Samsung is still working on its in-house Mach-1 AI inferencing chip. CEO Kyung Kye-hyun, who is in charge of the chip business, teased a second-gen Mach-2 AI accelerator in a new Instagram post.
Samsung Electronics CEO Kyung Kye-hyun said: "Client interest in inference-committed Mach-1 is increasing. Some of the clients want to use Mach in large-scale applications with more than 1 trillion parameters, which justifies the faster-than-expected development of Mach-2. We should get down to preparation".
The new Mach-1 AI accelerator was announced at Samsung Electronics' recent shareholder meeting, but few details were released: all we know is that it will be used for AI inferencing and will launch in early 2025. Samsung recently formed a new HBM team focused on increasing productivity and quality to ensure HBM leadership against South Korean rival SK hynix.
- Read more: Samsung forms dedicated 'HBM team' to boost AI memory chip production
- Read more: South Korean search giant Naver orders $752 million of AI chips from Samsung
Samsung was also recently the first to announce the development of new 12-layer HBM3E memory earlier this year, with production-ready for later this year. SK hynix and Micron also have HBM3E memory on the way, but they're only pumping out 8-layer HBM3E memory for now.
As for Samsung's new Mach-1, it's a new system-on-chip (SoC) that reduces the bottleneck between GPUs and HBM memory chips, while its next-generation model of the inference-committed AI accelerator -- Mach-2 -- is in development. Kyung said on Friday: "We need to accelerate the development of Mach-2, for which clients are showing strong interest".