aboutsummaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Expand)Author
2022-09-01Harmonize filenames of SAMPLES=1 BFLY4 microkernelsMarat Dukhan
2022-09-01Minor formatting fix in scalar BFLY4 microkernelsMarat Dukhan
2022-09-01Add primary_tile argument to xnn_indirection_init_dwconv2dZhi An Ng
2022-09-01Harmonize naming of specialized BFLY4 microkernelsMarat Dukhan
2022-08-31Optimization in ARM U32 FILTERBANK-ACCUMULATEFrank Barchard
2022-08-31Minor optimization in NEON U32 FILTERBANK-ACCUMULATEMarat Dukhan
2022-08-31filterbank_accumulate output 1 less valueFrank Barchard
2022-08-30Add primary_tile as an argument to DWCONV packing functionsZhi An Ng
2022-08-30Add inline helper functions to check if value is external input and/or outputZhi An Ng
2022-08-30Add RISC-V and WAsm specializations for math_cvt_sat_u32_f64Marat Dukhan
2022-08-30Fix signed integer overflow in convolution packing routinesAlan Kelly
2022-08-29Filterbank Accumulate in ARM assemblyFrank Barchard
2022-08-29Revert back to hex literal, guard with cpp check insteadZhi An Ng
2022-08-29Change hexadecimal float literal to float literal to fix CMake buildZhi An Ng
2022-08-26bfly4m1 NEON microkernelFrank Barchard
2022-08-24FILTERBANK-ACCUMULATE Neon microkernels with unweights accumulator set to 0Frank Barchard
2022-08-24Add x8 & x16 eager API call for transpose.Grant Jensen
2022-08-24Add test for FP16 rewrite when an external output happens to be an input to a...Zhi An Ng
2022-08-24Fix U32 VLOG microkernelsMarat Dukhan
2022-08-23Fix FILTERBANK-ACCUMULATE microkernelsMarat Dukhan
2022-08-23fftr microkernel single data pointerFrank Barchard
2022-08-23apply sort and template generationFrank Barchard
2022-08-23filterbank accumulate neon use for loop instead of do/whileFrank Barchard
2022-08-23Space to Depth operatorAlan Kelly
2022-08-23Aarch32 filterbank-accumulate assemblyFrank Barchard
2022-08-23Space to Depth operatorXNNPACK Team
2022-08-23Group math_doz_u32 with other u32 math functionsMarat Dukhan
2022-08-23Space to Depth operatorAlan Kelly
2022-08-23Variable size transpose ukernels no longer assume that input and output eleme...Alan Kelly
2022-08-22Remove batch argument for FILTERBANK-ACCUMULATE microkernelsMarat Dukhan
2022-08-22filterbank-accumulate use uint8 for weight count tableFrank Barchard
2022-08-22bfly4m1 remove multiplies by 1 and 0.Frank Barchard
2022-08-22Use explicit shift parameter in U64->U32 VSQRTSHIFT microkernelMarat Dukhan
2022-08-22bfly4m1 use a single pointer for dataFrank Barchard
2022-08-22Fix naming of the U64->U32 VSQRTSHIFT microkernelMarat Dukhan
2022-08-22U64->U32 VSQRTSHIFT microkernelMarat Dukhan
2022-08-22Unify WINDOW inferface with other microkernelsMarat Dukhan
2022-08-21Unify VLSHIFT interface with other VUNARY microkernelsMarat Dukhan
2022-08-21Refactor S16 RMAXABS microkernelMarat Dukhan
2022-08-21U64 SQRT evaluation stubsMarat Dukhan
2022-08-21Evaluation stubs for U32 SQRT using F32 SQRTMarat Dukhan
2022-08-20Specialized M1 variant of bfly4 scalarFrank Barchard
2022-08-19Rename xnn_qs8_minmax_params to xnn_qc8_conv_minmax_paramsMarat Dukhan
2022-08-19Enable Relaxed SIMD microkernels for QS8/QU8 VCVT & VLRELUMarat Dukhan
2022-08-18Specialized WINDOW microkernels for shift by constantsFrank Barchard
2022-08-18Refactor declarations of microkernel function pointersMarat Dukhan
2022-08-17u32 filterbank-subtract scalar microkernelFrank Barchard
2022-08-17Specialize binary elementwise operation task for 1D-4D casesMarat Dukhan
2022-08-17Use mulext for filterback-accumulate to multiply 2 uint32 values to produce a...Frank Barchard
2022-08-17Refactor U32 VLOG microkernels to use math_extmul_u32Marat Dukhan
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-13 17:16:53 +0000