SAPEON, a global AI semiconductor company, announced the launch of the X330, an AI semiconductor for data centres with four times higher performance than its predecessor, the X220.
The X330 is produced using TSMC’s 7nm technology. SAPEON plans to conduct X330 prototype testing and customer reliability verification for major customers and to begin mass production in the first half of next year.
Since the X330 offers enhanced performance and power efficiency, it represents an ideal choice for large language model (LLM) support while improving overall total cost of ownership (TCO). The X330 forms the core of SAPEON’s plan to proactively focus on AI service model development companies and data centre markets. X330-equipped servers will support performance optimisation of software stacks based on open neural network exchange (ONNX), while AI inference platform software and software development tools will also be offered.
Compared to its X220 predecessor, the X330 inference NPU’s application range has been significantly expanded based on standard technology. It is an NPU that can be efficiently utilised in a broader range of fields and industries.
The X330 boasts more than four times the computational performance and more than twice the power efficiency of the existing X220 AI semiconductor. This represents roughly twice the computational performance and 1.3 times better power efficiency than competitors’ 5nm products launched in 2023.
The X330 has a built-in video codec and video post-processing IP to improve the processing speed of video-related programmes. Additionally, 4-channel 4K 60fps video input processing is possible through the built-in hardware IP.
The existing SAPEON X220 was the first in Korea to demonstrate excellent performance in BERT inference, a high-performance AI language model, and the new X330 achieved large language model implementation based on transformer architecture, which is the original technology underpinning ChatGPT.
Along with the recently released X330, SAPEON plans to introduce AI NPUs for high-performance edge devices such as IP (semiconductor design assets) for self-driving cars and CCTV.
Soojung Ryu, CEO of SAPEON said, “Since SAPEON launched the X220 – Korea’s first AI semiconductor for data centres – in 2020, we have completed verification in the market by providing a set of basic services and are continuously expanding our commercial service areas into fields such as automobiles, security, and media. Our strategy is to accelerate targeting AI service model development companies and data centre markets with the X330, which maximises the advantages of the X220. By increasing the utilisation of AI semiconductors in all industries and making advanced AI technology affordable to everyone, we aim to help create a society where everyone can enjoy the benefits of cutting-edge technological development.”
SAPEON plans to expand into related fields, applying the X330 to AI Infrastructure, which is the backbone of three key areas of SK Telecom (“SKT”) ’s AI Pyramid Strategy designed to accelerate the company’s transformation into a global AI company – AI Infrastructure, AI Transformation (AIX) and AI Service. Additionally, SAPEON and SKT will utilise AI semiconductors to establish voice phishing and spam/smishing prevention systems based on AI and big data analysis to protect customers from external security threats.