ComputeLibrary.git -

Age	Commit message (Expand)	Author
2024-04-30	Add fp16 and integer data type support for ScatterNd in Gpu	Gunes Bayir
2024-04-25	Add update/index/output (m+1)/2d/(m+n) support for CLScatter	Gunes Bayir
2024-04-22	Scatter GPU Kernel Implementation for 1D tensors.	Mohammed Suhail Munshi
2024-03-20	Make Cpu/Gpu/Ref scalar/vectoral S32 division consistent	Gunes Bayir
2024-01-18	Fix divide-by-zero compilation error	Viet-Hoa Do
2023-12-22	Fix nightly issue caused by gemm_reshaped_only_rhs_mmul kernel	Gunes Bayir
2023-12-14	Fix validation error in CL generate proposals kernel	Gunes Bayir
2023-11-15	Fix device issue with CL softmax	Viet-Hoa Do
2023-10-31	[GPU] Update Reverse layer to allow negative axis and reversed axis order	Adnan AlSinan
2023-10-31	Optimize CL softmax	Viet-Hoa Do
2023-10-12	Remove padding from CL comparison operator	Viet-Hoa Do
2023-10-11	Optimize CL reduction operation	Viet-Hoa Do
2023-10-05	Optimize CLTranspose operator	Jakub Sujak
2023-09-29	Implement Quantized Matmul T/T and T/Nt kernels using MMUL extension	Gunes Bayir
2023-09-28	Implement Quantized Matmul Nt/T kernel using MMUL extension	Gunes Bayir
2023-09-21	Optimize the main loop in mat_mul_native_quantized_mmul_nt_nt	Gunes Bayir
2023-09-18	Implement Quantized MatMul kernel using MMUL extension	Gunes Bayir
2023-09-14	Add skeleton of ClMatMulLowpNativeMMULKernel	Gunes Bayir
2023-09-04	Remove legacy PostOps code	Jakub Sujak
2023-08-14	Optimize CLReduce for Min/Max Axis=0	Gunes Bayir
2023-08-03	Fix CL Tile operator	Viet-Hoa Do
2023-07-21	Enable S64 output in CLArgMinMax	Pablo Marquez Tello
2023-07-11	Add Bias to MatMul Kernels and add support for use in Fully Connected Layer	Mohammed Suhail Munshi
2023-07-06	Fix nightly failures in MatMulLowpNativeKernel when using bounded activation ...	Mohammed Suhail Munshi
2023-07-05	Rewrote CLArgMinMax for axis 0	Pablo Marquez Tello
2023-06-29	Implement FP32/16 MatMul Lhs T Rhs T/NT kernel using MMUL extension	Gunes Bayir
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
2023-05-03	Support multi-dimensional indices in the CL Gather Layer up to four-dimension...	Omar Al Khatib
2023-04-28	Fix the gather layer indices check	Viet-Hoa Do
2023-04-27	Add quantized CL MatMul kernel for LHS NT, RHS T	Jakub Sujak
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
2023-03-29	Add quantized support for unary elementwise in CPU	Viet-Hoa Do
2023-03-24	Add Texture Pipe Support for Matmul Lhs T/NT Rhs T kernels	Ramy Elgammal
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
2022-12-23	Make CLReshape kernel window based on dst instead of src	Ramy Elgammal
2022-11-03	Fix activation block in gemm.cl	Gian Marco Iodice
2022-10-06	Improve start-up time in gemmlowp reshaped rhs only.	Adnan AlSinan
2022-09-09	Add a macro guard in all OpenCL kernels in gemmlowp.cl	Gian Marco Iodice
2022-09-02	F16 Specialization for MeanStdDevNorm	Murray Kornelsen
2022-07-22	Add GemmLowp MMUL Reshaped Only Rhs Support for QASYMM8/QASYMM8_SIGNED	Freddie Liardet
2022-07-13	Add Gemm MMUL Reshaped Only Rhs Support for FP32/FP16	Gunes Bayir
2022-06-27	Implement new Elementwise Dynamic Fusion Operators: Div, Floor	Michalis Spyrou
2022-05-31	Add cl_khr_integer_dot_product extension support	Viet-Hoa Do