⋮    ⋮  

NVIDIA Reportedly Preparing Turing RTX 20 Series Refresh To Counter AMD Radeon Navi GPUs – Faster GDDR6 Memory Chips and Higher Clocks Expected

May 14, 2019
84Shares
Submit

NVIDIA may possibly be working on a refresh of their Turing GPUs based GeForce RTX 20 series lineup if rumors are to be believed. The refreshed RTX 20 series cards are being prepped in order for the company to compete against the AMD Radeon Navi GPUs which are expected to launch in the coming quarter for mainstream gamers.

NVIDIA Preps GeForce RTX 20 Series Refresh With Faster GDDR6 Memory and Higher Clocks, Aiming To Tackle The AMD Radeon Navi Lineup

The source of the rumor is RedGamingTech who report that their source has revealed that NVIDIA is working on a series of Turing based GeForce RTX 20 series refresh graphics cards that will come with faster GDDR6 memory chips. It is stated that the cards can feature higher clock speeds and a possible bump in core configuration but that’s mere speculation right now with the main highlight only being the memory speed bump that is acknowledged by the source. The reports of refreshed lineup come just weeks before AMD is going to announce their 7nm based Navi GPU lineup for the Radeon lineup so it’s possible that this is NVIDIA reacting to the recently leaked information on the Navi GPUs.

Related NVIDIA CEO Says It’s Crazy To Buy A GPU Without Ray Tracing In 2019, Implying GeForce RTX A Better Purchase Than AMD Radeon RX

Now while this is a rumor, we have to look back at similar things that NVIDIA has done in the past. We all remember the NVIDIA GeForce 10 series cards based on the Pascal GPU architecture. It was back in 2016 when NVIDIA unveiled their Pascal based GTX 1080 graphics card, the first to feature the GDDR5X memory interface for $599 US.

The card initially featured 10 Gbps memory chips but was upgraded with 11 Gbps memory after 11 months since its launch. That resulted in a bandwidth uplift of 352 GB/s from 320 GB/s. There were also price cuts offered on the pre-existing models that still featured 10 Gbps memory with the new price adjusted to $499 US. The NVIDIA GeForce GTX 1060 also received an upgrade of 9 Gbps chips (GDDR5) which offered a nice bandwidth bump over the 8 Gbps models.

Similarly, the price of the pre-existing models went down while the 9 Gbps models were available at the reference price. This move and the launch of NVIDIA’s flagship GTX 1080 Ti (of that time) happened before hype related to the AMD Radeon RX Vega series kicked up and similarly, now that hype around Navi is picking up, we are hearing news related to a new NVIDIA refresh.

Now that we have suggested that a refresh from NVIDIA is very much possible, it also needs to be checked whether the faster memory chips themselves that are being talked about actually exist or not. If you go over to the main GDDR6 memory providers, Samsung and Micron, product catalogs, you’d see that Micron isn’t offering any 16 Gbps solution at the moment although they have been far into developing their 16 Gbps memory chips.

Related NVIDIA Readies Another TU102 GPU Based GeForce RTX Graphics Card – Might Be The GeForce RTX 2080 Ti SUPER

Samsung on the other does indeed has two Dram variants listed for 16 Gbps. The 8Gb density dies are in production while the 16Gb dies are being sampled. Since NVIDIA relies on 8Gb dies and the far better implementation of Samsung dies over Micron, it is possible that the refreshed lineup may end up entirely using Samsung GDDR6 stock.

NVIDIA GeForce RTX/GTX "Turing" Family:

Graphics Card NameNVIDIA GeForce GTX 1650NVIDIA GeForce GTX 1660NVIDIA GeForce GTX 1660 TiNVIDIA GeForce RTX 2060NVIDIA GeForce RTX 2070NVIDIA GeForce RTX 2080NVIDIA GeForce RTX 2080 Ti
GPU ArchitectureTuring GPU (TU117)Turing GPU (TU116)Turing GPU (TU116)Turing GPU (TU106)Turing GPU (TU106)Turing GPU (TU104)Turing GPU (TU102)
Process12nm FNN12nm FNN12nm FNN12nm FNN12nm FNN12nm FNN12nm FNN
Die Size200mm2284mm2284mm2445mm2445mm2545mm2754mm2
Transistors4.7 Billion6.6 Billion6.6 Billion10.6 Billion10.6 Billion13.6 Billion18.6 Billion
CUDA Cores896 Cores1408 Cores1536 Cores1920 Cores2304 Cores2944 Cores4352 Cores
TMUs/ROPs56/3288/4896/48120/48144/64192/64288/96
GigaRaysN/AN/AN/A5 Giga Rays/s6 Giga Rays/s8 Giga Rays/s10 Giga Rays/s
Cache1.5 MB L2 Cache1.5 MB L2 Cache1.5 MB L2 Cache4 MB L2 Cache4 MB L2 Cache4 MB L2 Cache6 MB L2 Cache
Base Clock1485 MHz1530 MHz1500 MHz1365 MHz1410 MHz1515 MHz1350 MHz
Boost Clock1665 MHz1785 MHz1770 MHz1680 MHz1620 MHz
1710 MHz OC
1710 MHz
1800 MHz OC
1545 MHz
1635 MHz OC
Compute3.0 TFLOPs5.0 TFLOPs5.5 TFLOPs6.5 TFLOPs7.5 TFLOPs10.1 TFLOPs13.4 TFLOPs
MemoryUp To 4 GB GDDR5Up To 6 GB GDDR5Up To 6 GB GDDR6Up To 6 GB GDDR6Up To 8 GB GDDR6Up To 8 GB GDDR6Up To 11 GB GDDR6
Memory Speed8.00 Gbps8.00 Gbps12.00 Gbps14.00 Gbps14.00 Gbps14.00 Gbps14.00 Gbps
Memory Interface128-bit192-bit192-bit192-bit256-bit256-bit352-bit
Memory Bandwidth128 GB/s192 GB/s288 GB/s336 GB/s448 GB/s448 GB/s616 GB/s
Power ConnectorsN/A8 Pin8 Pin8 Pin8 Pin8+8 Pin8+8 Pin
TDP75W120W120W160W185W (Founders)
175W (Reference)
225W (Founders)
215W (Reference)
260W (Founders)
250W (Reference)
Starting Price$149 US$219 US$279 US$349 US$499 US$699 US$999 US
Price (Founders Edition)$149 US$219 US$279 US$349 US$599 US$799 US$1,199 US
LaunchApril 2019March 2019February 2019January 2019October 2018September 2018September 2018

Now that the pricing and memory availability aspect is covered, we now have to talk about the specifications. The rumor only talks about the new GDDR6 memory chips as the main reason to which NVIDIA is providing a refresh but there could also be a spec bump. No doubt that GeForce RTX 20 series will get a nice bump in bandwidth with the new chips with RTX 2070, RTX 2080 going for 512 GB/s over 448 GB/s and RTX 2080 Ti going for at least 704 GB/s.

The price cuts would also be something noteworthy but we have seen reports of NVIDIA ending production of non-A GPU dies and offering their A revision dies across all RTX cards. The RTX 20 series with A-dies offer a better overclocking environment and higher clock speeds and it is possible that the new refresh cards may end up being factory overclocked even higher than the current reference models. But this much is just speculation at the moment.

GPU Memory Technology Updates 2019

Graphics Card NameMemory TechnologyMemory SpeedMemory BusMemory BandwidthRelease
NVIDIA GeForce GTX 1080GDDR5X10.0 Gbps256-bit320 GB/s2016
NVIDIA GeForce RTX 2080GDDR614.0 Gbps256-bit448 GB/s2018
NVIDIA GeForce RTX 2080GDDR616.0 Gbps256-bit512 GB/s2019
AMD Radeon RX Vega 64HBM21.9 Gbps2048-bit483 GB/s2017
AMD Radeon R9 Fury XHBM11.0 Gbps4096-bit512 GB/s2015
NVIDIA Titan XpGDDR5X11.4 Gbps384-bit547 GB/s2017
NVIDIA Titan VHBM21.7 Gbps3072-bit652.8 GB/s2017
NVIDIA GeForce RTX 2080 TiGDDR614.0 Gbps352-bit616 GB/s2018
NVIDIA GeForce RTX 2080 TiGDDR616.0 Gbps352-bit704 GB/s2019
NVIDIA Tesla P100HBM21.4 Gbps4096-bit720 GB/s2016
NVIDIA Tesla V100HBM21.7 Gbps4096-bit901 GB/s2017

In the end, only time would tell if this is true or not as the likely announcement date of this lineup would be Computex 2019 which is two weeks from now. We also don’t know if only the RTX cards would be getting the updated design or the GeForce 16 series too but given that the 16 series is still a very fresh launch, I believe that the refresh would be kept exclusive to the RTX 20 series.

Will you be upgrading to the faster 16 Gbps models if you already own a GeForce RTX 20 series card?

Products mentioned in this post

GTX 1060
GTX 1060
USD 449
GTX 1080
GTX 1080
USD 879
RTX 2070
RTX 2070
USD 498

The links above are affiliate links. As an Amazon Associate, Wccftech.com may earn from qualifying purchases.

Submit