NVIDIA GPU A100 PCIe Tesla 40GB

5120 CUDA cores per card, 640 Tensor cores
40 GB HBM2 and 1555 GB / s bandwidth
Maximum consumption 250 W
19.5 Tflops in single precision. 9.2 Tflops double precision and 156 Tflops in Tensorflops (624 Tflops in half precision)
PCIe 4.0 bus
8-pin CPU power connector

Available:

Política de seguridad (editar con el módulo Información de seguridad y confianza para el cliente)

Política de envío (editar con el módulo Información de seguridad y confianza para el cliente)

Política de devolución (editar con el módulo Información de seguridad y confianza para el cliente)

The NVIDIA A100 Tensor Core GPU offers unprecedented acceleration at all scales for artificial intelligence, data analytics and HPC to tackle the world's toughest computing challenges. As the engine of the NVIDIA data center platform, A100 can efficiently scale up to thousands of GPUs or, using new Multi-Instance GPU (MIG) technology, can be split into seven isolated GPU instances to accelerate workloads of all sizes. A100's third-generation Tensor Core technology now accelerates more levels of precision for various workloads, accelerating time to information and time to market.