projects / platform / upstream / nnstreamer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 18cd1e5) | patch
Introduce FLOAT16 stream type
authorMyungJoo Ham <myungjoo.ham@samsung.com>
Fri, 10 Jun 2022 04:26:04 +0000 (13:26 +0900)
committerMyungJoo Ham <myungjoo.ham@samsung.com>
Sun, 3 Jul 2022 04:42:13 +0000 (13:42 +0900)
commitc94b44b297a782bb36c34a2b1243700ad4437f19
treef3cd4a4af776c299e1329b26924c1e139335f25btree | snapshot
parent18cd1e57b886c7a205606bceddaf6c2a5926bb3ccommit | diff
Introduce FLOAT16 stream type

Add FLOAT16 type.
Fortunately, gcc for x64, aarch64, and arm has extension for
float16.

@todo: update meson script so that arch-specific compiler
options for float16 can be added if float16 is enabled.

Addressed #3784

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
gst/nnstreamer/include/tensor_typedef.h diff | blob | history
gst/nnstreamer/nnstreamer_plugin_api_util_impl.c diff | blob | history
gst/nnstreamer/tensor_converter/tensor_converter.c diff | blob | history
gst/nnstreamer/tensor_data.c diff | blob | history
meson.build diff | blob | history
meson_options.txt diff | blob | history
Domain: Machine Learning / ML Framework;