Pope: TPUv1 announcement catalyzed the 2016-2017 AI chip startup wave
Reiner Pope · Reiner Pope of MatX on accelerating AI with transformer-optimized chips · Feb 26, 2026 · at 1:37
Reiner Pope, co-founder of MatX and former Google TPU architect, discusses how Google's TPUv1 announcement sparked the initial wave of specialized AI silicon startups.
0:00 / 0:12exact quote · 12.5s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“TPUv one was announced in 2016, I think. That was what actually kind of led to the creation of all of those 2016, 20 17 startups. So Cerebus, Gronk, Graphcore, SambaNova, all of those.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Reiner Pope
Pope: Groq and Cerebras are uncompetitive on dollars per token
“And then there's the Grok and Cerebris that are much better at latency because they've got this the SRAM, weights are in SRAM very low latency. The problem is, and the challenge when you go to a Grok or a Cerebris system is that the throughput you get there, i…”
Pope: Google completely stopped publishing its AI research around 2022
“In twenty-twenty-two was about the time when just Google completely stopped publishing its research. And so all the good papers are from before that as a result.”
Pope: Model parameter counts will grow much faster than context lengths
“Really tied into this context thing, I think the context size will stay ballpark the same way it is, maybe a few times larger. But the parameter count will go up. Like, parameter count should grow much, much faster than context length, actually, just because o…”
Pope: The best AI inference chip is also a great training chip
“I think the best inference chip today will be a train, a really good training chip as well.”
Pope: MatX combines SRAM and HBM for cheap, low-latency AI chips
“It is actually possible to do both in the same chip. You, it's kind of an obvious thing. You say you take the HPM, you take the SRAM, put them together in the same chip, you put the weights in SRAM, and you put the all of the inference data in HPM. That is wha…”