From 919dc1df3c0bda84ea85def5f9137174cf1ec0e3 Mon Sep 17 00:00:00 2001 From: Sung-Jae Lee Date: Fri, 25 Mar 2022 20:05:06 +0900 Subject: [PATCH 1/4] Update Overview.modified - Add NN Runtime contents in AI and Machine Learning section Signed-off-by: Sung-Jae Lee --- docs/platform/what-is-tizen/overview.md | 26 +++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/docs/platform/what-is-tizen/overview.md b/docs/platform/what-is-tizen/overview.md index 5fb564c6c4..1aaff363ab 100755 --- a/docs/platform/what-is-tizen/overview.md +++ b/docs/platform/what-is-tizen/overview.md @@ -47,6 +47,32 @@ The most important strengths that enable Tizen to move to the next level are IoT ![IoTivity for Connectivity](media/about_tizen_6.png) +## AI and Machine Learning + +NN Runtime serves as a backend for machine learning APIs for accelerating neural network inference on Tizen devices. It supports heterogeneous computing by combining CPU and GPU, and we plan to expand support to NPU in the near future. It is based on the independent open source project [ONE(On-device Neural Engine](https://github.com/Samsung/ONE), which consists of a runtime virtual machine running on the Tizen device and a compiler toolchain running on the developer's host computer. + +Runtime + +- Provides an optimized execution combination of various open kernels and private kernels based on a proprietary algorithm developed in-house. + - Kernels from open sources such as ARM Compute Library (ACL), Ruy, and XNNPACK, and customized improvements according to needs. +- Support for dynamic tensors whose shape keeps changing during inference. +- Support for models with control flow operators. (IF, WHILE) +- Provides various executors and is expandable. + - Linear executor. + - Parallel executor using CPU and GPU together. +- Partitioning and multithreading of neural network models at runtime to improve overall inference throughput. + +Compiler Toolchain + +- Support for interworking with various neural network frameworks and their models. + - TensorFlow & TensorFlow lite v1.x & v2.x. + - PyTorch & ONNX v1.10. +- Defining and serving extensible universal container called ‘NN package’. + - Accommodating circle(ONE), tflite(TensorFlow lite) model and meta-data in JSON format under directory structure. +- Includes various development tools that use common IR (circle) as standard input/output format. + - Graph-level neural network model optimizer. + - Neural network model quantizer. + - Various profiles and test scripts to evaluate performance on target. ## Convergence Platform for the Emerging Era From 26008aad9c19aaef9c6dad188fda8a5e307335a8 Mon Sep 17 00:00:00 2001 From: Sung-Jae Lee Date: Thu, 31 Mar 2022 19:21:38 +0900 Subject: [PATCH 2/4] Update docs/platform/what-is-tizen/overview.md Co-authored-by: arisha-srbd <97720350+arisha-srbd@users.noreply.github.com> --- docs/platform/what-is-tizen/overview.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/platform/what-is-tizen/overview.md b/docs/platform/what-is-tizen/overview.md index 1aaff363ab..5e7e4b2b03 100755 --- a/docs/platform/what-is-tizen/overview.md +++ b/docs/platform/what-is-tizen/overview.md @@ -48,7 +48,7 @@ The most important strengths that enable Tizen to move to the next level are IoT ![IoTivity for Connectivity](media/about_tizen_6.png) ## AI and Machine Learning - +### NN Runtime NN Runtime serves as a backend for machine learning APIs for accelerating neural network inference on Tizen devices. It supports heterogeneous computing by combining CPU and GPU, and we plan to expand support to NPU in the near future. It is based on the independent open source project [ONE(On-device Neural Engine](https://github.com/Samsung/ONE), which consists of a runtime virtual machine running on the Tizen device and a compiler toolchain running on the developer's host computer. Runtime From fd395a9840132f7b433f4bbc30dd0478252251d0 Mon Sep 17 00:00:00 2001 From: Sung-Jae Lee Date: Thu, 31 Mar 2022 19:21:46 +0900 Subject: [PATCH 3/4] Update docs/platform/what-is-tizen/overview.md Co-authored-by: arisha-srbd <97720350+arisha-srbd@users.noreply.github.com> --- docs/platform/what-is-tizen/overview.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/platform/what-is-tizen/overview.md b/docs/platform/what-is-tizen/overview.md index 5e7e4b2b03..71a8ed9ffc 100755 --- a/docs/platform/what-is-tizen/overview.md +++ b/docs/platform/what-is-tizen/overview.md @@ -49,7 +49,7 @@ The most important strengths that enable Tizen to move to the next level are IoT ## AI and Machine Learning ### NN Runtime -NN Runtime serves as a backend for machine learning APIs for accelerating neural network inference on Tizen devices. It supports heterogeneous computing by combining CPU and GPU, and we plan to expand support to NPU in the near future. It is based on the independent open source project [ONE(On-device Neural Engine](https://github.com/Samsung/ONE), which consists of a runtime virtual machine running on the Tizen device and a compiler toolchain running on the developer's host computer. +NN Runtime serves as a backend for machine learning APIs for accelerating neural network inference on Tizen devices. It supports heterogeneous computing by combining CPU and GPU, and we plan to expand support to NPU in the near future. It is based on the independent open source project [ONE (On-device Neural Engine)](https://github.com/Samsung/ONE), which consists of a runtime virtual machine running on the Tizen device and a compiler toolchain running on the developer's host computer. Runtime From a07154bc6ef59823f4fc975295f5a317e093b489 Mon Sep 17 00:00:00 2001 From: Sung-Jae Lee Date: Thu, 31 Mar 2022 19:21:59 +0900 Subject: [PATCH 4/4] Update docs/platform/what-is-tizen/overview.md Co-authored-by: arisha-srbd <97720350+arisha-srbd@users.noreply.github.com> --- docs/platform/what-is-tizen/overview.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/platform/what-is-tizen/overview.md b/docs/platform/what-is-tizen/overview.md index 71a8ed9ffc..15239029e9 100755 --- a/docs/platform/what-is-tizen/overview.md +++ b/docs/platform/what-is-tizen/overview.md @@ -68,7 +68,7 @@ Compiler Toolchain - TensorFlow & TensorFlow lite v1.x & v2.x. - PyTorch & ONNX v1.10. - Defining and serving extensible universal container called ‘NN package’. - - Accommodating circle(ONE), tflite(TensorFlow lite) model and meta-data in JSON format under directory structure. + - Accommodating circle (ONE), tflite (TensorFlow lite) model, and meta-data in JSON format under directory structure. - Includes various development tools that use common IR (circle) as standard input/output format. - Graph-level neural network model optimizer. - Neural network model quantizer.