Micron Announces Its Initial Launch Partner Status for NVIDIA RTX 20-Series GDDR6 Implementation

[Raevenlord]

Memory subsystems are an important part of graphics workloads, and both AMD and NVIDIA have always been looking to cross the cutting-edge of tech in both GPU production and memory fabrication technologies. AMD has been hitching itself to the HBM bandwagon with much more fervor than NVIDIA, albeit with somewhat lukewarm results - at least from a consumer, gaming GPU perspective. NVIDIA has been more cautious: lock HBM's higher costs and lower availability to higher-margin products that can leverage the additional bandwidth, and leave GDDR to muscle its way through consumer products - a strategy that has likely helped in keeping BOM costs for its graphics cards relatively low.

As it stands, Micron was the only company with both the roadmap and production volume to be NVIDIA's partner in launching the RTX 20-series, with products above (and including) the GTX 2070 all carrying the new high-performance memory subsystem. Micron has already announced GDDR6 memory as a product back in 2017, with sampling by the beginning of 2018 and mass volume production by June - just enough time to spool up a nice inventory for new, shiny graphics cards to come out in September. Of course, this ramp-up and initial Micron leadership doesn't mean they will be the only suppliers for NVIDIA - however, it's safe to say they'll be the most relevant one for at least a good while.



View at TechPowerUp Main Site

 

[coonbro]

I remember when micron/[Elpida] was not the memory you wanted to get in a card over Samsung or Hynix , boy times have changed

 

[randomUser]

Wheres the comparison to the HBM2?

 

[lukesky]

I remember when micron/[Elpida] was not the memory you wanted to get in a card over Samsung or Hynix , boy times have changed

I suspect Samsung/Hynix does not have quantity for Geforce RTX. Samsung produces GDDR6 for Quadro. From memory, GTX 1070 Samsung GDDR5 OC furthest, followed by Hynix, then Micron.

 

[JalleR]

HMB is 512GB/s

I like they are using an AGP card to illustrate

 

[Vayra86]

I remember when micron/[Elpida] was not the memory you wanted to get in a card over Samsung or Hynix , boy times have changed

That wasn't long ago, even Pascal's 1070's were preferable with Samsung chips, they reliably clocked higher.

 

[coonbro]

funny when the 10 series came out I seen micron was the memory of choice by the card venders , but getting a Samsung memory card was great luck of the draw card . [??? ]

seemed like now Hynix and or Samsung are the fill in memory when the micron ' are in short supply at the vid card factory

though the overclocking head room of 10 series was noy so great anyway like I said between a evga sc and there best oc'ed classy was only 17 MHz . [as far as factory ] use to be like 90 + between a sc and classy on older series

maybe now it don't matter what memory is in it cause its just at or near all your likely to get out of it at factory specs anyway .

seems NVidia wants to limit ant user oc'ing more and more each new series release to what you get per series line factory oc'ed out of the box . [opinion]