Real Alpha
Try Pro free

Uncapped · 3 min · Sep 15, 2026

Cerebras is developing memory and optical links alongside compute

Andrew Feldman describes work on HBM stacked onto an SRAM-based wafer and on optical switching at the wafer. Both target bottlenecks in memory access and moving results, not just raw compute.

Andrew Feldman

Andrew Feldman is cofounder and CEO of Cerebras Systems.

Co-founded and leads Cerebras Systems, whose wafer-scale engine is the largest processor in computing history.

  • Jack Altman, Host · General partner, Benchmark

    Co-founded Lattice and ran it until 2023, then started his fund, Alt Capital.

About this segment

Andrew Feldman describes work on HBM stacked onto an SRAM-based wafer and on optical switching at the wafer. Both target bottlenecks in memory access and moving results, not just raw compute.

From “Andrew Feldman on Building Cerebras and the Future of Chips | Ep. 57”, Sep 15, 2026. Watch the full episode

“And what this does is it enables HBM to behave like SRAM, which is exactly what everybody wants. You get the capacity of HBM and the speed of SRAM”
Andrew Feldmanat 14:47 · Uncapped14:47

Takeaways

  1. Cerebras is exploring HBM on an SRAM-based wafer.
  2. The goal is HBM capacity with SRAM-like speed.
  3. Optical wafer stacking aims to move results faster from compute.

In this episode

Full episode
  1. 4:09Attacking Goliath requires a radically better productPro pick 5:39
  2. 9:37Failure analysis kept Cerebras going through 18 months of setbacks3:29
  3. 16:13Chip fabs are a rare, tightly coupled supply chain6:53
  4. 43:57Data center delivery depends on power gear and site readiness6:05
  5. 51:57Faster inference can open new markets and increase throughput3:26
  6. 55:12Nvidia's long fight as a public company shaped its grit2:25
  7. 29:00Cerebras made architectural choices to adapt as AI changed4:15

  8. 12:55Cerebras is developing memory and optical links alongside compute3:07

Up next · The Pragmatic EngineerThe harness fills model gaps until training catches upPro pick 4:45

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

  1. 13:01

    and then everything around that, the packaging and cooling and powering it, all these things. but you know when you look at the r&d envelope that you have going forward over the next five years i know there's like things you're excited about but like where do you take like where do you take this like giant thing so what could be the next wafer scale innovation i i think I think if you simplify what we build down to its most fundamental elements, a computer is built of three things.

  2. 13:41

    We do calculations, we store the results, and then we move the results to where they're useful. So we build a core that does the calculation. We use memory, and we move data to and from memory, where we store the results. And then we have I.O., and that's how we ship the results to somewhere where it's useful. I think if you're in the computer business like we are for AI, you better be working on all three.

  3. 14:10

    You're going to be thinking about how to make your course faster, how to make them tuned for AI, but general enough to to withstand the innovation happening in AI you better be thinking about memory and both capacity how much you can store and how fast you can get data on and off it and then you got to be thinking about how you get the results off your chip and somewhere where they're useful and that's your IO and so we're working on all three of those and we have programs with the U.S. government already, big programs where we're thinking about how to stack memory, right, how to put HBM onto an SRAM-based wafer. And what this does is it enables HBM to behave like SRAM, which is exactly what everybody wants. You get the capacity of HBM and the speed of SRAM, right we're working on on uh optical wafer stacking so you put an optical switch onto a

  4. 15:14

    wafer this would change the world um you know jack dangara said and he's sort of one of the the pioneers in in big computing he said we've we've been better at making flops and moving flops right and that that's that's the io part and so thinking about how to how to solve that problem by bringing optical switching smack up against compute is something that we also have large government contracts for and we're enormously excited about so you know you got to get faster you got to find ways to store more and get to memory faster and you got to find ways to move that move those results at ten hundred a thousand x faster to where they're useful