Mqm8790-HS2r Ib Switch 40× 200g Full Duplex Port Supports Dragonfly+ Topology.

• Customization: Available
• Communication Mode: Full Duplex
• Type: Network Switch
• Model NO.: MQM8790-HS2R
• Transmission Rate: 200GB/S
• Ports: 40
• Aggregate Bandwidth: 1.6tbps
• Forwarding Rate: 7.2 Billion Packets Per Second (Bpps)
• Port-to-Port Latency: < 130ns
• Cooling Design: Hot-Swappable Fan, N+1 Redundancy
• Transport Package: Carton
• Specification: Original specification
• Trademark: NVIDIA
• Origin: China

Product Description

Scaling Out High-Performance Computing (HPC), AI, Cloud Applications, and Storage Infrastructures with 200G InfiniBand Fixed-Configuration Switches
 

Faster servers combined with high-performance storage and applications that use increasingly complex computations are causing data bandwidth requirements to spiral upward. As servers are deployed with next-generation processors, HPC, AI, and hyperscale cloud environments will need every last bit of network bandwidth.

NVIDIA Quantum QM8700 and QM8790 200 gigabits per second (Gb/s) InfiniBand fixed-configuration switches provide up to forty 200Gb/s ports with 16 terabits per second (Tb/s) of non-blocking bandwidth or eighty 100Gb/s ports with full bidirectional bandwidth per port with extremely low latency-an ideal choice for building flexible and scalable data centers at any size.
 

Collective Communication Acceleration

The QM8700 and QM8790 fixed-configuration switches are designed to enable

NVIDIA In-Network Computing offload engines through NVIDIA Scalable

Hierarchical Aggregation and Reduction Protocol  technology. Using in

switch silicon-embedded hardware, the switch architecture enables the usage

of all active data center devices to accelerate the communications frameworks,

resulting in order-of-magnitude performance improvements.

NVIDIA Quantum switches improve the performance of select collective

operations commonly used in HPC and deep learning communication

frameworks, such as Message Passing Interface (MPI), Shared Memory

(SHMEM), and NVIDIA Collective Communication Library (NCCL). By processing

data as it traverses the network, NVIDIA Quantum switches eliminate the need

to send data multiple times between server endpoints. They also support the

aggregation of large data vectors at wire speed, which are crucial for machine

learning applications.

Streamlining Network Design and Topologies

The QM8700, together with the NVIDIA® ConnectX®-6 adapter card, also supports

100Gb/s. With its support for up to 80 ports of 100Gb/s, this unique technology

provides double-density radix for 100Gb/s data speeds, thus reducing the cost

of network design and topologies. The QM8700 InfiniBand fixed-configuration

switch enables four-lane 200Gb/s ports to be split into two distinct two-lane

100Gb/s ports. As the switch creates a highly dense top-of-rack (ToR) switch,

it's the perfect solution for double-dense racks. In addition, NVIDIA Quantum

based fixed-configuration switches provide maximum flexibility, supporting a

variety of network topologies, including Fat Tree, DragonFly+, multi-dimensional

Torus, and more. NVIDIA Quantum fixed-configuration switches are backwards

compatible to previous generations and include extensive software ecosystem

support.

 

Enhanced Management

The internally managed QM8700 switch features an on-board subnet manager

that enables simple, out-of-the-box bring-up for up to 2,000 nodes. NVIDIA

MLNX-OS® delivers full chassis management through command-line interface

(CLI), web-based user (WebUI), Simple Network Management Protocol (SNMP),

or JavaScript Object Notation (JSON) interfaces.

The externally managed QM8790 switch can utilize the advanced NVIDIA Unified

Fabric Manager (UFM®) platform to empower data center operators to efficiently

provision, monitor, manage, preventatively troubleshoot, and maintain the

modern data center network to realize higher utilization and reduce overall opex.

Building Efficient Clusters

NVIDIA Quantum-based QM8700 and QM8790 switches are used as cost

effective building blocks for deploying high-performance and computing

efficient data centers. With features such as static routing, adaptive routing,

congestion control, and quality of service that enable modern topologies, the

switches ensure maximum effective fabric bandwidth by eliminating congestion

hot spots. Featuring best-in-class design to support low power consumption,

power is further reduced upon partial port utilization. Whether looking at price

to performance or energy to performance, the QM8700 series offers superior

performance, low power, and scalability, reducing capital and operating

expenses and providing the best return on investment.

 

Basic information	Brand	NVIDIA
	Model	MQM8790-HS2R
	Series	Quantum series HDR switch
Hardware parameters	Port Configuration	40 × 200Gb/s HDR QSFP56 port (which can be split into 80 × 100Gb/s HDR100 port)
	Interface Type	QSFP56
	Power Redundancy	Dual redundant hot plug power supply (AC 100-127V/200-240V)
	Cooling Design	Hot-swappable fan, N+1 redundancy
	Physical Dimensions	1U height, 43.6mm × 433.2mm × 590.6mm(H × W × D).
	CPU	x86 ComEx Broadwell D-1508
	Memory	8GB DDR4
	Management Ports	RJ45 Ethernet port, RS232 console port and USB management port.
Performance characteristics	Aggregate Bandwidth	16Tb/s Non-blocking bandwidth
	Forwarding Rate	7.2 billion packets per second (Bpps)
	Port-to-Port Latency	< 130ns
	Network Acceleration	Adaptive routing, congestion control
	Protocol Compatibility	InfiniBand 1.3 standard, compatible with HDR/EDR/FDR/QDR rate.
Application scenario	Use Cases	HPC High Performance Computing, AI/ML Training and Reasoning, Enterprise Storage Network, Very Large Data Center.
	Deployment Topology	ToR leaf switch, supporting DragonFly+, SlimFly and other topologies.
Reliability and environment	Redundancy Design	Power supply 1+1 redundancy, fan N+1 redundancy
	Operating Temperature	0ºC to 40ºC
	Storage Temperature	-40ºC to 70ºC
	Humidity Range	10%-85% (operational), 10%-90% (non-operational)
	Warranty	1-year standard warranty (extendable to 3 years)
additional function	Management OS	MLNX-OS (based on Linux)
	Split Cable Support	Supports splitting ports through branch cables (for example, 200G→2×100G).
	Virtualization Support	Support VL2VL mapping (virtual channel to virtual channel routing)
ORDERABLE PART NUMBER (OPN)	MQM8790-HS2R	NVIDIA Quantum 200Gb/s InfiniBand switch, 40 QSFP56 ports, two power supplies (AC),unmanaged, x86 dual core, standard depth,C2P airflow, rail kit

Q:Are you trading company or manufacturer?

A:We are factory.

Q:How long is your delivery time?
A:Generally it is 2-5 days if the goods are in stock. or it is 10 days if the goods are not in stock, it is according to quantity.

Q:Do you have MOQ?
A:For stock products,we don't have MOQ. For custom product,we ask for low MOQ.

Q:Can you offer a better price?Any discount?
A:Yes,surely. We're source factory and providing reasonable price.

Q:What is your warranty period?
A:Different products have different warranties.This warranty does not cover damage caused by man-made damage,improper care,negligence,normal wear tear,and force majeure such as natural disasters,earthquakes,fires ,etc.