projects / platform / core / ml / nntrainer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 35c4491) | patch
[ hdot ] Use precision-enhanced hdot
authorskykongkong8 <ss.kong@samsung.com>
Wed, 24 Apr 2024 01:39:41 +0000 (10:39 +0900)
committerJijoong Moon <jijoong.moon@samsung.com>
Fri, 10 May 2024 05:21:16 +0000 (14:21 +0900)
commit72ee686b74277a53fbaabcf888ce6c7875696ceb
tree51dc0eb8979f0820400ade92a2f0c6fad50d0deetree | snapshot
parent35c4491c56af150361c19eb74ec177251f1862facommit | diff
[ hdot ] Use precision-enhanced hdot

- Previous hdot was using full-fp16.
- Since this is also one of dimension-shrinking computation, should use inter-fp32 values to enhance precision.
- This has not been detected due to small dimension Tensor usage in unittest. Add higher dimension test case accordingly.

**Self evaluation:**
1. Build test:     [X]Passed [ ]Failed [ ]Skipped
2. Run test:     [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: skykongkong8 <ss.kong@samsung.com>
nntrainer/tensor/blas_neon.cpp diff | blob | history
test/unittest/unittest_nntrainer_tensor_neon_fp16.cpp diff | blob | history
Domain: Machine Learning / ML Framework;