aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMichalis Spyrou <michalis.spyrou@arm.com>2019-10-18 15:19:33 +0100
committerMichalis Spyrou <michalis.spyrou@arm.com>2019-10-18 16:28:46 +0000
commit422da26b44d517f38011a91888a1c5da4acfeed4 (patch)
tree2672073b9f3d9681196cad5e62242d9667f4856b
parent45ce566891c191ae766ced96d7f615a98174d0ff (diff)
downloadComputeLibrary-422da26b44d517f38011a91888a1c5da4acfeed4.tar.gz
COMPMID-2452: Update documentation for Weights Manager
Change-Id: Idba87bcc059e57a8f0d52fcdcb0d6a7bacc57951 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/2125 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
-rw-r--r--docs/01_library.dox21
1 files changed, 21 insertions, 0 deletions
diff --git a/docs/01_library.dox b/docs/01_library.dox
index 721e131acd..6e365865ba 100644
--- a/docs/01_library.dox
+++ b/docs/01_library.dox
@@ -489,6 +489,27 @@ However this process takes quite a lot of time, which is why it cannot be enable
But, when the @ref CLTuner is disabled ( Target = 1 for the graph examples), the @ref graph::Graph will try to reload the file containing the tuning parameters, then for each executed kernel the Compute Library will use the fine tuned LWS if it was present in the file or use a default LWS value if it's not.
+@section S4_10_weights_manager Weights Manager
+
+@ref IWeightsManager is a weights managing interface that can be used to reduce the memory requirements of a given pipeline by reusing transformed weights across multiple function executions.
+@ref IWeightsManager is responsible for managing weight tensors alongside with their transformations.
+@ref ITransformWeights provides an interface for running the desired transform function. This interface is used by the weights manager.
+
+@subsection S4_10_1_working_with_weights_manager Working with the Weights Manager
+Following is a simple example that uses the weights manager:
+
+Initially a weights manager must be set-up:
+@code{.cpp}
+auto wm = std::make_shared<IWeightsManager>(); // Create a weights manager
+@endcode
+
+Once done, weights can be managed, configured and run:
+@code{.cpp}
+wm->manage(weights); // Manage the weights
+wm->acquire(weights, &_reshape_weights_managed_function); // Acquire the address of the transformed weights based on the transform function
+wm->run(weights, &_reshape_weights_managed_function); // Run the transpose function
+@endcode
+
@section S5_0_experimental Experimental Features
@subsection S5_1_run_time_context Run-time Context