Skip to product information
1 of 1

Cisco

Cisco UCSC-GPUA100-80-D | NVIDIA A100 80GB HBM2e GPU, 300W Passive, PCIe 4.0

SKU:UCSC-GPUA100-80-D

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 We do not quote Gmail, Outlook or Hotmail addresses, or supply for home use. 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

This NVIDIA A100 Tensor Core GPU is the Cisco UCS C-Series version of the A100 PCIe accelerator, built for AI and machine learning training and inference, data analytics and HPC workloads in data centres. It suits teams that need to run large models or share one GPU between several users.

The card carries 80GB of HBM2e memory with 1,935 GB/s of memory bandwidth and connects over PCIe Gen4 x16 in a dual-slot form factor. Peak figures include 9.7 TFLOPS FP64, 19.5 TFLOPS FP32 and 312 TFLOPS FP16 or BF16 Tensor Core performance, rising to 624 TFLOPS with sparsity. Multi-Instance GPU lets you divide the card into up to seven isolated instances of 10GB each. It has a 300W maximum TDP and a passive heatsink, so it relies on server chassis airflow for cooling. The -D suffix identifies the 80GB, 300W passive C-Series part.

Cisco lists this GPU as supported on UCS C-Series rack servers such as the C240 M7. An optional NVLink Bridge can link two GPUs at 600 GB/s.

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

Features

- Third-generation Tensor Cores supporting FP64, TF32, BF16, FP16 and INT8 precisions
- Multi-Instance GPU partitions the card into up to seven isolated instances
- 80GB HBM2e memory with over 1.9 TB/s bandwidth for large models and datasets
- Optional NVLink Bridge to connect two GPUs
- Passive heatsink cooled by server chassis airflow
- Supported on Cisco UCS C-Series rack servers

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 memory: 80GB HBM2e
- Memory bandwidth: 1,935 GB/s
- Maximum TDP: 300W
- Cooling: Passive heatsink, server chassis airflow
- Host interface: PCIe Gen4 x16, 64 GB/s
- Form factor: Dual-slot
- Multi-Instance GPU: Up to 7 instances at 10GB
- FP64: 9.7 TFLOPS
- FP64 Tensor Core: 19.5 TFLOPS
- FP32: 19.5 TFLOPS
- TF32 Tensor Core: 156 TFLOPS (312 TFLOPS with sparsity)
- BF16 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)
- NVLink Bridge: 2 GPUs at 600 GB/s

FAQs

Q: Does this GPU need a separate power connection?
A: Yes. It has a 300W maximum TDP and needs a GPU power cable from the host server. The Cisco C-Series GPU power cable is a separate spare part.

Q: How is the card cooled?
A: It uses a passive heatsink with no onboard fan, so the server chassis must provide enough airflow across the card.

Q: Which servers is it supported in?
A: Cisco lists it as a supported GPU for UCS C-Series rack servers, for example the C240 M7 with Cisco IMC and BIOS version 4.1(3) or later.

Q: Can I link two cards together?
A: Yes. An optional NVIDIA NVLink Bridge connects two GPUs at 600 GB/s.

Q: How does this differ from the UCS X-Series A100 option?
A: The -D suffix with the UCSC prefix is the C-Series rack server part. The UCS X-Series equivalent for the X440p PCIe node is UCSX-GPUA100-80-D.

  • 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