dnnl_query_engine,
primitive_kind = dnnl_query_primitive_kind,
num_of_inputs_s32 = dnnl_query_num_of_inputs_s32,
num_of_outputs_s32 = dnnl_query_num_of_outputs_s32,
time_estimate_f64 = dnnl_query_time_estimate_f64,
memory_consumption_s64 = dnnl_query_memory_consumption_s64,
scratchpad_engine = dnnl_query_scratchpad_engine,
reorder_src_engine = dnnl_query_reorder_src_engine,
reorder_dst_engine = dnnl_query_reorder_dst_engine,
impl_info_str = dnnl_query_impl_info_str,
prop_kind = dnnl_query_prop_kind,
cache_blob_id_size_s64 = dnnl_query_cache_blob_id_size_s64,
cache_blob_id = dnnl_query_cache_blob_id,
strides = dnnl_query_strides,
dilations = dnnl_query_dilations,
padding_l = dnnl_query_padding_l,
padding_r = dnnl_query_padding_r,
epsilon_f32 = dnnl_query_epsilon_f32,
flags = dnnl_query_flags,
alg_kind = dnnl_query_alg_kind,
alpha_f32 = dnnl_query_alpha_f32,
beta_f32 = dnnl_query_beta_f32,
axis_s32 = dnnl_query_axis_s32,
local_size_s64 = dnnl_query_local_size_s64,
k_f32 = dnnl_query_k_f32,
p_f32 = dnnl_query_p_f32,
factors = dnnl_query_factors,
cell_kind = dnnl_query_cell_kind,
direction = dnnl_query_direction,
activation_kind = dnnl_query_activation_kind,
kernel = dnnl_query_kernel,
group_size_s64 = dnnl_query_group_size_s64,
src_md = dnnl_query_src_md,
diff_src_md = dnnl_query_diff_src_md,
weights_md = dnnl_query_weights_md,
diff_weights_md = dnnl_query_diff_weights_md,
dst_md = dnnl_query_dst_md,
diff_dst_md = dnnl_query_diff_dst_md,
workspace_md = dnnl_query_workspace_md,
scratchpad_md = dnnl_query_scratchpad_md,
exec_arg_md = dnnl_query_exec_arg_md,
ndims_s32 = dnnl_query_ndims_s32,
dims = dnnl_query_dims,
data_type = dnnl_query_data_type,
submemory_offset_s64 = dnnl_query_submemory_offset_s64,
padded_dims = dnnl_query_padded_dims,
padded_offsets = dnnl_query_padded_offsets,
format_kind = dnnl_query_format_kind,
inner_nblks_s32 = dnnl_query_inner_nblks_s32,
inner_blks = dnnl_query_inner_blks,
inner_idxs = dnnl_query_inner_idxs,
sparse_encoding = dnnl_query_sparse_encoding,
nnz_s64 = dnnl_query_nnz_s64,
num_handles_s32 = dnnl_query_num_handles_s32,
};Detailed Documentation
Primitive descriptor query specification.
In general, queries are not used with the C++ API because most queries are implemented as class members.
See dnnl_query_t for more information.
Enum Values
undefno query
engineexecution engine
primitive_kindprimitive kind
num_of_inputs_s32number of inputs expected
num_of_outputs_s32number of outputs expected
time_estimate_f64runtime estimation (seconds), unimplemented
memory_consumption_s64memory required for scratchpad (bytes)
See also:
Primitive Attributes: Scratchpad
scratchpad_enginescratchpad engine
engine to be used for creating scratchpad memory
reorder_src_enginereorder source engine
reorder_dst_enginereorder destination engine
impl_info_strimplementation name
prop_kindpropagation kind
cache_blob_id_size_s64size of cache blob ID in bytes
cache_blob_idcache blob ID (pointer to array)
stridesstrides
dilationsdilations
padding_lleft padding
padding_rright padding
epsilon_f32epsilon
flagsflags
alg_kindalgorithm kind
alpha_f32alpha
beta_f32beta
axis_s32axis
local_size_s64LRN parameter local size.
k_f32LRN parameter K.
p_f32Reduction parameter P.
factorsResampling parameter factors.
cell_kindRNN parameter cell kind.
directionRNN parameter direction.
activation_kindRNN parameter activation kind.
kernelPooling parameter kernel.
group_size_s64Shuffle parameter group size.
src_mdsource memory desc
diff_src_mdsource gradient (diff) memory desc
weights_mdweights memory descriptor desc
diff_weights_mdweights gradient (diff) memory desc
dst_mddestination memory desc
diff_dst_mddestination gradient (diff) memory desc
workspace_mdworkspace memory desc
scratchpad_mdscratchpad memory desc
exec_arg_mdmemory desc of an execute argument
ndims_s32number of dimensions
dimsvector of dimensions
data_typedata type
submemory_offset_s64submemory offset
padded_dimsvector of padded dimensions
padded_offsetsvector of padded offsets
format_kindformat kind
inner_nblks_s32number of innermost blocks
inner_blksvector of sizes of the innermost blocks
inner_idxsvector of logical indices of the blocks
sparse_encodingSparse encoding.
nnz_s64Number of non-zero entries.
num_handles_s32Number of buffers required for a memory descriptor.