diff options
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/user_guide/library.dox | 29 | ||||
| -rw-r--r-- | docs/user_guide/operator_list.dox | 17 | ||||
| -rw-r--r-- | docs/user_guide/release_version_and_change_log.dox | 4 |
3 files changed, 34 insertions, 16 deletions
diff --git a/docs/user_guide/library.dox b/docs/user_guide/library.dox index 6c7b7e941f..fc08dbc437 100644 --- a/docs/user_guide/library.dox +++ b/docs/user_guide/library.dox @@ -561,6 +561,35 @@ Selecting fat_binary when building Compute Library, will create a library that c Based on the CPU support, the appropriate kernel will be selected at runtime for execution. Currently this option is only supported with armv8.2-a as the base architecture. +@subsection architecture_experimental_per_operator_build Per-operator build + +Dependencies for all operators have been explicitly defined, this provides the ability to users to generate Compute Library +binaries that include a user-defined list of operators. + +An experimental flag 'build_config' has been introduced where a JSON configuration file can be provided and consumed. +An example config looks like: +@code{.py} +{ + "operators": [ + "Activation", + "DepthwiseConv2d", + "Conv2d", + "Permute", + "Pool2d", + "Reshape" + ], + "data_types": [ + "NHWC" + ] +} +@endcode + +Supported data-types options are: +- "NHWC" +- "NCHW" + +The list of supported operators can be found in filelist.json in the root of Compute Library repo. + @subsection architecture_experimental_build_high_priority_operators Build high priority operators Selecting high_priority when building Compute Library, one new library will be created: libarm_compute_hp and diff --git a/docs/user_guide/operator_list.dox b/docs/user_guide/operator_list.dox index 92b8f9b482..27ba52d72e 100644 --- a/docs/user_guide/operator_list.dox +++ b/docs/user_guide/operator_list.dox @@ -1404,9 +1404,9 @@ where N = batches, C = channels, H = height, W = width <tr><td>All<td>All </table> <tr> - <td rowspan="2">FillBorder - <td rowspan="2" style="width:200px;"> Function to fill the borders within the XY-planes. - <td rowspan="2"> + <td rowspan="1">FillBorder + <td rowspan="1" style="width:200px;"> Function to fill the borders within the XY-planes. + <td rowspan="1"> <ul> <li>n/a </ul> @@ -1421,17 +1421,6 @@ where N = batches, C = channels, H = height, W = width <tr><td>All<td>All </table> <tr> - <td>CLFillBorder - <td> - <ul> - <li>All - </ul> - <td> - <table> - <tr><th>src<th>dst - <tr><td>All<td>All - </table> -<tr> <td rowspan="2">FlattenLayer <td rowspan="2" style="width:200px;"> Reshape a tensor to be 1D <td rowspan="2"> diff --git a/docs/user_guide/release_version_and_change_log.dox b/docs/user_guide/release_version_and_change_log.dox index 2eb9aacce7..583cf4fb82 100644 --- a/docs/user_guide/release_version_and_change_log.dox +++ b/docs/user_guide/release_version_and_change_log.dox @@ -1315,7 +1315,7 @@ v17.09 Public major release - NEDequantizationLayerKernel / @ref NEDequantizationLayer - NEFloorKernel / @ref NEFloor - @ref NEL2NormalizeLayerKernel / @ref NEL2NormalizeLayer - - NEQuantizationLayerKernel @ref NEMinMaxLayerKernel / @ref NEQuantizationLayer + - NEQuantizationLayerKernel NEMinMaxLayerKernel / @ref NEQuantizationLayer - @ref NEROIPoolingLayerKernel / @ref NEROIPoolingLayer - @ref NEReductionOperationKernel / @ref NEReductionOperation - NEReshapeLayerKernel / @ref NEReshapeLayer @@ -1329,7 +1329,7 @@ v17.09 Public major release - CLGEMMTranspose1xW - CLGEMMMatrixVectorMultiplyKernel - @ref CLL2NormalizeLayerKernel / @ref CLL2NormalizeLayer - - CLQuantizationLayerKernel @ref CLMinMaxLayerKernel / @ref CLQuantizationLayer + - CLQuantizationLayerKernel CLMinMaxLayerKernel / @ref CLQuantizationLayer - @ref CLROIPoolingLayerKernel / @ref CLROIPoolingLayer - @ref CLReductionOperationKernel / @ref CLReductionOperation - CLReshapeLayerKernel / @ref CLReshapeLayer |