NVIDIA GeForce RTX 30 Series and the new Ampere Architecture
Last month, NVIDIA launched its latest GPUs, the RTX 30 Series, consisting of the RTX 3080, RTX 3070, and RTX 3090. It boasts the new Ampere architecture with faster 2nd-gen Ray Tracing Cores, faster 3rd-gen Tensor Cores, and new streaming multiprocessors to bring stunning visuals, faster frame rates, and AI acceleration for gamers and creators. Let’s take a look at those features and find out what makes the RTX 30 Series one of the most powerful GPUs in the market.
The NVIDIA Ampere architecture is the successor to both the Volta and Turing architectures and is crafted with 54 billion transistors, making it the largest 7 nanometer (nm) chip the company has ever built. This new architecture also powers the new RTX 30 series and brings the following cutting-edge technologies to gamers and creators:
- New streaming multiprocessors: This is the building block for the world’s fastest, most efficient GPU, and can deliver 2x the FP32 throughput of the previous generation, and 30 Shader-TFLOPS of processing power.
- Second-gen RT Cores: The new dedicated RT Cores deliver 2x the throughput of the previous generation, plus concurrent ray tracing and shading and compute, with 58 RT-TFLOPS of processing power.
- Third-gen Tensor Cores: The new dedicated Tensor Cores, with up to 2x the throughput of the previous generation, makes it faster and more efficient to run AI-powered technologies, like NVIDIA DLSS, and 238 Tensor-TFLOPS of processing power.
- NVIDIA RTX IO: This enables rapid GPU-based loading and game asset decompression, accelerating input/output performance by up to 100x compared with hard drives and traditional storage APIs. In conjunction with Microsoft’s new DirectStorage for Windows API, RTX IO offloads dozens of CPU cores’ worth of work to the RTX GPU, improving frame rates and enabling near-instantaneous game loading.
- World’s fastest graphics memory: NVIDIA has worked with Micron to create the world’s fastest discrete graphics memory for the RTX 30 Series, GDDR6X. It provides data speeds of close to 1TB/s system memory bandwidth for graphics card applications, maximizing game and app performance.
- Next-gen process technology: The RTX 30 series features the new 8N NVIDIA custom process from Samsung, which allows for higher transistor density and more efficiency.
In addition to the benefits of the Ampere architecture mentioned above, the RTX 30 series also sport up to 24GB GDDR6X VRAM; HDMI 2.1 for 4K high refresh rate and 8K gaming; support for the AV1 codec for high-resolution streams using significantly less bandwidth; and dual axial flow through cooling solutions for the Founders Edition cards.
Other features also include NVIDIA Reflex, which reduces system latency, providing split-second PC gaming responsiveness; NVIDIA Broadcast, which turns any room into a home broadcast studio with AI-enhanced video and voice comms; updates to NVIDIA DLSS for 8K HDR gaming on the GeForce RTX 3090 graphics card; and new NVIDIA Studio enhancements to make creative applications run faster.
Check out the key specs and price below:
NVIDIA GeForce RTX 3090
CUDA Cores: 10,496
VRAM: 24GB GDDR6X
Price (starting): USD 1,499
NVIDIA GeForce RTX 3080
CUDA Cores: 8,704
VRAM: 10 GB GDDR6X
Price (starting): USD 699
NVIDIA GeForce RTX 3070
CUDA Cores: 5,888
VRAM: 8 GB GDDR6
Price (starting): USD 499
NVIDIA partners, including ASUS, Colorful, EVGA, Gainward, Galaxy, Gigabyte, Innovision 3D, MSI, Palit, PNY and Zotac, offer custom cards on shelves alongside NVIDIA Founders Edition models.
To let gamers test the capabilities and features of the new RTX 30 series graphics card like the NVIDIA DLSS and NVIDIA Reflex, NVIDIA is bundling a PC digital download copy of Watch Dogs: Legion for those who purchase an RTX 30 series graphics card, or a pre-built GeForce RTX 30 Series PC at participating retailers and e-tailers. You can check them out here.
Watch Dogs: Legion will be playable starting October 29th, 2020.