Age | Commit message (Collapse) | Author |
|
Serialization_lib change: https://eu-gerrit-1.euhpc.arm.com/c/mltech/mirrors/tosa/serialization_lib/+/542261
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: I59752a3ba7981c356634b911160cedf30fb2599e
|
|
MacOS does not have the `sys/prctl.h` header. This patch conditionally
excludes `prctl.h` on MacOS and usage of its functionality in the same
way we currently do for windows.
Signed-off-by: Jack Frankland <jack.frankland@arm.com>
Change-Id: Ic56ec358552126b3a10827d9c52db388a8acc214
|
|
Updates the generate_api.py script and associated
templates to allow func_config and debug_config
to be passed when running individual operators
on the API.
This will allow us, for example, to set precise_mode
and abs_mode when running individual operators.
Signed-off-by: Grant Watson <grant.watson@arm.com>
Change-Id: Ia3e7ffc146f876daa307558433177c68285843b7
|
|
remove unnecessary change of tensor shape array for SHAPE data type
Signed-off-by: Tai Ly <tai.ly@arm.com>
Change-Id: I8e6ca98448188a1c30f9d29c22b3194d327b17ac
|
|
Signed-off-by: Won Jeon <won.jeon@arm.com>
Change-Id: Id5820033bb3cc98b5e284237a91b22ffd54a80e3
|
|
Signed-off-by: Won Jeon <won.jeon@arm.com>
Change-Id: Iea11ee5d3d98773e9c5e9b827593c05afb41ce3b
|
|
add support for bias broadcasting for operators:
- conv2d
- conv3d
- depthwise_conv2d
- transpose_conv2d
- fully_connected
could not add framework test for this because tf.nn.bias_add requires
bias size to match channel dimension.
manually tested reference model evaluation on tosa mlir with bias size
of 1
Signed-off-by: Tai Ly <tai.ly@arm.com>
Change-Id: I70d29d231a63fc03b10e3006cbd6b16b53cca1f2
|
|
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I22939e75a08349816a9c103eb7312edcec53855e
|
|
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I8645382983c257e5102982d487283560088e2d2a
|
|
Signed-off-by: Jiacheng Liang <jiacheng.liang@arm.com>
Change-Id: I473adc1525319b5574ee0e36d10a530277d9215d
|
|
- 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
|
|
- Also added run clang-format to pre-commit runs
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: I4e59ac0afbaa30dce0773aa63d92a1a3b119e2f3
|
|
Also move a large amount of redundant code to a macro
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Ib1dcb2ce15e56076e444a4739c4d1292389c4a78
|
|
Signed-off-by: Jiacheng Liang <jiacheng.liang@arm.com>
Change-Id: Ie31041cbcd01f6290be06eabfe5c619123ae989f
|
|
Would cause unresolved symbols to appear when building in
release mode.
There are a couple of minor compiler warning fixes as well.
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I0f7e9a8771442a6e3c848edfe034ef534d0d8ca7
|
|
Signed-off-by: Won Jeon <won.jeon@arm.com>
Change-Id: Ib42b867287b83a183a0d0fb1f1eb29974f58fae4
|
|
Signed-off-by: Grant Watson <grant.watson@arm.com>
Change-Id: I1296f968baca335ea88691bc973e2d01b2aa2c5b
|
|
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I45287af6b33cf07383250dc962a97728e65697a7
|
|
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: I7460ad9eed3ed5c7cec6e855a0303753ed28eb1c
|
|
Adds utility functions that enable compliance verification of TOSA MI
operators; as per section 1.8.2 in the TOSA specification.
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I0cced0ff8875ac8d78b1943211438713d1c51b88
|
|
- Allows axis attributes to be treated differently to other arguments in attribute.def
Signed-off-by: Grant Watson <grant.watson@arm.com>
Change-Id: I1be2595c24bf22e5391a2911a5283391d310df37
|
|
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
|
|
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I175ef0acc6a6633c3e351b935a04db16de1bfbd5
|
|
Update serialization library submodule
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I1d6e2700ac55f429de742931627b07c9a4a46f14
|
|
This adds a second run of reference model under precise_mode
when test_desc.json contains a "compliance" dictionary which
contains a "mode" entry with value "dot product".
In this second run, abs_mode will be set to true, which causes:
1. evaluation will take absolute values of inputs for these operators:
conv2d, conv3d, depthwise_conv2d, fully_connected,
matmul, transpose_conv2d, fft2d, rfft2d
reduce_sum, avg_pool2d
2. output files will have prefix "bounds_" prepended to them
Signed-off-by: Tai Ly <tai.ly@arm.com>
Change-Id: I7070ecc7ead2d2ea3375c44663d653c6772b88e0
|
|
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I0ef7607f4266296a1204c5cccdb5be36f345b5ba
|
|
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: Iad035b31d5e5e83040068e6311501490765bfff7
|
|
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
|
|
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I6deb355998ce88714b41eedc8170acbd7875f519
|
|
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: I5689d7c6b902a319a68fa4628b59e0bcc23aeca4
|
|
Signed-off-by: Tai Ly <tai.ly@arm.com>
Change-Id: Icefa594b25739ebaa331af2352bdcae1aaf81cf5
|
|
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
|
|
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: If3f8c5a1f2dffac36448101959557f86b6ab6c7f
|
|
Also include 0.70.0 draft serialization library
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Ibdd3d52ecd39e710e0decb7afb6d5f5fad497e7d
|
|
Also include the updated serialization library
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I8eb124533dbd00ef0c680fee4892d263c6a1f5ce
|
|
Use rint() instead of round() to get round to nearest even behavior
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I45957be0e863de2207850b023626a7c0ea11e5eb
|
|
Updated to align with corresponding changes to the
spec.
In addition, some ERROR_IF tests have been updated to
match the checks specified by the spec, including:
PAD, SLICE, TILE, TRANSPOSE.
Signed-off-by: Luke Hutton <luke.hutton@arm.com>
Change-Id: Ie2c5f48e79a5610eb82739170e25057a63dac1d8
|
|
Includes:
* FFT2d reference implementation
* Basic TOSA tests
Change-Id: Ie79fcb713542345d550ec013646810c1e890e388
Signed-off-by: Luke Hutton <luke.hutton@arm.com>
|
|
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: If67f503a1848967bc1671646c3011d055b622c52
|
|
* Add exclusion regex's to conformance generation
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: I15bef7451efd5662065060242d35bd7fa3381487
|
|
Includes:
* RFFT2d reference implementation
* TFLite framework tests
* Basic TOSA tests
* Serialization submodule upgrade with support for FFT/RFFT
Signed-off-by: Luke Hutton <luke.hutton@arm.com>
Change-Id: I2a687e9cf87fb62a26160ea52439ba9830bea36e
|
|
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I04261178694c004409aef2ff5c84c32b04729433
|
|
* Existing float attributes now serialized as bytes
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: I415276706b9daf0893e3a59189f387f872ff07c2
|
|
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I6958904c2c8932e9fe03b3092672d62a06e96ee6
|
|
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
|
|
- Added missing explicit template instantiations for abstract
operator base classes
Change-Id: I5eb678837f0edaf9bad0f7358b05abc5e3246af4
Signed-off-by: Jared Smolens <jared.smolens@arm.com>
|
|
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: I3339a78d9611905583272ffad0ef7668e046cfad
|
|
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: I440590fa59433b9ddc1934188f2b34b377129c1f
|
|
- Adds a script to generate operators.h and operators.cc
- Adds jinja2 templates for generating operators.h and operators.cc
- Adds unit tests for a subset of the operators generated
- Includes the TOSA specification as a submodule
- Adds supporting C++ and header files
Signed-off-by: Grant Watson <grant.watson@arm.com>
Change-Id: I5b60db4c56113110d8e75fe1152525d258233f9c
|
|
Also include the updated serialization submodule
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I7a97ae05d16c8a98c38f954ee8014d0f32b282d5
|