Age | Commit message (Collapse) | Author |
|
preferred presentation
Change-Id: Ib7dcfcbb24b408999dfae366b9da396485aacf78
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3525
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
The current implementation of the in-place mutator is limited by the
assumption that each node only produces one output and therefore all
its output edges represent the same tensor. This means that doing
in-place computations on it, would modify the input of other nodes.
However, this is not the case for operators like split, which creates N
different tensors, one for each output edge.
This patches relaxes this limitation by checking whether the tensor
related to a specific output edge is the same as any of the other edges.
If this is the case, then in-place computation cannot be done.
Change-Id: I3302b41b1f6ec3b4f2ac425ba381778f1c0a4f31
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3421
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Change-Id: I2102bfe95c2c2335bb587842f9d860cf939a9026
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3315
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: Id13d4f9860f25eeb8c4188ac9248653c4f7c1dc2
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3349
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
NEArithmeticAdditionKernel"
This reverts commit 4a61653202afb018f4f259d3c144a735d73f0a20.
Reason for revert: We will allow in-place computations by providing the same input1 (or input2) as output, thus avoiding changes in the interface.
Change-Id: I7c8669e207e15731dc26dc366150bf960508a879
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3035
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I0089657dd95d7c7b8592984def8e8de1d7e6d085
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3308
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Change-Id: I8f02bb67adae8cc7d884f2417cc9c408985f0d5a
Reviewed-on: https://review.mlplatform.org/c/2546
Reviewed-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Adds SyntheticDataTypeMutator, which is responsible for mutating graphs
to int8 and thus enable performance analysis on a wider range of models.
Change-Id: I9a00f0ae59421ab11952660f5115b5dcd9314aaf
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2418
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
|
|
Change-Id: I223a688cfc19465f8581f691b32891cefd375907
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1555
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Marquez <pablo.tello@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
|
|
- Added support for different input/output qinfo in ActivationLayer and DepthwiseConv
- Added support for different input/output qinfo in ConcatenateLayer introducing ConcatDescriptor
- Added reshape validate
- Allow OutputLayer to return a specific connection index from the input
- Not run Inplace and Depth mutator when input/output quantization info are different
Change-Id: I03f5e416fc43ddd284e1501887202a3145f76d8a
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
Reviewed-on: https://review.mlplatform.org/c/852
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
During the mutating passes accessors of optimized nodes were dropped
instead of being transfered to appropriate tensors.
Change-Id: I29183984d94806bdfb5c92af3acefd928c0fd171
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/136036
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
- Cleaned up build system
Change-Id: If2faa27ee5b31fa8b972836960ab3ef671059c8d
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/126435
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
|