DEEPX (CEO, Lokwon Kim), an original AI semiconductor technology company, is announcing that it has surpassed 40 customers for its flagship chip solution, DX-M1 — the only AI accelerator on the market to combine low power consumption, high efficiency and performance, and cost-effectiveness. The groundbreaking solution has been deployed for a hands-on trial to this customer pool, which spans global companies and domestic Korean enterprises across various sectors.

To experience how DX-M1 promises to revolutionize AI capabilities across industries, join DEEPX at Booth #8953, North Hall during CES 2024

DEEPX is currently running an Early Engagement Customer Program (EECP) to provide customers with early access to its small camera module, a one-chip solution featuring DX-V1; M.2 module featuring DX-M1; and DXNN®, the company’s developer environment. This allows customers to receive pre-production validation of DEEPX’s hardware and software, integrate them into mass-produced products, and realize AI technology innovations with the brand’s technical support.

Currently, DEEPX’s DX-M1 has been installed for pre-qualification testing in the mass production and development products of more than 40 global companies, covering robotics and smart mobility, AI video security systems, and AI servers. In particular, the robotics and smart mobility sectors increasingly require state-of-the-art, low-power, high-performance AI chips like DX-M1 that can be embedded in small form factors to enable highly advanced technologies such as autonomous driving and cognition.

The physical security market has one of the fastest AI penetration rates, making it essential to realize AI functions at the semiconductor level, such as object detection and intelligent video analysis. In this industry, DEEPX’s DX-M1, which uses a 5nm process, is the only one of its kind available, delivering an impressive power-to-performance ratio that far surpasses current market offerings. It supports real-time AI computational processing at over 30 frames-per-second (FPS) for more than 16 channels of multichannel video data on a single chip, and can process multiple AI algorithms simultaneously, such as object recognition and image classification. Moreover, unlike other AI chips, it has a wide spectrum of AI models supported, from the most popular YOLOv5 model for object recognition to the latest YOLOv8 and vision transformer models. Combining these technologies and advantages, DX-M1 leads the market through a blend of high efficiency and performance, low power consumption through its original technology, and cost effectiveness, all of which are critical for customers looking for AI chips.

While competing AI chips in the market currently use 32MB to 50MB of cache memory, DX-M1 only uses approximately one quarter of the cache memory, while also adding the advantages of AI chips such as computational processing power, compute accuracy, and support for a wide range of AI algorithms. (See table below).

Value AddedMethod
Lowermanufacturing costs– Reducing the use of higher unit cost SRAMs- Increased manufacturing count per wafer as product size shrinks
Lowpower consumption– Smaller form factors require less energy- Reusing data and memory reduces unnecessary operations
High efficiency and
performance
– Reducing unnecessary operations with data and memory reuse
also increases processing speeds- Optimized memory usage for faster processing- High computational accuracy- Supports SOTA AI models such as Yolov8 and others

The DX-M1 is also available in a compact M.2 module that can be quickly and easily plugged into existing embedded systems, allowing customers to easily upgrade to low-power, high-performance AI solutions without changing their existing systems.

As a testament to its potential impact on the market, the DX-M1 was honored with CES Innovation Awards 2024 in both the Embedded Technology and Robotics, adding DEEPX to a list of honorees that includes top-tier global brands.

As the company expands globally, DEEPX will showcase DX-M1’s full potential and more at Booth #8953, North Hall during CES 2024, January 9-12, 2024 in Las Vegas, NV.