aboutsummaryrefslogtreecommitdiff
path: root/src/backends/neon
AgeCommit message (Collapse)Author
2023-08-04IVGCVSW-7635 Remove deprecated code due to be removed in 23.08 (WorkloadFactory)Cian McGriskin
* WorkloadFactory.hpp CreateXXXWorkload replaced with CreateWorkload accepting LayerType for ABI stability. * These effect ref neon cl and mock backends * Also removed small deprecation comment in Optimization Views * Fixed ABI Version Issue Signed-off-by: Cian McGriskin <cian.mcgriskin@arm.com> Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: Id37af2f882fc9d12b8c779de6b714013af866028
2023-08-04IVGCVSW-7635 Remove deprecated code due to be removed in 23.08 (ILayerSupport)Francis Murtagh
* ILayerSupport interface - removed unstable virtual functions. * User instead uses IsLayerSupported accepting LayerType enum argument. * Backend developers should implement the ILayerSupport::IsLayerSupported method accepting LayerType as a switch statement with case being LayerType and each case calling their implementation of IsXXXSupported() Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: Iaaead8320bb1b2f1bdab6b5be2e1e69d0eb482d5
2023-08-03IVGCVSW-7635 Remove deprecated code due to be removed in 23.08 (SubgraphView)Francis Murtagh
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I6686ad0a16ef763dbdc771c7ef792ae2890e0ab2
2023-08-02IVGCVSW-7880 Add check for FP16 backend supportRyan OShea
* Check if preferred backends have FP16 support before enable fp16-turbo-mode * Unit tests * Replaced global gpuAccCapabilities with getter method construction * Replaced deprecated function call in SL shim Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: If29b62b330ca8987de8acf6408db11daf25ca0b5
2023-08-01Enable Slice EndToEndTests in all backends and Signed32 in CpuRefRyan OShea
* Enable SliceEndToEnd tests on CpuRef, CpuAcc, GpuAcc * Enable Signed32 support for slice in CpuRefLayerSupport Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: Ie9907c65dcb0eb2f2f346b22541ebfc692a109cb
2023-07-31MLCE-1092 Add Names to WorkloadsMike Kelly
* Added names to Workloads. * Workloads will be given the name of the Layer that created them. * Added new profiling macros to CL Neon and Ref that add the workload name to the event label * Updated workloads to use new macros. * Added missing profiling to Rank Workloads. * Fixed issue where ClConvolution2dWorkload was being reported as Undefined rather than GpuAcc. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I0a55eab6c2f455b73943aca8e99a247c3cb2a906
2023-07-31Update ACL pin to 16b37527906c68885f81a8db35f9d6040d73efecNikhil Raj
* Some header files have been moved from arm_compute/core to arm_compute/function_info in https://review.mlplatform.org/c/ml/ComputeLibrary/+/9979 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I1a52c9072417da65c3f7a847eac5c167eab983f1
2023-07-28Add datalayout to tensors in NeonStridedSliceWorkloadTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I9464970b0aa363f6ac3e0cb42ccb2bb3c8724ca4
2023-07-27IVGCVSW-2292 Tile Operator Neon ImplementationDavid Monahan
* Added Implementation of the Tile Operator Workload to Neon * Added calls to the existing unittests * Added Documentation Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: I0030ffe514215c79f5629d20671254dde9bec452
2023-07-24IVGCVSW-7907 Model cannot use SubtensorsMike Kelly
* On Neon we cannot remove a Reshape if it's connected to a SplitterLayer. * Removed clause 5 in SplitterLayer which could erroneously prevent the use of Subtensors in certain circumstances. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I437eb5d3ede25329a4d11d12c3fb1aec2e76efb6 Signed-off-by: Mike Kelly <mike.kelly@arm.com>
2023-07-21IVGCVSW-7830 Clean upMike Kelly
* Follow up review to clean up whitespace and copyright errors mentioned in https://review.mlplatform.org/c/ml/armnn/+/9885 * Added BinaryElementwiseOperation to .dot files * Refactored ConnectedToSplitterWithMoreThan4Dims function to more generally useful ConnectedToLayerType function Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I0e3d0895888f3a3f0a9758ce30bc031aba50812b
2023-07-20IVGCVSW-7850 block non const bias on NEON Depthwise conv.Colm Donelan
* There's currently a problem with using a non const bias value in NeonDepthwiseConvolution. We will block it for the moment. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: Ifd206cfd25a2305a80f8b0a88e07747e79468d18
2023-07-20IVGCVSW-7849 and IVGCVSW-7825 block non const bias on NEON CONV2D.Colm Donelan
* There's currently a problem with using a non const bias value in NeonConvolution2d. We will block it for the moment. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: Ia020cf48f7d5e0642f7763e82501f06ad89945d8
2023-07-17IVGCVSW-7891 Failure in Nightly testsMike Kelly
* Added check to ensure that Reshapes are not removed on Neon if they are before or after a SplitterLayer and have more than 4 dimensions. * Moved NCHW check to a function to reduce clutter. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I45d97634484e8dc0ca7675c23481caf84eb3fe90
2023-07-14IVGCVSW-7830 Add backend optimizations to remove Reshapes where possibleMike Kelly
* Added optimization to remove reshapes for Neon and Ref Backends by using overridden TensorInfos * Added ability to delete Subgraphs during Optimization * Fixed naming error in NeonEndToEndTests and CLEndToEndTests * Added LayerNameAndTypeCheck for testing. * Fixed error where layers were not marked as altered when removed in CLBackend Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I1ac25cd4ec9821470d961831ae2c8d24882276cc
2023-07-10IVGCVSW-7785 3D tensors in BATCH_TO_SPACE and SPACE_TO_BATCH in CpuAcc & GpuAccTeresa Charlin
* Add Reshape layers before and after to extend support for 3D tensors, as ACL only supports 4D tensors for those layers * Add Unit Tests Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I4431185ce3a3b2f595d2a79bdda7095212d1c52d
2023-06-26Update ACL pin to c952596e70f2fe0073029f053e329a4e930ced8cNikhil Raj
* activationInfo passed in directly to configure() rather than part of matMulInfo Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I546def1c1e1cabaf50629f7d78ae0ba459766ed4
2023-06-19Update ACL pin to 043613fbb199e2c4fdd12c2c9a1785db9b0c45faNikhil Raj
* Break up Utils.h a bit to reduce unused code being included everywhere * Add FullyConnectedLayerInfo.h to ArmComputeUtils.hpp and remove Types.h * Add MatMulInfo.h to Neon and CL BatchMatMulWokloads Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I2fbe90cb40dc59add90735dafe9fef9aab3fbf06
2023-06-14IVGCVSW-7791 Enable dynamic bias in Conv in CpuAcc and GpuAccKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I722a9e4f3dba2500c624c6326f74085277e0d631
2023-06-07IVGCVSW-7789 Enable dynamic bias in Depthwise Convolution in CpuAccTeresa Charlin
* Dynamic bias are supported by CpuAcc for this layer * Indentation and const modifiers minor changes Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I3b25f14feea55f746c254a832d97e21a1551ca36
2023-06-07Fix incorrect validation of Unidirectional Sequence LSTM on Cl and NeonNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I54c60fb98b9c560c300572f46d42b13aec7e402e
2023-05-23MLCE-1022 Fix failure on UnidirectionalSequenceLstm OperatorNarumol Prangnawarat
* Fix failure to parse UnidirectionalSequenceLstm Operator on CpuAcc * Fix failure to parse UnidirectionalSequenceLstm Operator on GpuAcc * Fix IsLayerSupported tests when there are multiple otutputs Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ia690f34d3c7fae87bd36c97056a3ff71baa865f6
2023-05-23IVGCVSW-7732 Enable dynamic bias in FullyConnected in CpuAcc and GpuAccTeresa Charlin
* Dynamic bias are supported by ACL for this layer. Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I428bd42a97e0c26c72f9925e3cb209c2fc9a650d
2023-05-18IVGCVSW-7400 POW IVGCVSW-7278 SQUARED_DIFFERENCE to CpuAcc and GpuAccJohn Mcloughlin
* Add POW SQUARED_DIFFERENCE and Unit tests for CpuAcc and GpuAcc Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com> Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ifa78af2a2fda2074586d8e4d9a506b1b13fa5755
2023-05-11Revert "IVGCVSW-7454 Enable dynamic bias in CpuAcc and GpuAcc in Conv2d ↵TeresaARM
DWConv and FC" This reverts commit fecd9ed396705a17805ffc49839bd82ae24c892b. Reason for revert: IVGCVSW-7727 Dynamic bias CTS failing Change-Id: I53f67d60fca0e60a81298f90450ceef26b97c321 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
2023-05-09IVGCVSW-7454 Enable dynamic bias in CpuAcc and GpuAcc in Conv2d DWConv and FCTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ib6914a9a208475b68e969eba6f70fae4061efa9b
2023-05-08IVGCVSW-7454 Fix CpuAcc FC dynamic weightsTeresa Charlin
* Pass to ACL the flag for constant weights and bias in FC, conv and DWconv workloads Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Iae2810c8d1a402d4afc1e757846665315a80d3ea
2023-05-08IVGCVSW-7307 Add CpuAcc Batch MatMul WorkloadTeresa Charlin
* Call dedicated MatMul kernel in ACL * Add int8 tests * Add int8 to documentation * Force tensors to be dynamic (nonConst) as per request of ACL Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I992ae9aae1174214607bf29305f21cdeaf3fdc1b
2023-04-28Make Convert workloads use arm_compute::NECast in CpuAcc backendMatthew Bentham
NECast can use conversion instructions where they are available so this should in general be faster. Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Change-Id: I3f259e17b280a4f4c36f363965ffbc8ee8c4c29f
2023-04-27Add unit test for Neon Convert workloadsMatthew Bentham
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Change-Id: I501a3e01932d44eca796e93a9383378dafc758c5
2023-04-18GitHub #719 Set quantization parameter scale to 1.0, instead of 0.0.Teresa Charlin
* Arm NN does not account for int8 or uint8 not quantized types, Tensorflow does. Not quantized int8 and uint8 is the same as quantized int8 and uint8 with scale = 1.0 and offset= 0 Default offset/zero_point was already 0, this review sets the default scale to 1.0. Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ibc3eecc281de516c2cc706e17bde01c64ff9556e
2023-04-12IVGCVSW-7197 Implement Pimpl Idiom for OptimizerOptionsJohn Mcloughlin
Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com> Change-Id: Id4bdc31e3e6f18ccaef232c29a2d2825c915b21c
2023-04-11IVGCVSW-7507 Pass m_Crops in BatchToSpaceND CpuAcc and GpuAcc workloadsTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I902c9187eefe7595271312fdc16273f7aa3d41cd
2023-04-04Remove GetGraph and include of Graph.hpp header from public headerMatthew Bentham
Remove deprecated GetGraph() from OptimizationViews. This method has been deprecated for a long time and no backends still need it. Remove include of Graph.hpp from the public headers. Add includes elsewhere to deal with the header fallout. Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: I8dae275a8a446d9d0e19be62684e9b3cd2fa493d
2023-03-31Revert "IVGCVSW-3808 Deprecation notices for old ElementwiseBinary layers"Mike Kelly
This reverts commit 52e90bf59ecbe90d33368d8fc1fd120f07658aaf. Change-Id: I5a0d244593d8e760ee7ba0c9d38c02377e1bdc24 Signed-off-by: Mike Kelly <mike.kelly@arm.com>
2023-03-30IVGCVSW-7454 Enable NonConstWeights in CpuAccTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I74a93b1e2e5c9f12ce4523df3f21e5c0967fddfb
2023-03-30IVGCVSW-3808 Deprecation notices for old ElementwiseBinary layersMike Kelly
* Added Deprecation notices for old ElementwiseBinary layers. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Iebbbaff38cc9c347b25eb2f9054c914a4f931c68
2023-03-14IVGCVSW-3808 Add ElementwiseBinaryLayerMike Kelly
!android-nn-driver:9329 * Added ElementwiseBinaryLayer that can represent all ElementwiseBinary operations including Add, Div, Sub, Maximum, Mul and Minimum. * Updated Delegate to use ElementwiseBinaryLayer instead of the Add, Div, Sub, Maximum, Mul and Minimum layers. * Updated Deserializer to use ElementwiseBinaryLayer instead of the Add, Div, Sub, Maximum, Mul and Minimum layers. * Updated OnnxParser to use ElementwiseBinaryLayer instead of the Add layer. * Updated TfLiteParser to use ElementwiseBinaryLayer instead of the Add, Div, Sub, Maximum, Mul and Minimum layers. * Updated CL and Neon tests to use ElementwiseBinaryLayer. * Updated CL and Neon Backend Specific Optimizations to accept ElementBinaryLayers as well as Add, Div, Mul, Sub, Maximum and Minimum layers. Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I7cbb96b60eb01f0e2b57b0541016d48a08b86c75
2023-01-13IVGCVSW-7173 Add Rsqrt to Tosa Ref BackendDavid Monahan
* Added ElementwiseUnary support with a mapping for Rsqrt * Added unittests * Added Rsqrt EndtoEnd tests for all backends * Changed TosaRefLayerSupport to default to false on unsupported layers Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: I3eaa9c684647ead61520a563815581aa68bee51b
2023-01-12IVGCVSW-5128 Add EndToEnd test for REDUCE_SUMTeresa Charlin
* Call Reshape EndToEnd test from 3 backends * Tidy up some naming of tests. Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I5546af35e89d352d3f1529368518aecc0a4a534b
2023-01-04IVGCVSW-7211 Fix float16 operators being wrongly unsupported with ↵Cathal Corbett
android-nn-driver. * Not a concern with the delegate/parser as tflite builtin operators have little float16 support * Will also fix float16 workloads running on the support_library. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Iec2033dbc8ece2140b188de1f193c344a68b9c36
2022-12-12IVGCVSW-7209 Remove deprecated code due to be removed in 23.02Mike Kelly
* Removed weights and bias from Convolution, DepthwiseConv & FullyConnected layers * Removed the weight and bias ConstTensorHandles from the QueueDescriptors * Updated Workloads to take tensors from WorkloadInfo rather than the QueueDescriptors * Removed unused RedirectMembersToConstantInputs optimization and tests. Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I9ffcdc4a1c0dff725539dd69fc435b700bd98a56
2022-12-07IVGCVSW-6853 Rewrite BuildArmComputePermutationVector()Teresa Charlin
* Some pemutation vectors were not converted correctly. * Add Transpose end to end test. * Comments added with an example to clarify the differences betweeen Transpose and Permute Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I6c0954ca6ce00ef5f2a6f3625abe6f4fd27b5cdf
2022-11-16IVGCVSW-7214 Disable BF16-Turbo-Mode and remove conversion layersRyan OShea
- Remove Bf16ToFp32 Conversion Layer - Remove Fp32ToBf16 Conversion Layer - Remove B16 Conversion tests * Throw exception if m_ReduceFp32ToBf16 optimzer option is set to true * Provide comments to enable fast math in order to use bf16 * Update docs to inform users to enable fast math for bf16 Execute Network Changes * Require bf16_turbo_mode to also have fast_math_enabled set to true - Remove setting m_ReduceFp32ToBf16 optimizer option Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: Ibaa6da9d29c96a1ce32ff5196b0847fde9f04a1c
2022-11-09IVGCVSW-7318 Support basic addition model in the TOSA Reference BackendRyan OShea
* Create Simple Addition EndtoEnd test * Create EndToEndTest file in TosaRef/test directory * Add AdditionEndToEnd test to CpuRef,CpuAcc,GpuAcc,TosaRef Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: Ic44e2b457c25dcb41bb3b17c05cce0e74bf17a80
2022-11-01IVGCVSW-6496 Add EndToEnd Layer test for Batch MatMul WorkloadTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I6a541db9a602609282cc6f33af930ca141b83c41
2022-10-28IVGCVSW-6494 Add CpuAcc Batch MatMul Workload Fp32Teresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I2def6995f81d33e68f1ea45d8d19a1e6294049b1
2022-10-11IVGCVSW-7222 Fix incorrect kernel measurements in profiling outputKevin May
* Some CL kernels are not run after the first inference and this breaks the profiler which is expecting a measurement for every kernel each run * Add a function HasKernelMeasurements() to ascertain if the Event is returning kernel measurements and if so insert 0.0 values for any missing kernel measurements. * Fix ExecuteNetwork to only print a json object after all inferences have completed Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I99f2bb0db847f5a52ab4c5705b072155c6b6f333
2022-08-05IVGCVSW-7111 change backend deprecation from 22.11 to 23.08Jim Flynn
Signed-off-by: Jim Flynn <jim.flynn@arm.com> Change-Id: I3a3aab7b5042349cb2df8517678306665e037610
2022-08-05IVGCVSW-6889 Seg fault running ExeNet with --bf16-turbo-mode on fpgaFrancis Murtagh
* Added case for Bf16 to switch and changed Assertion to Exception so it shows up in Release build. Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I817260dc7b7667386c4aa734bea649383866a785
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-27 20:35:19 +0000