HPE Apollo 6000 Chassis
Extreme compute performance in a high-density package

Overview:

The HPE Apollo k6000 Chassis is designed with density optimization and HPC solution integration in mind to address these demands. The new modular, fully integrated, and highly flexible chassis is designed to hold the Hewlett Packard Enterprise Gen10 compute servers to fit your specific HPC workloads. It accommodates up to 24 HPE ProLiant XL230k Gen 10 Server trays, redundant power and cooling, Ethernet and high speed fabric switches to address various HPC workload needs. It is a performance optimized, air-cooled solution that fits in customer’s space limitations. This solution offers outstanding configuration flexibility, simplified administration and rack-scale efficiency that lowers the total cost of ownership (TCO) needed for mass scale HPC deployments.

• Extreme Compute Capabilities with Flexibility
  • The HPE Apollo k6000 Chassis is a single 42U rack, 3 air-cooled chassis that take up only 36U and leave 6U for top of rack switches or other options. The chassis require 1.2m depth racks.
  • This 12U chassis supports 24 front cold aisle accessible nodes and IO options suitable for HPC deployments.
• High Density Solution That is Easy to Manage and Service
  • HPE Apollo k6000 Chassis supports 6 Hot-plug redundant 2650W power supplies and fans for cooling top bin processor.
  • Up to two high speed InfiniBand EDR or two Omni-Path fabric switches are supported for high bandwidth configurations that reduce cabling and reduces stranded ports.
  • Provides an option for HPE Apollo 10GbE Pass Thru Modules for customers who want to use their favorite vendor top of rack switch or the HPE Apollo 10/40GbE Ethernet Switch that reduces cable complexity along with simplicity of servicing and managing.
  • With integrated design, the reliability, accessibility, serviceability, and manageability are simplified.

Fast, resilient and secure compute, storage and fabric technologies, with rack-level efficiencies delivering exceptional price/performance

Whether you’re designing an airplane, discovering an oil reservoir, creating a feature‑length animated film, detecting fraud, or mapping the human genome—high-performance computing (HPC) enables you to bring more innovative, higher-quality products and services to the market faster than ever before. In many cases, HPE solution for HPC workloads makes it possible for you to solve problems that simply could not be solved otherwise.

Even so, enterprises are challenged to solve these highly complex computational problems quickly and with lower IT overhead—while minimizing unexpected costs and simplifying rack-level HPC deployments.

To address the growing demand for HPC and the relentless pursuit of efficiency, HPE has taken the lead on a new approach—thinking beyond the server and designing a rack-level solution that gives you the right compute at the right economics. The HPE Apollo 6000 Gen10 System offers you excellent compute performance with rack-level air-cooled density, and flexibility to tailor the system to precisely meet the most demanding HPC workload requirements.

For comprehensive HPE solution you may choose the HPC software suite and HPE Pointnext Services to build and support IT at scale to drive your business success.

Features:

Versatile Performance, Efficiency, and Time to Value

For IT managers who need to tackle the most complex problems quickly, the HPE Apollo 6000 Gen10 System’s new integrated design allows deploying hundreds of servers quickly and use the clusters immediately. Leading edge technologies of the system are optimized to deliver performance and conserve energy. Integrated design simplifies deployment and comprehensive management tools lower IT overhead.

Enjoy leading-edge technology and performance

• Achieve 323 TFLOPS per rack with Intel Xeon Processor Scalable family delivering up to a 2X performance increase over earlier generation processors
• Get the latest compute, storage, and fabric technologies available today, in an architecture future-proofed to support upcoming technologies
• Drive rack-scale efficiency
• Benefit from rack-level reliability, availability, serviceability, and manageability (RASM) features through an integrated design
• Quickly deploy, service, and manage the compute and storage with cold aisle front accessible nodes

Lower your TCO

• Lower power and space requirements with an optimized architectural integrated design
• Eliminate stranded switch ports with an optimized design aligned to fabric radix

HPE Apollo K6000 Chassis Features

• 12U air-cooled chassis
• 24 front-accessible nodes

Highly integrated chassis:

• Hot-plug redundant power supplies with common cooling
• A choice between high-speed InfiniBand Enhanced Data Rate (EDR) or Intel Omni-Path Architecture (OPA) switches
• 10GbE switch or pass-through module

High-Performance Fabric Interconnects

All HPE Apollo 6000 Gen10 Systems support the latest high-bandwidth, low-latency interconnect technologies. Choose between InfiniBand, which provides the performance and scalability required by HPC clusters and data center applications or Intel OPA, which delivers HPC workloads and scales to tens of thousands of servers.

System Management

Depending on their preference, customers can choose from the following system management software:

• HPE Performance Cluster Manager
  Fully integrated system management solution offering all the functionalities you need to manage your HPE Linux-based high performance computing (HPC) clusters, including HPE Apollo 6000, all day everyday including system setup, hardware monitoring and management and cluster health management, image management and software updates as well as power management. The software also integrates with leading HPC ISV and open source software solutions.

Alternatively, to manage heterogeneous clusters or for customers with additional requirements, HPE also offers:

• Bright Cluster Manager
  Software from Bright Computing automates the process of building and managing Linux clusters in the data center and in the cloud offering system monitoring and management, provisioning, GPU management, cloud bursting and more.

Besides Bright Cluster Manager, Bright Cluster Manager for Science Data and Bright OpenStack are also available.

Specifications:

Extreme compute configuration N + 0 (15.9 kW)	Typical configuration N + 1 (13.2 kW)
Node with 2 x 165 W SKL	Node with 2 x 145 W SKL
12 DDR4 DIMMs	12 DDR4 DIMMs
2 SATA HDDs	2 SATA HDDs
2 x EDR Mezzanine Adapter + switch	EDR Mezzanine Adapter + switch
2 x 10/40GbE switch	10/40GbE switch
APM module	APM module
4 x front and 12 x rear fans	4 x front and 12 x rear fans

HPE ProLiant XL230k Gen10 Server
Form factor	HPE ProLiant XL230k Gen10 Server is a single-slot tray for the HPE Apollo k6000 chassis
Processors	The Intel Xeon Processor Scalable family including Intel Xeon Platinum Processor
Cores	4/6/8/12/14/16/18/20/22/24/26/28
Chipset	Intel C622 series chipset
Max. processor speed	3.6 GHz
Drive description	4 SFF SAS/SATA/NVMe
Supported drives	Hot-plug 2.5-inch SAS/SATA
Memory slots	16 x DDR4-2666 DIMMs 12 x RDIMMs/LRDIMMs 4 x 3D XPoint
Memory max.	1024 GB (16 x 64 GB) per server tray
Memory type, ECC	DDR4; RDIMM/LRDIMM 2666 MHz
Network options	2 x 10GbE integrated ports, InfiniBand EDR or Intel OPA Mezzanine cards
Storage controller	HPE Dynamic Smart Array S100i SATA Controller HPE Smart Array E208i-p Controller HPE Smart Array P408i-p Controller
Expansion slots	2 x InfiniBand EDR or Intel OPA Mezzanine Adapters PCIe slot options: 1 x external x 16 low profile 1 x internal and 1 x external x 8 low profile PCIe Supports –F Omni-Path directly off CPU (independent of above I/O options)
USB ports	1 internal and 2 external via serial, USB, video (SUV) port
System Management	Embedded Management: iLO 5 Cluster Management: HPE Performance Cluster Manager
OS support	Microsoft Windows Server Red Hat Enterprise Linux 7 and 8 SUSE Linux Enterprise Server (SLES) 11.4 or later VMware ESX CentOS

Hardware Specs:

The HPE Apollo k6000 Chassis is designed with density optimization and HPC solution integration in mind to help you manage and scale to your HPC computing demands. The new modular HPE Apollo k6000 Chassis is designed to hold the next generation of compute servers to fit your specific HPC workloads.

The new modular, fully integrated, and highly flexible HPE Apollo k6000 Chassis accommodates up to 24 XL230k server trays, redundant power and cooling, ethernet and high speed fabric switches to address various HPC workload needs. The Apollo k6000 System is a performance optimized, air-cooled solution that fits in customer’s space limitations. This solution offers outstanding configuration flexibility, simplified administration and rack-scale efficiency that lowers the total cost of ownership needed for mass scale HPC deployments.

Cooling concerns are reduced by 12 hot-pluggable dual rotor fans while the chassis power can be managed by either HPE Chassis Controller or enhanced (simplified) with optional HPE Apollo Platform Manager (APM) which allows granular power control at rack level.

1. 1. HPE Apollo k6000 Chassis
   Front chassis components:
2. Server trays (qty. depends on configuration ordered)
3. Front chassis fan modules (4)
   Rear chassis components:
4. HPE Apollo 6000 dual-rotor fan modules (12) (fan type depends on the configuration ordered)
   Rear chassis components continued:
5. Chassis controller or HPE Platform Manager
   • Power data management cable (1) (Not shown)
   • APM power data management cable (1) (Not shown)
6. High-speed fabric switches
7. Data switches
8. Power supplies (6)
   Cables (per chassis) – (Not shown)
   • Power supply cables (3)
   • 2.5M 20 Pin Consolidated Management w/Latch Cable
   • APM USB to DB9 cable (1)

Front View with server bay numbering

Rear View with I/O module bay numbering

Views:

Services:

HPE Pointnext

HPE Pointnext leverages our breadth and depth of technical expertise and innovation to help to accelerate digital transformation. A comprehensive portfolio that includes—Advisory, Professional, and Operational Services is designed to help you evolve and grow today and into the future.

Operational Services

• HPE Flexible Capacity is a new consumption model to manage ondemand capacity, combining the agility and economics of public cloud with the security and performance of on-premises IT.
• HPE Datacenter Care offers a tailored operational support solution built on core deliverables. It includes hardware and software support, a team of experts to help personalize deliverables and share best practices, as well as optional building blocks to address specific IT and business needs.
• HPE Proactive Care is an integrated set of hardware and software support including an enhanced call experience with start to finish case management helping resolve incidents quickly and keeping IT reliable and stable.
• HPE Foundation Care helps when there is a hardware or software problem offering several response levels dependent on IT and business requirements.

Advisory Services includes design, strategy, road map, and other services to help enable the digital transformation journey, tuned to IT and business needs. Advisory Services helps customers on their journey to Hybrid IT, Big Data, and the Intelligent Edge.

Professional Services helps integrate the new solution with project management, installation and startup, relocation services, and more. We help mitigate risk to the business so there is no interruption when new technology is being integrated in the existing IT environment.

Documentation:

Download the HPE Apollo 6000 Chassis Datasheet (.PDF)