armnn.git -

Age	Commit message (Collapse)	Author
2022-01-26	IVGCVSW-6685-6686 Modify workloads to extend Neon/Cl BaseWorkload	Teresa Charlin
	* Neon workloads to extend NeonBaseWorkload instead of BaseWorkload * Cl workload to extend ClBaseWorkload instead of BaseWorkload Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I8f39a31a89a8865ac4acf18573ab290d548d2864
2021-12-15	IVGCVSW-6626 Promote backend headers in backendCommon to armnn/backends	Colm Donelan
	Move the following header files from backendsCommon to armnn/backends. * MemCopyWorkload.hpp * TensorHandle.hpp * Workload.hpp * WorkloadData.hpp * WorkloadFactory.hpp Replace them with forwarding headers and a pragma deprecation message. Resolve the deprecation messages in Arm NN code. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I47f116b30f86e478c9057795bc518c391a8ae514
2021-11-01	IVGCVSW-6440 Add profiling around CL workload configure calls	Kevin May
	Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I7626d5bd82e832d5be6913719a34d76fbd1dbed8
2021-08-10	IVGCVSW-6249 Add ProfilingDetails Macros to all workloads in CL	Keith Davis
	Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I92dd410da7ad633a46d025fdc2b26093041c439b
2021-05-06	IVGCVSW-5815 Generalise ConstCpuTensorHandle	James Conroy
	* Generalises ConstCpuTensorHandle and inherited classes by removing 'Cpu' from aliases. * New renamed classes: ConstTensorHandle, TensorHandle, ScopedTensorHandle, PassthroughTensorHandle, ConstPassthroughTensorHandle. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I1824e0e134202735fb77051f20a7252f161dfe16
2020-12-02	IVGCVSW-5482 'Add a ClCompileContext parameter to each ClWorkload Constructor'	Sadik Armagan
	* Injected CLCompileContext object to each CL workload. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I4837dbd3d5b56cf743b3b89c944e3cdf8b11a42a
2020-11-13	IVGCVSW-5328-5329 Fuse Activation	Mike Kelly
	* Added Fused Activation Optimization to both CL and Neon backends. * Added Fused Activation support to all the CL and Neon workloads that support it. * Changed ProfilingTest network to be a Convolution layer followed by an Abs layer rather than an Activation layer. * Added IBackendInternal::OptimizeSubgraphView function that can accept a ModelOptions. * Network will now call OptimizeSubgraphView passing in the ModelOptions. Signed-off-by: Keith Davis <keith.davis@arm.com> Signed-off-by: Mike Kelly <mike.kelly@arm.com> Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ib536ac3cbafc7d9b35c139ad9a65b7735262cd9d
2020-10-01	COMPMID-3784 Fix 1 CTS MUL INT32 failure due to using SATURATE	Teresa Charlin
	* LargeGraph_TENSOR_INT32_Rank4/26 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I9d07444db56e26c13a77bf022938644ed7953d6b
2018-11-02	IVGCVSW-1946: Remove armnn/src from the include paths	Aron Virginas-Tar
	Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
2018-10-22	IVGCVSW-1955: Unify backend exceptions (wrap cl::Error)	Aron Virginas-Tar
	* Added wrapper function around arm_compute::IFunction::run() that catches cl::Error and wraps it into an armnn::RuntimeException * Added MakeWorkload template inside ClWorkloadFactory that catches cl::Error and wraps it into an armnn::RuntimeException * Replaced cl::Error with armnn::RuntimeException in catch statements inside LoadedNetwork Change-Id: I2340f41ae02b8db1d7ef5157824a50e7410854e3
2018-10-10	IVGCVSW-1207 - Remove typing from ClMultiplicationWorkload	Matthew Bentham
	Don't need this now as it uses the compute library validation function, and all of the code for the supported types is identical. Adds Uint8 support to Cl backend, and unit test cases. Change-Id: I35d4edacc1aca241e95d1b19ae525a23d9513c99