aboutsummaryrefslogtreecommitdiff
path: root/tests/validation/NEON
AgeCommit message (Expand)Author
2023-09-27Implement tflite compliant reverse for CPUAdnan AlSinan
2023-09-15Remove deprecated support for BF16 in CpuCastAdnan AlSinan
2023-09-04Make zip and combine variadicViet-Hoa Do
2023-08-30Disable NEArgMinMaxLayer RunSmall_F32_S64 for armv7aPablo Marquez Tello
2023-08-22Optimize CpuReshapeKernelAnitha Raj
2023-08-08Add support for S64 output in NEArgMinMaxLayerPablo Marquez Tello
2023-08-08Fix failure in MeanReduce layerViet-Hoa Do
2023-08-01Improved testing for ArgMinMaxPablo Marquez Tello
2023-07-19Add support for input S64/U64 in CpuCastKernelPablo Marquez Tello
2023-07-18Break up core/Utils.h to reduce unused code being included everywhereMatthew Bentham
2023-07-07Enable transpose convolution with non-square kernelsViet-Hoa Do
2023-06-12Refactor activation LUT computationPablo Marquez Tello
2023-05-15Raise tolerance number for NEDeconvolutionLayer fp16 testsSiCong Li
2023-05-10Remove inclusion of NEReorderKernel header from NEReorderLayerRamy Elgammal
2023-05-10Fix validation issue with CPU scale on FP16Viet-Hoa Do
2023-05-03Guards to make NEReorder aarch64 onlyDavid Svantesson
2023-04-28Reorder addedDavid Svantesson
2023-04-26Only define validation test tolerance for quantized types in case of aarch64 ...Ramy Elgammal
2023-04-24Disable Neon/MatMul/Quantized for armv7aRamy Elgammal
2023-04-19Add quantized support for CPU MatMulViet-Hoa Do
2023-04-17Fix unhandled case in ElementwiseUnaryRamy Elgammal
2023-04-14Fix dynamic weights for CPU connected layerViet-Hoa Do
2023-04-13Increase tolerance for SME kernelsViet-Hoa Do
2023-04-13Implement MatMul Function and Operator with Floating Point support for CPUMohammed Suhail Munshi
2023-04-11Enable quantized data types for CpuElementwiseUnary on Armv7aRamy Elgammal
2023-03-30Add cropping support to NEBatchToSpaceSiCong Li
2023-03-29Fix GCC13 compiler errorsPablo Marquez Tello
2023-03-29Add additional FP16 guards to Convolution LayerNathan John Sircombe
2023-03-29Add quantized support for unary elementwise in CPUViet-Hoa Do
2023-03-21Add dynamic weights for CPU fully connected layerViet-Hoa Do
2023-03-01Add support for kernel indices in MaxpoolAdnan AlSinan
2023-02-24Fixes for CMake and Bazel builds, tests failing in sconsDavid Svantesson
2023-02-10Fix DeconvolutionLayer tolerance issues in FP16 testsGunes Bayir
2023-02-03Disable AddMulAdd armv7a testsGunes Bayir
2023-02-01Fix GEMMLowp/Batched MatMul mismatches on CPUMohammed Suhail Munshi
2023-02-01Add new operator AddMulAdd for Neon™ backend for Float/Quantized typesGunes Bayir
2023-02-01Remove fixed format strides hackJonathan Deakin
2023-01-17Fix ClGemm crashes on unsupported data typesSiCong Li
2023-01-11Deprecated BF16 support in DepthConvertPablo Marquez Tello
2023-01-10Fix CL DirectConvolutionLayer validate testsSiCong Li
2022-11-15Fix GemmLowp BatchMatMul Tests to use quantized OutputsMohammed Suhail Munshi
2022-11-08SVE Hard-Swish via Lookup table for quantized inputPablo Marquez Tello
2022-11-01Updateable weights in depthwise convolutionMilos Puzovic
2022-10-20Update reinterpret tensor as 1D for CPU addViet-Hoa Do
2022-10-20Add test in GEMMLowp for batch matmulMohammed Suhail Munshi
2022-10-03Fix Batch Matmul nightly failureAdnan AlSinan
2022-10-03Optimize CPU add layer on quantized dataViet-Hoa Do
2022-09-26Add FP32 Neon™ swish activationJonathan Deakin
2022-09-16Optimize Quantized/Integer Bilinear Scale for Neon™Gunes Bayir
2022-09-14Adding GELU activationMurray Kornelsen
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-23 03:34:13 +0000