GDDR6 Memory Being Developed by Micron, Coming to Mid-End Graphic Cards in 2022 - Alleges Report [Updated]

Update: Micron contacted us before long subsequently this article was published and has debunked the GDDR6 story. Looks like Fudzilla got this one wrong. The company is only working on GDDR5X which is intended to provide significant performance improvements to designs that are currently using GDDR5, therefore giving organisation designers the pick of delivering enhanced performance without dramatically altering current architectures.

The next generation of graphic cards volition be getting a big boost in raw processing ability thanks to the bound to FinFET engineering. However, equally any enthusiast knows, memory and bandwidth tin can chop-chop become a very undesirable bottleneck. To solve this problem, AMD and JEDEC introduced HBM 1.0 to the market this year and the much more than flexible HBM two.0 standard is expected to debut adjacent year in flagship products. Only what well-nigh the middle end lineup? The answer to that (according to an exclusive report by Fudzilla), is an upcoming GDDR6 standard.

AMD HBM Die TSV X-Ray ChipWorks 2 A die shot and external assay of the Fiji die past Chipworks. @ChipWorks.

GDDR6 retentivity allegedly landing in 2022, developed by Micron

At present here is the thing, reports of the upcoming GDDR6 standard accept been nowadays every bit far back as 2022 (example from VR Zone here). There are also a few oddities in what Fudzilla is reporting, which I would like to point out here for clarity's sake. Firstly, the source is attributing the GDDR6 standard to Micron, while in actuality GDDR is a JEDEC standard and no such verification for GDDR6 currently exists. This new initiative also seems slightly disruptive, considering Micron is already working on a JEDEC canonical GDDR5X standard which will offer around 2x the bandwidth of GDDR5.

GDDR5X is based on the GDDR5 standard and primarily doubles the prefetch of the standard while preserving "most of the command protocols of GDDR5". What that means is that while the bandwidth has been doubled, it is not, strictly speaking an improvement of the GDDR5 standard, rather a new branch of the aforementioned and arguably a completely new technology (reverse to what the 'GDDR'10 proper name might suggest). One of the examples given is DDR3 to DDR4, which also happens to be a proficient estimate analogy to remember of the GDDR5 to GDDR5X jump. Unfortunately, we do not, at this point know what difference, if any, there is between GDDR6 and GDDR5X. Micron GDDR5X Memory Standard

The source cited "internal sources" for the exclusive report, then it is possible that GDDR6 is actually GDDR5X rebranded (since the come from the same company). It is also possible (not probable!) that Micron is working on ii different standard, in collaboration with JEDEC, namely GDDR5X and GDDR6 just that seems unlikely to me. At whatever rate, GDDR5 has evolved from its 60nm debut in 2007 to a much more sleek and efficient 20nm version in 2022. I wouldn't be surprised if JEDEC finally decided to define the GDDR6 standard at the 20nm process in 2022. This transition to a lower node allows much higher clocks and low operating voltages – something that was not possible in the early on days of the standard.

In any case, the use of GDDR5X or GDDR6 remains a question in probability. The unproblematic fact of affair is that most eye order graphic cards practice non need more bandwidth than what the modern form of GDDR5 can already provide. And since all concerned parties accept already achieved economies of scale with GDDR5 there would be very little reason to shift to a make new standard such equally GDDR5X/GDDR6 since HBM 2.0 volition more than than cater for the loftier end stuff, where bandwidth can quickly go an actual issue.

That said, high bandwidth retention in economical packaging (as low as 2GB HBM) will also be arriving by 2022. Companies similar SK Hynix have been getting over their initial learning curve and yields are getting more mature by the calendar month. Before long enough, we will be able to get the low end HBM (retentiveness) in mobile devices such equally laptops where the energy efficiency of the standard will be able to do wonders. So fifty-fifty in the middle order, the decision of companies shifting to GDDR5X/GDDR6 remains a dubious proposition at best.