 
|
NVIDIA MSB7800-ES2F 100Gb/s InfiniBand Switch 36-Port 7.2Tb/s HPC & AI Switch
Produktdetails:
| Markenname: | Mellanox |
| Modellnummer: | MSB7800-ES2F |
| Dokumentieren: | MSB7800-ES2F.pdf |
Zahlung und Versand AGB:
| Min Bestellmenge: | 1 STÜCK |
|---|---|
| Preis: | Negotiate |
| Verpackung Informationen: | Äußere Box |
| Lieferzeit: | Auf der Grundlage der Bestände |
| Zahlungsbedingungen: | T/T |
| Versorgungsmaterial-Fähigkeit: | Versorgung nach Projekt/Batch |
|
Detailinformationen |
|||
| Anwendung: | Server | Zustand: | NEU UND ORIGINAL |
|---|---|---|---|
| Schaltkapazität: | 2,6 Tbps | Uplink -Konnektivität: | 200 Gbps |
| Name: | MSB7800-ES2F 36 Port-Mellanox Ethernet-Schalter | Stichwort: | mellanox Ethernet-Schalter |
| Hervorheben: | NVIDIA InfiniBand switch 100Gb/s,HPC AI switch 36-port,Nvidia network switch 7.2Tb/s |
||
Produkt-Beschreibung
NVIDIA MSB7800-ES2F 100Gb/s InfiniBand Switch
Model: MSB7800-ES2F | P2C Airflow | 36 x QSFP28 | 1U Top-of-Rack
Ultra-low latency, 7.2 Tb/s aggregate throughput, and SHARP™ in-network acceleration — purpose-built for HPC, AI, and hyperscale data centers. Reduce MPI operation time, free up CPU resources, and simplify cluster scaling with NVIDIA's 100Gb/s InfiniBand fixed-configuration switch.
- 36 non-blocking 100Gb/s ports
- 7.2 Tb/s bidirectional switching capacity
- ATIS weighted power as low as 122W
- 1+1 redundant & hot-swappable PSUs
- SHARP collective offloads (MPI performance boost)
- Dual-core x86 CPU + MLNX-OS management
- Front-to-rear (P2C) airflow, standard depth
- Compatible with NVIDIA UFM® AI-powered fabric management
Product Overview
The NVIDIA MSB7800-ES2F is a 100Gb/s InfiniBand fixed switch delivering 36 ports in a compact 1U chassis. Designed for small to extremely large clusters, it provides top-of-rack leaf connectivity with non‑blocking performance. This model features power‑to‑core (P2C) airflow, ideal for data center cold aisle configurations. Enterprises and research institutions leverage the SB7800 series to handle high‑performance computing, AI training, and storage workloads without compromising latency or scalability. The integrated x86 dual-core CPU runs the feature-rich MLNX-OS®, enabling full chassis management, while advanced telemetry and SHARP acceleration transform how collective communications are processed across the fabric.
Key Features
36 x 100Gb/s QSFP28 Ports
Each port delivers line-rate 100Gb/s InfiniBand, supporting full bisection bandwidth and non‑blocking architecture. Aggregate throughput reaches 7.2 Tb/s.
SHARP In‑Network Computing
NVIDIA Scalable Hierarchical Aggregation and Reduction Protocol offloads collective operations (MPI_Allreduce, etc.) from the host CPU to the switch data path, drastically reducing data traversals and latency.
Energy‑Efficient & Redundant Design
80 Plus Gold certified, ATIS weighted power as low as 122W. Redundant (1+1) hot‑swappable power supplies and fan modules maximize uptime and serviceability.
Dual‑Core x86 CPU & MLNX-OS
On‑board Intel Celeron 1047UE processor, 4GB DDR3, 16GB SSD — runs full switch OS, enabling robust telemetry, remote management, and automation.
NVIDIA UFM Ready
Integrate with UFM® (Unified Fabric Manager) to gain AI‑powered analytics, real‑time telemetry, predictive troubleshooting and proactive data center orchestration.
Flexible Airflow Options
MSB7800-ES2F provides power‑to‑core (P2C) airflow; ideal for hot‑aisle containment. This aligns with standard data center cooling patterns.
Technology: SHARP & In‑Network Acceleration
Traditional MPI operations require multiple passes of data between endpoints, consuming CPU cycles and increasing job completion time. NVIDIA SHARP technology integrates collective acceleration directly into the switch fabric. By performing arithmetic reductions (sum, min, max, etc.) as data passes through the aggregation nodes, the SB7800 reduces the number of packets traversing the network by up to a factor of 4× for certain workloads. This breakthrough not only cuts MPI operation time dramatically but also liberates valuable CPU resources for actual computation. Combined with Remote Direct Memory Access (RDMA) over Converged Ethernet (RoCE) support and native InfiniBand, the MSB7800-ES2F excels in HPC, deep learning, and large‑scale simulations.
Typical Deployments
- High‑Performance Computing (HPC) clusters — weather modeling, genomics, CFD
- AI & Machine Learning training farms — distributed training across GPU servers
- Top‑of‑Rack leaf in fat‑tree or dragonfly+ topologies
- High‑frequency trading environments requiring deterministic low latency
- Storage networks (NVMe over Fabrics) and hyperconverged infrastructures
Technical Specifications
| Parameter | Specification |
|---|---|
| Ports | 36 x QSFP28 (100Gb/s InfiniBand per port) |
| Aggregate Throughput | 7.2 Tb/s non‑blocking bidirectional |
| Latency | Ultra‑low port latency (typical <130ns, please consult NVIDIA datasheet) |
| CPU / System | Intel Celeron 1047UE dual-core, 4GB DDR3 RAM, 16GB SSD |
| Software | MLNX-OS (internally managed) |
| Management ports | 1x RJ45, 1x RS232 (console), 1x USB |
| Power supply | 1+1 redundant & hot‑swappable, AC input 100‑127VAC / 200‑240VAC, 80 Plus Gold, ENERGY STAR certified |
| Airflow | Power‑to‑core (P2C) — front‑to‑rear cooling |
| Dimensions (HxWxD) | 1.7 in (43.6 mm) x 16.85 in (433.2 mm) x 27 in (590.6 mm) |
| Weight | 11.978 kg (approx. 26.4 lbs) |
| Operating temperature | 0°C to 45°C |
| Non‑operating temperature | -40°C to 70°C |
| Humidity (operating) | 10% - 85% non‑condensing |
| Altitude | Up to 3,200 m |
| Safety & compliance | RoHS, CE, FCC, VCCI, ICES, RCM, cTUVus, CU |
Buyer Checklist for MSB7800-ES2F
- Confirm airflow: P2C (power-to-core) matches your rack cooling design.
- Ensure available AC power (100‑240V) and redundancy requirements.
- Select QSFP28 cables or optics based on distances (copper vs optical).
- Plan for subnet manager (internal or external) for InfiniBand fabric.
- Evaluate need for UFM licenses if advanced telemetry required.
- Verify rack depth: 590.6 mm (27 in) standard depth.
Important: Always confirm airflow direction (P2C or C2P) before ordering to match your rack cooling strategy. The MSB7800-ES2F is P2C. Rail kit included. Transceivers/cables sold separately. For specifications not explicitly listed (e.g., specific latency numbers per port under 100% load), please consult factory or request official datasheet.
About Hong Kong Starsurge Group Co., Limited
Founded in 2008, Starsurge is a technology-driven provider of network hardware, IT services, and system integration solutions. With a global customer base spanning government, healthcare, manufacturing, education, finance, and enterprise sectors, we deliver reliable networking infrastructure including switches, NICs, wireless controllers, cabling, and IoT solutions. Our experienced technical and sales teams ensure responsive service, custom development, and multilingual support. By partnering with Starsurge, clients build scalable, future-proof networks with a customer-first approach.
For volume quotes, custom firmware imaging, or extended warranty on NVIDIA MSB7800 series — contact our InfiniBand specialists today.
Möchten Sie mehr über dieses Produkt erfahren?