We use cookies to make your experience better.
To comply with the new e-Privacy directive, you agree to the privacy policy and our use of cookies.
HPE NVIDIA GB200 NVL72 by Compute Tray
SKU
S5E91A
| SKU | S5E91A |
|---|---|
| EAN | 0190017808345 |
| Manufacturer | HPE |
| Availability | Out of Stock |
Customer Experience
The NVIDIA GB200 NVL72 by HPE is supported by our extensive global installation, deployment, and support capabilities through HPE Services.
HPE teams of deployment engineers and project managers meet your delivery schedule to help enable your system is up and running as quickly as possible, at optimal performance with personalized customer deployment services.
High performance computing (HPC) and AI custom support services are tailored to meet your individual environment and customer requirements. With several levels of SLA coverage, we provide enhanced incident management with proactive support through dedicated remote and resident engineers.
We offer comprehensive on-site support through highly trained resident engineers, who work closely with your IT teams to help enable system availability and performance.
Our industry-leading performance engineering and benchmarking team is available to fine-tune your solution throughout the life of the system.
Advanced Direct Liquid Cooling from HPE
The NVIDIA GB200 NVL72 by HPE features a mix of air and liquid cooling to meet its demanding power requirements. Each rack consumes 132 kW of power, with 115 kW liquid cooled and 17 kW air cooled.
Hewlett Packard Enterprise offers proven in-row and rack mounted liquid cooling solutions validated for NVL72.
HPE brings five decades of innovation in liquid cooling and the expertise coming from delivering the world's largest direct-liquid cooled environments. [1]
HPE helps you prepare, deploy, test, and operate direct-liquid cooled environments with services such as site readiness assessment and planning, installation, connecting power/cooling, adding coolant, commissioning coolant distribution unit (CDU), leak detection, and thermal monitoring.
HPE experts can help with stabilization and ongoing support once the liquid-cooled environment is in operation.
Extreme Performance
The NVIDIA GB200 NVL72 by HPE system provides a unified, high-speed fabric that reduces communication bottlenecks, and boosts performance in scenarios that demand fast, efficient GPU-to-GPU data exchange.
The solution features a high-bandwidth, low-latency NVIDIA NVLink™ interconnect to create a 72 GPU single shared memory space.
NVIDIA Grace CPUs and NVIDIA Blackwell GPUs offer cutting-edge top-tier processing power and efficiency.
NVIDIA liquid cooled compute trays provide the necessary infrastructure to support high-density computing and NVIDIA NVLink™ Switch trays facilitate high-speed GPU-to-GPU interconnects for optimal data flow.
NVIDIA InfiniBand networking provides robust and reliable connectivity across the system.
Do you need a highly performant solution for training or inferencing of AI models over one trillion parameters? The NVIDIA GB200 NVL72 by HPE offers seamless integration of NVIDIA CPUs, GPUs, compute, switch trays, networking, and software. This powerful solution features a high-bandwidth, low-latency NVIDIA NVLink™ interconnect to create a 72 GPU single shared-memory space. Combined with HPE advanced direct liquid cooling technology and its industry-leading services and support, this offering delivers extreme performance, scalability, and efficiency for the largest AI models. HPE Services provides expertise for global installation and quick deployment of large AI clusters, helping enable stability and operational excellence, including vast experience with large direct-liquid cooled environments.
What is new supporting point:
48 RU MGX rack
NVIDIA BlueField-3 data processing units
HPE direct liquid cooling technology
HPE Services
72 NVIDIA Blackwell GPUs and 36 NVIDIA Grace CPUs interconnected through high-speed NVIDIA NVLink™
Up to 13.5 TB total HBM3E memory with 576 TB/s bandwidth
What is new supporting point:
48 RU MGX rack
NVIDIA BlueField-3 data processing units
HPE direct liquid cooling technology
HPE Services
72 NVIDIA Blackwell GPUs and 36 NVIDIA Grace CPUs interconnected through high-speed NVIDIA NVLink™
Up to 13.5 TB total HBM3E memory with 576 TB/s bandwidth
| Features | |
|---|---|
| Rack capacity | 48U |
| Technical details | |
|---|---|
| Chassis type | 48U Rackscale System |
| Rack capacity | 48U |
| Other features | |
| Chassis type | 48U Rackscale System |