ComputeLibrary.git -

Age	Commit message (Expand)	Author
2021-02-01	Make data_layout an attribute of the Scale function	Michele Di Giorgio
2021-01-27	Fix NEON/CL CustomConvolution failures	Manuel Bottini
2021-01-26	Make CLArithmeticAddition kernel and function state-less	Michele Di Giorgio
2021-01-26	Rename functions/classes for elementwise unary operations	Sang-Hoon Park
2021-01-22	Rename functions/classes for elementwise operations	Sang-Hoon Park
2021-01-22	Fixed segfault NEDeconvLayer due to overflow.	Pablo Marquez Tello
2021-01-21	Add window parameter to scheduler	Sang-Hoon Park
2021-01-21	Make Sub kernel and operator stateless	Sheri Zhang
2021-01-20	Integrate improved pooling layer on NEON	Michele Di Giorgio
2021-01-19	Make memset/copy functions state-less	Georgios Pinitas
2021-01-19	Make Add kernel and operator stateless	Sheri Zhang
2021-01-18	Make Concatenate kernels and operator stateless	Georgios Pinitas
2021-01-18	Add explicit cast to fix gcc10 build error	Sang-Hoon Park
2021-01-15	Release winograd transformed weights if not needed on NEON	Georgios Pinitas
2021-01-11	Make CpuActivation stateless	Georgios Pinitas
2021-01-08	Make CpuFloorKernel kernel stateless	Georgios Pinitas
2020-12-14	Enable FFT for FP16	Giorgio Arena
2020-12-11	Remove (CL/NE)UpsampleLayer in favor to (NE/CL)Scale	Georgios Pinitas
2020-12-10	Remove (NE/CL)YoloLayer support	Georgios Pinitas
2020-12-09	Move NEGEMMAssemblyDispatch as an internal function	Georgios Pinitas
2020-12-08	Wrap Flatten layer over reshape	Georgios Pinitas
2020-12-08	Remove (NE/CL)ComputeAllAnchors function	Georgios Pinitas
2020-12-07	Remove support for NEIm2Col, NECol2Im, NEGEMMInterleave4x4, NEGEMMTranspose1xW	Georgios Pinitas
2020-12-03	Fix NEGEMMLowpMatrixMultiplyCore nonfused activation	SiCong Li
2020-12-02	Remove support for (NE/CL)LocallyConnectedLayer	Georgios Pinitas
2020-12-01	Initialize batches variable in NEGEMMAssemblyDispatch	Georgios Pinitas
2020-12-01	Update default C++ standard to C++14	Georgios Pinitas
2020-11-23	Initialize unitialized M parameter in NEGEMMAssemblyDispatch	Georgios Pinitas
2020-11-20	Validate support of fused activation in NEFullyConnectedLayer	Georgios Pinitas
2020-11-17	COMPMID-3962: Add Logical And, Or, Not support on NEON	Georgios Pinitas
2020-11-12	COMPMID-3776: Indirect GEMM	Georgios Pinitas
2020-11-03	COMPMID-3638: Move NEON kernels	Michalis Spyrou
2020-10-20	COMPMID-3876: Fix wrong validation logic in QLSTM	Sang-Hoon Park
2020-10-20	COMPMID-3637: Move utility headers from arm_compute to src	Sang-Hoon Park
2020-10-19	COMPMID-3163: Remove padding from NEDepthwiseConvolutionLayerNativeKernel	Sang-Hoon Park
2020-10-14	COMPMID-3144: Remove padding from NEDirectConvolutionLayerKernel	Manuel Bottini
2020-10-07	MLCE-229: enabled gemmlowp asm kernel for neg shifts	morgolock
2020-10-06	COMPMID-3181: Remove padding from NEReductionOperationKernel	Sheri Zhang
2020-10-02	COMPMID-3145: Remove padding from NEScaleKernel	Manuel Bottini
2020-09-23	COMPMID-3773: Fix the accumulation of projection in QLSTM	Sang-Hoon Park
2020-09-22	COMPMID-3783: Segfaulting in Reduction layer with NEON on Mate20 with HFNet	Sheri Zhang
2020-09-22	COMPMID-3757: (u)int8: Don't select the 16-bit route on A53 for cases with ve...	David Mansell
2020-09-09	MLCE-229: Fixed requantization per channel in asm kernel	morgolock
2020-09-08	COMPMID-3151: Remove NEDepthwiseConvolutionLayer3x3Kernel	Georgios Pinitas
2020-09-03	COMPMID-3750: Disable asm kernels when shifts are negative.	morgolock
2020-08-25	COMPMID-3694 COMPMID-3695 COMPMID-3458: Softmax Axis	SiCong Li
2020-08-19	MLCE-229: Support for negative shifts in asm kernels	morgolock
2020-08-19	COMPMID-3502: Add support of different quantization input/output for ReduceMean	Manuel Bottini
2020-08-18	COMPMID-3687: Remove deprecated functions in 20.05 release	Sang-Hoon Park
2020-08-07	COMPMID-3656: Disabled reduce_axis in LOG_SOFTMAX and SOFTMAX	morgolock