Cart

  • Cart Empty!

Every effort has been made to ensure the accuracy of all information contained herein. e-nitiative shall not be liable for any changes resulting in wrong product description, tax code and/or price. The shown information (specifications, prices, taxes) should be considered as an indication and can be changed at any moment and without any prior notice.

ADVANCE COMPUTER CENTRE LTD
59 GEORGE LANE
E18 1JJ LONDON
UK
Telephone : 02085188353
VAT : 506794623

curve_type_3_left_tcurve_type_3_right_t
InfiniBand XDR/Ethernet 2x400GbE 1-port OSFP Pci-e6 x16 HHHL CX8 Crypto Adapter

InfiniBand XDR/Ethernet 2x400GbE 1-port OSFP Pci-e6 x16 HHHL CX8 Crypto Adapter

£7,961.46
£9,553.75
Part Number: P79114-H21
Language: IN
Real time Stock Check

Product Details

Introduction

Do your high performance computing (HPC) or artificial intelligence (AI) workloads need improved performance to enable research and development? HPE InfiniBand XDR Adapters deliver extremely fast, efficient network connectivity, significantly enhancing system performance for AI factories and cloud data center environments. The HPE InfiniBand XDR Adapters include single-port and dual-port options. The single-port adapters are offered in InfiniBand XDR speeds (800 Gb/s) and ethernet (2x400GbE) with OSFP connectors. The dual-port adapters are offered in InfiniBand XDR (400 Gb/s) and ethernet (400GbE) enabled with QSFP112 connectors. They seamlessly integrate with next-gen NVIDIA networking platforms, providing up to 800 Gb/s of end-to-end connectivity.

What is new supporting point:
Optimized to supercharge hyperscale AI computing workloads. With support for both InfiniBand and Ethernet networking at up to 800 Gb/s
These adapters offer the robustness, feature sets, and scalability required for trillion-parameter GPU computing, AI data platforms, and agentic AI applications
HPE InfiniBand XDR Adapters enhance the capabilities of NVIDIA Scalable Hierarchical Aggregation and Reduction Protocol (SHARP)
Boosting in-network computing in HPC environments, enhancing overall efficiency and performance for both training and inferencing at scale

Design

Compatible products

HPE Mainstream Compute Platforms; HPE Specialized Compute Platforms

Weight & dimensions

Width

242 mm

Depth

184.8 mm

Height

27.2 mm

Weight

350 g