Age | Commit message (Collapse) | Author |
|
!android-nn-driver:2642
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: Ibabb73c0ae0df2e530a68398f75c76e6b80c0701
|
|
Change-Id: I1f228fcaf1077867d9755a2b850c6703387fab34
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
|
|
* Added NeonSpaceToBatchNdWorkload class.
* Added CreateSpaceToBatchNd implementation to NeonWorkloadFactory.
* Added IsSpaceToBatchNdSupported implementation to NeonLayerSupport.
* Enabled SpaceToBatchNd tests on Neon backend.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ic7d469a380482ec9febd44450f72dd7e53cda03f
|
|
!android-nn-driver:2622
Change-Id: If99d3eff71ff66ba28af1e5af248299fe04511b9
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Added new layer named ElementwiseUnary
* Deprecated existing Abs/Rsqrt layer functions
* Updated existing Abs/Rsqrt test infrastructure to use new layer
* Added boilerplate for new Exp,Neg,Sqrt elemwise op layers
* AbsQuantize test removed pending future commit
* Serialization support added
!android-nn-driver:2550
Change-Id: Ic595c645925e17b45db568187fd05646daf2e87f
Signed-off-by: josh minor <josh.minor@arm.com>
|
|
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: Idb583f8de4470eefb47c90189cd3c90e74e0440a
|
|
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: I6c90eab1c6bad76d5c7b3bf094998fa4b454bcd1
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Iedfc196bfd18e8280e99a06db68df9c15c8ea835
|
|
Logging.hpp is mainly useful for raising Arm NN log messages. There's
very little point in automatically including it for users of the library
via the ArmNN.hpp convenience header.
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: I71fb3188dc0b30c1bbc86a31996470c707d38c19
|
|
!android-nn-driver:2572
Change-Id: I8fe52ceb09987b3d05c539409510f535165455cc
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
!referencetests:218340
Change-Id: If24a604310d0363b1f09b406e4d53ebfeb106aad
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: Ib00f185b431ab74fd9425d8f478bd2ddb182f74b
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: I9e8d5576b3ec04c871785d5f2f9545bf1136e59b
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: I649cd2304fb0040164763d31a12fc77c6c3bed87
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Add README of an example how to build standalone dynamic backends
* Change the links to public API for backends
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I32ee15ba1b9ea3a6317ae184de8d28bb31eb5d9d
|
|
* google provided a patch so mixed precision can be removed
!devenv:217181
Signed-off-by: janeil01 <jan.eilers@arm.com>
Change-Id: I13630f465e51c629a85ca4e1ac504feeeec39aaa
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I8d2050f4478fe9d9cdf9e374b8906827cc769689
|
|
Change-Id: If3d98e45a6e2fa8e1afd19a4052334335feacf63
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Redirect the backendsCommon headers to the new headers
in armnn/backends
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I53424a16b378e50a20cf1e3f7f8e9ea477fed52f
|
|
* Add example to build dynamic reference backend
* Add functions to clear dynamic backends
* Fix the error when dynamic backend is not deregistered
* Add DYARMNN_DYNAMIC_BACKEND_ENABLED to check disable empty
dynamic backend when dynamic backend is enabled
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I1ef3a3f10ed6ca5ec18d0af04b007fc3bc71a3cb
|
|
Change-Id: I98cfb913dbd00cb94bdb5dbe82753ca147f7f671
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
!android-nn-driver:2435
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I10ecd4a8937725953396805f33a3562a5384c4d4
|
|
Change-Id: I318bf92b8d1db593d9c30b9b4412bfecbe65bc12
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Create a public API for the common backend files
* Move OutputHandler to armnn internal
* Remove unused headers
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I3e86d908b021e3561befa9d45158d87d2cbb18c0
|
|
Change-Id: I0432539197b21e3f430970993276be2b8b99bda6
Signed-off-by: Robert Hughes <robert.hughes@arm.com>
|
|
!referencetests:214319
* Reduces arm nn binary size ~15%
* Also fixed test logging black hole issues
Change-Id: Iba27db304d9a8088fa46aeb0b52225d93bb56bc8
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Send post-optimisation network structure if profiling service is enabled
* Refactor TimelineUtilityMethods
* Fix RecordEvent to link eventGuid with eventClassGuid
* Add common types and guid to LabelsAndEventClasses
* Add CreateRelationship to TimelineUtilityMethods
* Add CreateTypedEntity to TimelineUtilityMethods
* Add MarkEntityWithType to TimelineUtilityMethods
* Move VerifyTimeline functions to ProfilingTestUtils
* Post-optimisation network structure unit tests to Ref, Cl, Neon
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I0194f2037c236450c912f4c3cb11e46b80c0f512
|
|
*Add the call to ReorderWeightChannelsForAcl for QuantizedSymm8PerAxis weights
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I0d2e4c8328753ad15858130945b4fbb193943dfa
|
|
* Moved the relevant armnnUtils headers to the new location:
include/armnnUtils
* Update the header usage throughout the source code
!android-nn-driver:2387
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Change-Id: I2ba15cebcacafad2b5a1a7b9c3312ffc585e09d6
|
|
Neon backend
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I6dadb36abc2e71f4d4309dcce6072c4a66384cf9
|
|
This stuff is handled in CLPerumuteLayer::validate now
Change-Id: I552e7c0bbd1557d6b5e217c1e96aaeb2377accbd
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
|
|
to per-axis case
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I66a8360b6d86e95325dee58927dcbe62ccf6ad58
|
|
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Ie43f20e6fb2f9b4a1e9e9eb561fcf7b5d6a01806
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Ib790b24cfde87c92e29615da942c25bf7c98f95e
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I2ed38744e1e8c839b369be8d44c0cffccfeb370e
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: If7d366b2894050c53a651016165f34be1a2ce7a6
|
|
* Enable FP16 mixed precision for Android Q
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I5ddb94b13385e1fec39e4407dffc8e4bc6b8d64a
|
|
* This is a temporary measure that needs to be
removed when quantization multiplier > 1.0f
support has been added for NEON and CL.
* Layers affected: convolution, depthwise convolution,
dilated depthwise convolution and transpose
convolution.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: Ief1aec2ff0eedf8250f6a8675288e1c343dcfce4
|
|
* Added support for data types QuantisedSymm8 and QuantizedSymm8PerAxis
as they are supported on CpuAcc
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I55f81b35c8869bc37b7634bdbe91b8e3339eb648
|
|
This reverts commit 60538ada2b90704abcf6473144639103d80287a5.
Change-Id: I099e397fe1232e0f470d89a11d220752543e4e4c
|
|
* Enable Neon EndToEnd tests for ArgMinMax QAsymm8
* Enable Neon Layer tests for ArgMinMax QAsymm8
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Ifa7463ded4397cacb82fb3667006f08ecbe3cd32
|
|
* Add Guid to Workload
* Remove circular dependency
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Signed-off-by: janeil01 <jan.eilers@arm.com>
Change-Id: I15342fa7481c6bdc050e057dce2d74bba07fe2dd
|
|
* Support added for ACL neon slice workload
* Utility function created to translate ArmNN slice layer params to ACL neon slice layer equivalent
* Neon slice layer tests added as per SliceTestImpl.hpp
Signed-off-by: josh minor <josh.minor@arm.com>
Change-Id: Id583465311879af139e8e977f16ed2280c937ac7
|
|
* Fixed numerous CTS/VTS failures related to Quantization
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: If5c20256366e80b6b9bbc46b2a1c410a9b8c48e1
|
|
* Add clipping parameter validation in LstmQueueDescriptor
* Related UnitTest
Signed-off-by: janeil01 <jan.eilers@arm.com>
Change-Id: I86ff81cacc0e1fff5b78a8d6c2dcbf9ff57e2272
|
|
Dequantize
* Check for output data type as well as input data type when determining
whether we should attempt to fall back to FP32 if FP16 is not supported
* Override output type for Dequantize in IsLayerSupported() instead of
input type
* Updated original input type from FP16 to FP32 in InsertConvertFp32ToFp16LayersAfter()
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Ic6477fd17cea5a91bd8bf9ae0cf836520897d5b7
|
|
DepthwiseConvolution on ACL backends
* This is a temporary measure that needs to be removed as soon as the
NEON and CL DepthwiseConvolution workloads will have added support
for per-axis quantization
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I24eb285230293392a6ed50aece1101e5aed7f90e
|
|
The current algorithm in SubgraphViewSelector has a bug that can lead to
it producing subgraphs which have a dependency cycle (see the newly
added test case 'ValidMerge' for a repro). It also fails to merge
subgraphs in some cases where it could, which leads to smaller subgraphs.
In the case of FSRCNN, the NPU cannot support these smaller subgraphs and
so this is blocking us from supporting that network.
This commit changes the algorithm to fix the dependency bug and
also make it so that subgraphs are merged in the cases that were missed
before. It also adds some unit tests to cover cases that were problematic
before, and to extend coverage for the new algorithm.
The new algorithm has two downsides compared to the previous one:
1. Disjoint subgraphs are not merged. This can never lead to a failed
compilation by the NPU and so I believe this is less of an issue than
the previous algorithm's "missed merges". This could however lead to a
runtime performance loss in some cases as the NPU will be unable
to parallelise as many operations. There are some unit tests that cover
this which I have disabled.
2. The performance is worse. I have spent some time analysing this and
for a graph with ~1000 layers the new algorithm takes 20ms vs. the
old algorithm's 4ms (on my desktop PC). I believe the performance is
still within acceptable limits. I also compared inception V3 (which was
the network which caused performance issues with the original version of
the splitting algorithm) and this new algorithm has not regressed there
(200-300us in both cases).
Change-Id: I1dd64a779f272723621e04d203b5a2752a6af2ef
Signed-off-by: Robert Hughes <robert.hughes@arm.com>
|
|
The default version of message("...") print to stderr, which is inappropriate
for informational messages such as the ones we are printing in these cases.
Using message(STATUS "...") makes these messages appear on stdout instead
which is more appropriate.
Change-Id: I02f41e6b4948e6938566f06d7164444bd5b8199e
Signed-off-by: Robert Hughes <robert.hughes@arm.com>
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Ia879f2d84a1b977474ee0dafa976f2aab32bd3ae
|