ComputeLibrary.git -

Age	Commit message (Expand)	Author
2023-07-11	Add Bias to MatMul Kernels and add support for use in Fully Connected Layer	Mohammed Suhail Munshi
2023-07-07	Fix unsupported configuration in CLFullyConnected validation	Gunes Bayir
2023-07-06	Fix nightly failures in MatMulLowpNativeKernel when using bounded activation ...	Mohammed Suhail Munshi
2023-06-29	Implement FP32/16 MatMul Lhs T Rhs T/NT kernel using MMUL extension	Gunes Bayir
2023-06-26	Add helpers to set CKW tensor components as OpenCL kernel arguments	Jakub Sujak
2023-06-26	Use MatMul in fully connected layer with dynamic weights when supported	Mohammed Suhail Munshi
2023-06-23	Implement FP32/FP16 MatMul NT/T kernel using the MMUL extension	Ramy Elgammal
2023-06-19	Implement FP32/FP16 MatMul NT/NT kernel using the MMUL extension	SiCong Li
2023-06-16	Add Fused Activation to OpenCL MatMul	Mohammed Suhail Munshi
2023-06-15	Break up Utils.h a bit to reduce unused code being included everywhere	Matthew Bentham
2023-06-15	Break up arm_compute/core/Types.h a bit	Matthew Bentham
2023-06-06	Fix ScaleKernel validate method.	Pablo Marquez Tello
2023-05-05	Connect CLMatMul function to quantized kernels and resolve NE BatchMatMul int...	Jakub Sujak
2023-05-04	Implement OpenCL MatMul heuristic for Arm® Mali™-G710	Gian Marco Iodice
2023-05-02	Fix export_to_cl_image issue in the fp16 GeMM implementation	Gian Marco Iodice
2023-05-02	Add fp16 GeMM heuristic for Arm® Mali™-G710	Gian Marco Iodice
2023-04-27	Add quantized CL MatMul kernel for LHS NT, RHS T	Jakub Sujak
2023-04-26	Change fp16 GeMM heuristic for Arm® Mali™-G77	Gian Marco Iodice
2023-04-26	Improve Winograd performance on OpenCL	Gian Marco Iodice
2023-04-20	Implement CL kernel for a native batched matmul Quantized - LHS transposed, R...	Omar Al Khatib
2023-04-17	Add quantized CL MatMul kernels for Lhs NT/T, Rhs NT	Gunes Bayir
2023-04-14	Align naming convention of ClMatMul	Jakub Sujak
2023-04-04	Support dynamic weights for Fully Connected layers on GPU	Jakub Sujak
2023-04-03	Implement MatMul Function	Ramy Elgammal
2023-03-24	Work around CLScale compiler-specific issue	SiCong Li
2023-03-24	Add Texture Pipe Support for Matmul Lhs T/NT Rhs NT kernels	Gunes Bayir
2023-03-20	Implement OpenCL MatMul for Lhs T Rhs T/NT FP32/16	Gunes Bayir
2023-03-17	Implementation of RSQRT for quantized int8	Ramy Elgammal
2023-03-17	Implement OpenCL MatMul for Lhs NT Rhs T/NT FP32/16	Ramy Elgammal
2023-03-06	Fix LWS search space used by CLTuner	SiCong Li
2023-02-28	Add an option to use lowest for max-pooling	Adnan AlSinan
2023-01-18	Add broadcast batched matmul validation cases	SiCong Li
2023-01-17	Fix ClGemm crashes on unsupported data types	SiCong Li
2023-01-10	Fix CL DirectConvolutionLayer validate tests	SiCong Li
2023-01-10	Extend cl image support to input and output tensors	Gian Marco Iodice
2022-12-29	Optimize CL Scale/Resize Quantized by removing (de)quant. code	Gunes Bayir
2022-12-29	Update the ClConv2d heuristic	Gian Marco Iodice
2022-12-29	Extend Transposed Conv. for tiles with N0>1	Gunes Bayir
2022-12-23	Make CLReshape kernel window based on dst instead of src	Ramy Elgammal
2022-12-14	Optimize Transposed Convolution for CL backend (Quantized)	Gunes Bayir
2022-12-13	Add CLAMP operator to Dynamic Fusion interface	Jakub Sujak
2022-12-12	Fix build error resulting from incorrect header path	Jakub Sujak
2022-12-09	Use heuristics for setting dynamic fusion direct conv2d tile sizes	Ramy Elgammal
2022-12-09	Implement the OpenCL kernel to compute the indirect convolution	Gian Marco Iodice
2022-11-25	Implement address precalculation for indirect conv2d - OpenCL	Gian Marco Iodice
2022-11-22	Remove dynamic fusion prototype with tests and examples	SiCong Li
2022-11-14	Optimize Transposed Convolution for CL backend (FP32/16)	Gunes Bayir
2022-11-01	Rework direct convolution heuristic on OpenCL	Gian Marco Iodice
2022-10-06	Rework DepthwiseConvolution heuristic on OpenCL	Gian Marco Iodice
2022-10-06	Improve start-up time in gemmlowp reshaped rhs only.	Adnan AlSinan