SRAM Compute-in-Memory

Cross-cuts: Compute
last updated 2026-06-14
Charge-Domain ComputeMemcapacitorADC Bottleneck (analog in-memory compute)SRAMSRAM Comput…

Why SRAM

The cost is density and volatility:

The density limit is the crux: if the whole model has to fit in on-die SRAM, SRAM-CIM is capped at model sizes that fit. This is exactly the bet Fractile is making (DRAM-less, model-in-SRAM) and exactly where the scepticism sits.

Analog vs digital SRAM-CIM

Where it sits against memcapacitor

SRAM-CIM and memcapacitor are the two charge-friendly CIM bets, and they trade off cleanly:

The honest read: SRAM-CIM is the safer, better-funded path to volume; memcapacitor is the higher-ceiling, higher-risk path that wins only if 3D monolithic growth yields. See Memcapacitor Compute Memory Bound Ai for the device-class survival question.

Related concepts

Frontier questions