aboutsummaryrefslogtreecommitdiff
path: root/src/cpu/operators
AgeCommit message (Expand)Author
2024-04-15Add s8f32 kernels and dynamic QuantizationInfoJonathan Deakin
2024-04-12Accumulation in Cpu Gemm kernels is not supported for quantized kernels in aa...Radu Salavat
2024-04-11Add in place summation to CPU GEMM kernelsRadu Salavat
2024-04-04Parallelise im2col along dimensions with higher number of iterationsMilos Puzovic
2024-03-21[ONCPUML-1451] Add matmul kernel to enable bf16 to bf16 operations via PyTorc...Renato Arantes
2024-03-12Optimize CpuSoftmaxKernel for axis != 0 and neon kernelsOmar Al Khatib
2024-03-11Prefer indirect Gemm vs. Direct convolution if supportedGunes Bayir
2024-03-04Fix performance regression in fixed-format kernelsGunes Bayir
2024-02-21Integrate new pretranspose_b_array with extra fused transpose of BGunes Bayir
2024-02-20Requantization cases for offset changes onlyMohammed Suhail Munshi
2024-02-12Fix parallel depthwise perf regression from 2db938cJonathan Deakin
2024-02-07Parallelize CPU depthwise over batch if only 1 rowJonathan Deakin
2023-12-12Winograd changes to enable fp16 in armv8a multi_isa buildsPablo Marquez Tello
2023-12-06Revert "thread_local _custom_scheduler"Pablo Marquez Tello
2023-12-05Optimize CpuSoftmaxKernel for axis=0Gunes Bayir
2023-11-24thread_local _custom_schedulerDavid Svantesson
2023-11-15Fix various coverity issuesSiCong Li
2023-11-10Fix CpuGemmConv2d int8 segfaultSiCong Li
2023-11-08Optimize CpuGemmConv2d start-up timeSiCong Li
2023-10-02Optimize CL and Neon Winograd testsGunes Bayir
2023-09-28Apply clang-format on repositoryFelix Thomasmathibalan
2023-09-20Fix the validation issue in AddMulAdd fused kernelGunes Bayir
2023-09-15Remove deprecated support for BF16 in CpuCastAdnan AlSinan
2023-09-15Fix include dependencies for mass reformatting patchGunes Bayir
2023-09-04Remove legacy PostOps codeJakub Sujak
2023-08-23Update CpuGemmConv2d and CpuFlatten to use CpuReshape operatorAnitha Raj
2023-08-22Optimize CpuReshapeKernelAnitha Raj
2023-08-17Fix various static check issuesViet-Hoa Do
2023-08-07Document the Conv2D heuristicGian Marco Iodice
2023-07-28Retain back-compatibility for arm_compute/core/Types.hSiCong Li
2023-07-19Add support for input S64/U64 in CpuCastKernelPablo Marquez Tello
2023-07-10Do not include headers necessary for logging when logging is disabledMatthew Bentham
2023-07-04Depthwise channel pre-multiplicationMichael Tyler
2023-06-23Address the issues with the ACL coverage pipeline failures related to matmul.Renato Arantes
2023-06-16Add Fused Activation to OpenCL MatMulMohammed Suhail Munshi
2023-06-15Break up Utils.h a bit to reduce unused code being included everywhereMatthew Bentham
2023-06-15Break up arm_compute/core/Types.h a bitMatthew Bentham
2023-05-10Re-enable dyanmic weights in Neon™ depthwise convolutionRamy Elgammal
2023-05-05Connect CLMatMul function to quantized kernels and resolve NE BatchMatMul int...Jakub Sujak
2023-05-05Disable dynamic weights in unsupported operatorsViet-Hoa Do
2023-05-03Fix im2col for fast-maths mode with padding.Renato Arantes
2023-05-03Fix CPU MatMul broadcast detectionViet-Hoa Do
2023-05-02Fix fully connected and matmul mismatchesViet-Hoa Do
2023-04-26Integrate multi-threaded pretranspose_B_arraySiCong Li
2023-04-19Add quantized support for CPU MatMulViet-Hoa Do
2023-04-14Fix dynamic weights for CPU connected layerViet-Hoa Do
2023-04-13Implement MatMul Function and Operator with Floating Point support for CPUMohammed Suhail Munshi
2023-03-21Add dynamic weights for CPU fully connected layerViet-Hoa Do
2023-03-13[ONCPUML-1174] Allow src/weights mismatch for fixed formatJonathan Deakin
2023-03-03NEGEMMLowpMatrixMultiplyCore should be configured for optimized int8 kernel.Ethan Doe
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-16 19:27:27 +0000