Last year, Huawei unveiled the world’s first artificial intelligence (AI) computing platform — Kirin 970, integrated into the Huawei Mate 10 series.
It brought a new and innovative AI experience and a key new feature: A neural processing unit (NPU), which enables cloud-based and on-device AI to run alongside each other, providing faster performance.
Today, from a performance and application perspective, the Huawei Kirin 970 chip is at the top due to its AI integration in the hardware-processing unit.
In terms of performance, because the AI process involves a large number of intensive convolution operations, Huawei integrates independent processing units into the hardware.
Kirin 970 is the company’s first mobile AI computing platform featuring a dedicated NPU. Moreover, the Kirin 970’s new heterogeneous computing architecture delivers up to 25 times the performance of a central processing unit (CPU) with 50 times greater efficiency. Simply put, the Kirin 970 can perform the same AI computing tasks faster and use far less power. In a benchmark image-recognition test, the Kirin 970 processed 2,000 images per minute, considerably faster than other chips with similar capabilities in the market.
Furthermore, the NPU gives users peace of mind and reassurance about their phone’s ability to keep up with their long days effectively and safely. Also, if the phone’s temperature increases, the battery management feature turns the phone off automatically, providing maximum safety.
AI not only requires “hard power” performance but also needs to adapt to “soft power” for application support. Huawei has already integrated AI in its devices, for example, Huawei’s Kirin 970 processing is already in the market in applications, such as AI camera, AI voice recognition, and AI integrated translator, which are all found on the Huawei Mate 10 series. Also, one of the benefits of apps using AI running on a Kirin 970 device is the reduced battery power consumption compared to those without the dedicated hardware.
The NPU promotes the development of innovative apps that use on-device AI, giving developers the choice to use either on-device or cloud AI, depending on which option best suits the app.
It brought a new and innovative AI experience and a key new feature: A neural processing unit (NPU), which enables cloud-based and on-device AI to run alongside each other, providing faster performance.
Today, from a performance and application perspective, the Huawei Kirin 970 chip is at the top due to its AI integration in the hardware-processing unit.
In terms of performance, because the AI process involves a large number of intensive convolution operations, Huawei integrates independent processing units into the hardware.
Kirin 970 is the company’s first mobile AI computing platform featuring a dedicated NPU. Moreover, the Kirin 970’s new heterogeneous computing architecture delivers up to 25 times the performance of a central processing unit (CPU) with 50 times greater efficiency. Simply put, the Kirin 970 can perform the same AI computing tasks faster and use far less power. In a benchmark image-recognition test, the Kirin 970 processed 2,000 images per minute, considerably faster than other chips with similar capabilities in the market.
Furthermore, the NPU gives users peace of mind and reassurance about their phone’s ability to keep up with their long days effectively and safely. Also, if the phone’s temperature increases, the battery management feature turns the phone off automatically, providing maximum safety.
AI not only requires “hard power” performance but also needs to adapt to “soft power” for application support. Huawei has already integrated AI in its devices, for example, Huawei’s Kirin 970 processing is already in the market in applications, such as AI camera, AI voice recognition, and AI integrated translator, which are all found on the Huawei Mate 10 series. Also, one of the benefits of apps using AI running on a Kirin 970 device is the reduced battery power consumption compared to those without the dedicated hardware.
The NPU promotes the development of innovative apps that use on-device AI, giving developers the choice to use either on-device or cloud AI, depending on which option best suits the app.
