aboutsummaryrefslogtreecommitdiff
path: root/ArmnnDriverImpl.cpp
AgeCommit message (Collapse)Author
2023-04-07IVGCVSW-7197 Android NN driver Opaque delegate changesJohn Mcloughlin
!armnn:9369 Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com> Change-Id: Ia31ef139ea78da92e324fb9428ad3cbbdb220047
2022-03-08IVGCVSW-6649 Add Timepoints to Android NN DriverRyan OShea
* Added timepoints to ArmnnDriverImpl across all versions * Added ALOGV message to display time taken for prepareModel function * Added ALOGV message to display time taken for prepareModelFromCache function Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: I07f341099e81a0da45db0e8f575ba3c26631e024
2022-02-16Revert "Revert "IVGCVSW-6700 Enable import aligned host memory in ↵Narumol Prangnawarat
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>
2021-11-04IVGCVSW-5636 'Implement NNAPI caching functions'Sadik Armagan
* Cached serialized ArmNN model. !armnn:6384 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I78120a7f8ea892a28c0ff25f1b54e67a4f912574
2021-06-23IVGCVSW-6062 Rework the async threadpoolFinn Williams
!armnn:5801 Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I9964d0899ce752441f380edddbd974010257b2dd
2021-05-26IVGCVSW-5781 Add Async Support to Android-NN-DriverFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I1f13d04100fdb119495b9e3054425bf3babc59f1
2021-02-16IVGCVSW-5686 Add GpuAcc MLGO tuning file configuration argument to nnapiFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I15ca7db703065b0c70766a18b1a9a213834f39e0
2021-02-15IVGCVSW-5665 Basic NN Driver support for next OS VersionSadik Armagan
Signed-off-by: Kevin May <kevin.may@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I1e1db52322092c6b1b7ac6183c3adc90aabcec24
2021-02-12IVGCVSW-5685 Add CpuAcc specific configuration option numberOfThreadsMatthew Sloyan
* Added --number-of-threads command line option to android-nn-driver !armnn:5068 Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I248326bf3c0355a7a17b70cb1aac7b7976820c12
2021-01-13IVGCVSW-4417 'Serialise ArmNN Model on android-nn-driver'Sadik Armagan
* Implemented serialization of the network on android-nn-driver !armnn:4850 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I3caf07bd4d1d2a3068c58f0b344303c4cf977ca6
2021-01-11IVGCVSW-5485 'Add CacheLoadedNetwork options to Android NN Driver'Sadik Armagan
* Added Flatbuffers dependency to android-nn-driver * Added CacheLoadedNetwork options to android-nn-driver Options will be android.hardware.neuralnetworks@1.3-service-armnn -v -c GpuAcc -n arm-armnn -s -q <file_path> & Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I2cdf0b84062cb1c6ad4346cd64b00161cfe85920
2020-10-07IVGCVSW-5298 Remove boost::format from Android-nn-driverColm Donelan
* 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
2020-09-30MLCE-233 Added ability to enable fast_math through the NNAPI driverMike Kelly
* Added -a command line option to enable fast_math on Neon/CL when launching the NNAPI driver * The invocation will look something like: /vendor/bin/hw/android.hardware.neuralnetworks@1.3-service-armnn -v -c GpuAcc -n arm-armnn -a * Enabling fast_math may cause an increase in VTS or CTS test failures due to a change in precision Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Ifd8931f95efd65d3ae3aca9d9d61bd381e4e24a5
2020-03-26IVGCVSW-4447 Add Hal 1_3 SupportKevin May
* 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
2020-03-03IVGCVSW-4473 Android R pre Hal 1_3 build changesKevin May
* 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>
2020-01-24IVGCVSW-4270 Change .dot file name to start with netIdJim Flynn
* .dot file will start with the same number as the associated input and output tensor dump files Change-Id: Ic64539854c2b8c34a7034fa18a142b2dfe67df7d Signed-off-by: Jim Flynn <jim.flynn@arm.com> IVGCVSW-4271 Add getSupportedOperations marker file * Also fix segfault in previous graph dump code Change-Id: I01915f47ae17d89ad3595430d073a17b1a1fda58 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-11-29Catch std::exception instead of armnn::ExceptionDerek Lamberti
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com> Change-Id: I89ae4f3b607ccb83f1bf16e085c805d5fc5cf89c
2019-11-08IVGCVSW-3987 Fix for potential unique_ptr.release() bugKevin May
* Use an android strong pointer instead of a unique_ptr to avoid undefined behaviour of releasing unique_ptr to strong pointer Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Icac255ba2407796888f20ffaba99a7988cb6f63c
2019-06-11IVGCVSW-3181 Add HAL 1.2 support to android-nn-driverMike Kelly
* 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
2019-05-07IVGCVSW-2911 Work towards compatibility with QMatthew Bentham
Explicitly use HAL V1_0 Operand, OperandType, and IPreparedModelCallback Change-Id: If6aa6e9dc1bd0b7673ec247ac3560e7f072ef699 Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2019-04-04IVGCVSW-2886 Support multiple backends in Android driverNattapat Chaimanowong
Change-Id: I4abe1f750801911570b6dc65c187b828c5929b5f Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-04-02MLCE-110 Propagate error from armnn EnqueueWorkloadMatthew Bentham
Change-Id: Ic53b1cdbdd3a7d656932651c74911940affc09b6 Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2018-10-25IVGCVSW-2051 Added unit tests in the Android NN Driver for the newMatteo Martincigh
Mean layer * Added unit tests (in a new file test/1.1/Mean.cpp) * Refactored ArmnnDriverImpl to remove redundant tags in the log messages * Modified AddInputOperand to accept a quantized input tensor Change-Id: Ie037ce426777daab28b0501124e1cc8686ad6184
2018-10-12IVGCVSW-1929: Optimize function signature changejimfly01
* Optimize now returns reasons for failure !armnn:152481 Change-Id: I1cd7f5796b3c469e9baecbed80e392ac74e40ef4
2018-09-18IVGCVSW-1806 More Android NN Driver refactoringMatteo Martincigh
* Changed #if defined to #ifdef * Simplified the Android ML namespace resolution * Fixed the relative path in some include directives Change-Id: I46e46faff98559c8042c1a4b8b82007f462df57d
2018-09-18IVGCVSW-1806: Refactor Android-NN-Driver ModelToINetworkConverterarovir01
* Moved conversion logic into new V1_0 and V1_1 HalPolicy classes * Extracted common helper functions into ConversionUtils class Change-Id: I1ab50edc266dd528c0cb22a5cd1aa65e103674d9
2018-09-18IVGCVSW-1807: change license text in file headersDavid Beck
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
2018-09-18IVGCVSW-1806 Restored the fp16 flag left behind during the previousMatteo Martincigh
refactoring * Split getCapabilities and getCapabilities_1_1 as it was before * Setting relaxedFloat32toFloat16Performance when using HAL 1.1 as required by one of the VTS test Change-Id: Iff883b8cbd0511596e9848fa40e91e4fa58d4260
2018-09-18IVGCVSW-1806 Refactored Android-NN-Driver, added common "getCapabilities",Matteo Martincigh
"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
generated by cgit v1.2.1 (git 2.23.0) at 2024-04-29 03:09:57 +0000