Samsung goes after Nvidia’s billions with new AI chip – Mach-1 accelerator combines CPU, GPU and memory to tackle inference tasks, but not training
Samsung is reportedly planning to launch its own AI accelerator chip, the ‘Mach-1’, in a bid to challenge Nvidia’s dominance in the AI semiconductor market.
The new chip, which will likely focus on low-power edge applications, will go into production at the end of this year and make its debut in early 2025, according to the Seoul Economic Journal.
The announcement was made during the company’s 55th annual shareholders’ meeting. Samsung Semiconductor CEO Kye Hyun Kyung said the chip design has passed technology validation on FPGAs and SoC finalization is underway.
Completely new type of AGI semiconductor
The Mach-1 accelerator is designed to tackle AI inference tasks and will reportedly overcome the bottlenecks found in existing AI accelerators when transferring data between the GPU and memory. This often results in slower data transfer speeds and reduced energy efficiency.
The Mach-1 is reportedly a “lightweight” AI chip, using low-power (LP) memory instead of the expensive HBM typically used in AI semiconductors.
The move is widely seen as Samsung’s attempt to regain its position as the world’s largest semiconductor company by fighting back against Nvidia, which completely dominates the AI chip market and has seen its shares soar in recent months, making it the third most valuable company in the world. behind Microsoft and Apple.
While the South Korean tech giant currently has no plans to challenge Nvidia’s H100, B100 and B200 AI powerhouses, Seoul Economic Journal reports that Samsung has established an AGI computing laboratory in Silicon Valley to accelerate the development of AI semiconductors. Kyung stated that the specialized laboratory is “working to create an entirely new type of semiconductor, designed to meet the processing requirements of future AGI systems.”