Age | Commit message (Collapse) | Author |
|
Signed-off-by: Won Jeon <won.jeon@arm.com>
Change-Id: I1498313f56626011d39f765fed71f82be53b3d8d
|
|
Signed-off-by: Won Jeon <won.jeon@arm.com>
Change-Id: I74f9ac096e5030a86bd7c1ffff542d9061b09ab4
|
|
Change FP_SPECIAL testing to be used for DOT_PRODUCT cases only.
Use default EXACT matching - where zeroes of different signs will
be ignored when testing for equality
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I0461c42258611cae597f693507075b3ef15fbe19
|
|
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I8c4439189756a4d20cf5395fbbbe4aa6af7873ce
|
|
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I6b6a303a475525840a281c7e4e6ecc326c6a1aac
|
|
Signed-off-by: Won Jeon <won.jeon@arm.com>
Change-Id: I75840f6b4ff11a63c4c874f8ded23afb5a71ad55
|
|
Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
Change-Id: Ib2b95e73b226d64c4db5ad1ed22c123e04d7e6f9
|
|
Cope with large error bounds with small reference values.
Change how error bounds of NaN are avoided for ABS_ERRORs.
Update SIN/COS compliance to latest spec and use input value as
magnitude.
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I55aca59e0255e1cfd255b08edb845c3e33ca7eff
|
|
When width or height are one then H/2 or W/2
are not integral.
Signed-off-by: Dmitriy Smirnov <dmitriy.smirnov@arm.com>
Change-Id: I1a849bec7cbb1d55fd5f085ebe58be45ea0b508e
|
|
This warning is raised in the integer comparison of `applyClip`.
Signed-off-by: TatWai Chong <tatwai.chong@arm.com>
Change-Id: If427cb08b8456480898375d8b77302ca7162f737
|
|
Signed-off-by: evacha01 <evan.chandler@arm.com>
Change-Id: I5a9a1c63345bd83ca04bc6c2a99b0ef3612971ee
|
|
This changes to use native type serialization and deserialization
for pad_const, clamp min_val/max_val and const data attribute values
whereby fp16 values are stored as 2 bytes each, fp8 values are stored
in 1 byte each, etc.
Signed-off-by: Tai Ly <tai.ly@arm.com>
Change-Id: Ia95d320fe8c546ce1d1ccc035d6e9bcaadcc9ca3
|
|
Remove assert statements on bad tensor types and returns
nullptr so caller can properly generate return errors.
Signed-off-by: Tai Ly <tai.ly@arm.com>
Change-Id: I8687ba0c7bc1000e3e7f8a0651a949c3c61c5128
|
|
Signed integer type is used to retain QMax and QMin no matter what
the value of `output_unsigned` is, but the value of QMax and QMin
are unsigned integer when output_unsigned is true.
Also add a handful of arithmetic helpers to align the pseudo code.
Change-Id: Ie3cd444a290ddae08884186cd4b349a88acad032
Signed-off-by: TatWai Chong <tatwai.chong@arm.com>
|
|
Also simplify the check to align the pesudo code structure.
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Signed-off-by: TatWai Chong <tatwai.chong@arm.com>
Change-Id: I6023046026d2784dedd963b2b4d34a1117d45c23
|
|
Signed-off-by: evacha01 <evan.chandler@arm.com>
Change-Id: I8c59ecb5a1fb53d0e9bf64333709f9e3cc908b49
|
|
* Enable showing actual runtime shapeType tensor value when the
--dump_intermediates=1 flag is on
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: Ibd5aa8aa27505364fbbf9d1addd0bdef0deda885
|
|
Set QMin and QMax based on the value of attribute `output_unsigned`.
Change-Id: I7f21f3edd7311295285fb3988b3c800de114777a
Signed-off-by: TatWai Chong <tatwai.chong@arm.com>
|
|
Make sure the magnitude bias check is not positively biased
Update unit tests
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I00a9470b5e3233ad65360400ed312b0a354130f1
|
|
This patch implements changes required by the new acc_type field in
ConvAttribute and TransposeConvAttribute
Signed-off-by: Tai Ly <tai.ly@arm.com>
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: Ib13dbeec4d8920e0ddbcca02b727e7277f2c8d62
|
|
This implements changes due to ClampAttribute and PadAttribute
field changes.
Signed-off-by: Tai Ly <tai.ly@arm.com>
Change-Id: Ide01e2a27fe3c1ea7794e7a4b6780b7eae436caf
|
|
Signed-off-by: Won Jeon <won.jeon@arm.com>
Change-Id: I7efc03f16136b2b74f8dfef79a6e7e147c93f4ed
|
|
Added support to ref model and testing
Signed-off-by: evacha01 <evan.chandler@arm.com>
Change-Id: Iece53d07c8986332fdd8f1ce5ed6265349df1b6a
|
|
Signed-off-by: evacha01 <evan.chandler@arm.com>
Change-Id: I81bb322132daf25328a40342edc62d8e1db9edd6
|
|
This patch implements changes required for RescaleOp's
multiplier and shift changing from attributes to inputs
Signed-off-by: Tai Ly <tai.ly@arm.com>
Change-Id: I178919727e3220c749dad0ebce141e695868fee0
|
|
- Users have to specify the --test_desc filename argument for using
reference_model
- Update the initTestDesc function to allow users to use pure
command line arguments to specify all test descriptions
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: Ia23d4ba550aace6c3cd202e21bc8fbe6e0be1cf0
|
|
- Add Tosa Sin/Cos operators to reference_model
- Add conformances tests
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: I3f597ddf5dac2c64d6dd6aa15781b40b8468eaa6
|
|
Improve internal config naming and remove old config info.
Make sure all configs are properly initialized.
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I674e23eddc9694237ea4e66a689481c13965eb90
|
|
Always create the shift as a tensor for all types in testing.
In the reference model, set the shift operand to be available for
all types, but only read in the shift tensor for i32.
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Signed-off-by: TatWai Chong <tatwai.chong@arm.com>
Change-Id: Ia267cbf8b63ca0a9c97b38e8fb4db83eeb8c0538
|
|
Signed-off-by: Won Jeon <won.jeon@arm.com>
Change-Id: I55f663c19a1d2579d24b25c7f0d476e56e7e6dd2
|
|
- 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
|
|
This patch adjusts reference model for attribute name changes in
tosa.fb schema, and for obsoleted slice/tile/reshape attributes
also updated examples due to the breaking tosa flatbuffers changes
Signed-off-by: Tai Ly <tai.ly@arm.com>
Change-Id: I105eb99a4c35f289c5078aed0a7f9cbb6dfe9123
|
|
Add general validateData function used by ABS_ERROR, ULP,
RELATIVE and REDUCE_PRODUCT to find and output largest deviance
from the error bounds.
Clean up naming inconsistencies bewteen verify modes.
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: Ib903faf36f784cacae91edab61d8e489461a727c
|
|
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I1fb734285c60f71a74a5815e76ace51ace719400
|
|
This patch implements changes needed for resize op's
scale/offset/border changing from attributes to inputs
Signed-off-by: Tai Ly <tai.ly@arm.com>
Change-Id: I20db0687fad40711f3ded644af51096292dd05b3
|
|
also check if tensors of start and size are allocated.
Change-Id: I6a72d11ebcb8d0725fe267058dfd792102459427
Signed-off-by: TatWai Chong <tatwai.chong@arm.com>
|
|
* Int16/UInt16 reference outputs were previously saved to INT32
* Save those in their native dtypes and updated other affected code
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: I0c3b7fba096a8cb1ddabef20ad13498b8f46d36f
|
|
Right shift result on i32_t data type only, i.e. other data types
don't carry the shift operand.
In the spec, the shift type is a tensor in MT profile and is an
attribute in BI/MI profiles. Currently we treat the shift as tensor
throughout.
In implementation, since `ternaryExpr` is not implemented in Eigen,
decompose the original calculation into multiply and shift operation
seperately, and execute them via `binaryExpr`.
Change-Id: I349f4969545134ac5f13bc83032cd75cca3e7ba0
Signed-off-by: TatWai Chong <tatwai.chong@arm.com>
|
|
Signed-off-by: Won Jeon <won.jeon@arm.com>
Change-Id: I99b70f94aff2ccd4af64875697e124eb60bc5b08
|
|
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I365da379f599e5eca1841e6d299b4005a7b0f082
|
|
Add RELATIVE verify mode for RESIZE.
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I4fe352579507211dae7a048bf080c24426ce42a2
|
|
Correct ref model to produce imaginery values of zero as specification
indicates at certain output positions.
Fix up precise and abs modes for RFFT2D in ref model to produce correct
results and bounds using abs weights.
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I33767e4219a260278f7933f28b1799223a95a3cc
|
|
Signed-off-by: evacha01 <evan.chandler@arm.com>
Change-Id: Ie05f88db15cd07fd5483ab669329d7048bd3349c
|
|
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I8f7678706e517d7f8d9742dcddd0ea5875b30a00
|
|
Improve access to DOT_PRODUCT generator index and location for debugging.
Enable multiple result files for compliance and improve output.
Fix up precise and abs modes for FFT2D in ref model to produce correct results
and bounds using abs weights.
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: Ide0c9f9f80397e5f1e07ca30a1036d6014b5784d
|
|
Signed-off-by: evacha01 <evan.chandler@arm.com>
Change-Id: I95b931c032ce16c56ee05caab4dd26ea89557b3c
|
|
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I7296840137d29718d14ca1470d02a806d880bc11
|
|
This offers dynamism support for slice op.
Change-Id: I4521c072c663a01e03e575e0cbbc8671c832f646
Signed-off-by: TatWai Chong <tatwai.chong@arm.com>
|
|
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: Ibab6aa2bbaee95f4ead737249d72e9169298bdde
|
|
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: If748c75ac713bb5bd7c7e6bc787ce9993a97a8a0
|