Tuesday, February 28th 2017
NVIDIA Announces the GeForce GTX 1080 Ti Graphics Card at $699
NVIDIA today unveiled the GeForce GTX 1080 Ti graphics card, its fastest consumer graphics card based on the "Pascal" GPU architecture, and which is positioned to be more affordable than the flagship TITAN X Pascal, at USD $699, with market availability from the first week of March, 2017. Based on the same "GP102" silicon as the TITAN X Pascal, the GTX 1080 Ti is slightly cut-down. While it features the same 3,584 CUDA cores as the TITAN X Pascal, the memory amount is now lower, at 11 GB, over a slightly narrower 352-bit wide GDDR5X memory interface. This translates to 11 memory chips on the card. On the bright side, NVIDIA is using newer memory chips than the one it deployed on the TITAN X Pascal, which run at 11 GHz (GDDR5X-effective), so the memory bandwidth is 484 GB/s.
Besides the narrower 352-bit memory bus, the ROP count is lowered to 88 (from 96 on the TITAN X Pascal), while the TMU count is unchanged from 224. The GPU core is clocked at a boost frequency of up to 1.60 GHz, with the ability to overclock beyond the 2.00 GHz mark. It gets better: the GTX 1080 Ti features certain memory advancements not found on other "Pascal" based graphics cards: a newer memory chip and optimized memory interface, that's running at 11 Gbps. NVIDIA's Tiled Rendering Technology has also been finally announced publicly; a feature NVIDIA has been hiding from its consumers since the GeForce "Maxwell" architecture, it is one of the secret sauces that enable NVIDIA's lead.
The Tiled Rendering technology brings about huge improvements in memory bandwidth utilization by optimizing the render process to work in square sized chunks, instead of drawing the whole polygon. Thus, geometry and textures of a processed object stays on-chip (in the L2 cache), which reduces cache misses and memory bandwidth requirements.
Together with its lossless memory compression tech, NVIDIA expects Tiled Rendering, and its storage tech, Tiled Caching, to more than double, or even close to triple, the effective memory bandwidth of the GTX 1080 Ti, over its physical bandwidth of 484 GB/s.
NVIDIA is making sure it doesn't run into the thermal and electrical issues of previous-generation reference design high-end graphics cards, by deploying a new 7-phase dual-FET VRM that reduces loads (and thereby temperatures) per MOSFET. The underlying cooling solution is also improved, with a new vapor-chamber plate, and a denser aluminium channel matrix.
Watt-to-Watt, the GTX 1080 Ti will hence be up to 2.5 dBA quieter than the GTX 1080, or up to 5°C cooler. The card draws power from a combination of 8-pin and 6-pin PCIe power connectors, with the GPU's TDP rated at 220W. The GeForce GTX 1080 Ti is designed to be anywhere between 20-45% faster than the GTX 1080 (35% on average).
The GeForce GTX 1080 Ti is widely expected to be faster than the TITAN X Pascal out of the box, despite is narrower memory bus and fewer ROPs. The higher boost clocks and 11 Gbps memory, make up for the performance deficit. What's more, the GTX 1080 Ti will be available in custom-design boards, and factory-overclocked speeds, so the GTX 1080 Ti will end up being the fastest consumer graphics option until there's competition.
Besides the narrower 352-bit memory bus, the ROP count is lowered to 88 (from 96 on the TITAN X Pascal), while the TMU count is unchanged from 224. The GPU core is clocked at a boost frequency of up to 1.60 GHz, with the ability to overclock beyond the 2.00 GHz mark. It gets better: the GTX 1080 Ti features certain memory advancements not found on other "Pascal" based graphics cards: a newer memory chip and optimized memory interface, that's running at 11 Gbps. NVIDIA's Tiled Rendering Technology has also been finally announced publicly; a feature NVIDIA has been hiding from its consumers since the GeForce "Maxwell" architecture, it is one of the secret sauces that enable NVIDIA's lead.
160 Comments on NVIDIA Announces the GeForce GTX 1080 Ti Graphics Card at $699
What really sucks is that this embarrassment has to be on the main page. Hard to be a reputable site when a guy with genius (lol?) in his name goes through the trouble of fixing something that isn't broken. What's even worse is that some people probably STILL haven't figured it out.
tpucdn.com/reviews/Gigabyte/GTX_1080_Aorus_Xtreme_Edition/images/perfrel_3840_2160.png
That's 15%+ higher than a stock 1080, and that's using a list that includes many older games. All of this is just the bare minimum too. If you actually look at the architectural enhancements and leaked specs it could be as much as high as twice as strong - we just don't know yet.
The point is that the 7970 was practically twice as strong as the 6970, and the 290X was 50 - 65% stronger than the 7970. We should expect at least that much from AMD considering how long it has been.
Still debating if I want to trade up.
Annoyingly, Nvidia have finally gone for 1:1 $>£ currency conversion, so its £699, i was hoping it might be £649
Seems they took that opportunity to jack the price of the Titan from £1099 to £1179 too:(
Wallet ready to put one inside my case!
It's not like Vega is going to beat this anyway.How will this be a fiasco?
None of the memory controllers or chips are crippled in any way.Because the DVI-port is blocking ~30 of the exhaust of GTX 1060/1070/1080, even though it's not that useful any more.
for £ prices, thank brexit. especially titan x one. nvidia actually has a press release or something about that, saying they needed to adjust prices to due £/$ rate changes.
for the rest - usd has been gaining a lot against other currencies, € is also almost 1:1 now.not really separate controllers.
idea is correct though, memory controller can work with somewhat arbitrary width of memory bus. memory bus width increments are defined by the data bus width of a single memory chip, in case of gddr5(x) that is 32 bits.
nitpicky, i know. sorry. :)
Modern GPUs work by having multiple separate 32-bit memory controllers, each complete with their own ROPs. GTX 1080 Ti has one of these disabled, which is why it also has fewer ROPs. This is one of the nice modular features of modern GPUs.
When a cluster of cores wants to access a block of memory it addresses the respective memory controller.
Isn't all that matters what it actually gives you?
If Nvidia needs to add more cores/controllers/etc. to get decent yields and keep the prices low, precisely how is this bad for the end user?