With AI, HPC and networking memory demand growing there is a need for SRAM/Logic disintegration allowing the implementation of separate SRAM and Logic at the most efficient process nodes.
Layers of CPU and SRAM (Last Level Cache, packet buffers) dies can be assembled over and under interconnect/IO dies using TSMC's 3DFabric packaging technology and these expandable SRAM and modular computing applications can be enabled by GUC GLink-3D high bandwidth, low latency, low power, and point-to-multipoint interface between 3D stacked dies.
As a result, CPUs, SRAMs, Interconnects, and I/Os (SerDes, HBM, DDR) can be implemented in more efficient process nodes, while different die combinations can be assembled to address different market segments. At boot time, assembled SRAM and CPU dies are identified, unique die IDs are distributed, available memory space and computing resources are defined and a point-to-multipoint GLink-3D interface to the stacked dies is enabled.
Using TSMC's 3DFabric SoIC platform technology more efficient connectivity is now possible and GLink-3D has been able to achieve six times higher bandwidth/area density, six times lower latency and twice lower power consumption than best-in-class 2.5D interface GLink-2.0 (it was taped out in Dec 2020). Several 3D die stacks can be assembled using CoWoS and InFO_oS, interconnected using GLink-2.5D links and combined with HBM memories.
"GLink-3D is a new addition to a rich portfolio of best-in-class and silicon-proven HBM2E/3 PHY/Controller and GLink-2.5D IPs. CoWoS, InFO_oS, 3DIC expertise, package design, electrical and thermal simulations, DFT and production testing under one GUC roof provide our ASIC customers with quick design cycles, fast bring up and production ramp up." explained Dr. Ken Chen, president of GUC.
"3D die stacking technology will start a revolution in the way we design HPC, AI and Network Processors. Die-to-die interface is not limited any more to the die boundary, it can be located exactly where processors need to connect to SRAM and additional CPUs.
"3DFabric and GLink-3D pave way to the processors of the future, combining huge and scalable processing power with vast, high bandwidth and low latency memory, when every component is implemented using the most efficient process node." added Igor Elkanovich, CTO of GUC.