aboutsummaryrefslogtreecommitdiff
path: root/reference_model/src/subgraph_traverser.cc
AgeCommit message (Collapse)Author
2024-02-28Update tensor allocator for FP16 caseJerry Ge
- With the update of ConvertU8toF16 to store F16 data in - F16 containers instead of F32, need to update the - function caller to have updated signatures Signed-off-by: Jerry Ge <jerry.ge@arm.com> Change-Id: I8568120c5e67e837eaf6ec70f8db791c4e33d48b
2024-02-21Add support for FP8 to reference modelWon Jeon
Signed-off-by: Won Jeon <won.jeon@arm.com> Change-Id: I99b70f94aff2ccd4af64875697e124eb60bc5b08
2024-01-18[reference model] Add shape operatorsTai Ly
- fixed up reshape conformance tests to use shape input instead of attribute - fixed up tile conformance tests to use shape input instead of attribute - fixed output and output rank of dim op - allow rank 0 and rank 1 tensors for tosa.shape values (for shape = {}) - added initialization of rank 0 const_shape tensors (for shape = {}) - Update conformance tests to use new rescale attributes Signed-off-by: Tai Ly <tai.ly@arm.com> Signed-off-by: Won Jeon <won.jeon@arm.com> Change-Id: I6cce0d2a9ab066fe20a2abf9d2cfde3eb3d8c18b
2023-09-15[reference_model] Support StatefulOps and the tests for CallOnceOpTai Ly
Signed-off-by: Jerry Ge <jerry.ge@arm.com> Change-Id: I03cb878736ccd7e1f5e1f780d7171949a19a9de2
2023-08-18Add DIM operator to reference modelWon Jeon
Signed-off-by: Won Jeon <won.jeon@arm.com> Change-Id: Iea11ee5d3d98773e9c5e9b827593c05afb41ce3b
2023-07-27Enable lazy tensor allocationJerry Ge
- The previous ref_model was allocating the memory for all tensors in the graph upfront which is unnecessary and wasteful. - This patch changes to only allocate initial input tensors on the entry point using the allocateInputTensor() function. - The output tensors are ensured to have been allocated before executing a node. The output tenosrs are the inputs for the next node. - When a node's evaluation is finished, its input tensors will be freed if they will no longer be used by anyone else. Signed-off-by: Jerry Ge <jerry.ge@arm.com> Change-Id: Ibb3e8c9e6344f6cd9eb20532a03b2097b93247f9
2023-07-25Run clang-format and update copyrightJerry Ge
- Also added run clang-format to pre-commit runs Signed-off-by: Jerry Ge <jerry.ge@arm.com> Change-Id: I4e59ac0afbaa30dce0773aa63d92a1a3b119e2f3
2023-07-17Update tensor allocation loggingEric Kunze
Also move a large amount of redundant code to a macro Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: Ib1dcb2ce15e56076e444a4739c4d1292389c4a78
2023-06-02Add support for boolean outputs in model runnerJiacheng Liang
Comparison operators produce boolean outputs, which need to be written into client data Allow subgraph traverser to use main block to look for tensors when serialization handler is missing Signed-off-by: Jiacheng Liang <jiacheng.liang@arm.com> Change-Id: I6f9af470185541fa6466b3f7786c48f1555fa6f6
2023-05-05[reference model] Add precise modeTai Ly
This adds --precise_mode=1 option to tosa_referece_model, which will cause reference model to convert all floating point tensors to FP64 tensors and compute all operators accordingly. Also adds optional -p arguments to test runners tosa_verif_run_tests.py and tosa_verif_framework_compiler_runner.py to run tests in precise mode Signed-off-by: Tai Ly <tai.ly@arm.com> Change-Id: I156055216ad61710096497a8fa1a653be2a602a3
2023-04-06[reference model] support multiple regionsTai Ly
This allows IF/WHILE serialization to use regions instead of blocks to serialize nested regions. For backward compatibility, both region and block serialization are supported for IF/WHILE ops. Signed-off-by: Tai Ly <tai.ly@arm.com> Change-Id: Icf935561f9f5db38767ff76410bcd36896119395
2023-01-13Reference model update for control flow operators supportJerry Ge
Rationale for making this change: - In the original design, for control flow operators like WhileOp, child blocks couldn't read the tensor variables (global consts) in the root level block, this patch added the machanism for child blocks to access their parent level block's tensors. - This change also relies on another serialization change on adding another layer of abtraction called Region: - Serialization patch: [region] Add TosaSerializationRegion to serialization_lib - Updated the corresponding python version of the serialization code: TosaSerializerRegion to python version of serialization_lib - This change also relies on the TOSA MLIR Translator change: Add RegionBuilder to TOSA MLIR Translator - Added the WhileOp related test cases: While, LSTM, GRU, RNN - Other related fixes Signed-off-by: Jerry Ge <jerry.ge@arm.com> Change-Id: I13ae33628ad07e41d248e88652ce1328654694ab
2022-11-09Add BF16 support to reference modelJames Ward
* Upgrade Eigen to 3.4.0 (for bfloat16 support) and add work- arounds for reduce.any() and reduce.all() bugs (introduced between 3.3.7 and 3.4.0) * Truncation to bfloat16 now performed in eval() methods Signed-off-by: James Ward <james.ward@arm.com> Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com> Change-Id: If5f5c988d76d3d30790acf3b97081726b89205fe
2022-10-18Update to check tensor size is validEric Kunze
Validate tensor arguments Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: Iac398f2c3e600944c6f65c3d8433bd17095f820b
2022-10-13Rename FLOAT type to FP32Jeremy Johnson
Update tensor operations naming to state input type as TxT in all cases. Effects CONV2D, CONV3D, DEPTHWISE_CONV2D, FULLY_CONNECTED, TRANSPOSE_CONV2D. Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com> Change-Id: Ic959acfcb3aa0a910b33b774a5a85fac08219205
2022-10-13Minor fixes & add FP16 support to refmodel testing and conformance genJeremy Johnson
Improve base inference conformance generation: * Change to target specific dtypes required for conformance tests. * Reduce dimension sizes of ERROR_IF tests. NOTE: Will impact tensor, clamp and all ERROR_IF tests. Add option to change seed on conformance generation for extra testing. Stop creation of convolution tests with negative output dimensions. Improve reporting on failing to allocate tensor due to above issue. Fix runner to correctly pass ref model debug flags. Update reference_model examples. Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com> Change-Id: I992180dcfe265a7d50edfb151c9f38eeaef5c369
2022-10-11Reference model changes for fp16 supportJames Ward
Change-Id: I72f21fcfa153046274969d327313e3349981dbe6 Signed-off-by: James Ward <james.ward@arm.com>
2022-06-15Remove quantization info from serialization attributesEric Kunze
Any needed information moves into the attributes for each operator. New serialization library version removes teh quantization information attributes from the schema Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: Icf6165687ab1fd34a01f64c01b0b92b2820e72fa
2021-10-18More ERROR_IF supportsKevin Cheng
- Also delay tensor allocation after operator being validated ERROR_IF can be caught first before 0 or negative dimension set the graph_status to UNPREDICTABLE - Rescale, Argmax, FullyConnected, Matmul, Pad, Reshape, Slice, Transpose, Clamp, Concat, Equal, Greater, GreaterEqual, Table Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: I4e1b3e5794fe195ce1a37e28443ae584645a3b91
2021-10-05Couple of reference model fixesKevin Cheng
- comparison ops could have different type of input/output - add SUBGRAPH_ERROR_IF() when operator doesn't have any output tensor Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: I10f2c10f92de1c7a979221a421fa8e86b26fcc72
2021-09-30Fixes to pass NEGATE op test.Kevin Cheng
- Elementwise unary op input/output type should match. - TOSA_UNPREDICTABLE should ONLY be sent when a tensor with negative dimension is read/written Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: I689518933a2b56cd62793e3f28ea66a6e57b057c
2021-09-30Add SUBGRAPH_ERROR_IF() to catch graph-level error.Kevin Cheng
- Also replace SIMPLE_FATAL_ERROR() with FATAL_ERROR() since they're duplicate - Replace FATAL_ERROR()/ASSERT_MSG() with ERROR_IF_SUBGRAPH() if the condition is a graph error FATAL_ERROR()/ASSERT() should only be used by model internal/runtime error like file reading. Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: If1e1e2488054a0ecd800fb0f2ea6487019282500
2021-09-16Implement Conv3D kernel.Kevin Cheng
Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: Ic16e918b1a2423ad563684e29ce70d9efdbf9c02
2021-08-20Replace node level check ASSERT_MSG_NODE()/FATAL_ERROR_NODE() with REQUIRE() ↵Kevin Cheng
or ERROR_IF() - Adding return code enum class: {VALID, UNPREDICTABLE, ERROR} - Runtime errors (e.g. memory allocation failure) will abort immediately, or will return one of the three return codes Part of the codes are re-written to pass REQUIRE() to the top-level (e.g. apply_scale_32/16()) - Update setExpectedFailure() to setExpectedReturnCode() on test generation script - Update test regression script to interface with reference model change Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: Ia063c936bcb2a54d6e379a5bb6801aa72d1186f1
2021-08-12Support int4 weights read. Added conv2d int8xint4 in test generation.Kevin Cheng
Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: I61620f160c7dad6aac5fcc3da0a6e97f3bae5b40
2021-06-24Update to use new serialization_lib API.Kevin Cheng
- Constant tensors are now initialized from embedded u8 array instead from numpy. - Python unit test generator and built-in test hasn't been updated. Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: I5cb86f8e5ec8f23fee5dcbf257874a0f204ede04
2021-06-04Rewrite model frontend to be json-driven.Kevin Cheng
Change-Id: Iac786eff96183938d2fd11cde9313c6e8e1270a5
2021-05-12Update to v0.22.0Kevin Cheng
- remove identityN and placeholder - add div - update serialization_lib hash - update apply_scale_16() assertion - regenerate examples/ due to serialization_lib change Change-Id: I7183d92bec33697c65adfc07cb8eb89c6882675a
2021-04-27Replace serialization/ and verif/ with MLPlatform's serialization_lib submoduleKevin Cheng
- Remove Usage and Format - Run black on verif/*.py scripts Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: Ie81515891eb0039540f614894f4b6b0e0e78ba74
2021-02-22Fix operator initialization bug when rank/dtype fails to initialize with ↵Kevin Cheng
Usage arrays Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: Iefa2959996871d06b766dadbc4cba601e2e739fe
2020-10-14Initial checkin of TOSA reference_model and testsEric Kunze
Change-Id: I2f8e7fa63e2ae40203e57d2cc8814bde3b312cb6 Signed-off-by: Eric Kunze <eric.kunze@arm.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-27 00:25:27 +0000