Описание Характеристики Ревюта / Въпроси

NVIDIA A100X

Converged Accelerators | Networking and Compute, Unified

The A100X brings together the power of the NVIDIA A100 Tensor Core GPU with the BlueField-2 DPU. It's ideal for I/O intensive, GPU-accelerated workloads. Examples include 5G with massive multiple-input, multiple-output (MIMO) capabilities, AI-on-5G deployments, and specialized workloads such as signal processing and multi-node training

In one unique, efficient architecture, NVIDIA converged accelerators like the A100X combine the powerful performance of NVIDIA GPUs with the enhanced networking and security of NVIDIA smart network interface cards (SmartNICs) and data processing units (DPUs). Deliver maximum performance and enhanced security for I/O intensive GPU accelerated workloads, from the data center to the edge.

Architecture	Ampere
CUDA Cores	6912
Tensor Cores	432
FP32 Performance	19.5 TFLOPS
GPU Memory	80 GB
GPU Memory Type	HBM2 ECC
Memory Bandwidth	2039 GB/s
Memory Interface	5120-bit
System Interface	PCI-E 4.0 x16
Max Power Consumption	300 W
Form Factor	Full Height Dual Slot
Thermal Management	Passive
MIG support	up to 7 GPU Instances
NVLink Interconnect	600 GB/s Bidirectional
Network Controllers	2x 100 Gbps ports, Ethernet or InfiniBand

JAR Computers може да предложи ремонт/смяна/монтаж в наш сервиз или при партньор.

Виж още Видео карти PNY
Виж всички Видео карти в категорията

Технически характеристики

GPU производител:	nVidia
Капацитет:	80 GB
Тип памет на видеокарта:	HBM2
Битове (BUS памет):	5120 Bit
Интерфейс:	Няма

Добави Ревю / Въпрос

Оцени продукта или задай въпрос?

0.00 от 0 ревюта

Добави ревю | Задай въпрос