Skip to content
This project is mirrored from https://review.mlplatform.org/tosa/specification. Pull mirroring updated .
  1. Sep 13, 2023
  2. Aug 18, 2023
  3. Aug 17, 2023
    • Eric Kunze's avatar
      Change TOSA specification to signless types · fb0284e2
      Eric Kunze authored
      Integer inputs and outputs to TOSA operators are now defined as signless
      values. In most instances the operator will used signed arithmetic as
      indicated in previous versions of the specification resulting in little
      functional change to the specification.
      
      New attributes have been added to the RESCALE operator to indicate
      whether the input and output values should be treated as signed or unsigned.
      
      Explicit use of static_cast, sign_extend, zero_extend and truncate are added
      to the pseudocode to avoid ambiguity.
      
      Change-Id: I71c67d3e5aeaabc418c768f821fce6ee3eebb65b
      fb0284e2
  4. Aug 16, 2023
    • Dominic Symes's avatar
      Main conformance: Add local bound flag for convolutions · b5b06781
      Dominic Symes authored
      
      
      Adds a local_bound flag to convolution operations.
      
      If the local_bound flag is true then the output accuracy
      for floating-point is measured relative to the
      input tensor data local to the particular convolution output.
      
      If the local_bound flag is false then the output accuracy
      for floating-point is measured relative to the whole input tensor.
      This accuracy measure is the default and more approapriate for
      implementations with non local optimizations (such as
      transform based fast convolutions).
      
      Signed-off-by: default avatarDominic Symes <dominic.symes@arm.com>
      Change-Id: I64e3e4981a63e26e6391149e28d5d71e7ef5560a
      b5b06781
    • Dominic Symes's avatar
      Add DIM operator and operations on shape_t values · 830b43b1
      Dominic Symes authored
      
      
      Shape inference derives the shape of tensors in
      the graph from input shapes. Operations such as RESHAPE
      may need calculations to derive the new tensor shape.
      This patch:
      
      - Adds a DIM operator to get the size of a tensor in
        a given axis as a rank 0 tensor of type shape_t
      
      - Allows RESHAPE to take a 1D shape tensor as input for
        the new shape
      
      - Allows RESIZE, TILE, PAD to take input sizes based
        on shape tensors.
      
      - Allows ADD, SUB, MUL, INTDIV to operate on rank 0
        shape_t tensors
      
      - Allows CONCAT to concatenate 0D shape_t tensors to
        a 1D shape_t tensor
      
      - Adds CONST support for shape_t tensors
      
      In this version of the specification shape tensors must
      be resolvable to constants at backend compile time.
      
      Signed-off-by: default avatarDominic Symes <dominic.symes@arm.com>
      Change-Id: I484bd44452453b5e05d0d8a82689564587b224e4
      830b43b1
  5. Aug 15, 2023
  6. Aug 11, 2023
  7. Aug 07, 2023
  8. Aug 03, 2023
  9. Jul 24, 2023
  10. Jul 11, 2023
  11. Jul 06, 2023
  12. Jun 23, 2023
  13. Jun 21, 2023
  14. Jun 08, 2023
  15. Jun 02, 2023
  16. Jun 01, 2023
  17. May 25, 2023
  18. May 24, 2023
    • Kevin Petit's avatar
      Formalise the description of operator argument types · 5333c25b
      Kevin Petit authored
      
      
      - Standardise the terminology for operator arguments. Argument,
        Operand, and Parameter were used interchangeably.
      - Introduce a templatized tensor_t<> type for tensor arguments.
        Scalars are represented by rank-0 tensors.
      - Types can be checked with the XSD schema.
      
      Signed-off-by: default avatarKevin Petit <kevin.petit@arm.com>
      Change-Id: Ic57b9387950824e994c5e7f9ec1489c29159b974
      5333c25b
  19. May 23, 2023
  20. May 22, 2023
  21. May 19, 2023
  22. May 18, 2023
  23. May 17, 2023
  24. May 15, 2023
    • Eric Kunze's avatar
      Add TOSA rank requirements to TOSA XML · 42085e36
      Eric Kunze authored
      
      
      Adds new optional element to argument 'rank'
      - Must supply minimum and maximum rank
         - Integer values or the level based "MAX_RANK"
         - trailing modifiers allowed for "MAX_RANK"
      - Displays in a new column in the document
      - Document generation validates rank against specified shape
      
      Change-Id: I507dc51bfe012d3230af43103c6c423a6f1e92b5
      Signed-off-by: Eric Kunze's avatarEric Kunze <eric.kunze@arm.com>
      42085e36
  25. May 09, 2023
    • Dominic Symes's avatar
      Main inference compliance testing updates · 5b936a3c
      Dominic Symes authored
      
      
      - Add additional main inference compliance test
      data sets for dot product testing in Appendix A.
      
      - Express dot product test criteria in terms of
      tensors rather than individual dot products.
      
      - Add per-operation details on test set generation
      in Appendix A.
      
      - Clarify compliance vs conformance wording.
      
      - Clarify that the comment in the table of section 1.8.2
      on integer saturation applies to the CAST from
      floating point to integer operation.
      
      Change-Id: I1b4c4493b02ed7c8a6eb547656c91ca67d4b0e86
      Signed-off-by: default avatarDominic Symes <dominic.symes@arm.com>
      5b936a3c
  26. May 02, 2023
  27. Apr 28, 2023
    • Kevin Petit's avatar
      Fix resize_t enum name · 53e76592
      Kevin Petit authored
      
      
      resize_t is already used in the type support table for RESIZE, rename
      the mode enum to resize_mode_t.
      
      Also add a python function to get an enum object by name to the spec
      object.
      
      Change-Id: Id12c10929beda469c6e3714518d6e26f18ddd440
      Signed-off-by: default avatarKevin Petit <kevin.petit@arm.com>
      53e76592
  28. Apr 27, 2023
  29. Apr 26, 2023
  30. Apr 18, 2023
  31. Apr 14, 2023
  32. Apr 06, 2023
  33. Mar 21, 2023
  34. Mar 20, 2023
Loading