Skip to content
This project is mirrored from https://review.mlplatform.org/tosa/reference_model. Pull mirroring updated .
  1. Mar 09, 2023
  3. Mar 08, 2023
  5. Mar 04, 2023
  7. Mar 03, 2023
    • TatWai Chong's avatar
      Refactor resize test builder · 0cef07ec
      TatWai Chong authored 
      

Also add input size = 1 in the shape list, and extend scaling to
1x, 2x and 3x, so that the cases of broadcasting, power-of-two
scaling, no-scaling (e.g. 1x1 -> 1x1), scaling accuracy (3x) can
be tested. Since the scalar tensor is tiny, should not noticeably
impact the execution time of the framework test.

Change-Id: Iec53da3cbb60e087077d6e2d8eb205e76e6c1313
Signed-off-by: TatWai Chong's avatarTatWai Chong <tatwai.chong@arm.com>
      0cef07ec
    • Eric Kunze's avatar
      Update CAST fp to int rounding · 57bc0796
      Eric Kunze authored 
      

Use rint() instead of round() to get round to nearest even behavior

Signed-off-by: Eric Kunze's avatarEric Kunze <eric.kunze@arm.com>
Change-Id: I45957be0e863de2207850b023626a7c0ea11e5eb
      57bc0796
  9. Mar 02, 2023
  11. Mar 01, 2023
  13. Feb 28, 2023
  15. Feb 24, 2023
  17. Feb 22, 2023
  19. Feb 14, 2023
  21. Feb 10, 2023
  23. Feb 07, 2023
  25. Feb 06, 2023
  27. Feb 02, 2023
  29. Jan 31, 2023
  31. Jan 30, 2023
  33. Jan 27, 2023
    • Luke Hutton's avatar
      Add RFFT2d to optimized only kernel list · 5c844210
      Luke Hutton authored 
      

This fixes framework test generation when the "optimized"
kernel mode option is not selected. As a result, the
optimized RFFT2d kernel is used when generating tests in
the reference kernel mode to prevent "op not found"
errors.

Signed-off-by: Luke Hutton's avatarLuke Hutton <luke.hutton@arm.com>
Change-Id: Ice18bfa08c46e237e39c99f849622bf99d9b849c
      5c844210
    • TatWai Chong's avatar
      Add framework test for math.sign · d713a4d8
      TatWai Chong authored and Eric Kunze's avatar Eric Kunze committed 
      

The result comparison between Tensorflow runtime and the reference
model hasn't been checked as the sign operator is not supported by
the native TFLite runtime. That said, since the generated tosa ops
for tf.sign and tfl.sign is identical, the correctness presumably
can be proved by the result from tf.sign.

Change-Id: I72eb415df7fb6ca4dc9103f9ddc7104b0ba39234
Signed-off-by: TatWai Chong's avatarTatWai Chong <tatwai.chong@arm.com>
      d713a4d8
  35. Jan 25, 2023
  37. Jan 24, 2023
  39. Jan 23, 2023
  41. Jan 19, 2023
  43. Jan 18, 2023
  45. Jan 13, 2023
    • Jerry-Ge's avatar
      Reference model update for control flow operators support · 9e94af8f
      Jerry-Ge authored and Eric Kunze's avatar Eric Kunze committed 
      

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's avatarJerry Ge <jerry.ge@arm.com>
Change-Id: I13ae33628ad07e41d248e88652ce1328654694ab
      9e94af8f
  47. Jan 04, 2023