|
mxnet
|
|
mxnet
|
|
Classes | |
| struct | dnnl_blocking_desc_t |
| struct | dnnl_wino_desc_t |
| Description of tensor of weights for winograd 2x3 convolution. More... | |
| struct | dnnl_rnn_packed_desc_t |
| Description of tensor of packed weights for rnn. More... | |
| struct | dnnl_memory_extra_desc_t |
| Description of extra information stored in memory. More... | |
| struct | dnnl_memory_desc_t |
| struct | dnnl_memory |
Macros | |
| #define | DNNL_MAX_NDIMS 12 |
| #define | DNNL_RUNTIME_DIM_VAL INT64_MIN |
| #define | DNNL_RUNTIME_SIZE_VAL ((size_t)DNNL_RUNTIME_DIM_VAL) |
| #define | DNNL_RUNTIME_F32_VAL (DNNL_RUNTIME_F32_VAL_REP.f) |
| #define | DNNL_RUNTIME_S32_VAL DNNL_RUNTIME_S32_VAL_REP |
| #define | DNNL_RNN_MAX_N_PARTS 4 |
| #define | DNNL_MEMORY_NONE (NULL) |
| #define | DNNL_MEMORY_ALLOCATE ((void *)(size_t)-1) |
Typedefs | |
| typedef int64_t | dnnl_dim_t |
| A type to describe tensor dimension. More... | |
| typedef dnnl_dim_t | dnnl_dims_t[DNNL_MAX_NDIMS] |
| A type to describe tensor dimensions. More... | |
| typedef struct dnnl_memory * | dnnl_memory_t |
| A memory handle. More... | |
| typedef const struct dnnl_memory * | const_dnnl_memory_t |
| A constant memory handle. More... | |
| #define DNNL_MAX_NDIMS 12 |
Maximum number of dimensions a tensor can have. Only restricts the amount of space used for the tensor description. Individual computational primitives may support only tensors of certain dimensions.
| #define DNNL_MEMORY_ALLOCATE ((void *)(size_t)-1) |
| #define DNNL_MEMORY_NONE (NULL) |
| #define DNNL_RNN_MAX_N_PARTS 4 |
Maximum number of parts of RNN weights tensor that require separate computation.
| #define DNNL_RUNTIME_DIM_VAL INT64_MIN |
A wildcard value for dimensions that are unknown at a primitive creation time.
| #define DNNL_RUNTIME_F32_VAL (DNNL_RUNTIME_F32_VAL_REP.f) |
A wildcard value for floating point values that are unknown at a primitive creation time.
| #define DNNL_RUNTIME_S32_VAL DNNL_RUNTIME_S32_VAL_REP |
A wildcard value for int32_t values that are unknown at a primitive creation time.
| #define DNNL_RUNTIME_SIZE_VAL ((size_t)DNNL_RUNTIME_DIM_VAL) |
A size_t counterpart of the DNNL_RUNTIME_DIM_VAL. For instance, this value is returned by dnnl_memory_desc_get_size() if either of the dimensions or strides equal to DNNL_RUNTIME_DIM_VAL.
| typedef const struct dnnl_memory* const_dnnl_memory_t |
A constant memory handle.
| typedef int64_t dnnl_dim_t |
A type to describe tensor dimension.
| typedef dnnl_dim_t dnnl_dims_t[DNNL_MAX_NDIMS] |
A type to describe tensor dimensions.
| typedef struct dnnl_memory* dnnl_memory_t |
A memory handle.
| enum dnnl_data_type_t |
Data type specification.
| enum dnnl_format_kind_t |
Memory format kind.
| Enumerator | |
|---|---|
| dnnl_format_kind_undef |
Undefined memory format kind, used for empty memory descriptors. |
| dnnl_format_kind_any |
Unspecified format kind. The primitive selects a format automatically. |
| dnnl_blocked |
A tensor in a generic format described by the stride and blocking values in each dimension. See dnnl_blocking_desc_t for more information. |
| dnnl_format_kind_wino |
Weights format used in 8bit Winograd convolution. |
| dnnl_format_kind_rnn_packed |
Packed weights format used in RNN. |
| enum dnnl_format_tag_t |
Memory format tag specification.
oneDNN formats describe physical data layout. The physical layout is described as a sequence of the dimensions as they are laid out in the memory (from the outer-most to the inner-most). Note that this order doesn't affect the logical order of the dimensions that is kept in the dims field of the dnnl_memory_desc_t structure. The logical order of the dimensions is specified by the primitive that uses the tensor.
For example, CNN 5D tensor always has its logical dimensions in the order (batch, channels, depth, height, width), while the physical layout might be NCDHW (corresponds to dnnl_ncdhw format tag) or NDHWC (corresponds to dnnl_ndhwc format tag).
Memory format tags can be further divided into two categories:
a to l to denote logical dimension from 1 to 12, and form the order in which the dimensions are laid in memory. For instance, dnnl_ab is used to denote 2D tensor where the second logical dimension (aka b) is the innermost, i.e. has stride = 1, and the first logical dimension (a) laid out in memory with stride equal to the size of second dimension. On the other hand, dnnl_ba is just transposed version of the same tensor: the first dimension (a) becomes the innermost one.a), channels correspond to the second one (b).The following domain-specific notation applies to memory format tags:
'n' denotes the mini-batch dimension'c' denotes a channels dimension'i' and 'o' denote dimensions of input and output channels'd', 'h', and 'w' denote spatial depth, height, and width respectivelyUpper-case letters indicate that the data is laid out in blocks for a particular dimension. In such cases, the format name contains both upper- and lower-case letters for that dimension with a lower-case letter preceded by the block size. For example: dnnl_nChw8c describes a format where the outermost dimension is mini-batch, followed by the channel block number, followed by the spatial height and width, and finally followed by 8-element channel blocks.
| Enumerator | |
|---|---|
| dnnl_format_tag_undef |
Undefined memory format tag. |
| dnnl_format_tag_any |
Undefined memory format tag. The primitive selects a format automatically. |
| dnnl_a |
plain 1D tensor |
| dnnl_ab |
plain 2D tensor |
| dnnl_abc |
plain 3D tensor |
| dnnl_abcd |
plain 4D tensor |
| dnnl_abcde |
plain 5D tensor |
| dnnl_abcdef |
plain 6D tensor |
| dnnl_abdc |
permuted 4D tensor |
| dnnl_abdec |
permuted 5D tensor |
| dnnl_acb |
permuted 3D tensor |
| dnnl_acbde |
permuted 5D tensor |
| dnnl_acbdef |
permuted 6D tensor |
| dnnl_acdb |
permuted 4D tensor |
| dnnl_acdeb |
permuted 5D tensor |
| dnnl_ba |
permuted 2D tensor |
| dnnl_bac |
permuted 3D tensor |
| dnnl_bacd |
permuted 4D tensor |
| dnnl_bacde |
permuted 5D tensor |
| dnnl_bca |
permuted 3D tensor |
| dnnl_bcda |
permuted 4D tensor |
| dnnl_bcdea |
permuted 5D tensor |
| dnnl_cba |
permuted 3D tensor |
| dnnl_cdba |
permuted 4D tensor |
| dnnl_dcab |
permuted 4D tensor |
| dnnl_cdeba |
permuted 5D tensor |
| dnnl_decab |
permuted 5D tensor |
| dnnl_defcab |
permuted 6D tensor |
| dnnl_Abc16a | |
| dnnl_ABc16a16b | |
| dnnl_ABc32a32b | |
| dnnl_ABc4a4b | |
| dnnl_aBc16b |
3D tensor blocked by 2nd dimension with block size 16 |
| dnnl_ABc16b16a | |
| dnnl_Abc4a | |
| dnnl_aBc32b |
3D tensor blocked by 2nd dimension with block size 32 |
| dnnl_aBc4b |
3D tensor blocked by 2nd dimension with block size 4 |
| dnnl_ABc4b16a4b | |
| dnnl_ABc2b8a4b | |
| dnnl_ABc16b16a4b | |
| dnnl_ABc16b16a2b | |
| dnnl_ABc4b4a | |
| dnnl_ABc8a16b2a | |
| dnnl_ABc8a8b | |
| dnnl_ABc8a4b | |
| dnnl_aBc8b |
3D tensor blocked by 2nd dimension with block size 8 |
| dnnl_ABc8b16a2b | |
| dnnl_BAc8a16b2a | |
| dnnl_ABc8b8a | |
| dnnl_Abcd16a | |
| dnnl_Abcd8a | |
| dnnl_ABcd16a16b | |
| dnnl_Abcd32a | |
| dnnl_ABcd32a32b | |
| dnnl_aBcd16b |
4D tensor blocked by 2nd dimension with block size 16 |
| dnnl_ABcd16b16a | |
| dnnl_aBCd16b16c | |
| dnnl_aBCd16c16b | |
| dnnl_Abcd4a | |
| dnnl_aBcd32b |
4D tensor blocked by 2nd dimension with block size 32 |
| dnnl_aBcd4b |
4D tensor blocked by 2nd dimension with block size 4 |
| dnnl_ABcd4b16a4b | |
| dnnl_ABcd16b16a4b | |
| dnnl_ABcd16b16a2b | |
| dnnl_ABcd4b4a | |
| dnnl_ABcd4a4b | |
| dnnl_aBCd2c4b2c | |
| dnnl_aBCd4b8c2b | |
| dnnl_aBCd4c16b4c | |
| dnnl_aBCd2c8b4c | |
| dnnl_aBCd16c16b4c | |
| dnnl_aBCd16c16b2c | |
| dnnl_aBCd4c4b | |
| dnnl_aBCd4b4c | |
| dnnl_ABcd8a16b2a | |
| dnnl_ABcd2b8a4b | |
| dnnl_ABcd8a8b | |
| dnnl_ABcd8a4b | |
| dnnl_aBcd8b |
4D tensor blocked by 2nd dimension with block size 8 |
| dnnl_aBCd4c8b2c | |
| dnnl_ABcd8b16a2b | |
| dnnl_aBCd8b16c2b | |
| dnnl_BAcd8a16b2a | |
| dnnl_ABcd8b8a |
4D tensor blocked by 1st and 2nd dimension with block size 8 |
| dnnl_aBCd8b8c | |
| dnnl_aBCd8b4c | |
| dnnl_aBCd8c16b2c | |
| dnnl_ABcde8a16b2a | |
| dnnl_aCBd8b16c2b | |
| dnnl_aBCd8c8b | |
| dnnl_Abcde16a | |
| dnnl_Abcde32a | |
| dnnl_ABcde16a16b | |
| dnnl_BAcde8a16b2a | |
| dnnl_aBCd2b4c2b |
4D tensor blocked by 3rd dimension with block size 4 |
| dnnl_ABcde4b16a4b |
5D tensor blocked by 1st dimension with block size 16 |
| dnnl_ABcde2b8a4b |
5D tensor blocked by 1st dimension with block size 8 |
| dnnl_aBcde16b |
5D tensor blocked by 2nd dimension with block size 16 |
| dnnl_ABcde16b16a | |
| dnnl_aBCde16b16c | |
| dnnl_aBCde16c16b | |
| dnnl_aBCde2c8b4c | |
| dnnl_Abcde4a | |
| dnnl_aBcde32b |
5D tensor blocked by 2nd dimension with block size 32 |
| dnnl_aBcde4b |
5D tensor blocked by 2nd dimension with block size 4 |
| dnnl_ABcde4b4a | |
| dnnl_ABcde4a4b | |
| dnnl_aBCde4b4c | |
| dnnl_aBCde2c4b2c | |
| dnnl_aBCde4b8c2b | |
| dnnl_aBCde4c16b4c | |
| dnnl_aBCde16c16b4c | |
| dnnl_aBCde16c16b2c | |
| dnnl_aBCde4c4b | |
| dnnl_Abcde8a | |
| dnnl_ABcde8a8b | |
| dnnl_ABcde8a4b | |
| dnnl_BAcde16b16a | |
| dnnl_aBcde8b |
5D tensor blocked by 2nd dimension with block size 8 |
| dnnl_ABcde8b16a2b | |
| dnnl_aBCde8b16c2b | |
| dnnl_aBCde4c8b2c | |
| dnnl_aCBde8b16c2b | |
| dnnl_ABcde8b8a | |
| dnnl_ABcde32a32b | |
| dnnl_aBCde8b8c | |
| dnnl_aBCde8b4c | |
| dnnl_ABc4a8b8a4b | |
| dnnl_ABcd4a8b8a4b | |
| dnnl_ABcde4a8b8a4b | |
| dnnl_BAc4b8a8b4a | |
| dnnl_BAcd4b8a8b4a | |
| dnnl_BAcde4b8a8b4a | |
| dnnl_ABcd2a8b8a2b | |
| dnnl_aBCd4b8c8b4c | |
| dnnl_aBCde4b8c8b4c | |
| dnnl_aBCde2b8c8b2c | |
| dnnl_aBCde8c16b2c | |
| dnnl_aBCde8c8b | |
| dnnl_aBCde2b4c2b |
5D tensor blocked by 3rd dimension with block size 4 |
| dnnl_aBcdef16b |
6D tensor blocked by 2nd dimension with block size 16 |
| dnnl_aBCdef16b16c | |
| dnnl_aBCdef16c16b | |
| dnnl_aBCdef4c16b4c | |
| dnnl_aBCdef2c8b4c |
6D tensor blocked by 2nd dimension with block size 8 |
| dnnl_aBCdef4c8b2c | |
| dnnl_aBCdef2b4c2b |
6D tensor blocked by 3rd dimension with block size 4 |
| dnnl_aBcdef4b |
6D tensor blocked by 2nd dimension with block size 4 |
| dnnl_aBCdef4c4b | |
| dnnl_aBCdef4b4c | |
| dnnl_aBCdef2c4b2c | |
| dnnl_aBCdef4b8c2b | |
| dnnl_aBCdef8b8c | |
| dnnl_aBCdef8b4c | |
| dnnl_aBCdef8c16b2c | |
| dnnl_aBCdef4b8c8b4c | |
| dnnl_aBCdef8b16c2b | |
| dnnl_aCBdef8b16c2b | |
| dnnl_aBCdef8c8b | |
| dnnl_aBdc16b | |
| dnnl_aBdC16b2c | |
| dnnl_aBdC16b4c | |
| dnnl_aBdc4b | |
| dnnl_aBdc8b | |
| dnnl_aBdec16b | |
| dnnl_aBdeC16b2c | |
| dnnl_aBdeC16b4c | |
| dnnl_aBdec32b | |
| dnnl_aBdec4b | |
| dnnl_aBdec8b | |
| dnnl_aBdefc16b | |
| dnnl_aBdefC16b2c | |
| dnnl_aCBdef16c16b | |
| dnnl_aBdefc4b | |
| dnnl_aBdefc8b | |
| dnnl_Abcdef16a | |
| dnnl_Abcdef32a | |
| dnnl_Acb16a | |
| dnnl_AcB16a2b | |
| dnnl_AcB16a4b | |
| dnnl_Acb4a | |
| dnnl_Acb8a | |
| dnnl_aCBd16b16c | |
| dnnl_aCBd16c16b | |
| dnnl_aCBde16b16c | |
| dnnl_aCBde16c16b | |
| dnnl_Acdb16a | |
| dnnl_AcdB16a2b | |
| dnnl_AcdB16a4b | |
| dnnl_Acdb32a | |
| dnnl_Acdb4a | |
| dnnl_Acdb8a | |
| dnnl_Acdeb16a | |
| dnnl_AcdeB16a2b | |
| dnnl_Acdeb4a | |
| dnnl_Acdeb8a | |
| dnnl_BAc16a16b | |
| dnnl_BAc16b16a | |
| dnnl_BAcd16a16b | |
| dnnl_BAcd16b16a | |
| dnnl_aCBd4c8b8c4b | |
| dnnl_aCBde4c8b8c4b | |
| dnnl_aCBdef4c8b8c4b | |
| dnnl_BAcde16a16b | |
| dnnl_aCBdef16b16c | |
| dnnl_format_tag_last |
Just a sentinel, not real memory format tag. Must be changed after new format tag is added. |
| dnnl_x |
1D tensor, an alias to dnnl_a |
| dnnl_nc |
2D CNN activations tensor, an alias to dnnl_ab |
| dnnl_cn |
2D CNN activations tensor, an alias to dnnl_ba |
| dnnl_tn |
2D RNN statistics tensor, an alias to dnnl_ab |
| dnnl_nt |
2D RNN statistics tensor, an alias to dnnl_ba |
| dnnl_ncw |
3D CNN activations tensor, an alias to dnnl_abc |
| dnnl_nwc |
3D CNN activations tensor, an alias to dnnl_acb |
| dnnl_nchw |
4D CNN activations tensor, an alias to dnnl_abcd |
| dnnl_nhwc |
4D CNN activations tensor, an alias to dnnl_acdb |
| dnnl_chwn |
4D CNN activations tensor, an alias to dnnl_bcda |
| dnnl_ncdhw |
5D CNN activations tensor, an alias to dnnl_abcde |
| dnnl_ndhwc |
5D CNN activations tensor, an alias to dnnl_acdeb |
| dnnl_oi |
2D CNN weights tensor, an alias to dnnl_ab |
| dnnl_io |
2D CNN weights tensor, an alias to dnnl_ba |
| dnnl_oiw |
3D CNN weights tensor, an alias to dnnl_abc |
| dnnl_owi |
3D CNN weights tensor, an alias to dnnl_acb |
| dnnl_wio |
3D CNN weights tensor, an alias to dnnl_cba |
| dnnl_iwo |
3D CNN weights tensor, an alias to dnnl_bca |
| dnnl_oihw |
4D CNN weights tensor, an alias to dnnl_abcd |
| dnnl_hwio |
4D CNN weights tensor, an alias to dnnl_cdba |
| dnnl_ohwi |
4D CNN weights tensor, an alias to dnnl_acdb |
| dnnl_ihwo |
4D CNN weights tensor, an alias to dnnl_bcda |
| dnnl_iohw |
4D CNN weights tensor, an alias to dnnl_bacd |
| dnnl_oidhw |
5D CNN weights tensor, an alias to dnnl_abcde |
| dnnl_iodhw |
5D CNN weights tensor, an alias to dnnl_bacde |
| dnnl_dhwio |
5D CNN weights tensor, an alias to dnnl_cdeba |
| dnnl_odhwi |
5D CNN weights tensor, an alias to dnnl_acdeb |
| dnnl_idhwo |
5D CNN weights tensor, an alias to dnnl_bcdea |
| dnnl_goiw |
4D CNN weights tensor (incl. groups), an alias to dnnl_abcd |
| dnnl_wigo |
4D CNN weights tensor (incl. groups), an alias to dnnl_dcab |
| dnnl_goihw |
5D CNN weights tensor (incl. groups), an alias to dnnl_abcde |
| dnnl_hwigo |
5D CNN weights tensor (incl. groups), an alias to dnnl_decab |
| dnnl_giohw |
5D CNN weights tensor (incl. groups), an alias to dnnl_acbde |
| dnnl_goidhw |
6D CNN weights tensor (incl. groups), an alias to dnnl_abcdef |
| dnnl_giodhw |
6D CNN weights tensor (incl. groups), an alias to dnnl_acbdef |
| dnnl_dhwigo |
6D CNN weights tensor (incl. groups), an alias to dnnl_defcab |
| dnnl_tnc |
3D RNN data tensor in the format (seq_length, batch, input channels). |
| dnnl_ntc |
3D RNN data tensor in the format (batch, seq_length, input channels). |
| dnnl_ldnc |
4D RNN states tensor in the format (num_layers, num_directions, batch, state channels). |
| dnnl_ldigo |
5D RNN weights tensor in the format (num_layers, num_directions, input_channels, num_gates, output_channels).
|
| dnnl_ldgoi |
5D RNN weights tensor in the format (num_layers, num_directions, num_gates, output_channels, input_channels).
|
| dnnl_ldio |
4D LSTM projection tensor in the format (num_layers, num_directions, num_channels_in_hidden_state, num_channels_in_recurrent_projection). |
| dnnl_ldoi |
4D LSTM projection tensor in the format (num_layers, num_directions, num_channels_in_recurrent_projection, num_channels_in_hidden_state). |
| dnnl_ldgo |
4D RNN bias tensor in the format (num_layers, num_directions, num_gates, output_channels).
|
| dnnl_nCdhw32c |
5D CNN activations tensor blocked by channels with block size 32, an alias to dnnl_aBcde32b |
| dnnl_nCdhw16c |
5D CNN activations tensor blocked by channels with block size 16, an alias to dnnl_aBcde16b |
| dnnl_nCdhw4c |
5D CNN activations tensor blocked by channels with block size 4, an alias to dnnl_aBcde4b |
| dnnl_nCdhw8c |
5D CNN activations tensor blocked by channels with block size 8, an alias to dnnl_aBcde8b |
| dnnl_nChw32c |
4D CNN activations tensor blocked by channels with block size 32, an alias to dnnl_aBcd32b |
| dnnl_nChw16c |
4D CNN activations tensor blocked by channels with block size 16, an alias to dnnl_aBcd16b |
| dnnl_nChw4c |
4D CNN activations tensor blocked by channels with block size 4, an alias to dnnl_aBcd4b |
| dnnl_nChw8c |
4D CNN activations tensor blocked by channels with block size 8, an alias to dnnl_aBcd8b |
| dnnl_nCw32c |
3D CNN activations tensor blocked by channels with block size 32, an alias to dnnl_aBc32b |
| dnnl_nCw16c |
3D CNN activations tensor blocked by channels with block size 16, an alias to dnnl_aBc16b |
| dnnl_nCw4c |
3D CNN activations tensor blocked by channels with block size 4, an alias to dnnl_aBc4b |
| dnnl_nCw8c |
3D CNN activations tensor blocked by channels with block size 8, an alias to dnnl_aBc8b |
| dnnl_NCw16n16c | |
| dnnl_NCdhw16n16c | |
| dnnl_NChw16n16c | |
| dnnl_NCw32n32c | |
| dnnl_NChw32n32c | |
| dnnl_NCdhw32n32c | |
| dnnl_IOw16o16i | |
| dnnl_IOw16i16o | |
| dnnl_OIw16i16o | |
| dnnl_OIw16o16i | |
| dnnl_Oiw16o | |
| dnnl_OIw4i16o4i | |
| dnnl_OIw2i8o4i | |
| dnnl_OIw16i16o4i | |
| dnnl_OIw16i16o2i | |
| dnnl_OIw4i4o | |
| dnnl_OIw4o4i | |
| dnnl_Oiw4o | |
| dnnl_OIw8i16o2i | |
| dnnl_OIw8i8o | |
| dnnl_OIw8o16i2o | |
| dnnl_IOw8o16i2o | |
| dnnl_OIw8o8i | |
| dnnl_OIw8o4i | |
| dnnl_Owi16o | |
| dnnl_OwI16o2i | |
| dnnl_OwI16o4i | |
| dnnl_Owi4o | |
| dnnl_Owi8o | |
| dnnl_IOhw16i16o | |
| dnnl_IOhw16o16i | |
| dnnl_Ohwi16o | |
| dnnl_OhwI16o2i | |
| dnnl_OhwI16o4i | |
| dnnl_Ohwi32o | |
| dnnl_Ohwi4o | |
| dnnl_Ohwi8o | |
| dnnl_OIhw16i16o | |
| dnnl_OIhw16o16i | |
| dnnl_Oihw16o | |
| dnnl_OIhw4i16o4i | |
| dnnl_OIhw16i16o4i | |
| dnnl_OIhw16i16o2i | |
| dnnl_OIhw4i4o | |
| dnnl_OIhw4o4i | |
| dnnl_Oihw4o | |
| dnnl_OIhw8i16o2i | |
| dnnl_OIhw8i8o | |
| dnnl_OIhw8o16i2o | |
| dnnl_OIhw2i8o4i | |
| dnnl_IOhw8o16i2o | |
| dnnl_OIhw8o8i | |
| dnnl_OIhw8o4i | |
| dnnl_Odhwi16o | |
| dnnl_OdhwI16o2i | |
| dnnl_Odhwi4o | |
| dnnl_Odhwi8o | |
| dnnl_OIdhw16i16o | |
| dnnl_OIdhw16o16i | |
| dnnl_Oidhw16o | |
| dnnl_OIdhw4i4o | |
| dnnl_OIdhw4o4i | |
| dnnl_Oidhw4o | |
| dnnl_OIdhw8i16o2i | |
| dnnl_OIdhw8i8o | |
| dnnl_OIdhw8o16i2o | |
| dnnl_IOdhw8o16i2o | |
| dnnl_OIdhw4i16o4i | |
| dnnl_OIdhw2i8o4i | |
| dnnl_OIdhw8o8i | |
| dnnl_OIdhw8o4i | |
| dnnl_IOdhw16i16o | |
| dnnl_OIdhw4o8i8o4i | |
| dnnl_IOdhw16o16i | |
| dnnl_Goiw16g | |
| dnnl_Goiw8g | |
| dnnl_gIOw16o16i | |
| dnnl_gIOw16i16o | |
| dnnl_gOIw16i16o | |
| dnnl_gOIw16o16i | |
| dnnl_gOiw16o | |
| dnnl_gOIw4i16o4i | |
| dnnl_gOIw2i8o4i | |
| dnnl_gOIw16i16o4i | |
| dnnl_gOIw16i16o2i | |
| dnnl_gOIw4i4o | |
| dnnl_gOIw4o4i | |
| dnnl_gOiw4o | |
| dnnl_gOIw8i16o2i | |
| dnnl_gOIw8i8o | |
| dnnl_gOIw8o16i2o | |
| dnnl_gIOw8o16i2o | |
| dnnl_gOIw8o8i | |
| dnnl_gOIw8o4i | |
| dnnl_gOwi16o | |
| dnnl_gOwI16o2i | |
| dnnl_gOwI16o4i | |
| dnnl_gOwi4o | |
| dnnl_gOwi8o | |
| dnnl_Goiw32g | |
| dnnl_gOIw2i4o2i | |
| dnnl_gOIw2o4i2o | |
| dnnl_gOIw4i8o2i | |
| dnnl_gOIw4o8i2o | |
| dnnl_gIOhw16i16o | |
| dnnl_gIOhw16o16i | |
| dnnl_gOhwi16o | |
| dnnl_gOhwI16o2i | |
| dnnl_gOhwI16o4i | |
| dnnl_gOhwi32o | |
| dnnl_gOhwi4o | |
| dnnl_gOhwi8o | |
| dnnl_Goihw16g | |
| dnnl_gOIhw16i16o | |
| dnnl_gOIhw16o16i | |
| dnnl_gOihw16o | |
| dnnl_gOIhw2i8o4i | |
| dnnl_gOIhw4i16o4i | |
| dnnl_gOIhw16i16o4i | |
| dnnl_gOIhw16i16o2i | |
| dnnl_gOIhw4i4o | |
| dnnl_gOIhw4o4i | |
| dnnl_gOihw4o | |
| dnnl_Goihw8g | |
| dnnl_gOIhw8i16o2i | |
| dnnl_gOIhw8i8o | |
| dnnl_gOIhw8o16i2o | |
| dnnl_gIOhw8o16i2o | |
| dnnl_gOIhw8o8i | |
| dnnl_gOIhw8o4i | |
| dnnl_Goihw32g | |
| dnnl_OIw4o8i8o4i | |
| dnnl_OIhw4o8i8o4i | |
| dnnl_IOw4i8o8i4o | |
| dnnl_IOhw4i8o8i4o | |
| dnnl_IOdhw4i8o8i4o | |
| dnnl_OIhw2o8i8o2i | |
| dnnl_gOIw4o8i8o4i | |
| dnnl_gOIhw4o8i8o4i | |
| dnnl_gOIdhw4o8i8o4i | |
| dnnl_gIOw4i8o8i4o | |
| dnnl_gIOhw4i8o8i4o | |
| dnnl_gIOdhw4i8o8i4o | |
| dnnl_gOIhw2o8i8o2i | |
| dnnl_gOIhw2i4o2i | |
| dnnl_gOIhw2o4i2o | |
| dnnl_gOIhw4i8o2i | |
| dnnl_gOIhw4o8i2o | |
| dnnl_gIOdhw16i16o | |
| dnnl_gIOdhw16o16i | |
| dnnl_gOdhwi16o | |
| dnnl_gOdhwI16o2i | |
| dnnl_gOdhwi4o | |
| dnnl_gOdhwi8o | |
| dnnl_gOIdhw16i16o | |
| dnnl_gOIdhw4i16o4i | |
| dnnl_gOIdhw2i8o4i | |
| dnnl_gOIdhw16o16i | |
| dnnl_gOidhw16o | |
| dnnl_gOIdhw4i4o | |
| dnnl_gOIdhw4o4i | |
| dnnl_gOidhw4o | |
| dnnl_gOIdhw8i16o2i | |
| dnnl_gOIdhw8i8o | |
| dnnl_gOIdhw8o16i2o | |
| dnnl_gIOdhw8o16i2o | |
| dnnl_gOIdhw8o8i | |
| dnnl_gOIdhw8o4i | |
| dnnl_Goidhw16g | |
| dnnl_Goidhw32g | |
| dnnl_gOIdhw2i4o2i | |
| dnnl_gOIdhw4i8o2i | |
| dnnl_gOIdhw2o4i2o | |
| dnnl_gOIdhw4o8i2o | |
Flags for memory special features.
Winograd-specific formats.
| dnnl_status_t DNNL_API dnnl_memory_create | ( | dnnl_memory_t * | memory, |
| const dnnl_memory_desc_t * | memory_desc, | ||
| dnnl_engine_t | engine, | ||
| void * | handle | ||
| ) |
Creates a memory object.
Unless handle is equal to DNNL_MEMORY_NONE, the constructed memory object will have the underlying buffer set. In this case, the buffer will be initialized as if dnnl_memory_set_data_handle() had been called.
| memory | Output memory object. |
| memory_desc | Memory descriptor. |
| engine | Engine to use. |
| handle | Handle of the memory buffer to use as an underlying storage.
|
| int DNNL_API dnnl_memory_desc_equal | ( | const dnnl_memory_desc_t * | lhs, |
| const dnnl_memory_desc_t * | rhs | ||
| ) |
Compares two memory descriptors.
Use this function to identify whether a reorder is required between the two memories
| lhs | Left-hand side of the comparison. |
| rhs | Right-hand side of the comparison. |
| size_t DNNL_API dnnl_memory_desc_get_size | ( | const dnnl_memory_desc_t * | memory_desc | ) |
Returns the size of a memory descriptor.
| memory_desc | Memory descriptor. |
| dnnl_status_t DNNL_API dnnl_memory_desc_init_by_strides | ( | dnnl_memory_desc_t * | memory_desc, |
| int | ndims, | ||
| const dnnl_dims_t | dims, | ||
| dnnl_data_type_t | data_type, | ||
| const dnnl_dims_t | strides | ||
| ) |
Initializes a memory descriptor using dimensions and strides.
abc... format tag, and the physical meaning of the dimensions depends on both the primitive that consumes the memory and the context of that consumption.| memory_desc | Output memory descriptor. |
| ndims | Number of dimensions |
| dims | Array of dimensions. |
| data_type | Elements data type. |
| strides | Strides in each dimension. |
| dnnl_status_t DNNL_API dnnl_memory_desc_init_by_tag | ( | dnnl_memory_desc_t * | memory_desc, |
| int | ndims, | ||
| const dnnl_dims_t | dims, | ||
| dnnl_data_type_t | data_type, | ||
| dnnl_format_tag_t | tag | ||
| ) |
Initializes a memory descriptor using dimensions and memory format tag.
abc... format tag, and the physical meaning of the dimensions depends on both the primitive that consumes the memory and the context of that consumption.| memory_desc | Output memory descriptor. |
| ndims | Number of dimensions |
| dims | Array of dimensions. |
| data_type | Elements data type. |
| tag | Memory format tag. Can be dnnl_format_tag_any which would allow a primitive to chose the final memory format. In this case the format_kind field of the memory descriptor would be set to dnnl_format_kind_any. |
| dnnl_status_t DNNL_API dnnl_memory_desc_init_submemory | ( | dnnl_memory_desc_t * | memory_desc, |
| const dnnl_memory_desc_t * | parent_memory_desc, | ||
| const dnnl_dims_t | dims, | ||
| const dnnl_dims_t | offsets | ||
| ) |
Initializes a memory descriptor for a region inside an area described by an existing memory descriptor.
| memory_desc | Output memory descriptor. |
| parent_memory_desc | An existing memory descriptor. |
| dims | Sizes of the region. |
| offsets | Offsets to the region from the encompassing memory object in each dimension |
| dnnl_status_t DNNL_API dnnl_memory_desc_permute_axes | ( | dnnl_memory_desc_t * | out_memory_desc, |
| const dnnl_memory_desc_t * | in_memory_desc, | ||
| const int * | permutation | ||
| ) |
Initializes a memory descriptor by permuting axes in an existing one.
The physical memory layout representation is adjusted accordingly to maintain the consistency between the logical and physical parts of the memory descriptor.
The new memory descriptor inherits the data type. This operation is valid only for memory descriptors that have format_kind set to dnnl_blocked or dnnl_format_kind_any.
The logical axes will be permuted in the following manner:
Example:
| out_memory_desc | Output memory descriptor. |
| in_memory_desc | An existing memory descriptor. Must have format_kind set to dnnl_blocked or dnnl_format_kind_any. |
| permutation | Axes permutation (of size in_memory_desc->ndims). |
| dnnl_status_t DNNL_API dnnl_memory_desc_reshape | ( | dnnl_memory_desc_t * | out_memory_desc, |
| const dnnl_memory_desc_t * | in_memory_desc, | ||
| int | ndims, | ||
| const dnnl_dims_t | dims | ||
| ) |
Initializes a memory descriptor by reshaping an existing one. The new memory descriptor inherits the data type. This operation is valid only for memory descriptors that have format_kind set to dnnl_blocked or dnnl_format_kind_any.
The operation ensures the transformation of the physical memory format corresponds to the transformation of the logical dimensions. If such transformation is impossible, the function returns dnnl_invalid_arguments.
The reshape operation can be described as a combination of the following basic operations:
1. This is always possible.1. This is possible only if the dimension has no padding (i.e. padded_dims[dim] == dims[dim] && dims[dim] == 1).padded_dims[dim] = dims[dim]).stride for dim[i] == (stride for dim[i + 1]) * dim[i + 1];i < j if and only if stride for dim[j] <= stride for dim[i].| out_memory_desc | Output memory descriptor. |
| in_memory_desc | An existing memory descriptor. Must have format_kind set to dnnl_blocked or dnnl_format_kind_any. |
| ndims | Number of dimensions for the output memory descriptor. |
| dims | Dimensions for the output memory descriptor. |
| dnnl_status_t DNNL_API dnnl_memory_destroy | ( | dnnl_memory_t | memory | ) |
Destroys a memory object.
| memory | Memory object to destroy. |
| dnnl_status_t DNNL_API dnnl_memory_get_data_handle | ( | const_dnnl_memory_t | memory, |
| void ** | handle | ||
| ) |
Returns memory object's data handle.
| memory | Memory object. |
| handle | Output data handle. For the CPU engine, the data handle is a pointer to the actual data. For OpenCL it is a cl_mem. |
| dnnl_status_t DNNL_API dnnl_memory_get_engine | ( | const_dnnl_memory_t | memory, |
| dnnl_engine_t * | engine | ||
| ) |
Returns the engine of a memory object.
| memory | Memory object. |
| engine | Output engine on which the memory is located. |
| dnnl_status_t DNNL_API dnnl_memory_get_memory_desc | ( | const_dnnl_memory_t | memory, |
| const dnnl_memory_desc_t ** | memory_desc | ||
| ) |
Returns the memory descriptor for a memory object.
| memory | Memory object. |
| memory_desc | Output memory descriptor (a copy). |
| dnnl_status_t DNNL_API dnnl_memory_map_data | ( | const_dnnl_memory_t | memory, |
| void ** | mapped_ptr | ||
| ) |
Maps a memory object and returns a host-side pointer to a memory buffer with a copy of its contents.
Mapping enables explicit direct access to memory contents for the engines that do not support it implicitly.
Mapping is an exclusive operation - a memory object cannot be used in other operations until this memory object is unmapped.
memory should be completed before the memory is mapped. Use dnnl_stream_wait to synchronize the corresponding execution stream.| memory | Memory object. |
| mapped_ptr | Output pointer to the mapped buffer. |
| dnnl_status_t DNNL_API dnnl_memory_set_data_handle | ( | dnnl_memory_t | memory, |
| void * | handle | ||
| ) |
Sets the underlying memory buffer.
See the description of dnnl_memory_set_data_handle_v2() for more details.
| memory | Memory object. |
| handle | Data handle. For the CPU engine, the data handle is a pointer to the actual data. For OpenCL it is a cl_mem. |
| dnnl_status_t DNNL_API dnnl_memory_set_data_handle_v2 | ( | dnnl_memory_t | memory, |
| void * | handle, | ||
| dnnl_stream_t | stream | ||
| ) |
Sets the underlying memory buffer.
This function may write zero values to the memory specified by the handle if the memory object has a zero padding area. This may be time consuming and happens each time this function is called. The operation is always blocking and the stream parameter is a hint.
handle parameter cannot and does not have a const qualifier.| memory | Memory object. |
| handle | Data handle. For the CPU engine, the data handle is a pointer to the actual data. For OpenCL it is a cl_mem. |
| stream | Stream to use to execute padding in. |
| dnnl_status_t DNNL_API dnnl_memory_unmap_data | ( | const_dnnl_memory_t | memory, |
| void * | mapped_ptr | ||
| ) |
Unmaps a memory object and writes back any changes made to the previously mapped memory buffer. The pointer to the mapped buffer must be obtained via the dnnl_memory_map_data() call.
| memory | Memory object. |
| mapped_ptr | Pointer to the mapped buffer that must have been obtained using the dnnl_memory_map_data() function. |
1.8.11