Per-operator build dependencies
Creates a list of operators their respective dependencies.
Alters the build system to walk-through them resolve the dependencies
and build Compute Library.
Removes the following unused kernels/functions:
-[NE|CL]MinMaxLayerKernel
-CLFillBorder
Resolves: COMPMID-4695,COMPMID-4696
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I35ebeef38dac25ec5459cfe9c5f7c9a708621124
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/357914
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
Comments-Addressed: bsgcomp <bsgcomp@arm.com>
Signed-off-by: Freddie Liardet <frederick.liardet@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6295
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/docs/user_guide/library.dox b/docs/user_guide/library.dox
index 6c7b7e9..fc08dbc 100644
--- a/docs/user_guide/library.dox
+++ b/docs/user_guide/library.dox
@@ -561,6 +561,35 @@
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 92b8f9b..27ba52d 100644
--- a/docs/user_guide/operator_list.dox
+++ b/docs/user_guide/operator_list.dox
@@ -1404,9 +1404,9 @@
<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 @@
<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 2eb9aac..583cf4f 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 @@
- 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 @@
- 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