4 Comments
User's avatar
Rs's avatar
Feb 28Edited

Great piece. If there is one master clock what does it mean for sitm?

Ben Pouladian's avatar

SiTime actually benefits here. A master clock architecture raises the bar on timing precision. You still need ultra-low-jitter reference oscillators at the source. Higher requirements = tailwind for SITM.​​​​​​​​​​​​​​​​

Andy J's avatar

Thanks Ben for the insights! Great piece as always!

I have a quick question about completely bypassing HBM to only use SRAM: is the capability for SRAM scalable enough for the ever growing context window and model size/weights?

Ben Pouladian's avatar

Not for everything and that’s the point. Huge training models stay on GPUs with HBM. This targets high-volume inference with models co-designed to fit. SSM hybrids keep state fixed, 3D stacking pushes SRAM capacity each gen. Two lanes, each doing what it does best.​​​​​​​​​​​​​​​​