AgeCommit message (Collapse)Author
2020-05-27IVGCVSW-4787 Update NNAPISupport.txt for 20.05v20.05branches/android-nn-driver_20_05Teresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I8c496346ccdcfc6ed6cfe2ba08edf5779beb0b69
2020-05-26Minor updates to FAQ in the android-nn-driver/docsNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Idbccd8870daa832cb525862246673651720e209f
2020-05-25Updating boost download URL in the setup.shNikhil Raj
* AndroidNNOOB test was failing to download boost from the sourceforge.net mirror. Hence switching back to boostorg URL Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Ida65ea690ced44d382358b0ea6eac021a99a9b0a
2020-05-25IVGCVSW-4792 Update android-nn-driver README and IntegratorGuideNarumol Prangnawarat
* Add android.hardware.neuralnetworks@1.3 HAL Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I9cdf3e8c6e43570918533ba759f8b969cf2214a7
2020-05-22IVGCVSW-4453 Add Support for ANEURALNETWORKS_QLSTM to HAL 1.3 DriverSadik Armagan
* Input 30 for QLSTM is zero point of the hidden state, ANEURALNETWORKS_INT32 * Input 31 for QLSTM is the scale of the hidden state, ANEURALNETWORKS_FLOAT32 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I1c6304fa4772895ce57286b58b2c3363c25c38e2
2020-05-20IVGCVSW-IVGCVSW-4772 Fixes for android-nn-driver unit tests on Android RDavid Monahan
* Added missing operand parameter numberOfConsumers to DriverTestHelpers * Added nullptr checks to unit tests * Disabling QuantizedLstmTest when ARMCOMPUTECL_ENABLED is undefined Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: I46dc413d3bb1805eb0e7c982177b6d60d0b297f5
2020-05-19IVGCVSW-4453 Add Support for ANEURALNETWORKS_QLSTM to HAL 1.3 DriverSadik Armagan
* Add QLSTM support for Android NN Driver * Add overrideOutputInfo parameter to SetupAndTrackLayerOutputSlot * Add optional condition to GetInputScalar * Refactor Quantized 16 Bit LSTM impl Change-Id: Ie8fa98ad5ee4a62174ef91ca80f1df62b7fde937 Signed-off-by: Keith Davis <keith.davis@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
2020-05-15IVGCVSW-4837 Add driver service name command line optionKevin May
* revert commit 8a510e8e9ed22ec0bbd295b69a6700ad0ba7cfd8 * Add driver option to give service a name, default to "armnn" Change-Id: I9755206494f637bee4c8299bf6370fc4731638c8 Signed-off-by: Kevin May <kevin.may@arm.com>
2020-05-14IVGCVSW-4531 StridedSlice Failures on HAL DriversSadik Armagan
* Check if the output is large enough to hold the slice in the driver Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Iaef16167e891a41186de030324bb45b8bbca4d80
2020-05-06IVGCVSW-4673 Change ArmNN driver service name to arm-armnnKevin May
* Change service name from "armnn" to "arm-armnn" * Rename .rc files * Update Android.mk to use new service name * Update Integrator Guide Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: If2a4ac9756101472d30255afbf8c90859e29aabf
2020-04-30IVGCVSW-4771 Add support for Boolean and QAsymmS8 in dump filesTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I89c245c0d3ca291e1d9864121b68762205278f35
2020-04-27IVGCVSW-4692 HAL 1.3 VTS/NNT, Unit test FailuresSadik Armagan
* Check if the model is prepared. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ia6ea7c5b61a1da97acddddfc5431925cbb4f0227
2020-04-24IVGCVSW-4677 Refactor Timepoint duplicationKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I6d37e7b8022ada1d875be01014babc5d31d07290
2020-04-23IVGCVSW-4677 Fix FencedComputeTest Hal 1.3Sadik Armagan
* Implemented executeFenced() function in HAL 1.3 Driver Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I11f8f532e9688d4e194992b46dbed575a19be3c5
2020-04-21IVGCVSW-4675 Fix VTS 1.3 GeneratedTest.Test/armnn_resize*David Monahan
* Added GetOptionalBool function * Added checks to Resize for unsupported operands AlignCorners and HalfPixelCenters !armnn:3062 Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: Ic0305014ed2638e3a3d1e7520972e3a2909e504b
2020-04-21IVGCVSW-4679 Fix VTS DeadlineTest failures 1.3 CpuAcc CpuRefSadik Armagan
* Optional timeline parameters are not supported yet. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ic5d6cd6af0cd87d4acba102a48fc94ec8b406377
2020-04-17MLCE-186 Adding Android Q VTS and CTS failures to FAQMike Kelly
* Added note to explain VTS and CTS failures to the FAQ. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I847e240d1f8e2b3f9bd6fdceae9e16f02055ef3d
2020-04-16IVGCVSW-4672 Fix VTS 1.2/1.3 GetCapabilities testKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I13be6896dd313bfeaf2f6b08ce0e47116116c3c0
2020-04-09IVGCVSW-4641 Investigate Hal 1.3 VTS FailuresSadik Armagan
* Return correct ErrorStatus for MemoryDomain test * Return if ErrorStatus is different than NONE Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I4224256b7c382e5a46349ac730e5f6d5828539ed
2020-04-07IVGCVSW-4378 Fix transpose outputInfo for skipped Concat VTS in CL and NeonTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I7962be3a77cacf15dad594f0a907499c5b39bfeb
2020-04-07IVGCVSW-4485 Remove Boost assertNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: If602024a339df7548333e470545f9400c3daf7b3
2020-04-07Fixed missed change to libOpenCL exclusion flowalered01
Part of "Add flow to exclude libOpenCL when building AndroidNN" Signed-off-by: alered01 <Alex.Redshaw@arm.com> Change-Id: I7d57db8a314312d7c160c2759224a54d9bf3d0af
2020-04-03Add flow to exclude libOpenCL when building AndroidnNNalered01
When building AndroidNN for a commercial silicon device, there's no need to include libOpenCL as we should be able to use the one already on the device Change-Id: I5ef5776010399dd2d2d48958465daf4b71e4f825 Signed-off-by: alered01 <Alex.Redshaw@arm.com>
2020-04-03IVGCVSW-4641 Investigate Hal 1.3 VTS FailuresSadik Armagan
* Return correct error status for executeFenced function Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I25c41f064ac5cc233561cbd2b6547c02053b33da
2020-04-01IVGCVSW-4441 Add Support for ANEURALNETWORKS_ELU to HAL 1.3 DriverSadik Armagan
* Read alpha parameter for ELU operation * Created ConvertionUtils_1_3 for 1.3 Driver * Added QAsymmS8 data type support to swizzle the tensor Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I9d66a4e8d5468efa305bb8f6c352f13d27602274
2020-03-31IVGCVSW-4640 Fix HAL 1.3 build issues from update of AOSP masterKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I19dd23f938f571f3f63bb1e070d27d27cbe65c1a
2020-03-31IVGCVSW-4407 HAL 1.3 Operators SupportSadik Armagan
* IVGCVSW-4441 Add Support for ANEURALNETWORKS_ELU * IVGCVSW-4443 Add Support for ANEURALNETWORKS_HARD_SWISH * IVGCVSW-4448 Add TENSOR_QUANT8_ASYMM_SIGNED data type support Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Idb9bb3f463b956221711423c15b6557eeb1af7db
2020-03-30Downloading boost from sourceforge instead of boostorgNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I7da8fdf2afef8382f1544ebda5aeb40cef8608e2
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
2020-03-23IVGCVSW-3813 Add Unary Elementwise Operation 'NEG' support to the ↵Sadik Armagan
android-nn-driver !armnn:2917 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I6e38fd3d11dc3e30dfac0ddfc39b216b2a15d047
2020-03-19IVGCVSW-4565 TENSOR_BOOL8 data type not supported in AndroidNN DriverSadik Armagan
* Added TENSOR_BOOL8 support * Added Broadcast support to comparision operators !armnn:2903 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I844e32b57399eff2dc60af9b2099145316c80cae
2020-03-18Less code duplication in HAL 1.2Derek Lamberti
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com> Change-Id: Ic2e8964745a4323efb1e06d466c0699f17a70c55
2020-03-11IVGCVSW-4482 Remove boost::ignore_unusedJan Eilers
* replaced boost::ignore_unused with armnn::IgnoreUnused Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I4443a3620ed7d51b151af67c070d4225e410b5fa
2020-03-09MLCE-149 Build problemsMike Kelly
* Updated FAQ to better explain how to resolve build problems due to missing or mismatched versions of boost, clframework and armnn Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I115e075e9160d01d400cc53fc4d3f7fc788f3b50
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>
2020-02-28IVGCVSW-4375 Add driver support for TransposeMike Kelly
* Changed ConvertTranspose to use Transpose instead of Permute * Removed unused code related to permutation !armnn:2787 Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Ie59ca80203109bd6bb2abcdedc5ac53c2b2eb157
2020-02-28IVGCVSW-4525 Adding TPIP comments to sourceJan Eilers
Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I4cd521f01172889966e64d03cdf899a355bd39d3
2020-02-26Update IntegratorGuide.md fileNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I901b8529f0bdfa281348853ad8ea944d2bcf01b9
2020-02-21IVGCVSW-4471 ValidationTestIntrospection.DeviceGetType fails in Q NN testsSadik Armagan
* Throw an exception if there is no known backend specified for the driver Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I8b0be33c0a8786b493ac1f8c17573853db8e8218
2020-02-20IVGCVSW-4375 Fixed driver crashesMike Kelly
* Fixed driver crashes caused by ignoring the result of GetTensorInt32Values. * Fixed driver crashes where padding, axis, permutation dimension or block size operands were inputs. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I59867e9545a240e6be46b7f68da6adaa120a56d8
2020-02-20IVGCVSW-4432 Update Readme for 20.02Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Iac553b5b6b3890a13aa617bc64cbe626967e6d2b
2020-02-19IVGCVSW-4430 Update NNAPISupport.txt for 20.02Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: If475b0448a1adaa7c08cbdaa5efed1e0eae3c89a
2020-02-11Partial Revert "IVGCVSW-4130 Remove clframework from android-nn-driver build."Mike Kelly
* Partial reversion to restore Android.mk files. * Changed armnn-arm_compute library name to arm_compute_library. !armnn:2714 This reverts commit 826dd41dc4de616059a61fb0aaec432311372c6c. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Idb4a2eeb6cbb19a249c1a85eec2cf597d6b6d970
2020-02-10IVGCVSW-3987 Add armnn::Exception warning and std::exception errorKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I4963fb4d44501287e161f7366f38557962d06cac
2020-01-31IVGCVSW-4130 Remove clframework from android-nn-driver build.Colm Donelan
Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I019bdab899de19c1a2cb6bbd72dd38ceb677d98b
2020-01-31IVGCVSW-4388 Update ACL pinTeresa Charlin
* Update Android.bp file with new created files. !armnn:2672 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ic56c041018073679c10074ea4c5e95eb7525a631
2020-01-28MLCE-153 Padding calculation for TransposeConv ignores strideMike Kelly
* Changed ConvertTransposeConv2d to use the unsigned values for strideX and strideY not the signed values from the descriptor. !ComputeLibrary:2599 !armnn:2612 Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Iee300041f3ed585820b7c7e2edd8ab541f339d59
2020-01-28IVGCVSW-4360 Update ACL pinSadik Armagan
* Update Android.bp file with new created files. !armnn:2612 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Idedc9cc3f4bbdb99c29cd1ba0f355aae870fe2e5
2020-01-27IVGCVSW-4301 Correctly validate reshape for broadcastable inputsDerek Lamberti
!android-nn-driver:2642 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com> Change-Id: I4db6ea4ed0a192c85f124c4a9ced60b1666a3870 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
2020-01-24IVGCVSW-4262 Add Calls to IsReshapeSupported and IsPermuteSupportedKevin May
!armnn:2643 * Add calls before addition of these layers in ConvertConcatenation * Add outputInfo parameter wherever needed for IsReshapeSupported Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Ic5d142ea046161960ff2fc137bd261ebb4e6ac0c