aboutsummaryrefslogtreecommitdiff
path: root/reference_model
AgeCommit message (Collapse)Author
41 hoursAdd missing signed/unsigned data types of input/output for RESCALE opHEADmainWon Jeon
Signed-off-by: Won Jeon <won.jeon@arm.com> Change-Id: I1498313f56626011d39f765fed71f82be53b3d8d
42 hoursUpdate reference generator test set calculationWon Jeon
Signed-off-by: Won Jeon <won.jeon@arm.com> Change-Id: I74f9ac096e5030a86bd7c1ffff542d9061b09ab4
2024-05-01Fix MAXIMUM/MINIMUM handling of NaNs and zeroesJeremy Johnson
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
2024-04-25Update main branch version to 1.1.0 draftEric Kunze
Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I8c4439189756a4d20cf5395fbbbe4aa6af7873ce
2024-04-19Update version to 1.0.0 draftv1.0.0-rc0v1.00Eric Kunze
Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I6b6a303a475525840a281c7e4e6ecc326c6a1aac
2024-04-19Update float8 header and namespaceWon Jeon
Signed-off-by: Won Jeon <won.jeon@arm.com> Change-Id: I75840f6b4ff11a63c4c874f8ded23afb5a71ad55
2024-04-18[reference_model] Remove output_shape from transpose_conv2dSuraj Sudhir
Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com> Change-Id: Ib2b95e73b226d64c4db5ad1ed22c123e04d7e6f9
2024-04-18Update compliance verify checksJeremy Johnson
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
2024-04-18RFFT2D, refmodel. Correct code when size is oneDmitriy Smirnov
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
2024-04-17Fix gcc warning of comparison of different signedness integersTatWai Chong
This warning is raised in the integer comparison of `applyClip`. Signed-off-by: TatWai Chong <tatwai.chong@arm.com> Change-Id: If427cb08b8456480898375d8b77302ca7162f737
2024-04-16SPECIAL data gen mode for FP16 and FP32evacha01
Signed-off-by: evacha01 <evan.chandler@arm.com> Change-Id: I5a9a1c63345bd83ca04bc6c2a99b0ef3612971ee
2024-04-15[ref model] fix const/pad/clamp attribute serializationTai Ly
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
2024-04-11[ref_model] Remove assert on bad tensor typeTai Ly
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
2024-04-08Fix the wrong QMax and QMin type assignment in rescale opTatWai Chong
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>
2024-04-08Modify Rescale signedness check to look at attributesEric Kunze
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
2024-04-03Make Full Range FP16 tests into extra testsevacha01
Signed-off-by: evacha01 <evan.chandler@arm.com> Change-Id: I8c59ecb5a1fb53d0e9bf64333709f9e3cc908b49
2024-04-02Show actual runtime value of shapeType tensorsJerry Ge
* 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
2024-03-28Take into account of `output_unsigned` in rescale operationTatWai Chong
Set QMin and QMax based on the value of attribute `output_unsigned`. Change-Id: I7f21f3edd7311295285fb3988b3c800de114777a Signed-off-by: TatWai Chong <tatwai.chong@arm.com>
2024-03-26Compliance Test Set 3 data fixJeremy Johnson
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
2024-03-20[ref model] Add acc_type to Conv OpsTai Ly
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
2024-03-17[ref model] Change Clamp and Pad attribute fieldsTai Ly
This implements changes due to ClampAttribute and PadAttribute field changes. Signed-off-by: Tai Ly <tai.ly@arm.com> Change-Id: Ide01e2a27fe3c1ea7794e7a4b6780b7eae436caf
2024-03-15Add missing FP8 definition and instantiation for FULLY_CONNNECTED opWon Jeon
Signed-off-by: Won Jeon <won.jeon@arm.com> Change-Id: I7efc03f16136b2b74f8dfef79a6e7e147c93f4ed
2024-03-07Add INT48 and INT4 datatype support to IDENTITYevacha01
Added support to ref model and testing Signed-off-by: evacha01 <evan.chandler@arm.com> Change-Id: Iece53d07c8986332fdd8f1ce5ed6265349df1b6a
2024-03-07FULL data gen mode for FP16evacha01
Signed-off-by: evacha01 <evan.chandler@arm.com> Change-Id: I81bb322132daf25328a40342edc62d8e1db9edd6
2024-03-06[ref model] Change RescaleOp attrs to inputsTai Ly
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
2024-03-05Fix the usage of command line arguments for reference_modelJerry Ge
- 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
2024-03-05Add Tosa Sin/Cos operatorsJerry Ge
- Add Tosa Sin/Cos operators to reference_model - Add conformances tests Signed-off-by: Jerry Ge <jerry.ge@arm.com> Change-Id: I3f597ddf5dac2c64d6dd6aa15781b40b8468eaa6
2024-03-05Minor fix ups in verify libJeremy Johnson
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
2024-03-01Testing support for MUL with shift as inputJeremy Johnson
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
2024-02-29Fix padding value for PAD op and tensor writing to npy for FP8Won Jeon
Signed-off-by: Won Jeon <won.jeon@arm.com> Change-Id: I55f663c19a1d2579d24b25c7f0d476e56e7e6dd2
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
2024-02-27[reference_model] tosa.fb name changesTai Ly
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
2024-02-26Verifier - change to output largest error devianceJeremy Johnson
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
2024-02-26Ref-model generate build warning fixJeremy Johnson
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com> Change-Id: I1fb734285c60f71a74a5815e76ace51ace719400
2024-02-26[ref_model] Change resize attrs to inputsTai Ly
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
2024-02-23Fix comparing unsigned int and int in slice evaluationTatWai Chong
also check if tensors of start and size are allocated. Change-Id: I6a72d11ebcb8d0725fe267058dfd792102459427 Signed-off-by: TatWai Chong <tatwai.chong@arm.com>
2024-02-22Save Int16/UINT16 test outputs to native dtypesJerry Ge
* 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
2024-02-22Change the shift of mul to tensor typeTatWai Chong
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>
2024-02-21Add support for FP8 to reference modelWon Jeon
Signed-off-by: Won Jeon <won.jeon@arm.com> Change-Id: I99b70f94aff2ccd4af64875697e124eb60bc5b08
2024-02-08Fix REDUCE ops to support 8k MAX_RANKJeremy Johnson
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com> Change-Id: I365da379f599e5eca1841e6d299b4005a7b0f082
2024-02-08Main Compliance: Add RESIZE supportJeremy Johnson
Add RELATIVE verify mode for RESIZE. Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com> Change-Id: I4fe352579507211dae7a048bf080c24426ce42a2
2024-02-08Main Compliance: RFFT2D supportJeremy Johnson
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
2024-02-08Main Compliance testing for CONV3Devacha01
Signed-off-by: evacha01 <evan.chandler@arm.com> Change-Id: Ie05f88db15cd07fd5483ab669329d7048bd3349c
2024-02-07Main Compliance: Update POW error boundJeremy Johnson
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com> Change-Id: I8f7678706e517d7f8d9742dcddd0ea5875b30a00
2024-02-07Main Compliance: FFT2D supportJeremy Johnson
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
2024-02-06Main Compliance testing for TRANSPOSE, REVERSE, and CONSTevacha01
Signed-off-by: evacha01 <evan.chandler@arm.com> Change-Id: I95b931c032ce16c56ee05caab4dd26ea89557b3c
2024-02-05Update version to 0.100.0 draftv0.100a0Eric Kunze
Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I7296840137d29718d14ca1470d02a806d880bc11
2024-01-31Change the start and size of slice to tosa shape typeTatWai Chong
This offers dynamism support for slice op. Change-Id: I4521c072c663a01e03e575e0cbbc8671c832f646 Signed-off-by: TatWai Chong <tatwai.chong@arm.com>
2024-01-31Fix the improvement of the ABS_ERROR outputJeremy Johnson
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com> Change-Id: Ibab6aa2bbaee95f4ead737249d72e9169298bdde
2024-01-31Fix verify REDUCE_PRODUCT reportingJeremy Johnson
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com> Change-Id: If748c75ac713bb5bd7c7e6bc787ce9993a97a8a0
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-19 14:34:04 +0000