projects / platform / upstream / nnstreamer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 41f8726) | patch
tensor-transform: float16 support.
authorMyungJoo Ham <myungjoo.ham@samsung.com>
Fri, 17 Jun 2022 04:26:33 +0000 (13:26 +0900)
committerMyungJoo Ham <myungjoo.ham@samsung.com>
Sun, 3 Jul 2022 04:42:13 +0000 (13:42 +0900)
commit6405aa7fd9aaf59a91dffb09757bf8c9bbe2c76e
treeebd19a5cbf782fc772599ee1533fa961b4d38cb8tree | snapshot
parent41f87260648ddc246386ccb25671766466b9ef83commit | diff
tensor-transform: float16 support.

ORC/SIMD support not included.
Float16 w/ heavy tensor-transform is not recommended.

- Generate error if float16 is used in unsupported build
- Generate warning if float16 op is used too heavily (it's slow!)
- Future todo: support SIMD for float16 ops

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
gst/nnstreamer/tensor_data.c diff | blob | history
gst/nnstreamer/tensor_transform/tensor_transform.c diff | blob | history
Domain: Machine Learning / ML Framework;