Age | Commit message (Collapse) | Author |
|
!armnn:11542
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Ia0750f8ada84b605a8674acbfb9b9a0c983a5376
|
|
* Added test to ensure that all inputs and outputs do not go out of
bounds.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ia97e85f71e46cd2203306243e4dcbc23e0f29ec1
|
|
* Modify all versions of ExecuteGraph to include timing information. This
can give a rough guide as to how much overhead the driver is adding.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Ie168e060c22b8417efa2ede0c9bdc7ef2631b913
|
|
android-nn-driver""
This reverts commit 8069603dc44b7673b356f66517cd8b25af8080f0.
* Reason for revert: Try reenable import aligned host memory in android-nn-driver
* Added a check to ArmNNDriverImpl.cpp to not call ExecuteWithDummyInputs with GpuAcc
* Added new android-nn-driver driver options to enable / disable Import and Export
* Import is disabled by default for now due to conv2d issues
* Export is enabled by default
!armnn:7147
Change-Id: I91110c58ebb3931d1c458e3774944e55c1250dd8
Signed-off-by: David Monahan <David.Monahan@arm.com>
|
|
* In the destructor of ArmnnPreparedModel, DumpJsonProfilingIfRequired
was being called with a potentially null profiler.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Id0d3a2403878fedc4e05dc498edb48d574232c71
|
|
This reverts commit 8509422e1e7d629f88d6a5e4e4bded8a682f435b.
Reason for revert: Reverting as this might be the cause of several segfaults on CI
Change-Id: I902b4ddaec23dc46a2459f8512ec458e1aa722f3
|
|
!armnn:7025
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Iaa6112fb52d0f2942e6c52f90d96a8dc96000518
|
|
!armnn:6495
* Made fixes to 3 files ArmnnPreparedModel(_1_2/_1_3).cpp to set
TensorInfo to constant in PrepareMemoryForInputs().
* Fixes made due to cts and vts failures in
https://review.mlplatform.org/c/ml/armnn/+/6495
when a Tensor is passed to a ConstTensor without the
TensorInfo isConstant parameter being set.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Iee179586652f365665a22f1e3409c1488c2d8bb3
|
|
* Changed asserts to check for errors and return appropriate values or
throw exceptions
* Changed unit tests to use Doctest's long macro names as the short
macro names clashed with Android's Logging macros
* Removed unused #includes
* Clarified ambiguous #includes
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ice92a37590df727fd581d3be5ff2716665f26a13
|
|
the threadpool
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Ie350a11eab5d677dd6a5571ea4094aa51b23c501
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I7cb21e18a7031b8cfe579046b33ad0491aa5c629
|
|
!armnn:5801
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I9964d0899ce752441f380edddbd974010257b2dd
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I4037e3bb47ed0f5585663ca56eed2866bc8a9ef7
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I1f13d04100fdb119495b9e3054425bf3babc59f1
|
|
Signed-off-by: Kevin May <kevin.may@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I1e1db52322092c6b1b7ac6183c3adc90aabcec24
|
|
* Replaced with stringstream, string or filesystem::path
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I2aa80d88cc0eaff5de4dc6a121370ebf41dcb0a8
|
|
* Change NN Driver m_Network to now have ShapeInferenceMethod::InferAndValidate
* Implement dynamic tensor support for:
- ArgMinMax layer
- Pooling2d layer
- Activation layer
* Skip dynamic tensor tests for any HAL other than 1.3
Change-Id: Icf66c968e49cdd4822b8c79c5f18b3f9e97dc53f
Signed-off-by: Finn Williams <Finn.Williams@Arm.com>
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
|
|
* Add new 1.3 files HalPolicy, ArmnnDriver, ArmnnDriverImpl
* Add new .rc file for 1.3 service
* Add ArmnnPreparedModel_1_3 and implement new functions
* Update Android.mk with 1.3 driver and service
* Refactor ifdef to include ARMNN_ANDROID_NN_V1_3
* Create Utils getMainModel for new 1.3 Model Main Subgraph
* Use android Utils to convertToV1_X in ArmnnPrepapredModel_1_3
* Refactor HAL 1.2 convert functions into ConversionUtils_1_2.hpp
* Replace ArmnnBurstExecutorWithCache with call to ExecutionBurstServer
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I514069e9e1b16bcd1c4abfb5d563d25ac22d02e3
|
|
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
Change-Id: Ic2e8964745a4323efb1e06d466c0699f17a70c55
|
|
* Update ErrorStatus to V1_0::ErrorStatus
* Update Request to V1_0::Request
* Update OperandType to V1_2::OperandType
* Add namespace android::nn::hal in ArmnnDriverImpl for R only
* Add missing g_RelaxedFloat32toFloat16PerformancePowerUsageName
* Add namespace V1_0 or V1_1 where necessary
* Update Android.mk with R macro and android.hardware.neuralnetworks@1.3
* Remove androidnn.go
* include IAllocator in DriverTestHelpers
* Remove unused LOCAL_CFLAGS
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I1787f1ed6784b3bbec017536d87d49197405e853
Signed-off-by: Kevin May <kevin.may@arm.com>
|
|
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I4963fb4d44501287e161f7366f38557962d06cac
|
|
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
Change-Id: I89ae4f3b607ccb83f1bf16e085c805d5fc5cf89c
|
|
*Updating ArmnnPreparedModel_1_2 to work with output shapes and timing.
Change-Id: I06c4ecaf1e2c36ef77a0731ece4885fc3997cd3b
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
|
|
* Updated Android.mk to build HAL 1.2 driver
* Added 1.2 HalPolicy and ArmnnDriver
* Added 1.2 ArmnnPreparedModel
* Updated converters and utilities to accept new HAL 1.2 operands and operand types.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I62856deab24e106f72cccce09468db4971756fa6
|
|
Changes needed to RequestThread and ArmnnPreparedModel
to compile in the Q environment
Change-Id: Ib072afa1fe6a6a1b0931df79cec76cfac8b21f0c
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
|
|
Change-Id: Ic53b1cdbdd3a7d656932651c74911940affc09b6
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
|
|
* Changed #if defined to #ifdef
* Simplified the Android ML namespace resolution
* Fixed the relative path in some include directives
Change-Id: I46e46faff98559c8042c1a4b8b82007f462df57d
|
|
before and after passing the FP16 flag in the Android-nn-driver
Change-Id: If8d4ca12421c3bee2526eec98f11d393af822373
|
|
* Moved conversion logic into new V1_0 and V1_1 HalPolicy classes
* Extracted common helper functions into ConversionUtils class
Change-Id: I1ab50edc266dd528c0cb22a5cd1aa65e103674d9
|
|
All changes are the same:
//
// Copyright © 2017 ARM Ltd. All rights reserved.
-// See LICENSE file in the project root for full license information.
+// SPDX-License-Identifier: MIT
//
Change-Id: Ibb7ed1e4e2191b9a978e26b5bacf916db403a60e
|
|
"getSupportedOperations" and "prepareModel" implementations
* Added common base ArmnnDriverImpl class
* Added common template implementation of the driver's "getCapabilities",
"getSupportedOperations" and "prepareModel" methods
* Refactored ArmnnPreparedModel and RequestThread to support HAL
v1.1 models
* Moved "getStatus" to the common base class, as it is shared by both
HAL implementations
* Refactored the code where necessary
Change-Id: I747334730026d63b4002662523fb93608f67c899
|
|
Android NN Driver
* Moved the profiling enable to the ArmnnPreparedModel constructor
* Moved the dump fo the profiling info to the ArmnnPreparedModel
destructor
Change-Id: Ide208688bcf9d0cd25fa23890a059e523b808902
|
|
profiling output to a file
If profiling enabled and dump directory specified, re-test needed to ensure flags are used correctly
* Minor formatting changes.
* Added check for runtime null pointer.
Change-Id: I1e7e433a958c16c7d9b59a484b18a7902c1ad8ad
|
|
|
|
|
|
Change-Id: I41a89c149534a7c354a58e2c66a32cba572fc0c1
|