Tech »  Topic »  However, the thermal simulations reveal severe challenges for the 3D HBM-on-GPU design.

However, the thermal simulations reveal severe challenges for the 3D HBM-on-GPU design.


Imec presented an examination of a 3D HBM-on-GPU design aimed at increasing compute density for demanding AI workloads at the 2025 IEEE International Electron Devices Meeting (IEDM).

The thermal system-technology co-optimization approach places four high-bandwidth memory stacks directly above a GPU through microbump connections.

Each stack consists of twelve hybrid-bonded DRAM dies, and cooling is applied on top of the HBMs.

'4kW is certainly possible, but it can go much higher': Microsoft-backed startup could dissipate 10kW GPUs, its founder confirmsAmbitious Chinese GPU vendor debuts liquid-cooled, single-slot, dual GPU card with 48GB RAM and the ability to get four of them in a system - sadly, it's the Intel Arc Pro B60The AI race explodes as HPE deploys AMD’s Helios racks, crushing limits with Venice CPUs and insane GPU density

Thermal mitigation attempts and performance trade-offs

The solution applies power maps derived from industry-relevant workloads to test how ...


Copyright of this story solely belongs to techradar.com . To see the full text click HERE