KARTA TOWARU O ID: 5826
PNY NVIDIA A100X Module 80GB HBM2 ECC 5120-bit, NVlink support with 3x opt. bridges, integrated BlueField-2 DPU
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 |
| 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 |