aboutsummaryrefslogtreecommitdiff
path: root/src/operator-run.c
AgeCommit message (Expand)Author
2022-08-17Specialize binary elementwise operation task for 1D-4D casesMarat Dukhan
2022-08-17Depth to space nhwc uses transpose.Alan Kelly
2022-08-17Depth to space nchw2nhwc uses transposeAlan Kelly
2022-08-15Add fused operators support to convolution operatorsZhi An Ng
2022-04-07Add x32 Nd transpose operator with tests.Alan Kelly
2022-02-20F16 Softmax NC operatorMarat Dukhan
2022-01-05Refactor F32 RADDSTOREEXPMINUSMAX microkernelsMarat Dukhan
2022-01-05Minor refactoring of RADDSTOREEXPMINUSMAX interfaceMarat Dukhan
2021-12-09Refactor VCVT microkernelsMarat Dukhan
2021-12-08Optimize single-threaded execution of vector unary elementwise operatorsMarat Dukhan
2021-12-08Fix bug in Convert NC operator with large number of elementsMarat Dukhan
2021-09-08Auto-generate X8 LUT microkernels and testsMarat Dukhan
2021-08-08Generalize PAD microkernels to all 8-/16-/32-bit data typesMarat Dukhan
2021-08-07Generalize FILL microkernels to all 8-/16-/32-bit data typesMarat Dukhan
2021-06-09Add XNN_FLAG_YIELD_WORKERS flag to avoid busy-wait at op-levelMarat Dukhan
2021-02-26Fix mismatch in block layout in mixed-layout Depth-To-Space operatorMarat Dukhan
2020-12-05Simplify parallelization in elementwise binary and Padding operatorsMarat Dukhan
2020-11-25NHWC version of Depth-To-Space operatorMarat Dukhan
2020-11-20Refactor naming of DEPTHTOSPACE microkernelsMarat Dukhan
2020-11-16Add output_stride argument in SpMM microkernelsMarat Dukhan
2020-11-05Introduce DEPTH_TO_SPACE operator and enable it for graph rewritingArtsiom Ablavatski
2020-10-27Add operator implementation and tests for IBILINEAR CHW microkernelArtsiom Ablavatski
2020-10-20Remove remnants of SpCHW layout in DWCONV-CHW microkernelsMarat Dukhan
2020-10-15Avoid batch-replication of indirection buffer in DW Conv and Avg PoolingMarat Dukhan
2020-08-19Added support for specialized batch_size == 1 convolutions.Fabio Riccardi
2020-07-17Remove min/max parameters from ARGMAXPOOL microkernelsMarat Dukhan
2020-06-19Replace xnn_params.initialized with fine-grained xnn_params.init_flagsMarat Dukhan
2020-06-05Remove Channel Pad NC operatorMarat Dukhan
2020-06-04Remove Add NC operatorMarat Dukhan
2020-05-22Refactor X32 PAD micro-kernelsMarat Dukhan
2020-05-21N-dimensional Pad operatorMarat Dukhan
2020-05-17DWCONV add input_offset and zero parametersFrank Barchard
2020-05-15Refactor CHW micro-kernelsMarat Dukhan
2020-05-11Update CHW DWCONV to pass in input_height and not output_height.Erich Elsen
2020-05-07CHW DWCONV with implicit paddingErich Elsen
2020-04-15Support CMake build with MSVCMarat Dukhan
2020-04-14Avoid two more cases of arithmetics on void*Marat Dukhan
2020-04-13Replace VLAs with direct alloca callsMarat Dukhan
2020-03-26Dynamically choose micro-kernel depending on active coreMarat Dukhan
2020-03-06More descriptive entry point names for operators with groupsMarat Dukhan
2020-02-27Refactor Average Pooling operatorMarat Dukhan
2020-02-27Support input_offset in AVGPOOL and PAVGPOOL micro-kernelsMarat Dukhan
2020-02-24Remove output_min & output_max arguments in PReLU operatorMarat Dukhan
2020-02-13Optimized Indirect Deconvolution algorithm for 1x1 subconvolutionsMarat Dukhan
2020-01-27Rename SoftArgMax operator to SoftMaxMarat Dukhan
2020-01-27SoftArgMax operatorMarat Dukhan
2019-12-03Support up to 6 dimensions in ND operators with broadcastingMarat Dukhan
2019-11-19Refactor MaxPool and ArgMaxPool micro-kernelsMarat Dukhan
2019-11-18Unify operator implementations filenames and testsMarat Dukhan
2019-11-15ND elementwise Multiply operator with broadcasting supportMarat Dukhan
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-15 21:18:13 +0000