ComputeLibrary.git -

Age	Commit message (Expand)	Author
3 days	Scatter GPU Kernel Implementation for 1D tensors.	Mohammed Suhail Munshi
10 days	Add s8f32 kernels and dynamic QuantizationInfo	Jonathan Deakin
2024-03-27	Added new NEON fixed format fast math mode hybrid kernel with maximum height ...	Milos Puzovic
2024-03-21	Add skeleton for CLScatter op, reference and tests	Mohammed Suhail Munshi
2024-03-21	[ONCPUML-1451] Add matmul kernel to enable bf16 to bf16 operations via PyTorc...	Renato Arantes
2024-02-21	Integrate new pretranspose_b_array with extra fused transpose of B	Gunes Bayir
2024-02-09	Remove CKW prototype and Template Writer	Gunes Bayir
2024-01-22	Don't build CKW as part of Android.bp	Jakub Sujak
2024-01-10	Use look up table for fp16 activation	Mohammed Suhail Munshi
2023-12-22	Add Mali™-G720 and Mali™-G620 as GpuTargets	Gunes Bayir
2023-12-07	Optimize CPU depth-to-space	Viet-Hoa Do
2023-11-27	BatchNorm changes to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-11-27	CpuMul changes to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-11-16	NormalizationLayer changes to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-10-31	Optimize CL softmax	Viet-Hoa Do
2023-10-30	DirectConv and Im2Col changes to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-10-17	arm_gemm: Add SME2 FP16 GEMV using FP16->FP32 dot product.	David Mansell
2023-10-17	Revert "arm_gemm: Add SME2 FP16 GEMV."	David Mansell
2023-10-12	arm_gemm: Add SME2 FP16 GEMV.	David Mansell
2023-10-10	Port MatMul to Dynamic Fusion + CKW boilerplate code	Adnan AlSinan
2023-10-10	CpuSubKernel changes to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-10-04	Port DepthwiseConv2d operator to Ckw	ramy.elgammal@arm.com
2023-09-28	Reimplement erf function	Viet-Hoa Do
2023-09-26	Select changes to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-09-26	Maxunpooling changes to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-09-21	L2Norm changes to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-09-18	Add CL command buffer class	Viet-Hoa Do
2023-09-15	Remove deprecated support for BF16 in CpuCast	Adnan AlSinan
2023-09-15	Fuse batch normalization changes to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-09-14	Add skeleton of ClMatMulLowpNativeMMULKernel	Gunes Bayir
2023-09-13	Changes in NECropResize to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-09-06	Changes to ElementwiseOp to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-09-04	Extend Neon ReshapeLayer validation tests	Anitha Raj
2023-09-04	Remove legacy PostOps code	Jakub Sujak
2023-09-01	Pool3d changes to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-08-31	Port ClTemplatePool2d to ckw	Adnan AlSinan
2023-08-30	Port Resize operator to CKW	Gunes Bayir
2023-08-30	Changes in roi_align to enable fp16 in armv8a multi_isa builds	Pablo Marquez Tello
2023-08-29	NEFuseBatchNormalizationKernel rework	Pablo Marquez Tello
2023-08-07	Port DirectConv2d to CKW backend	Jakub Sujak
2023-07-19	Add support for input S64/U64 in CpuCastKernel	Pablo Marquez Tello
2023-07-18	Break up core/Utils.h to reduce unused code being included everywhere	Matthew Bentham
2023-07-14	Port ClTemplateCast into Ckw	Adnan AlSinan
2023-07-14	Port ClTemplateActivation into Ckw	Adnan AlSinan
2023-07-12	Add compute kernel writer arguments export	Viet-Hoa Do
2023-07-06	Move CKW prototype to separate directory	Viet-Hoa Do
2023-07-04	Depthwise channel pre-multiplication	Michael Tyler
2023-07-04	Add Kernel Writer driver code to dynamic fusion	SiCong Li
2023-06-27	Compute kernel writer API and prototype	Viet-Hoa Do
2023-06-26	Add helpers to set CKW tensor components as OpenCL kernel arguments	Jakub Sujak