aboutsummaryrefslogtreecommitdiff
path: root/src/backends
AgeCommit message (Expand)Author
2020-02-04IVGCVSW-4390 Refactor QUANTIZE to make use of Decoder/Encoder typesKeith Davis
2020-02-03IVGCVSW-4399 Create Sample Dynamic backendNarumol Prangnawarat
2020-02-03IVGCVSW-4334 Wire Signed Quantized 8 bit type into ACLKeith Davis
2020-01-31IVGCVSW-4390 Refactor QUANTIZE to make use of Decoder/Encoder typesKeith Davis
2020-01-31IVGCVSW-4388 Update ACL pin to 6a342648ae50beb8457871862f14fc9baef6b74fTeresa Charlin
2020-01-29IVGCVSW-4149 Enable quantisation multiplier > 1 in all convolutionsRyan OShea
2020-01-29IVGCVSW-4316 First draft of IBackendProfiling and IBackendProfilingContextColm Donelan
2020-01-29IVGCVSW-4152 Remove check for QAsymm8 in ArgMinMax CL layer supportRyan OShea
2020-01-28IVGCVSW-4306 Verify the tflite Yolo v3Keith Davis
2020-01-28IVGCVSW-4369 Add default offset and scale to IsLayerSupportedTestImplTeresa Charlin
2020-01-27IVGCVSW-4380 Add NEON backend support for BatchToSpaceNdMike Kelly
2020-01-24IVGCVSW-4262 Use ACL Permute and Reshape Validate function in Neon and CLKevin May
2020-01-24MLCE-156: Add Division workload in CpuAccPablo Tello
2020-01-24IVGCVSW-4374 Add NEON backend support for SpaceToBatchNdMike Kelly
2020-01-24IVGCVSW-4370 Deprecate DataType::QuantizedSymm8PerAxisDerek Lamberti
2020-01-23IVGCVSW-4259 Add frontend and reference workload for UnaryOperationLayerjosh minor
2020-01-20Remove inclusion of ArmNN.hpp where it is unnecessary.Matthew Bentham
2020-01-20Remove use of ArmNN.hpp where it is unnecessary.Matthew Bentham
2020-01-17Add Signed32 to debug layerNarumol Prangnawarat
2020-01-16Remove Logging.hpp from ArmNN.hppMatthew Bentham
2020-01-13Rename quantized data types to remove ambiguity for signed/unsigned payloadsDerek Lamberti
2020-01-07IVGCVSW-4246 Enable -Wextra by defaultDerek Lamberti
2020-01-03IVGCVSW-4246 Clean build of parsers with -WextraDerek Lamberti
2020-01-02IVGCVSW-4246 Clean build of backends with -WextraDerek Lamberti
2019-12-31IVGCVSW-4246 Clean build Layers with -WextraDerek Lamberti
2019-12-19IVGCVSW-4214 Add README for standalone dynamic backend developer guideNarumol Prangnawarat
2019-12-19IVGCVSW-4295 Disable mixed precision in ClPooling2dWorkloadjaneil01
2019-12-18IVGCVSW-4302 Depthwise CTS. Fix ReorderWeightChannelsForAcl.Teresa Charlin
2019-12-17IVGCVSW-4246 Clean build of LayerTests with -WextraDerek Lamberti
2019-12-14IVGCVSW-4261 Add backward compatibility to the Backend APINarumol Prangnawarat
2019-12-10IVGCVSW-4212 Example of standalone dynamic reference backendNarumol Prangnawarat
2019-12-09IVGCVSW-4157 Pass custom options directly to backendsDerek Lamberti
2019-12-09IVGCVSW-4211 Add Signed 8 bit Quantisation support into the Reference backendFinn Williams
2019-12-09IVGCVSW-4227 Add CpuAcc backend support for DetectionPostProcessDerek Lamberti
2019-12-09IVGCVSW-4210 Create a public API for the common backend filesMatteo Martincigh
2019-12-06Add asserts to check memcpy addressesRob Hughes
2019-12-05Replace boost logging with simple loggerDerek Lamberti
2019-11-29IVGCVSW-4070 Implement "send post-optimized network structure"Narumol Prangnawarat
2019-11-29IVGCVSW-3860 Per-channel QSymm8 support of DepthwiseConvolution2d in ClTeresa Charlin
2019-11-29IVGCVSW-4209 Create a public API for the ArmNN UtilsMatteo Martincigh
2019-11-29IVGCVSW-3864 Add support for per-channel QSymm8 DepthwiseConvolution2d to Neo...Aron Virginas-Tar
2019-11-28MLCE-115 Remove redundant error checking in CL backendMatthew Bentham
2019-11-27IVGCVSW-4148 Extend reporting of quant multiplier > 1 as unsupported on ACL t...Aron Virginas-Tar
2019-11-27IVGCVSW-3859 Per-channel QSymm8 support of Convolution2d in ClKeith Davis
2019-11-27Add IsQuantizeType(DataType) for use in validation functionsAron Virginas-Tar
2019-11-27IVGCVSW-3728 Add CL workload for SliceAron Virginas-Tar
2019-11-26IVGCVSW-3866 Add support for per-channel QSymm8 Convolution2d to Neon backendAron Virginas-Tar
2019-11-23IVGCVSW-4158 FP16 Mobilenet V1 and V2 30% regression on ArmNN on Mate20Sadik Armagan
2019-11-21IVGCVSW-4148 Report quant multiplier > 1 as unsupported for ACLJames Conroy
2019-11-20IVGCVSW-4151 HAL 1_2 Dequantize FP32 Per Channel Tests on CpuAcc FailingSadik Armagan
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-28 20:25:37 +0000