LogInNvidia Corp announced a new high-performance graphics processing unit for AI training and inference based on the team's new Ampere architecture.
Nvidia Corp announced a new high-performance graphics processing unit for AI training and inference based on the team's new Ampere architecture.
The Nvidia A100 will provide a 20-times performance boost compared to the Volta GPU, si it's perfect for AI, data analytics, scientific computing, and other complex tasks.
The new product was revealed at the company’s annual GPU Technology Conference. The team also presented a new AI system, the Nvidia DGX A100. The company plans to expand its EGX Edge AI platform ecosystem with the EGX A100 converged accelerator and the EGX Jetson Xavier NX micro-edge server,.
Nvidia wants to reimagine the GPU with its new A100 which boosts performance massively and unifies AI training and inference acceleration within a single architecture. The new product supports massive data center scalability, including scale-up capabilities for AI training and data analytics, plus scale-out for AI inference.
The company has also discussed RTX and how it will change the future of 3D graphics:
The A100 Ampere is said to be the largest GPU Nvidia ever featuring 54 billion transistors, also coming with third-generation tensor cores and acceleration for sparse matrix operations.
The A100 GPU is said to make its debut in the new Nvidia DGX A100 third-generation integrated AI system that was launched by the company today. The new system features eight A100 GPUs with 320 gigabytes of memory in total.
You can learn more and find other announcements here.