Product & chips · Aug 31, 2026

Sixteen times the capacity per stack in flash memory — and dropping it straight in starves the GPU. Oxford proposes the compromise.

Chips & semiconductors · This week (published August 30)

From the Aug 31, 2026 daily brief

A research team at the University of Oxford published a paper: at comparable bandwidth, high-bandwidth flash memory holds 16 times the capacity per stack of the high-bandwidth memory in use today. That looks like the answer to inference workloads that cannot fit a large model in memory. Swapping it straight in drags performance down badly, because the tail latency of flash leaves the GPU's scheduler waiting. Their approach mixes the two kinds of memory and uses prediction to keep the slow half off the critical path (Semiconductor Engineering, 08-30; the paper, IEEE Computer Architecture Letters, August 2026). Why it is worth keeping: items 1 and 2 of the main line are both about the money in inference, and the physical floor under that cost is whether the model fits in memory. Capacity at a sixteenth of the cost is a big number, and what you pay for it is latency. Nobody has finished that calculation, and until someone does, every argument that memory is about to get cheaper is missing half its case. The signal that it has been finished is a published latency measurement of the mixed architecture under a real inference load, rather than one more capacity multiple.

More in this section

Product & chips Sep 10, 2026 1 sources
Customers of chip-design tool vendors have started capping tokens engineer by engineer — and a year ago nobody cared what that line cost.
Product leaders from five electronic design automation and AI chip-design tool vendors sai…
Product & chips Sep 10, 2026 1 sources
The new flagship's enterprise edition went live with its first published prices, and its own account of the mechanism doubles as an audit cost.
OpenAI's enterprise announcement on September 9 recast this model from "the smartest model…
Product & chips Sep 9, 2026 1 sources
OpenAI says its first in-house inference chip delivers 1.5 to 1.9 times the throughput per watt of "the commercial systems tested" — and does not say which systems those were.
A document signed by CFO Sarah Friar gives the first numbers for Jalapeño, OpenAI's first …
Product & chips Sep 9, 2026 1 sources
Meta launched a personal AI agent called Muse, and the part worth recording is not what it does but that a payment network has written terms for a non-human buyer for the first time.
Meta introduced Muse on September 8: it runs on a cloud virtual machine dedicated to each …

Sixteen times the capacity per stack in flash memory — and dropping it straight in starves the GPU. Oxford proposes the compromise.

Subscribe free — first issue lands tomorrow morning

More in this section

Customers of chip-design tool vendors have started capping tokens engineer by engineer — and a year ago nobody cared what that line cost.

The new flagship's enterprise edition went live with its first published prices, and its own account of the mechanism doubles as an audit cost.

OpenAI says its first in-house inference chip delivers 1.5 to 1.9 times the throughput per watt of "the commercial systems tested" — and does not say which systems those were.

Meta launched a personal AI agent called Muse, and the part worth recording is not what it does but that a payment network has written terms for a non-human buyer for the first time.