Industry News

Qualcomm and NVIDIA Compete for AI Chip Energy Efficiency Indicators

Update time : 2023-04-08 11:08:24

According to industry information reports, in a new set of test data released yesterday, Qualcomm and NVIDIA compete for AI chip-related performance indicators, among which, Qualcomm's AI 100 chip is superior to NVIDIA's flagship H100 chip in image classification, and in the natural language processing test, NVIDIA's absolute performance and energy efficiency are superior to Qualcomm.

AI chips are also known as AI accelerators or compute cards, that is, modules dedicated to processing a large number of computing tasks in artificial intelligence applications (other non-computing tasks are still responsible for the CPU), and AI chips are currently divided into GPU, FPGA, ASIC in the industry. Much of AI's data processing involves matrix multiplication and addition, and GPUs that work heavily in parallel offer an inexpensive method, but the disadvantage is higher power. FPGAs with built-in DSP blocks and local memory are more energy efficient, but they are generally more expensive.
Some analysts in the industry believe that the market for data center inference chips will grow rapidly as companies apply AI technology to their products, but companies such as Google are already exploring how to control the additional costs that add to doing so. One of the main costs is electricity, and Qualcomm has used its history of designing chips for battery-powered devices such as smartphones to create a chip called Cloud AI 100 that focuses on reducing power consumption. In test data released Wednesday by MLCommons, an engineering consortium that maintains a test benchmark widely used in the AI chip industry, Qualcomm's AI 100 beat Nvidia's flagship H100 chip in image classification, based on how many data center server queries can run per chip per unit of power.
Qualcomm's chips reached 197.6 server queries/watt, while Nvidia reached 108.4 queries/watt, and surprisingly, Neuchips, a startup founded by veteran Taiwanese chip scholar Lin Yonglong, topped the list with 227 queries/watt. Qualcomm also beat Nvidia in object detection with a score of 3.2 queries per watt, compared to Nvidia's 2.4 queries per watt, object detection can be used to analyze applications such as retail store lenses to see where shoppers go most often. However, in natural language processing tests, NVIDIA ranked among the best in absolute performance and energy efficiency, which is the most widely used AI technology in systems such as chatbots. Nvidia reached 10.8 samples per watt, while Neuchips ranked second with 8.9 samples per watt and Qualcomm came in third with 7.5 samples per watt.

Previous : IBM Releases New Single-Cabinet Versions of z16 and LinuxONE 4 to Further Improve Data Center Flexibility, Sustainability and Security

Next : Infineon introduces high-voltage MCU with USB-C PD and boost charge controller to simplify embedded system design

How many chips does a car need?

Sep .19.2024

Automotive chips can be divided into four types according to their functions: control (MCU and AI chips), power, sensors, and others (such as memory). The market is monopolized by international giants. The automotive chips people often talk about refer to

Position and Function of Main Automotive Sensors

Sep .18.2024

The function of the air flow sensor is to convert the amount of air inhaled into the engine into an electrical signal and provide it to the electronic control unit (ECU). It is the main basis for determining the basic fuel injection volume. Vane type: The

Chip: The increasingly intelligent electronic brain

Sep .14.2024

In this era of rapid technological development, we often marvel at how mobile phones can run various application software smoothly, how online classes can be free of lag and achieve zero latency, and how the functions of electronic devices are becoming mo

LDA100 Optocoupler: Outstanding Performance, Wide Applications

Sep .13.2024

In terms of characteristics, LDA100 is outstanding. It offers AC and DC input versions for optional selection, enabling it to work stably in different power supply environments. The small 6-pin DIP package not only saves space but also facilitates install

About Us

About Us What we do Quality People

Products

CHIP/IC Active devices Passive device Components OTHER

China electronic components supplier----Wah Luen Shing Electronic.----www.wlschip.com

Leave a message