Nvidia Ampere A100 GPU
Nvidia has announced new GPU architecture today but you won’t be using it in your next gaming PC. the corporate raised a curtain on its next-generation Ampere architecture that’s designed for data centers, cloud computing, scientific computing, and data analytics.
Called the A100, the new Nvidia Ampere GPU is a component of the businesses drives into cloud computing. Considering the continued COVID-19, CEO Jensen Huang told reporters at GTC 2020 how important it’s to be a part of the info business.
“Those dynamics are really quite good for our data center business … My expectation is that Ampere goes to try to remarkably well. It’s our greatest data center GPU ever made and it capitalizes on nearly a decade of our data center experience.”
In terms of power, the A100 has over 54 billion transistors and Huang says Nvidia reached “nearly the theoretical limits of what’s possible in semiconductor manufacturing”. Certainly, the GPU is that the world’s largest 7nm chipset.
Elsewhere, the new Ampere GPU has 40GM of memory, 6,912 CUDA cores, 19.5 teraflops of FP32 performance, and 1.6TB/s of bandwidth. Yes, in other words, it’s a beast. Nvidia’s focus is on combining A100 chips to make a stacked system supported AI which will run its data centers.
The company will use its NVLink technology to mix 8 A100s for a complete of 320GB of GPU memory and 12.4TB/s of memory bandwidth.
“If you’re taking a glance at the way modern data centers are architected, the workloads they need to try to are more diverse than ever,” explains Huang. “Our approach going forward isn’t to only specialize in the server itself but to believe the whole data center as a computing unit. Going forward I think the planet goes to believe data centers as a computing unit and we’re getting to be brooding about data center-scale computing. not just personal computers or servers, but we’re getting to be operating on the info center scale.”
Nvidia’s new Ampere architecture is already shipping to organizations and has helped with COVID-19 research conducted at the US Argonne National Laboratory.
Source : winbuzzer.com