Nvidia today announced its next-generation RTX 30 series of graphics cards. Based on the new Ampere architecture, the three new cards announced today (RTX 3090, RTX 3080, and RTX 3070) call for major improvements in ray-traced and raster 3D rendering.
The RTX 3090 is the new flagship graphics card in this line, which will take over from the Titan RTX. The RTX 3090 boasts 50% improved performance over the Titan RTX and even claims to do 8K at 60fps “in a lot of the best games.”
The RTX 3090 has 24GB of GDDR6X memory, the same capacity as the Titan RTX but faster. It also has a new triple slot design with dual axial fans that claims to be 10 times quieter and runs 30 degrees cooler than the Titan RTX.
The RTX 3090 is priced at $ 1,499, which is more expensive than the RTX 2080 Ti’s $ 1,299 launch price. However, it is cheaper than the $ 2,499 launch price of the Titan RTX. It will be available from September 24.
Next up is the RTX 3080, also known as the handy flagship to most people. With this card, Nvidia promises a performance improvement of up to twice that of the RTX 2080 (the normal, not the Super). It features 10GB of the new and improved GDDR6X memory that runs at 19Gbps and Nvidia claims this card can do 4K 60fps consistently.
The RTX 3080 is priced at $ 699, which is the same as the launch price of the RTX 2080 Super. The RTX 3080 will be available starting September 17.
Finally, there is the RTX 3070. This is the most interesting; Nvidia claims that the RTX 3070 is faster than the RTX 2080 Ti, which if true is a pretty bold claim. The RTX 3070 is also on average 60% faster than the original RTX 2070. It comes with 8GB of GDDR6 memory and Nvidia says this card is suitable for 4K and 1440p gaming, which from what we know of the 2080 Ti is a reasonable claim. to make.
The RTX 3070 is priced at $ 499, the same as the launch price of the RTX 2070 Super, and will be available in October.
Regarding the new RTX 30 series and the Ampere architecture, Nvidia is making several improvements and also introduces some new key features. The CUDA cores, which make up most of the processing hardware in this new GPU, claim to offer twice the performance of FP32 over Turing and 30 shader-TFLOPS of processing power. The new second-generation RT Cores offer twice the performance of Turing, plus simultaneous ray tracing, shading and computation, with 58 RT-TFLOPs of power. Finally, third-generation Tensor Cores also have twice the performance of Turing, with 238 Tensor-TFLOP of processing power.
As mentioned above, two of the three new cards are using faster GDDR6X memory, which Nvidia worked with Micron to create. The new Ampere cards also use a new custom Nvidia 8N process made by Samsung.
The new cards will also feature RTX IO. This enables fast GPU-based loading and decompression of game assets, accelerating I / O performance by up to 100x compared to traditional hard drives and storage APIs. RTX IO also works in conjunction with Microsoft DirectStorage for Windows API to offload tasks from CPU to GPU.
The Nvidia cards will feature a unibody design with dual-axis fan design that claims to offer twice the cooling performance. The cards will also feature the new 12-pin power connector that Nvidia recently revealed and is compatible with existing 8-pin connectors on power supplies that use adapters.
For owners of 8K 60p and 4K 120p TVs, the new RTX 30 series cards will also feature the highly sought after HDMI 2.1 connector, which will allow 8K 60Hz or 4K 144Hz signals to be passed through a single HDMI cable. Finally, the new Ampere cards will also become the first discrete GPUs to have full support for the AV1 codec. AV1 is the open source alternative to HEVC / VVC and is supported by various companies, but until now there was no dedicated hardware to speed it up, slowing down adoption.
Full spec comparison
Nvidia also announced three new software features: Reflex, Broadcast, and Omniverse Machinima.
Nvidia Reflex is a set of functions designed to optimize and measure latency. These include Nvidia Reflex Low-Latency Mode (included in Apex Legends, Call of Duty: Warzone, Fortnite, and Valorant) which reduces latency by up to 50 percent, and Nvidia Reflex Latency Analyzer, which detects input from the mouse. and then measures the time it takes for the resulting pixels to change on the screen. Reflex Latency Analyzer will be included in all upcoming 360Hz G-Sync monitors from Acer, Alienware, ASUS and MSI.
Nvidia Broadcast is a plug-in that improves the quality of microphones and webcams using RTX-accelerated AI effects such as audio denoising, virtual background effects, and webcam auto frame. We have already seen this feature partially in action in beta.
Nvidia Omniverse Machinima allows users to create their own cinematic videos using in-game assets. Users will be able to take assets from supported games and use their webcam and artificial intelligence to create characters, add high-fidelity physics and facial and voice animation, and publish cinematic-quality cinematics. Omniverse Machinima features a path tracing viewer tool and engine designed for physical precision, simulating light, physics, materials, and artificial intelligence.
Nvidia also provided an update on new titles that will be compatible with RTX functions. New titles to support ray tracing include Fortnite and Call of Duty: Black Ops Cold War. Fortnite will feature ray-traced reflections, shadows, global lighting, and ambient occlusion. Among the titles that get DLSS are Boundary, Bright Memory Infinite, Call of Duty: Black Ops Cold War, Cyberpunk 2077, Fortnite, Ready or Not, Scavengers and Watch Dogs: Legion.
The RTX 30 series cards will be available from stock and in factory overclocked variants from OEMs such as ASUS, Colorful, EVGA, Gainward, Galaxy, Gigabyte, Innovision 3D, MSI, Palit, PNY and Zotac. Nvidia itself will also sell the Founders Edition models on its website. The cards will also be included in pre-built systems from companies like CyberPower PC, Digital Storm, Falcon NW, IBUYPOWER, Maingear, Origin, NZXT, Puget, and more.
