[addaon]

> SRAM has virtually stopped scaling in new nodes.

But there are several 1T memories that are still scaling, more or less — eDRAM, MRAM, etc. Is there anything preventing their general architecture from moving to a 1T technology once the density advantages outweigh the need for pipelining to hide access time?

[aurareturn]

I’m pretty sure that HBM4 can be 20-30x faster in terms of bandwidth than eDRAM. That makes eDRAM not an option for AI workloads since bandwidth is the main bottleneck.

[addaon]

HBM4 is limited to a few thousand bits of width per stack. eDRAM bandwidth scales with chip area. A full-wafer chip could have astonishing bandwidth.