SK Hynix stated that it had began quantity manufacturing of its HBM3E reminiscence and would provide it to a buyer in late March. The South Korean firm would be the second DRAM producer to announce mass manufacturing of HBM3E, so the market of ultra-high-performance reminiscence may have some competitors, which is nice for corporations that plan to make use of HBM3E.
Based on specs, SK Hynix’s HBM3E recognized good stack dies (KGSDs) function a 9.2 GT/s information switch fee, a 1024-bit interface, and a bandwidth of 1.18 TB/s, which is massively larger than the 6.4 GT/s and 819 GB/s provided by HBM3. The corporate doesn’t say whether or not it mass produces 8Hi 24GB HBM3E reminiscence modules or 12Hi 36GB HBM3E gadgets, however it’ll possible start its HBM3E ramp from lower-capacity merchandise as they’re simpler to make.
We already know that SK Hynix’s HBM3E stacks make use of the corporate’s superior Mass Reflow Molded Underfill (MR-RUF) expertise, which guarantees to cut back warmth dissipation by 10%. This expertise entails using an enhanced underfill between DRAM layers, which not solely improves warmth dissipation but additionally reduces the thickness of HBM stacks. In consequence, 12-Hello HBM stacks may be constructed which can be the identical peak as 8-Hello modules. Nonetheless, this doesn’t essentially suggest that the stacks at the moment in mass manufacturing are 12-Hello HBM3E stacks.
Though the reminiscence maker doesn’t formally affirm this, SK Hynix’s 24GB HBM3E stacks will arrive simply in time to deal with Nvidia’s H200 GPU for synthetic intelligence and high-performance computing functions.
“With the success story of the HBM enterprise and the sturdy partnership with clients that it has constructed for years, SK Hynix will cement its place as the overall AI reminiscence supplier,” stated Sungsoo Ryu, Head of HBM enterprise at SK Hynix. In consequence, Nvidia will be capable of use HBM3E reminiscence from each Micron and SK Hynix.
In the meantime, AMD just lately confirmed that it was trying ahead to increasing its Intuition MI300-series lineup for AI and HPC functions with higher-performance reminiscence configurations, so SK Hynix’s HBM3E reminiscence may be used for this.
Supply: SK Hynix
