⋮    ⋮  

Nvidia GTX 1080 Ti Launching In 2017 With Titan X Performance At A Much Lower Price

Author Photo
Sep 28, 2016
28Shares
Submit

Nvidia’s upcoming GTX 1080 Ti graphics beast is reportedly launching in 2017 featuring the company’s high-end GP102 GPU. Packing 3328 CUDA cores, a 1.6Ghz boost clock, 12GB of GDDR5X memory & an impressive 10.8 TFLOPs of graphics horsepower. The new GeForce GTX 1080 Ti is set to deliver Titan X Pascal flagship performance at a significantly lower price. This latest leak comes from China where effectively all of Nvidia’s channel partners manufacture their graphics cards.

Nvidia GeForce GTX 1080 Ti, A Price Cut Titan X Pascal For The Masses

Just a couple of weeks ago we reported that Nvidia’s announcement that its CEO Jen-Hsun Huang was going to “break news” regarding a new gaming product. A couple of weeks before that we reported on the alleged GTX 1080 Ti specifications that surfaced on the web. Which indicated that the 1080 Ti will, for all intents and purposes, render the GTX Titan X Pascal effectively obsolete. Delivering nearly identical performance with an identical memory capacity at a significantly lower price.

The GTX 1080 Ti will be powered by a slightly cut back variant of the GP102 GPU. 52 out of a total of 60 SMs are enabled with the remainder 8 SMs lasered off. This is only four SMs fewer than the GP102 variant used to power the GTX Titan X Pascal, Nvidia’s fastest graphics card to date. Although the GTX 1080 Ti will come with fewer functional CUDA cores than its bigger brother, it will actually perform just as well.

Cutting a few more SMs from GP102 has more to do with improving yields rather than roping in performance. In fact, to make up for the cut SMs Nvidia has reportedly pushed the clock speeds up significantly compared to the Titan X Pascal. The result is 10.8 teraflops of FP32 compute compared to the Titan X’s 11. Furthermore, because Nvidia is allowing its partners to go wild with designs we’re bound to see factory overclocked 1080 Ti’s that outperform the Titan X right out of the box. Very much exactly like what we had seen with the GTX 980 Ti & the original Titan X last year.

WCCFtech GTX TItan X Pascal GTX 1080 Ti
(rumored specs)
GTX 1080
Process 16nm 16nm 16nm
Transistors 12 Billion 12 Billion 7.2 Billion
Die Size 471mm² 471mm² 314mm²
Memory 12GB GDDR5X 12GB GDDR5X 8GB GDDR5X
Memory Speed 10Gbps 10Gbps 10Gbps
Memory Interface 384-bit 384-bit 256-bit
Memory Bandwidth 480GB/s 480GB/s 320GB/s
CUDA Cores 3584 3328 2560
Base Clock 1417 1503 1607
Boost Clock 1530 1623 1730
Compute 11 TFLOPS 10.8 TFLOPS 9 TFLOPS
TDP 250W 250W 180W

Nvidia GTX 1080 Ti Specs – 3328 CUDA Cores, 12GB GDDR5X, 1.6Ghz Boost Clock & 250W TDP

At the heart of the GTX 1080 Ti is Nvidia’s flagship gaming graphics processing unit, code named GP102.  In terms of compute throughput & resources, GP102 has exactly 50% more of everything compared to GP104, the GPU that powers the GTX 1080 and GTX 1070 graphics cards. We’re talking 50% more CUDA cores, 50% more TMUs & ROPs, 50% larger cache & 50% wider memory interface. It also happens to be exactly 50% larger than the 314mm² GP104.

Nvidia GeForce GTX 1080 Ti Block Diagram WatermarkedNvidia GeForce GTX 1080 Ti GP102 Block Diagram

This is a huge 471mm² chip with 12 billion transistors. A whopping 66% increase in transistor count compared to the 7.2 Billion of GP104. Which is actually very interesting, because it’s not clear at all as to why Nvidia needed to increase the transistor count by 66% for a 50% increase in resources. And it’s definitely not reflected in the die area. Since GP102, as we had just mentioned above, is exactly 50% larger than GP104.

For a more in-depth look at the Pascal architecture and what it’s capable of you should check out our Pascal architecture breakdown article.

Nvidia GeForce GTX 1080 Ti Rumored Specs:

  • GPU : GP102
  • Process : TSMC 16FF
  • Die Size : 471mm²
  • Transistors : 12 Billion
  • SMs : 52
  • CUDA Cores : 3328
  • Core Clock : ~1.5Ghz
  • Boost Clock : ~1.6Ghz
  • Peak FP32 Compute : 10.8 TFLOPs
  • Memory Interface : 384bit
  • Memory : 12GB GDDR5X
  • Bandwidth : 480GB/s
  • TDP – 250W

The card will feature a 12 gigabyte configuration of GDDR5X 10Gbps memory running across a 384bit memory interface. Yielding a massive 480GB/s of memory bandwidth. The card’s core clock is around 1.5Ghz and will boost to 1.6Ghz+. There’s obviously room for overclocking as well, especially on custom models with high-end aftermarket air and water cooling solutions. Finally, the card has a thermal design power of 250 watts, just like its bigger brother the Titan X.

Nvidia GeForce GTX 1080 Ti Coming In 2017

The GTX 1080 Ti is planned for an initial debut in January 2017 with availability scheduled to trickle in soon after. Pricing wise all reports indicate that it will be significantly less expensive than the Titan X. However, we haven’t heard of a specific MSRP yet. Which isn’t surprising, considering the launch is still relatively far out in time. It’s safe to assume that no final MSRP has been decided on at this for competitive reasons.

With that being said the trend with Pascal’s base MSRP seems to be Maxwell + $50. The base MSRP for the GTX 1080 was $600, $50 more compared to the GTX 980 at launch, the same is true for the GTX 1070 compared to the 970 and the GTX 1060 compared to the 960. So we’re likely looking at $700 being the base MSRP for aftermarket GTX 1080 Ti’s & $800+ for the Founder’s Edition. A modest price cut to the GTX 1080 is very likely as well.

The GTX 1080 Ti will compete directly with AMD’s upcoming “Vega 10” high-end graphics cards. Which will either carry RX 500 series brand names or updated “Fury” series brand names. These cards will feature 16 gigabytes of second generation stacked high bandwidth memory, up to 4096 GCN cores and 12 teraflops of graphics horsepower. AMD has teased the launch venue for its upcoming Vega 10 flagship GPU just a month ago. And has been talking up Vega for the past couple of months. Although, we’ll likely see the GTX 1080 Ti & Titan X Pascal go head to head with AMD’s upcoming VEGA 10 cards in the first half of 2017 rather than 2016. That’s going to be one hell of a show and certainly one you won’t want to miss.

AMD Radeon Graphics Architectures

WCCFTech Year Consumer
Product
GPU Process Transistors In Billions Performance Memory Bandwidth
Southern Islands 2012 HD 7970 Ghz Tahiti 28nm 4.3 4.1 TFLOPS 3GB GDDR5 264GB/s
Volcanic Islands 2013 R9 290X Hawaii 28nm 6.2 5.6 TFLOPS 4GB GDDR5 320GB/s
Caribbean Islands 2015 R9 Fury X Fiji 28nm 8.9 8.6 TFLOPS 4GB HBM1 512GB/s
POLARIS 2016 RX 480 Polaris 10 14nm 5.7 5.2 TFLOPS 8GB GDDR5 256 GB/s
VEGA 2017 RX Vega 64 Vega 10 14nm 12.5 13 TFLOPS 8GB HBM2 480GB/s
VEGA Refresh
VEGA 2
2018

2018
TBA

TBA
TBA

Vega 20
12nm

7nm
12.5

TBA
TBA

TBA
TBA

32GB HBM2
TBA

1 TB/s
NAVI 2019 TBA Navi 10 7nm TBA TBA Nextgen Memory TBA
Submit