Follow

new moore's law: every CPU will become twice as slow every two years from all the predictive branching mitigations

@devurandom shouldn't have thrown away my first Celeron! computer from 22 years ago, so I'd have a nice comparison point

Branch Predictor: The New Generation 

@devurandom, no stress, we'll add a new generation of BPs, powered by new on-chip statistics co-processors¹, backed by a linked list E2EE³ memory², with optional distribution, opt-out, of course.

--
¹) AI in Software-Defined Silicon As A Service, of course.

²) with PoS not that PoW 💩. And all this for better performance on cold boots and offsite backups, of course.

³) E2EE is army-grade, developed in-house, we can't tell you more, of course.

Branch Predictor: The New Generation 

@devurandom, it seems that I'm late to the game, this was first proposed in 2001, and now: "The AMD Ryzen multi-core processor's Infinity Fabric and the Samsung Exynos processor include a perceptron-based neural branch predictor."

But we're still missing the software-defined silicone subscription and that distributed linked-list storage for improved performance after a cold boot.

Now, seriously, how can one trust those?

en.wikipedia.org/wiki/Branch_p

Sign in to participate in the conversation
Cybrespace

cybrespace: the social hub of the information superhighway jack in to the mastodon fediverse today and surf the dataflow through our cybrepunk, slightly glitchy web portal support us on patreon or liberapay!