aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2019-11-07MLCE-133 Fixed ASR hero use-casePablo Tello
* Added workaround in FC to deal with non const weights * Added workaround in LSTM to deal with non const weights Signed-off-by: Pablo Tello <pablo.tello@arm.com> Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: I854eea6a74a6959606ff25b52a0ed80b3e0a18ab
2019-11-06IVGCVSW-3841 Add support for per-axis quantizationAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ife7fa63b8839465e8f9f8626f34ca8c0f4d12788
2019-11-01MLCE-143 Fix for reference implementation for service stopping when running CTS.Teresa Charlin
*ConvertDepthwise reports that weights are not supported with the first dimension of the tensor is not 1 *ConvertConcat was missing one case for reporting unsupported inputs. Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I7759ad2fea55d272e98b9eabbf4821dc9ac826e1
2019-10-30IVGCVSW-3805 Add Comparison support to the android-nn-driverAron Virginas-Tar
* Added support for the following HAL1.2 operations: EQUAL, GREATER, GREATER_EQUAL, LESS, LESS_EQUAL and NOT_EQUAL Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I71b68db70232da4aaad28caa7b0b5f9a1d7778d0
2019-10-29Improve logging in hal_1_2::HalPolicy::ConvertResize()Aron Virginas-Tar
* Added resize method (Bilinear or NearestNeighbor) to log * Removed superfluous call to SetTensorInfo() for output slot !armnn:2179 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I4d1ad0d4c1df67c62c71f79125612b0dffa85455
2019-10-18Github #275 Improved getting ArmNN's version at compile timeMatteo Martincigh
* The version macro is set in the Version.hpp just like before, so parsing it from file is no longer necessary !armnn:2090 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: I3f8d10bd7b8947f9361e50edf033ea4e93451faf
2019-10-17Move version definition to its own fileMatteo Martincigh
* Move the ArmNN version to a separate ArmnnVersion.txt file * Updated makefiles accordingly !referencetests:206978 !armnn:2089 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: I02b838bc71611a866b3f96335e44a33b0167134f
2019-10-15IVGCVSW-3894 Add support for LOG_SOFTMAX to the HAL 1.2 driverAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I59645b339f3b176e5d0852769acb95f5657101d3
2019-10-10IVGCVSW-3891 Remove FLOAT16 from the list of supported types for ↵Aron Virginas-Tar
INSTANCE_NORMALIZATION * Since CpuAcc does not support FLOAT16 for INSTANCE_NORMALIZATION, it should be removed from the list of (fully) supported types Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ice557a7a08eca6faa8283c399fa2b03e64e3ddc6
2019-10-09IVGCVSW-3891 Add support for INSTANCE_NORMALIZATION to the HAL1.2 Android driverAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ia4dfbda7aceb4cdfb8f83d49e4df21dedd415b7b
2019-10-04IVGCVSW-3818 Support Group convolution from AndroidTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ie98688175203563ae08019c0c3c876d9c5eae24c
2019-10-04IVGCVSW-3889 Add ACL source files required for ClInstanceNormalizationWorkloadAron Virginas-Tar
* Add CLInstanceNormalizationLayer.cpp and CLInstanceNormalizationLayerKernel.cpp to Android.bp Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I1f86c961c52cda95c6d92aa6108b3eb6bb942f30
2019-10-03IVGCVSW-3947 Update ACL pin to 79f88e6d825402388bb79fc123ee2dfe01985bdaAron Virginas-Tar
* Added runtime/IWeightsManager.cpp to list of required ACL source files !armnn:2034 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I0366e936be4a48fe140cd2571b83c8d0c08443d0
2019-10-02IVGCVSW-3737 Add support for converting DEPTH_TO_SPACEAron Virginas-Tar
* Added ConvertDepthToSpace() to hal_1_0::HalPolicy and hal_1_2::HalPolicy * Implemented ConvertDepthToSpace() template inside ConversionUtils.hpp * Changed unsupported operation from DEPTH_TO_SPACE to HASHTABLE_LOOKUP in GenericLayerTests/GetSupportedOperations Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I12bf73ea721e7b6d49cc4a76000b43a3f274c6f5
2019-10-01IVGCVSW-3873 Update ACL pinNarumol Prangnawarat
* Update ACL pin to include change of ArgMinMax NEON/CL output type to Signed32 !armnn:2010 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I27c470d02253cbfd57c75c915e1e5ab9707e48dc
2019-09-16IVGCVSW-3663 Add EXPAND_DIMS to the android-nn-driverNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ibf6c53822f728c0e15a9ca1cd2c2ad3593edbd82
2019-09-13IVGCVSW-3873 Update ACL pinSadik Armagan
* Update ACL pin to include fix for Activation.Sqrt issue on Neon * Changes to Android.bp to build the driver with the latest ACL version !armnn:1925 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I59c4a7bc9c4fe7399f7d8320d2eb32bf57d6431f
2019-09-10IVGCVSW-3833 Add RSQRT to list of supported operators in NnapiSupport.txtAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I1e0909fa7fce64e9085889d645b093b51d63d8b2
2019-09-10IVGCVSW-3832 Implement ConvertRsqt() method in 1.2/HalPolicy.cppAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I1baf88f15c9bdcffd38e910070c97909b7f913b3
2019-09-09IVGCVSW-3746 Add Android NN Driver support for ABSKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Icd32bf6f4d5f58e689b55c1c71b0d028155603c8
2019-09-04IVGCVSW-3660 Add SQRT to the android-nn-driverSadik Armagan
* Implemented Convert() function for SQRT operator * Fixed some typos in HAL 1.2 Policy Change-Id: I1e0bc7a43622c52f053927248ee1a71cb797145e Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
2019-09-03IVGCVSW-3686 Update ACL pinMatteo Martincigh
* Changes to Android.bp to build the driver with the latest ACL version !armnn:1855 Change-Id: I3360c41b7b4f30c5adb46977a1ea7bd8946f433e Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-30IVGCVSW-3507 Remove unsupported operation sectionsMike Kelly
* Removed unsupported operation sections Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I79216c5c015efeb5d2e19cd85f186c2f73bd1ca8
2019-08-29IVGCVSW-3656 Undo wrong rename of the backend control macrosMatteo Martincigh
* Renamed the cl/neon backend macros to their original values, as they were renamed by mistake * Reverted misleading comment * Updated the readme file !armnn:1837 Change-Id: I49faabae2c8ad196f51eca5f8dd049ecf74b36e1 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-28IVGCVSW-3656 Rename ARMNN_COMPUTE_REF_ENABLED to ARMNN_REF_ENABLEDMatteo Martincigh
Change-Id: I5982d8dc733bd8bf1eed51c467df5a16a6aabcdb Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-27IVGCVSW-3656 Rename ARMCOMPUTEREF to ARMNNREFMatteo Martincigh
* Renamed ARMCOMPUTEREF to ARMNNREF (and relative symbols) as the previous name was misleading Change-Id: Ia0400a7d63a76c80fb5bdd26410553db1c15cba0 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-22IVGCVSW-3613 Add Quantized LSTM test to Android NN DriverEllen Norris-Thompson
Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com> Change-Id: Ie3c535789186571df9000d75ad2a62ac8c94dcb4
2019-08-22IVGCVSW-3613 Refactoring Android NN driver for QuantisedLstm testEllen Norris-Thompson
* Templated AddPoolAndGetData and AddPoolAndSetData to accept different types * Moved scale and offset to arguments of Add*Operand functions Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com> Change-Id: Iaf4c2d5f4183ea54799bedae20950b23b914a727
2019-08-21IVGCVSW-3512 Update NNAPISupport.txt for 19.08Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ie222e046f2fe832ad48d4b2279c8815f860f76d5
2019-08-20IVGCVSW-3656 Make the reference backend optionalMatteo Martincigh
* Added ARMNN_COMPUTE_REF_ENABLED to programmatically build the reference backend * Adjusted the makefiles to allow any backend combination to build * Refactoring where necessary Change-Id: I04cf23245971fcd460b776dd60e01cacb0458dab Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-19IVGCVSW-3618 Fix VTS/Neural Netwok Test FailuresSadik Armagan
* Added IsReshapeSupported check on available backend(s) after adding Reshape layer. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I38a36d5a3db0d67f0e4b4be2ef672dedb75bff22
2019-08-15IVGCVSW-3643 Fix Ref Normalization failuresMike Kelly
* Added check for unsupported optional parameters for L2Normalization and LocalResponseNormalization to skip the related tests rather than fail them. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Ia17be706b14b2e2faf8eb5a0ec335c2e3863bf16
2019-08-14IVGCVSW-3633 Refactor HalPolicy to fully support V1.2 modelsMike Kelly
* Templated and moved V1.0 and V1.1 Convert methods to ensure they can work with later versions of models, operations and operands. * The V1.2 HalPolicy no longer converts V1.2 models, operations and operands to earlier versions. * The V1.2 HalPolicy no longer passes operations to the V1.1 or V1.0 HalPolicies for conversion. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I5de59d43a3abb1f8ac0253dc637ad68318960c76
2019-08-13IVGCVSW-3619 Fix GpuAcc NN Test FailuresSadik Armagan
* Fixed TransposedConv2d failures calculateExplicitPaddingTransposeConv expects int32_t. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I6ea9ea2d1ccfd17debcf93ee518287a083815f01
2019-08-07IVGCVSW-3595 Implement the LoadDynamicBackends function in the Runtime classMatteo Martincigh
* Updated the makefiles to include boost::filesystem !armnn:1702 Change-Id: Ibe0a696d9fd473b552602266a89465289e9dc043 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-07IVGCVSW-3540 Fixed PReLU Being SkippedMike Kelly
* PReLU layers were being skipped due to logic error. Resubmitting due to accidental reversion. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I6aeed11519d19ba7ec8b4993694e414f58799028
2019-08-06IVGCVSW-3614 Limit support of Softmax to 2D with axis 1 in HAL 1.2Narumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I3ef659c8b87f2c0a3d3ed5d14f74f3b05a9f94b9
2019-08-05IVGCVSW-3340 Add support for Quantized_LSTM to HAL1.2 DriverEllen Norris-Thompson
* Added conversion method to HAL1.2 Policy Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com> Change-Id: Ida6734d34931148add2f3464c3283191ea34b712
2019-08-05IVGCVSW-3340 Add Neon and Cl LSTMLayerQuantized to Android.bpNarumol Prangnawarat
Change-Id: I6829921c08898865ce61ea1ae32eebdfe4a5c98c Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
2019-08-02IVGCVSW-3604 Fix TransposeConv2d padding calculationNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Signed-off-by: Aron Virginas-Tar <aron.virginas-tar@arm.com> Change-Id: I5c10ab18343ecf0ebeab24a436e5be2b6c2831c7
2019-08-02IVGCVSW-3577 Update ACL pin to include NEON convolution output multiplier fixAron Virginas-Tar
!armnn:1679 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I09e75e8182d647bd16b25a815812ca2b03ad7614
2019-08-01Fix explanatory comment around SanitizeBiasQuantizationScale()Aron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I92700da149a800f1d8215e964d1e67056628f067
2019-07-31IVGCVSW-3601 Fix skipped VTS Concatenate TestsMike Kelly
* Fixed Skipped VTS Concatenate Tests. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I29e7dcdedefc0e9c54f86fa5de23aa714c469585
2019-07-31IVGCVSW-3586 Fix Skipped Space_To_Batch Hal 1.2 VTS FailuresFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I9d0d0a75d54c25075d8d87c6265e350486157f5c
2019-07-31IVGCVSW-3166 Rename ConvertTransposeConvolution2d() to ConvertTransposeConv2d()Aron Virginas-Tar
* Renamed to be consistent with ConvertConv2d() and ConvertDepthwiseConv2d() Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Iaa872498e32129178bc3971cabf7f43bdb9962af
2019-07-31IVGCVSW-3583 Correct data layout index for ConvertBatchToSpaceNdFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: Ibd683c147b6f2fb966a8f90105c9213880100cf8
2019-07-30IVGCVSW-3583 Fix Skipped Batch_To_Space Hal 1.2 TestsFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I3f2928ba86a9d306a7eb400db3a420e42cf3fa7e
2019-07-30IVGCVSW-3594 Add LSTM Dynamic output tensors checkFerran Balaguer
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Change-Id: I7c0d704b53caeac3a950c6957c4cab11686f6793
2019-07-30IVGCVSW-3166 Add support for TransposeConv2D to 1.2 HalPolicyDavid Monahan
Signed-off-by: David Monahan <david.monahan@arm.com> Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I7b855efaddb18e8f184f4b85196b3b95b69bca6e
2019-07-30IVGCVSW-3592 Add Support for Quantize to HAL 1.2 DriverSadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ie7421078b2bdd16d7ac67b635953b34721e8c8fe
generated by cgit v1.2.1 (git 2.23.0) at 2024-04-28 18:32:31 +0000