Skip to content
This project is mirrored from https://review.mlplatform.org/tosa/reference_model. Pull mirroring updated .
  1. Sep 15, 2021
  2. Sep 14, 2021
  3. Sep 08, 2021
    • Matthew Haddon's avatar
      Remove invalid tests from test generator · b724efc0
      Matthew Haddon authored
      
      
       * Implemented InvalidValidator to remove existing invalid tests.
       * Removed invalid tests for resize, rescale, conv2d, depthwise_conv2d,
      transpose_conv2d, avg_pool2d, and max_pool2d (note default avg/max_pool
      never produced negative tests, but theoretically could).
       * Changed behaviour of computerMultiplierAndShift to produce the allowed
      range of shift values.
      
      Signed-off-by: default avatarMatthew Haddon <matthew.haddon@arm.com>
      Change-Id: I5e7b11030deb5322e2ca08fd4f4467fb02b7740d
      b724efc0
    • Matthew Haddon's avatar
      Allow user to specify test type generated · 74567097
      Matthew Haddon authored
      
      
       * The option --test-type allows the user to select 'positive', 'negative',
      or 'both' types of tests produced by the test generator.
       * Reset RNG when looping through negative test generation (generation not
      implemented)
      
      Signed-off-by: default avatarMatthew Haddon <matthew.haddon@arm.com>
      Change-Id: I1bfcb3170e7380be0f98b36b3d4abc4779a05abe
      74567097
  4. Sep 07, 2021
  5. Aug 31, 2021
  6. Aug 25, 2021
  7. Aug 20, 2021
    • Kevin Cheng's avatar
      Replace node level check ASSERT_MSG_NODE()/FATAL_ERROR_NODE() with REQUIRE() or ERROR_IF() · acb550f4
      Kevin Cheng authored
      
      
      - 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: default avatarKevin Cheng <kevin.cheng@arm.com>
      Change-Id: Ia063c936bcb2a54d6e379a5bb6801aa72d1186f1
      acb550f4
    • Matthew Haddon's avatar
      Make MATMUL output shape random · 68e7aee6
      Matthew Haddon authored and Eric Kunze's avatar Eric Kunze committed
      
      
       * Currently when a target shape is specified, the W value of the input
      tensor is always equal to N, this is not the case when no target shape
      is defined.
       * A random value for W is generated every time.
      
      Signed-off-by: default avatarMatthew Haddon <matthew.haddon@arm.com>
      Change-Id: I8f8ecb32308cef4a1ece1871f76ebbd5f0cf881f
      68e7aee6
  8. Aug 19, 2021
  9. Aug 12, 2021
  10. Aug 10, 2021
  11. Jul 29, 2021
  12. Jul 27, 2021
  13. Jul 20, 2021
  14. Jul 15, 2021
  15. Jul 13, 2021
    • Matthew Haddon's avatar
      Make operator tests follow consistent naming scheme · 43e37194
      Matthew Haddon authored and Eric Kunze's avatar Eric Kunze committed
      
      
       * By making the naming scheme consistent for MUL tests
      (shape_type_perm_shift) we are more easily able to parse parameters.
      This is the same system used for operators like RESHAPE, where perm0 is
      the only permutation allowed, but it still included in the test name.
       * For multiple operators axis and axis value were split by an underscore,
      Now the form is axisX in line with other parameters.
      
      Signed-off-by: default avatarMatthew Haddon <matthew.haddon@arm.com>
      Change-Id: I92e5af6fd1e2b83bdb23ac4a4ab350010aeeeccb
      43e37194
    • Jeremy Johnson's avatar
      Allow selection of higher rank tests using --target-rank · 97eb75f2
      Jeremy Johnson authored and Eric Kunze's avatar Eric Kunze committed
      
      
       * The default rank range has been increased from 1-4 to 1-6.
       * Higher ranks often make tests too large so a default_test_rank_range
      has been included which makes the test generator produce only tests with
      ranks 1-4.
       * The user can now specify target-rank up to rank 6 which is allowed
      for all operators with the default rank range.
       * The maximum rank allowed (6) stored in TOSA_TENSOR_MAX_RANK variable.
       * User specified target shapes up to maximum rank are accepted without
      need for setting target-rank filter.
      
      Signed-off-by: Jeremy Johnson's avatarJeremy Johnson <jeremy.johnson@arm.com>
      Change-Id: Ie4ca408d329cb1000ce9d3592b2c7d62bf311b3b
      97eb75f2
  16. Jul 09, 2021
  17. Jul 07, 2021
    • Matthew Haddon's avatar
      Fix bug causing identical reshape permutations · 2ad047dc
      Matthew Haddon authored and Eric Kunze's avatar Eric Kunze committed
      
      
       * When generating permutations of a reshape operator test there was
      no check to ensure that the permutation was unique, this patch adds
      a check to ensure that no two newShape variables are the same.
       * Added a 'escape_counter' which will break out of while loop
      if it continues on for too long.
      
      Signed-off-by: default avatarMatthew Haddon <matthew.haddon@arm.com>
      Change-Id: I231eb9b546a73431835b5dc899784f69cc22a773
      2ad047dc
  18. Jul 01, 2021
  19. Jun 28, 2021
    • Jeremy Johnson's avatar
      Fix transpose test gen of permutations & rank · a618557b
      Jeremy Johnson authored and Eric Kunze's avatar Eric Kunze committed
      
      
      Change transpose permutation generation to limit to the number of
      possible permutations that can be created by the shape size or the
      argument setting which ever is smaller. Also make sure all
      permutations up to this number are generated rather than randomly
      skipped due to duplicates.
      Allow rank 1 transpose tests as the specification allows rank 1.
      
      Change-Id: I28ea64c1d819f3af72c97bed43cfe7279c7e2f9c
      Signed-off-by: Jeremy Johnson's avatarJeremy Johnson <jeremy.johnson@arm.com>
      a618557b
  20. Jun 24, 2021
  21. Jun 09, 2021
  22. Jun 04, 2021
  23. May 25, 2021
  24. May 14, 2021
  25. May 12, 2021
    • Kevin Cheng's avatar
      Update to v0.22.0 · 14d7f7a2
      Kevin Cheng authored
      - 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
      14d7f7a2
  26. May 06, 2021
  27. Apr 30, 2021
Loading