armnn.git -

Age	Commit message (Expand)	Author
2023-11-02	IVGCVSW-7889 Add support for Signed64 data type in Cast layer	Teresa Charlin
2022-11-16	IVGCVSW-7214 Disable BF16-Turbo-Mode and remove conversion layers	Ryan OShea
2021-10-02	IVGCVSW-5985 Remove deprecated code	Jan Eilers
2021-06-16	IVGCVSW-5826 Change weights layout for depthwise to [1,H,W,I*M]	Jan Eilers
2020-11-09	IVGCVSW-5091 Add Logical ops frontend and ref impl	James Conroy
2020-06-30	IVGCVSW-5007 Implement an Int32 reference Elementwise workload	Finn Williams
2020-04-06	IVGCVSW-4485 Remove Boost assert	Narumol Prangnawarat
2020-03-19	IVGCVSW-4565 TENSOR_BOOL8 data type not supported in AndroidNN Driver	Sadik Armagan
2020-03-09	IVGCVSW-4517 Implement BFloat16 Encoder and Decoder	Narumol Prangnawarat
2020-02-07	IVGCVSW-4386 Add ArmNN reference support for QAsymmS8	Ryan OShea
2020-01-24	IVGCVSW-4370 Deprecate DataType::QuantizedSymm8PerAxis	Derek Lamberti
2020-01-13	Rename quantized data types to remove ambiguity for signed/unsigned payloads	Derek Lamberti
2019-12-09	IVGCVSW-4211 Add Signed 8 bit Quantisation support into the Reference backend	Finn Williams
2019-11-29	IVGCVSW-4209 Create a public API for the ArmNN Utils	Matteo Martincigh
2019-11-05	IVGCVSW-3836 Add support for Int32 per-axis scales	Aron Virginas-Tar
2019-11-04	IVGCVSW-3835 Create Encoder and Decoder for QSymm8PerAxis	Keith Davis
2019-09-10	IVGCVSW-3824 Implement Float 16 Encoder and Decoder	Matthew Jackson
2019-08-02	IVGCVSW-3609 Fix decoding and encoding of INT32 tensors	Aron Virginas-Tar
2019-07-02	IVGCVSW-3307 Don't assume TensorInfo::Map() can be called before Execute()	Matthew Bentham
2019-05-27	IVGCVSW-3134 Refactor FullyConnected workloads into single workload	Francis Murtagh
2019-05-23	IVGCVSW-3025: Refactor reference Convolution2d workload	Mike Kelly
2019-04-29	IVGCVSW-2982 Refactor reference Activation workload	Nattapat Chaimanowong
2019-04-10	IVGCVSW-2946 RefElementwiseWorkload configures prior to first execute	Derek Lamberti