Age | Commit message (Collapse) | Author |
|
* Improve tests with greater number of threads
Change-Id: I6855cdee463809045b10fff85ed9193dd3d3207a
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
* Added missing virtual destructors to recently added profiling
interface classes
Change-Id: Id2c4b3bb22ef233b26723d3e578477c59018fbda
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I9e034b0caaff5371fadfdba20fdbe3171d4cd2e6
|
|
Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com>
Change-Id: I3f8e716ae432737bb314e26792d18aa518aa1952
|
|
Introduce a new test utility that simulates the Gatord service.
This will be used to test the external profiling features.
Change-Id: Ib7c75c1302650e140945cd66d272c23af3aac760
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
|
|
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: If13b731d95c79e3e296d7dfc6c1ac94bf3a93ff3
|
|
* Implemented RefAbsWorkload and unit tests
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ibfcdb2b37fd8d240c181f96856e2c997a4b88914
|
|
Change-Id: I31c5616bea3097f30cde68442d3222e0b0fe2235
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
|
|
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I5bed5196c256883fb704fe14b60bb8f7a77cc9df
|
|
* Fix race condition where result was read before execution of write
Change-Id: I8961c4ce5a9000cb4d465106fe56e615beecf4dc
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
* Add Abs Layer
* Add no-op factory implementations for CpuRef, CpuAcc, GpuAcc
* Add Queue Descriptor in WorkloadData
* Add IsAbsLayerSupported to LayerSupport
* Add LayerVisitor tests
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: Ib0992571d1c80de851cea466291be904e9bdb430
|
|
Change-Id: Ic976fc36955bec5e7721d1e34e89e7be79e23053
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
* Create CaptureData and Holder classes
* Add unit test
Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com>
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I9f2766a8a6081ae4f9988904af2ca24cd434ebca
|
|
* Generic layer parameters now show up in dot file
* Convolution layer parameters have also been added to dot file
* ExecucteNetwork has an additional -v flag which generated dot file if there
Change-Id: I210bb19b45384eb3639b7e488c7a89049fa6f18d
Signed-off-by: Andre Ghattas <andre.ghattas@arm.com>
Signed-off-by: Szilard Papp <szilard.papp@arm.com>
|
|
* Updates ACL pin to include patch for asymmetric padding in TransposeConvolution2D, used by FSRCNN
!android-nn-driver:1857
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: Ie9c8c75b6cff3caa87623ec4021e03d409fdb18a
|
|
Change-Id: I30ae52d38181a91ce642e24919ad788902e42eb4
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
|
|
SendCounterPacket.SendPeriodicCounterSelectionPacket() function
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: Ib034a4f5ca589759d925e3dd0ca50e5a3dfa74c5
|
|
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I0d9b0ab12f17cb86544163ce3f0dc4945151e9e1
|
|
* Added "output-tensor-files,w" option to save output tensors to a file
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ida457177c5cbd7dca228772405fd505d03b61bf9
|
|
Change-Id: Id49e43680b306e762672f2681eaf45788dcfcdd0
Signed-off-by: Surabhi Mehta <surabhi.mehta@arm.com>
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Icf39434f09fd340ad664cb3b97b8bee6d9da4838
|
|
* If the number of the declared output types does not match
the number of outputs, throw an error (just like we do for
the inputs)
Change-Id: I1cb873bf443a31ecdbc11195462e9614ae3a6637
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Renamed ARMNN_COMPUTE_REF_ENABLED to ARMNN_REF_ENABLED in the
Android makefiles
Change-Id: I12af2ca00c719568274585482d428b035674737c
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Changed the default value of the new ARMNNREF option to ON in
the global makefile, so to always build the reference backend
by default, thus keeping the same behaviour as of the previous
releases
Change-Id: Id4941522ac7987c797ac8331ea421edb2a54287f
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: Id7ab186ec607ff6e5ee6869c4ad562af4c40b97a
|
|
ElementwiseTestHelper
* Refactored tests for element-wise operations to use ElementwiseTestHelper
* Moved the etasts for each operation in a separate file under backendsCommon/test/layerTests
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Icefb6b35df78b9619f69378229789505bf92670e
|
|
* Renamed ARMCOMPUTEREF to ARMNNREF (and relative symbols) as the
previous name was misleading
!android-nn-driver:1819
Change-Id: I912e9f521750b91539e48f8a2fb4de73fb6f7425
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Added null checks prior of using either the source or the destination
handle factory when checking if the tensor requires to be copied
Change-Id: Icc6737562849be5e7d1a62243327366e06312eb9
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* FCRN and FSRCNN aren't supported on all backends yet.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ibaddfba731224aac24de05c225fb94efd3fe7f94
|
|
* Added ARMCOMPUTEREF option to the build guides, as the
reference backend is not built by default
Change-Id: I2cd8dab12ed72a795ff79fe1087ab8bf7606694e
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Adds compatibility between Cl and Neon
* Adds related unit test
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Iaa454ea2a6392c89c0a83836c3156d4ddb354879
|
|
Failing VTS tests were "NeuralnetworksHidlTest.depthwise_conv2d_*"
In depthwise convolution there was a difference in weight tensor channel
order between the reference and ACL implementations. This specifically related
to NCHW. This commit:
* Adds ReorderWeightChannelsForAcl to WorkloadUtils which will correct the weight tensor channel order.
* Add unit tests to detect this problem.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Icaeac08e14b3d5da9e222ad2f118db55ebb15d09
|
|
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I6f16ea0dca359283a3b187e2f046f82a7dc2ff7c
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I912312f31d4fd82b23bafe8e3ec461b179f3e97a
|
|
* Created classes Device, Counter, Category, CounterDirectory
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Iaec4b0e154d962983c60460714bafcc1fb16f47e
|
|
* Added path override for dynamic backend loading
* Do not default to CpuRef, as there could be dynamic backends loaded at
runtime
* Do not check right away whether the backends are correct, as more of
them can be loaded at runtime as dynamic backends
Change-Id: If23f79aa1480b8dfce57e49b1746c23b6b9e6f82
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Create first version of PacketVersionResolver class
* Add basic unit test
* Move existing classes inside the armnn::profiling namespace
* Add utility methods for Version
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: If0ea0e1b9dea7fbfcd8b808e97b1e2aa91964dfa
|
|
* CMake "install" commands require a RUNTIME argument for platforms with
DLLs (e.g. Windows).
* Replace use of non-standard variable length array with vector
* Remove unnecessary #include of unistd.h
* Add #ifdefs to dynamic backend code to disable for non-Unix platforms
where you can't use dlopen etc. We could implement this properly for Windows
later using LoadLibrary etc., but for now erroring is fine.
* Add missing #include of <algorithm>
Change-Id: Ic8ef5fd599b37bf8772510157b6e479819f6a1eb
|
|
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I87d003ae14575d7d7be67b2a7d00d69ef6201849
|
|
* Made the build of the reference backend depend on a new ARMCOMPUTEREF
macro
* Made the relevant targets dependent on the ref backend
* Moved Cl and Neon static registry initializers to separate files
* Wrapped some of the unit tests into proper ifdefs where necessary
Change-Id: I7f2c42699682630233a4c4b6aed2f005083de189
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I64f82c0e3c5cddcaebe0d5001020880a759ec444
|
|
* Updated the NDK build guide to include instructions on what
extra files to deploy for running the dynamic backend unit test
Change-Id: I0a77b0bf911cfdd90be62f136dd06c118810d0c8
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: Ibfd5a81b2dbf9eeef49f6209885798804adee5a4
|
|
Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com>
Change-Id: Ibf2b5ce5e50d72d661a7c720c1f3bb1c0d811700
|
|
* Move DeepSpeaker, FCRN and FSRCNN from TensorFlowSupport.md
to TensorFlowLiteSupport.md
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I82d508d3599073eb8f6638994a91f46b4b95c247
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I3da43122240fda7864e0932d47b3efeea8bbed40
|
|
* Reordered and edited inputs in ParseTransposeConv method
* Updated test cases to reflect changes
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: Icd090cf6ab340eed4f098ef8641daf7c6e0d0949
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I9d19ae4559a98b9e740c1d4d05add0c5788093d6
|
|
* Fixed Quant8 VTS test failures where an output value should have been greater than 255 before a negative bias was applied.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ie0084c1c8c4a4b5f069112d523765ed338277e58
|
|
* NEON support for TransposeConolution2d
* Indentation fix on SpaceToDepth LayerSupport method
Signed-off-by: Keith Davis <keith.davis@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Signed-off-by: Aron Virginas-Tar <aron.virginas-tar@arm.com>
Change-Id: Ie3a01a22e05f62f475f768dfe05ce561d2f3b0ad
|