aboutsummaryrefslogtreecommitdiff
path: root/src/backends/reference/workloads/ConvImpl.cpp
AgeCommit message (Collapse)Author
2022-04-11IVGCVSW-6707 Enables a bare metal compileJim Flynn
Change-Id: Icc2f83c5f27f413758fee3e5c1445e9fc44f42c8 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2021-06-16IVGCVSW-5826 Change weights layout for depthwise to [1,H,W,I*M]Jan Eilers
* This change is necessary because tflite uses a [1,H,W,I*M] format and uses the I*M dimension for per axis quantization. Our previous layout [M,I,H,W] can't handle the correlating quantization scales. * Updates Onnx-, TfLiteParser and TfliteDelegate * Updates the CpuRef, CpuAcc and GpuAcc backends * Adjusts unit tests * Adds test to ensure models with old layout can still be read and executed * Adds conversion function to previous layout [1,H,W,I*M] --> [M,I,H,W] which can be used by backend developers !android-nn-driver:5553 Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ifef23368b8c3702cf315a5838d214f7dc13c0152
2020-10-01IVGCVSW-5325 Fix non-channel per axis quantizationFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: Ie0cf69b2cd76d6ecedab43d3d9ae267d23bbc052
2020-09-28IVGCVSW-5325 Speed up the reference backendFinn Williams
Change-Id: Id8bd0a0418be31d975b944b54bbacb25051ffb2e Signed-off-by: Finn Williams <Finn.Williams@arm.com>
2020-06-03remove BOM from filesLaurent Carlier
Change-Id: Ia4b4bb3be0ed6e933c77d58f8e9879b1370e9537 Signed-off-by: Laurent Carlier <laurent.carlier@arm.com>
2020-04-06IVGCVSW-4485 Remove Boost assertNarumol Prangnawarat
* Change boost assert to armnn assert * Change include file to armnn assert * Fix ARMNN_ASSERT_MSG issue with multiple conditions * Change BOOST_ASSERT to BOOST_TEST where appropriate * Remove unused include statements Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I5d0fa3a37b7c1c921216de68f0073aa34702c9ff
2019-11-06IVGCVSW-3837 Add support for per-axis quantization to reference ↵Aron Virginas-Tar
Convolution2d workload Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I0ac08ba4864d48e6f64c4ac645dad8ea850be112
2019-06-07IVGCVSW-3223 Fix ref convolution performance regressionMatteo Martincigh
* Do not use DataLayoutIndexed::GetIndex for weights and inputs, as it causes a large regression in performance * It turned out that the calculation of the indexes for the weights and inputs was the way it was because of an optimization done many months ago * Reverted the relevant hunks and added some comments so we won't make the same mistake again in the future * Made the GetIndex function inline to speed up other usages Change-Id: I343b2ef0446993086f58b9dea1f0de0ba2d92216 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-06-05IVGCVSW-3223 Use GetIndex from DataLayoutIndexed.cpp in ConvImpl.cppMatteo Martincigh
* Used DataLayoutIndexed::GetIndex wherever possible * Removed unnecessary GetOffset function Change-Id: Ieaad2def60e8de48dbc3afb63e550ac5883b3690 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-05-23IVGCVSW-3025: Refactor reference Convolution2d workloadMike Kelly
* Refactored RefConvolution2dWorkload to support all DataTypes through Encoders and Decoders. * Added Convolute function to ConvImpl that uses Encoders and Decoders to support all DataTypes. * Deleted RefConvolution2dFloat32Workload and RefConvolution2dUint8Workload. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ic5ef0f499d08b948fa65fdee54b5f681fd0b1c05
2018-10-10IVGCVSW-1898 : Ref backend folder structureDavid Beck
* Reference backend is renamed to backends/reference as per https://confluence.arm.com/display/MLENG/Pluggable+backends Change-Id: I27a13c274eb60995dfb459e3c49c0e2f60bcd32c
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-09 17:50:10 +0000