aboutsummaryrefslogtreecommitdiff
path: root/ethosu/vela/tosa_graph_optimiser.py
AgeCommit message (Collapse)Author
2023-05-17MLBEDSW-7223: Fusing Pad and AvgPool causes diffTim Hall
- Fixed an issue with the fusing of PAD and AVERAGE_POOL_2D whereby the rounding away from zero didn't work because it requires the zero point to be at zero but the input padding required it to be set to the desired zero point. This affected both int8 and int16. The solution was to remove it by using the bias prior to the scaling - Refactored the rounding away from zero mode Change-Id: I8f2df69df06d2a9722315c346646e5a901cb2c3b Signed-off-by: Tim Hall <tim.hall@arm.com>
2023-05-02MLBEDSW-2082: Add Exp supportJohan Alfven
- Added int8 and int16 Exp support, implemented as LUT. - Added generic 8bit and 16bit LUT table functions following the implementation in the latest reference. If new ops are added by the reference, they can easily be implemented in Vela using the generic functions. - Moved convert_to_lut to lut.py to have all LUT related code in one file. - Updated SUPPORTED_OPS.md Change-Id: I388e76ea4b39162313599a5341cfb9bad71a782c Signed-off-by: Johan Alfven <johan.alfven@arm.com>
2023-01-20MLBEDSW-7151: MLCE: Difference in model output between x86 & aarch64Tim Hall
- The issue is due to undefined behaviour when casting a NumPy float to a NumPy unsigned integer which occurs in create_const_tensor() - The fix is to make sure that the values are first cast to a Python float - In addition, the values datatype argument has been removed from create_const_tensor() to stop the tensor and values datatypes getting out of sync Change-Id: I134b9be8c941b361929a5ae7db8cb35f2e9728f2 Signed-off-by: Tim Hall <tim.hall@arm.com>
2022-11-16MLBEDSW-6620: Update copyright notice and yearsRickard Bolin
- Update copyright notices to use SPDX format and add OSS mail as contact. - Update years on files where it had been missed. Signed-off-by: Rickard Bolin <rickard.bolin@arm.com> Change-Id: I7e9715ea4e17b76252728c708e46df12ad67ab1f
2022-03-30Update version of Black to 22.3.0Jonas Ohlsson
Update version of Black to 22.3.0 due to updated dependencies. Updates to fix reported issues due to new version. Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com> Change-Id: I60056aae452093ce8dcea1f499ecced22b25eef1
2021-10-08TOSA: Added support for Const outputPatrik Gustavsson
Added support for a Const operator generating network output. Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: Ia81990a94cc497a58535914124a29e7dbb511247
2021-10-06TOSA: Added decomposition of PADPatrik Gustavsson
Added support for: -Rank > 4 and batch > 1 -Tensor dimensions exceeding NPU limit -Padding in any dimension (Implementation for functional compliance, not considering performance) Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: Ief58fb3233d885f10ba5e68c5374b190efbe9351
2021-10-01TOSA: Add support for Identity operationPatrik Gustavsson
Added support for Identity operation. Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: If00b30528932f7531807ce3914d6c1875ab72fa4
2021-09-29TOSA: Added decomposition of RESHAPEPatrik Gustavsson
-Added support for unlimited number of dimensions -Added support for tensors exceeding maxlimit of NPU -Fixed regression for PAD Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: Ib2ce50a30cc5cf396032d85d57dab9968e3fc06a
2021-09-28TOSA: Decomposition of CONCATPatrik Gustavsson
-Added support for unlimited number of dimensions -Added support for Tensors with dimension size exceeding maximum limit of NPU. Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I3cc7327ac759e69042a600e686160aeb18a5ec59
2021-09-21TOSA: Decompose elem op tensorsPatrik Gustavsson
Added decomposition of tensors exceeding maximum size supported by NPU. Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I17a99cb72947d2f1064a631ad6975ce895c258d5
2021-09-20TOSA: Elementwise Rank > 4 and Batch > 1Patrik Gustavsson
Added support for elementwise operations: -Support for up to Rank == 6 -Support for Batch > 1 for Rank == 4 -For binary elementwise ops this includes handling of broadcasting in dimensions above H-dimension Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I73850bbfb288077a99bd2ceecbf989172016da24
2021-09-15TOSA: Support for TABLE operator (int8)Patrik Gustavsson
Added support to map TABLE operator to LUT. Limitations: -Only supported for int8 -TABLE input must be constant This also adds the support for TFLite legalisation of Tanh/Sigmoid (int8/uint8). Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I1a95f61fb02fdd42c4a690494418cc0765c8b275
2021-09-15MLBEDSW-5102 Update removal of memory only operatorsJonas Ohlsson
Memory only operators such as Reshape, Squeeze and ExpandDims are removed in the graph optimiser step. - Added semantic check that memory only operators have same quantisation parameters on ifm/ofm. - Added support for the ExpandDims operator. - Addition and cleanup of related unit tests. - Removed TOSA from the generated SUPPORTED_OPS.md documentation. Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com> Change-Id: If848d8afc58c18806e10997ed94e4dae83f30879
2021-09-09TOSA: Support for standalone CLAMP/RELUPatrik Gustavsson
Added support for standalone CLAMP/RELU. Limited to: -Rank <= 4 -N = 1 if Rank = 4 Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: If1a32fb330ce6c67c09ec4b554b4a0688444d5f0
2021-09-09TOSA: Add support for PADPatrik Gustavsson
Added support for TOSA PAD operator in line with legacy support Limitations: -Rank <= 4 -N = 1 if Rank = 4 for ifms/ofm -only padding in W and H dimensions -bool_t not supported Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I511608202b4c9bf6d86285b559c517fb41741fdf
2021-09-08TOSA: Fix AVGPOOL scalingPatrik Gustavsson
-Only support for avgpool when there is no padding. For this case, global scaling can be used. Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I026b83b05f02c57c79f49935f5ec501a6d28bb91
2021-09-07TOSA: Added RESHAPE, SLICE and CONCATPatrik Gustavsson
Added support for Data layout ops RESHAPE, SLICE and CONCAT. -No support for bool_t -Support limited to Rank <= 4 and N = 1 Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I487ac494b6506a2a6ba947ee758aa193194dd796
2021-09-03TOSA: Added Depthwise supportPatrik Gustavsson
This is mainly to add support for depthwise conv2d with dephmultiplier = 1. (But there are no testcases suited, all I have sourced has depth_multiplier set to 2, which is not supported.) -Added support for depthwise conv2d. -Added support for removing Transpose of constant data -Added support for removing reshape Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I143e6246becfa78fd9f7510af0bf0d6b3fbbf2c7
2021-09-03TOSA: Support for AVGPOOL, MAXPOOL and CONV2DPatrik Gustavsson
Added support for -AVGPOOL and CONV2D with TFLite correspondence -MAXPOOL -additional support for replacing RESCALE ops with avgpool. No support for breaking down tensors over the size supported by NPU. Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I1d2aa50ac30a26283b3e6f1fe88cba1544b7c189
2021-07-09MLBEDSW-4840 Move setting of input indices to tflite readerPatrik Gustavsson
Mapping to internal input indexing has been added to tflite_reader.py and tosa_reader.py. And the other way around in tflite_writer.py. Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I4d8596e747cfa7c4203884c4e785eb1977e2bcc1
2021-07-08MLBEDSW-4838 Added basic TOSA support.Patrik Gustavsson
Added basic TOSA support, enabling Vela to read and compile a .tosa file corresponding to CONV2D + Rescale + Clamp, and writing it to an optimized .tflite file. The optimized .tflite file, will in this case, hold a commandstream where the Rescale and Clamp has been fused into the CONV2D. The optimized tflite file is not output from Vela. -Added support to read .tosa file into Vela internal structure. - Added tosa_reader.py, tosa_mapper.py and helper files stored under tosa/ - Support for this limited to ~10 ops -Added reader_util.py for functions common for TOSA and TFLite -Added tosa_graph_optimiser.py -Added support to fuse Rescale into convolution -Modified handling for padding -Added support to fuse Clamp to previous op -Added graph_optimiser_util.py -Moved functions common for TOSA/TFLite graph optimization to this file. -Renamed graph_optimiser.py to tflite_graph_optmiser.py -Added separate tosa_supported_operators.py -Added supported_operator_util.py -For functions in common for TOSA/TFLite Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: Ic3c540504ec8c5eb4771397fdc6882050ecf33ab
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-02 19:52:45 +0000