At Nvidia’s Gamescom 2018 press conference, the company, as expected, announced its latest high-end graphics card: the GeForce RTX 2080.
While many of us were expecting to see a new GPU from Nvidia, we’re still excited about the specs and raw gaming potential this graphics card has.
However, how does it stack up to its predecessor, the GTX 1080? We pit what we know so far about the new GPU against its older sibling to see just how much of a leap in performance the RTX 2080 will provide.
Nvidia GeForce RTX 2080 vs Nvidia GeForce GTX 1080 price
When the GTX 1080 first launched on May 27, 2016, it sold for $549 (£529, around AU$900), while the Founder’s edition sold for a bit more.
With the RTX 2080, Nvidia is selling it for $699 (about £527, AU$936). Considering the performance leap between the GTX 1080 and the RTX 2080 (which we’ll look at more closely in a moment), this is a pretty impressive amount of power for the money. Of course, it’s not cheap, but we were not expecting Nvidia’s next generation high-end GPU to be a budget affair.
However, since the launch of the GTX 1080, the GPU has had a few price cuts (when it wasn’t being inflated by cryptocurrency miners), and we’d expect its price to fall further once the RTX 2080 is out. Because the GTX 1080 is still a very capable card, it means you could pick up an excellent bargain.
Nvidia GeForce RTX 2080 vs Nvidia GeForce GTX 1080 architecture
Back in 2016, the GTX 1080 was a showcase for Nvidia’s Pascal GPU architecture, which introduced the company’s 16nm FinFET process. This allowed for improved efficiencies, higher densities of transistors, and increased performance.
Meanwhile, the GeForce RTX 2080 is based on Nvidia’s highly-anticipated Turing GPU architecture. This features the debut of RT Cores, which are specialized cores used to compute how light and sound travel in a 3D environment at a rate of up to 10 GigaRays. They should allow Turing GPUs like the RTX 2080 to process real-time ray tracing 25-times faster than Pascal architecture.
According to Nvidia, its Turing-based GPU nodes can outperform CPU nodes by 30 times when used for final-frame rendering for film effects. While this applies to the professional Turing GPUs like the Quadro RTX 8000, Quadro RTX 6000 and Quadro RTX 5000, gaming and consumer GPUs like the RTX 2080 could also see the benefits of this tech.
Turing architecture also carries over Tensor Cores from its Volta architecture, which can deliver up to 500 trillion tensor operations a second that benefits AI-driven rendering methods, such as deep learning anti-aliasing.
As with Volta, Nvidia Turing has adopted GDDR6 memory that clocks in as fast as 14Gbps, and features 18.6 billion transistors compared to Pascal’s 11.8 billion transistors.
Nvidia GeForce RTX 2080 vs Nvidia GeForce GTX 1080 specifications
The GTX 1080 comes with 8GB of GDDR5X memory, with a 10Gbps memory speed, 256-bit memory interface and a memory bandwidth of 320GB/sec.
The base clock is 1,607 MHz, with a boost of 1,733 MHz, and it comes with 2560 Cuda cores. Overall, the GTX 1080 is capable of 9 teraflops of computing power.
Meanwhile, the Nvidia GeForce RTX 2080 comes with 8GB of GDDR6 memory with 14Gbps memory speed, a 256-bit memory interface and 448GB/sec memory bandwidth.
Its base clock is 1,515 MHz with a boost of 1,710 MHz and it features 2944 Cuda cores.
There will also be a GeForce RTX 2080 Founders Edition that will have an overclocked boost clock at 1,800 MHz.
These specs show a big boost in performance for the RTX 2080 over the GTX 1080, with faster video memory and a lot more cores. The architecture changes we mentioned earlier will also help the RTX 2080 blow past its predecessor when it comes to performance.
As soon as we get our hands on an RTX 2080 we’ll properly pit it against the GTX 1080 to see how the new card really stacks up.
- Here’s our pick of the best graphics cards you can buy right now
from TechRadar: computing components news https://ift.tt/2OS0Htc
via IFTTT
No comments:
Post a Comment