aboutsummaryrefslogtreecommitdiff
path: root/src/graph/mutators
AgeCommit message (Collapse)Author
2023-09-28Apply clang-format on repositoryFelix Thomasmathibalan
Code is formatted as per a revised clang format configuration file(not part of this delivery). Version 14.0.6 is used. Exclusion List: - files with .cl extension - files that are not strictly C/C++ (e.g. Android.bp, Sconscript ...) And the following directories - compute_kernel_writer/validation/ - tests/ - include/ - src/core/NEON/kernels/convolution/ - src/core/NEON/kernels/arm_gemm/ - src/core/NEON/kernels/arm_conv/ - data/ There will be a follow up for formatting of .cl files and the files under tests/ and compute_kernel_writer/validation/. Signed-off-by: Felix Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com> Change-Id: Ib7eb1fcf4e7537b9feaefcfc15098a804a3fde0a Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10391 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
2023-09-04Remove legacy PostOps codeJakub Sujak
PostOps was the experimental interface for Dynamic Fusion. It is now replaced by the new Dynamic Fusion interface with code generation using the Compute Kernel Writer. Resolves: COMPMID-6190 Change-Id: I813b48facef2fd6f3aee332588886b4f9b3d33d8 Signed-off-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10219 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-07-18Break up core/Utils.h to reduce unused code being included everywhereMatthew Bentham
Makes a small difference to compile times and opens up other opportunities to simplify code. Change-Id: I232876910bbe4fa9719f4a0ce4a54c090faeb5ef Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/532429 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9856 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-06-15Break up Utils.h a bit to reduce unused code being included everywhereMatthew Bentham
Move some maths-related things from Utils.h to new Math.h header in utils/math. Move some routines used for Tensor shape validation to Validate.h Change-Id: I8ce89fe03ec3ae1b61d1a80c282b8b91eea0cfb3 Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/524783 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Viet-Hoa Do <viet-hoa.do@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9743 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-12-09Graph Fusion With Post Ops Fixramelg01
- Fusing ConvolutionBatchNormalization Nodes with post ops (activation or element wise ops) Resolves: COMPMID-4982 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Change-Id: I5b2d32cad00f710fd744cb5aa2d59fd7e5c97e0a Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6766 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sheri Zhang <sheri.zhang@arm.com>
2021-11-25Fix node fusion mutator orderingSiCongLi
Partially resolves COMPMID-4966 Signed-off-by: SiCongLi <sicong.li@arm.com> Change-Id: I533bd29f416c923b71e7b753965a169253b00a52 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6694 Reviewed-by: Ramy Elgammal <ramy.elgammal@arm.com> Reviewed-by: Sheri Zhang <sheri.zhang@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-11-04Refine code for graph level fusionSheri Zhang
Partially resolves: COMPMID-4701 Signed-off-by: Sheri Zhang <sheri.zhang@arm.com> Change-Id: I11fb89bd31ef5a98ad9a2d6bb5fd0c1e8371b52f Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6572 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-11-03Add graph level convolution fusion with post operatorSheri Zhang
Resolves: COMPMID-4701 Signed-off-by: Sheri Zhang <sheri.zhang@arm.com> Change-Id: I8a0d3c2ed4bf84489d94b8ae6641d6041aadaee5 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6557 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-09-15Provide tests for fusing pad layer in graph APIGunes Bayir
There are two tests: - A unit test that checks if certain padding configurations are to be fused or not - A fixture test that compares a reference implementation of pad+conv vs target implementation using the same fusing logic as graph API Tests are written for CL backend only to prevent code duplication. The code written in the graph API remains untested. Resolves: COMPMID-4702 Change-Id: Ie84d1cb910013033b46ac9d66cf5fc556d4963d2 Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6252 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sheri Zhang <sheri.zhang@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-09-07Fuse pad layer with subsequent convolution layerGunes Bayir
Fusing occurs only if - the padding is only for height/width - padding pixel value is 0 - padding node output has no accessors Resolves: COMPMID-4702 Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Change-Id: I0755d5fb0bd3a55d9f10b32ce9da44e7c5a25279 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6189 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Georgios Pinitas <georgios.pinitas@arm.com>
2021-07-13Add in-place calculation support for CL elementwise arithmetic kernelsSheri Zhang
- Add in-place calculation support in ClArithmeticKernel, ClSaturatedArithmeticKernel and ClMulKernel - Add in-place test cases Resolves: COMPMID-4431 Signed-off-by: Sheri Zhang <sheri.zhang@arm.com> Change-Id: Id484bdb76b74478a33fedb471ae0c7f799c599f6 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5885 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-07-02Implement FP GPU depthwise convolution 1x1 kernel for in-place computationSiCongLi
* Implement in-place graph node mutator for 1x1 depthwise convolution * Add in-place to validation fixture except for DepthwiseConvolutionLayerNativeValidationFixture as it would be a duplicate test otherwise (DepthwiseConvolutionLayerNative test tests the underlying kernel) Resolves: COMPMID-4432 Change-Id: Id7f10f5ebdce7d49f550c0b62dbaaab7f5b59d29 Signed-off-by: SiCongLi <sicong.li@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5874 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2021-06-23Add in-place computation for elementwise operationsSheri Zhang
- Add in-place computation for elementwise operations at graph level - Modify support case to test in-place computation for elementwise operations Resolves: COMPMID-4414 Signed-off-by: Sheri Zhang <sheri.zhang@arm.com> Change-Id: I5a4de1235dd29a31160e770a16d62f4b98c84ae6 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5803 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-05-26Fix node fusion mutatorSiCongLi
Node fusion mutator adds new nodes to the node list, invalidating the list iterator during iteration. The fix uses index instead. Resolves COMPMID-4543 Change-Id: Ibb38e2394c616ac6e458568e73f09fb5243e94fe Signed-off-by: SiCongLi <sicong.li@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5717 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-03-03Add QASYMM8_SIGNED support to graph examples via graph mutatorSiCongLi
Related to COMPMID-4279 Signed-off-by: SiCongLi <sicong.li@arm.com> Change-Id: I6c737536b4e614cc9975003acca766803f55bf0b Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5206 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-12-01Update default C++ standard to C++14Georgios Pinitas
(3RDPARTY_UPDATE) Resolves: COMPMID-3849 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I6369f112337310140e2d6c8e79630cd11138dfa0 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4544 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-10-20COMPMID-3637: Move utility headers from arm_compute to srcSang-Hoon Park
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: If9d6fa8c900b68c4b6fd373f2fc1f9abb83ea917 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4145 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-09-22COMPMID-3791: Add support for all activation types in NodeFusionMutatorGian Marco Iodice
Change-Id: I9b548966201c00df8290fea7acf55c2173b0e0aa Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4011 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2020-07-09COMPMID-3324: Adjusting capitalization of Arm copyright claim to reflect Arm ↵Michele Di Giorgio
preferred presentation Change-Id: Ib7dcfcbb24b408999dfae366b9da396485aacf78 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3525 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-06-23COMPMID-3324: Allow in-place mutation on nodes with separate multiple inputsMichele Di Giorgio
The current implementation of the in-place mutator is limited by the assumption that each node only produces one output and therefore all its output edges represent the same tensor. This means that doing in-place computations on it, would modify the input of other nodes. However, this is not the case for operators like split, which creates N different tensors, one for each output edge. This patches relaxes this limitation by checking whether the tensor related to a specific output edge is the same as any of the other edges. If this is the case, then in-place computation cannot be done. Change-Id: I3302b41b1f6ec3b4f2ac425ba381778f1c0a4f31 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3421 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2020-06-22COMPMID-3479: Perform in-place computations in NEElementwiseUnaryKernelManuel Bottini
Change-Id: I2102bfe95c2c2335bb587842f9d860cf939a9026 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3315 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-06-19COMPMID-3480: Enable in-place elementwise operations in graph APIMichele Di Giorgio
Change-Id: Id13d4f9860f25eeb8c4188ac9248653c4f7c1dc2 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3349 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-06-18Revert "COMPMID-3480: Perform in-place computations in ↵Michele Di Giorgio
NEArithmeticAdditionKernel" This reverts commit 4a61653202afb018f4f259d3c144a735d73f0a20. Reason for revert: We will allow in-place computations by providing the same input1 (or input2) as output, thus avoiding changes in the interface. Change-Id: I7c8669e207e15731dc26dc366150bf960508a879 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3035 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-06-16COMPMID-3381: Implement graph example for YoLo v3 output detectorSheri Zhang
Add sub/exp/splitv support in graph api Signed-off-by: Sheri Zhang <sheri.zhang@arm.com> Change-Id: I4e08cc19a46655717068b12c93d67e619a595d9a Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3309 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-06-15COMPMID-3480: Perform in-place computations in NEArithmeticAdditionKernelMichele Di Giorgio
Change-Id: I0089657dd95d7c7b8592984def8e8de1d7e6d085 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3308 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-03COMPMID-3101 Fuse activation with floating point elementwise operation ↵Giorgio Arena
layers in CL Signed-off-by: Giorgio Arena <giorgio.arena@arm.com> Change-Id: I1693f8664ba7c0dc8c076bbe7365cef1e667bd25 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2718 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-03-25COMPMID-3098 Fuse Relu and Bounded Relu with FullyConnected NEONSiCongLi
Change-Id: Id28062445590d6c06b35f7d7434eb38393ae94a7 Signed-off-by: SiCongLi <sicong.li@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2875 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-03-10COMPMID-3069: Improve build time by splitting up ToolchainSupport.hMatthew Bentham
Split out the parts of ToolchainSupport coming from <memory> and the parts coming from <string> into their own new header files. This accounts for 99% of uses of ToolchainSupport, which means that expensive header files such as arm_neon.h don't need to be included everywhere. Knocks about 10% of compilation time off kernel files. Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: I2ae718fe766b5ff28608812b0f686f30eeac1b21 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2852 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2020-03-02COMPMID-3097 Fuse activation with fully connected layer CLGiorgio Arena
Change-Id: I447030e69b9e565f2f81529a41af8c5e7ece7ecf Signed-off-by: Giorgio Arena <giorgio.arena@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2702 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-01-16COMPMID-2856 Add PrintLayer at graph levelGiorgio Arena
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com> Change-Id: I8f02bb67adae8cc7d884f2417cc9c408985f0d5a Reviewed-on: https://review.mlplatform.org/c/2546 Reviewed-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-12-06COMPMID-2779: Add support for generating synthetic int8 graphs.Georgios Pinitas
Adds SyntheticDataTypeMutator, which is responsible for mutating graphs to int8 and thus enable performance analysis on a wider range of models. Change-Id: I9a00f0ae59421ab11952660f5115b5dcd9314aaf Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/2418 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2019-11-12COMPMID-2579: Fuse batch normalization with convolution and depthwise ↵Gian Marco Iodice
convolution at graph level on NEON Change-Id: Ib263a680bbd2dc1a4947102ee8d6da76b95f02bf Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/2252 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-10-01COMPMID-2581: Fuse batch normalization with convolution and depthwise ↵giuros01
convolution at graph level for OpenCL - FP16 Change-Id: I757e27f45b5c25a5f98dacf2a6d519450d366760 Signed-off-by: giuros01 <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/c/2007 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-08-30compmid-2573: Investigate FP16 Winograd reference implementationsgiuros01
Change-Id: I5a3e692c046a5ad28a676c03e3e51950c64cf503 Signed-off-by: giuros01 <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/c/1845 Reviewed-by: Pablo Marquez <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-08-14COMPMID-2582: Disable fuse batch normalization on OpenCL for FP16Gian Marco Iodice
Change-Id: I53bf35ff9f6d8c7e3664983ebcc94552a4ebf90d Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/1732 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez <pablo.tello@arm.com>
2019-08-01COMPMID-2055: Fusion of ConvolutionLayer with BatchNormalization at graph ↵Manuel Bottini
only for CL Change-Id: Ibdd0c56c1f59205dcaf15ca504b6e9c7fb30f34a Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/1618 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-07-16COMPMID-2336: Fix InPlaceMutator condition and add SaveNumpyAccessorIsabella Gottardi
Change-Id: I223a688cfc19465f8581f691b32891cefd375907 Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com> Reviewed-on: https://review.mlplatform.org/c/1555 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
2019-07-11COMPMID-2273: Fuse Batch Normalization with Depthwise Convolution layer at ↵Manuel Bottini
graph level (only for CL) Change-Id: I1d941c6e66722f39583bf68148c980bb28ff89a1 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/1423 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-05-07COMPMID-2177 Fix clang warningsMichalis Spyrou
Change-Id: I4beacfd714ee3ed771fd174cce5d8009a2961380 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/1065 Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-04-15COMPMID-2111: ConcatenateLayer API should accept an index instead of an enumGeorgios Pinitas
Alters the concatenate layer to be layout agnostic and accept an index as thec concatenation axis instead of an typed layout dependent enumeration. Change-Id: I0eaaf919f66a1ba1b09bbfb47c171fc1d4045530 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/994 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-03-29COMPMID-1995: Fixed graph fusion mutator for float types.Georgios Pinitas
-Fixes precondition checks for fusing activation with other nodes. -Fixes is_relu6 check to capture bounded relu as well. Change-Id: Iba193af51491b537c884a35ca85172151534f3ec Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/918 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-03-20COMPMID-1995: Prepare Graph to support different input/output quantization infoIsabella Gottardi
- Added support for different input/output qinfo in ActivationLayer and DepthwiseConv - Added support for different input/output qinfo in ConcatenateLayer introducing ConcatDescriptor - Added reshape validate - Allow OutputLayer to return a specific connection index from the input - Not run Inplace and Depth mutator when input/output quantization info are different Change-Id: I03f5e416fc43ddd284e1501887202a3145f76d8a Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com> Reviewed-on: https://review.mlplatform.org/c/852 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-03-14COMPMID-1995: Revert fusing convolution to batch norm due to performance ↵giuros01
regressions Change-Id: I1476727e8e22f03d7dc7d79956ac02f16c06e814 Signed-off-by: giuros01 <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/c/857 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-03-13COMPMID-1740: Fuse batch normalization with Convolution Layer at graph levelgiuros01
Change-Id: I77ca51c2c72783cc26a099a6a9c3210cdbbe822d Signed-off-by: giuros01 <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/c/797 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-14COMPMID-1451: Perform fusion before GroupConvolution unrollingGeorgios Pinitas
Change-Id: Id94fb9c88a498d7b938f4f707e2e7b9b6df94880
2018-11-02COMPMID-1451: Fuse activation in DepthwiseConvolution.Georgios Pinitas
Change-Id: Id964d9068e18aaa13ab8adcbf7a9375b034ea6c3 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/154651 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-1451:Fuse RELU,LU_BOUNDED_RELU with requantization in ↵Georgios Pinitas
NEGEMMConvolutionLayer. Change-Id: Iea5f2c5bcac8051c4c7655a6eabb2c43772eb31f Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/154104 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-1246: Fix bug in handling backends that can't be loaded in the Graph APIAnthony Barbier
Change-Id: Iefd175af2f472179d86df5358a1527a79c5666ed Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145182 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-1505: Add native grouping support at graph levelGeorgios Pinitas
Change-Id: Iedc91b0aee743b59af5140c8acb8124548da3163 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/144362 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
2018-11-02COMPMID-1367: Enable NHWC in graph examplesGeorgios Pinitas
Change-Id: Iabc54a3a1bdcd46a9a921cda39c7c85fef672b72 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/141449 Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-31 14:58:04 +0000