Skip to product information
1 of 1

Cisco

Cisco UCSC-GPU-A100 | NVIDIA A100 40GB PCIe 4.0 GPU Accelerator, 250W

SKU:UCSC-GPU-A100

Request Quote
Sale Sold out
Shipping calculated at checkout.

Stock Status: Enquire

 Trade supply only. Server & GPU quote requests need a company name, ABN and work email address. We do not quote Gmail, Outlook or Hotmail addresses, or supply for home use. 

20-min response

Need a quote or bulk pricing? Answered within 20 minutes, Sydney business hours.

Custom Built Servers

Need a different spec, quantity or configuration?

We build configured-to-order refurbished servers from Cisco, Dell, HPE, NVIDIA Lenovo and Supermicro. Tell us what you need and we'll come back with options within 24 hours.

Configure your server now →

Description

The NVIDIA A100 40GB GPU accelerator is a GPU option for Cisco UCS C-Series rack servers. Built on the Ampere architecture, it targets AI training and inference, data analytics and high-performance computing workloads in the data centre.

This card pairs 40GB of GPU memory with a PCIe Gen4 interface rated at 64GB/s and a 250W power rating. Third-generation Tensor Cores support a broad range of precisions, including FP64, TF32, BF16, FP16 and INT8, with structural sparsity support for up to 2X higher performance on sparse models. Multi-Instance GPU (MIG) lets a single card be partitioned into up to seven hardware-isolated GPU instances, so several workloads can share one accelerator.

An optional NVIDIA NVLink Bridge connects up to two PCIe GPUs at 600GB/s for larger multi-GPU jobs.

Enquire with XS Network Tech for new or used pricing and availability.

Features

- Third-generation Tensor Cores for deep learning training and inference
- Multi-Instance GPU (MIG) partitions one GPU into up to seven hardware-isolated instances
- Optional NVLink Bridge links up to 2 PCIe GPUs
- High-bandwidth HBM2e memory
- Structural sparsity support for up to 2X higher performance on sparse models
- Broad precision support: FP64, TF32, BF16, FP16 and INT8

Warranty

All products sold by XS Network Tech include a 12-month warranty on both new and used items. Our in-house technical team thoroughly tests used hardware prior to sale to ensure enterprise-grade reliability.

All technical data should be verified on the manufacturer data sheets.

View full details

specs-tabs

Collapsible content

Technical Specifications

FAQs

Technical Specifications

- GPU: NVIDIA A100 Tensor Core (Ampere architecture)
- GPU memory: 40GB
- Interface: PCIe Gen4, 64GB/s
- Power rating: 250W
- Form factor: PCIe, dual-slot, air cooled
- Multi-Instance GPU: up to 7 instances
- NVLink Bridge (optional): 600GB/s for up to 2 GPUs
- FP64: 9.7 TFLOPS
- FP64 Tensor Core: 19.5 TFLOPS
- FP32: 19.5 TFLOPS
- TF32 Tensor Core: 156 TFLOPS, 312 TFLOPS with sparsity
- BFLOAT16 Tensor Core: 312 TFLOPS, 624 TFLOPS with sparsity
- FP16 Tensor Core: 312 TFLOPS, 624 TFLOPS with sparsity
- INT8 Tensor Core: 624 TOPS, 1248 TOPS with sparsity

FAQs

Q: What workloads is this GPU designed for?
A: It is designed for AI training and inference, data analytics and high-performance computing in the data centre.

Q: Can the GPU be shared between workloads?
A: Yes. Multi-Instance GPU (MIG) can partition one A100 into up to seven hardware-isolated GPU instances.

Q: Can two of these GPUs be linked together?
A: Yes. An optional NVIDIA NVLink Bridge connects up to two PCIe A100 GPUs at 600GB/s.

Q: What power rating does this GPU have?
A: This SKU is rated at 250W and draws its power from the host server.

Q: Which servers is it intended for?
A: It is a GPU option for Cisco UCS C-Series rack servers.

  • Request a Quote

    Looking for competitive pricing? Submit a request, and our team will provide a tailored quote that fits your needs.

  • Contact Us Directly

    Have a question or need immediate assistance? Call us for expert advice and real-time support.

    Call us Now  
  • Contact Us Directly

    Have a question or need immediate assistance? Call us for expert advice and real-time support.

    Contact us