[ML] Update NNFWType name of TRIx NPU Series 50/262350/2 accepted/tizen/unified/20210810.135347 submit/tizen/20210809.021120
authorMyungJoo Ham <myungjoo.ham@samsung.com>
Mon, 9 Aug 2021 03:06:36 +0000 (12:06 +0900)
committerPiotr Kosko <p.kosko@samsung.com>
Mon, 9 Aug 2021 08:38:17 +0000 (08:38 +0000)
SRNPU is an unofficial name of TRIx NPU series.
Update the name with the official name.
Fortuately "SRNPU" was first introduced with Tizen 6.5 releases.

We have decided to expose the official name of these NPU series of
TRIV and TRIA series, which are exposed via a common NPU-Engine
low-level driver: "TRIx-Engine".

Note that in some commercial products with TRIx NPU series,
the low-level drivers might be not available to applications.
In such cases, high-level drivers (with less hardware control)
that wrap the low-level drivers will be provided (e.g., VD-AIFW).

[ACR] https://code.sec.samsung.net/jira/browse/TWDAPI-280

Change-Id: I7385749ec94981c3a89fe918d548d2fc582594bd
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
src/ml/js/ml_manager.js
src/ml/ml_utils.cc

index afdc2a3a9cdd4181f14489dac3e5ca02bd1f3457..05dcef065f79b9d0a4dce59d36485c80c0452c15 100755 (executable)
@@ -44,7 +44,7 @@ var NNFWType = {
     PYTORCH: 'PYTORCH',
     NNTR_INF: 'NNTR_INF',
     VD_AIFW: 'VD_AIFW',
-    SRNPU: 'SRNPU'
+    TRIX_ENGINE: 'TRIX_ENGINE'
 };
 
 var HWType = {
index 14a516eccf8f96c44c0fcb3977fda7d1cfe317b8..fe0f5a889b6b00404cf6c016be8ca528aebd3ee7 100644 (file)
@@ -46,7 +46,7 @@ const PlatformEnum<ml_nnfw_type_e> NNFWTypeEnum{{"ANY", ML_NNFW_TYPE_ANY},
                                                 {"OPEN_VINO", ML_NNFW_TYPE_OPENVINO},
                                                 {"PYTORCH", ML_NNFW_TYPE_PYTORCH},
                                                 {"SNPE", ML_NNFW_TYPE_SNPE},
-                                                {"SRNPU", ML_NNFW_TYPE_SRNPU},
+                                                {"TRIX_ENGINE", ML_NNFW_TYPE_TRIX_ENGINE},
                                                 {"TENSORFLOW", ML_NNFW_TYPE_TENSORFLOW},
                                                 {"TENSORFLOW_LITE", ML_NNFW_TYPE_TENSORFLOW_LITE},
                                                 {"VD_AIFW", ML_NNFW_TYPE_VD_AIFW},