Nvidia claims that the second-generation RTX cards, which come with the flagship GeForce RTX 3080, offer up to twice the graphics functionality and 1. 9 times the power of the chipmaker’s previous Turing-based cards. “The launch of Ampere is a giant step into the future,” says CEO Jensen Huang.
Nvidia has unveiled its next generation of RTX graphics cards, the GeForce RTX 3080, which CEO Jensen Huang said represents the company’s “biggest generational leap” in graphics performance.
Huang said that the second-generation RTX cards, which also come with the new mid-range GeForce RTX 3070 and Titan’s successor, the GeForce RTX 3090, will provide up to twice the graphics functionality and 1. 9 times the power of Nvidia’s previous Turing. Card based, while also offering competitive pricing.
[Related: Nvidia and Arm deal could close in the ‘coming weeks’: report]
Tuesday’s reveal comes after Nvidia unveiled in May the first product based on its new Ampere architecture, the A100 data center GPU, which unifies education and inference into a single architecture and can be broken down into seven separate GPU examples, the new multi-GPU sample feature.
The GeForce RTX 3080 Founder’s Edition is expected to launch first, on September 17, with a value of $699, the same value as the previous-generation RTX 2080 Super while also providing particularly higher performance. The graphics card comes with 8,704 CUDA cores, 10GB of GDDR6X RAM, and an upgraded frequency of 1. 71GHz.
The Founder’s Edition of the GeForce RTX 3090, which the company says is its first 8K gaming GPU, will be available on September 24 for $1,499, $1,000 less than its predecessor, the RTX Titan, and more than Nvidia’s previous mainstream GPU. The RTX 2080 Ti. La card comes with 10,496 CUDA codes, 24GB of GDDR6X RAM, and an upgraded clock of 1. 7GHz.
The founder‘s edition of the mid-tier GeForce RTX 3070 will launch in October for $499, the same as the previous generation RTX 2070 Super while offering greater performance than the $1,199 RTX 2080 Ti. The card comes with 5,888 CUDA cores, 8 GB in GDDR6 RAM and a 1.73 GHz boost clock. Nvidia did not announce a successor to the RTX 2060 Super.
Based on Nvidia‘s new Ampere architecture, the GPUs powering the graphics cards come with streaming multiprocessors that provide twice the throughput for single-precision floating-point math, when compared to Turing. The GPUs also double the throughput for ray tracing performance with second-generation Ray Tracing cores and for artificial intelligence with third-generation Tensor Cores, which enables Deep Learning Super Sampling 2.0 possible.
The new GeForce RTX graphics cards require a PCIe 4. 0 connection, which means that only third-generation AMD Ryzen processors can take advantage of this, as Intel has yet to supply desktop processors that can have this point of connectivity.
During a virtual presentation on Tuesday, Huang unveiled the new graphics cards, which will come with models made through expansion card partners, as a replacement for the PC gaming market, especially since he believes it will allow more gamers to access them. In-game tracking to generate genuine lights and reflections in real-time.
“The launch of Ampere is a giant step into the future. This is our biggest generational leap to date,” he said. “The second-generation Nvidia RTX, which fuses programmable shading, ray tracing, and synthetic intelligence, gives us photorealistic graphics and the highest frame rates. At the same time, what was once the holy grail of PC graphics, ray tracing is now the norm.
Nvidia also introduced new software to take advantage of its graphics cards: Nvidia Reflect, which optimizes the rendering process on the CPU and GPU to reduce gaming latency by 50%; Nvidia Broadcast, a live streaming tool that uses artificial intelligence to remove background noise and create virtual background effects; and Nvidia Omniverse, a tool for creating video game assets.