AMD’s 3D Infinity Cache could be its secret weapon in its fight against Nvidia

AMD could be set to announce its 3D V-Cache technology to its Infinity Cache architecture in the next-gen RDNA 3 GPUs anticipated around next year, and it could give Nvidia some grave heartburn.

Initial revealed all through AMD’s Computex 2021 keynote back in June, 3D chipset technology is AMD’s newest architecture modernisation, which exploits upright space on a silicon die to fit more component integrated circuit technology into the similar parallel magnitudes.

3D V-Cache, or upright cache, is the firm’s first recognised application of the tech, which it has previously executed on a Ryzen 9 5950X processor prototype to enhance gameplay performance which is verified all through June keynote.

By loading cache vertically, as TweakTown notes, a processor can have admittance to suggestively more cache memory which can intensely progress performance, so it would be a noticeable phase to contrivance it in the firm’s next-generation GPU construction, RDNA 3.

That seems to be the strategy, conferring to Twitter leaker Greymon55, who mysteriously tweeted out “3D IFC” in the early morning hours of November 8. Approved, a two-word tweet isn’t gospel, but it’s practically undoubtedly on point. AMD’s Big Navi GPUs aid power some of the finest graphics cards on the market right now, but the addition of 3D V-Cache to mix would be a very vast deal.


Definitely, AMD 3D Infinity Cache is coming to RDNA 3. Why wouldn’t it?

Infinity Cache finished a bit of squish when AMD announced it with Big Navi since it permits upgraded remembrance bandwidth deprived of having to trust on a more power-crazy reminiscence 512-bit bus, which would be double the prevailing 256-bit bus.

Infinity cache is proficient in enhancing actual memory bandwidth to be slightly competitive with Nvidia’s higher bus capacity with its higher-end RTX cards like the 320-bit bus in the RTX 3080 and the 384-bit bus in the RTX 3090.

Merging this technology with a 3D V-Cache architecture could make a much more dramatic modification. Having a vividly extended cache for the GPU could do more than counterbalance the broader bus in an Nvidia card.

If an extended 3D V-Cache operated the identical presentation developments of AMD’s Infinity Cache, then you would be speaking about significantly quicker data admittance with fewer page culpabilities and far fewer fetch cycles to VRAM.

Having a stripper bus isn’t a delinquent if you never actually need to use it, and if an RDNA 3 GPU can keep fetching from a suggestively extended V-Cache while an Nvidia card has to fetch from VRAM much more often, it could be a game-changing performance boost for AMD’s next-gen graphics processors.

Also Read: Nvidia RTX 3080 Ti GPU spotted in a leaked gaming laptop benchmark


Leave a Comment