QuickSpecs HPE Cray Supercomputing EX

Overview

HPE Cray Supercomputing EX

The HPE Cray Supercomputing EX is a liquid cooled blade-based, high-density clustered computer
system designed from the ground up to deliver the utmost in performance, scale, and density. The basic
building block of the HPE Cray Supercomputing EX is the EX4000 liquid cooled cabinet or EX2500 liquid
cooled rack. The EX4000 cabinet is a sealed unit using closed-loop cooling technology and does not
exhaust heated air into the data center. The EX2500 offers the same sealed closed-loop cooling
capabilities as the EX4000. However, it also offers the ability to use part of the rack for air cooled hardware
in certain configurations. In both configurations, direct attached liquid cooled cold plates provide for
efficient heat removal from high power devices including processors, GPUs, and switches via a cooling
distribution unit (CDU).

HPE Cray Supercomputing EX - Closed and With Trim

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 1

QuickSpecs HPE Cray Supercomputing EX

Overview
HPE Cray Supercomputing EX4000 System Details
A single cabinet can accommodate up to 64 compute blade slots within 8 compute chassis. The cabinet is
not configured with any cooling fans. All cooling needs for the cabinet are provided by direct liquid cooling
and the CDU. This approach to cooling provides greater efficiency for the rack-level cooling, decreases
power costs associated with cooling (no blowers) and utilizes a single water source per CDU.
One cabinet supports the following:

8 compute chassis
4 power shelves with a maximum of 8 rectifiers per shelf- 32 total 15kW rectifiers per cabinet.
Notes: 1 rectifier per shelf is used for redundancy

4 PDUs (1 per power shelf)

4 power input whips (3-phase)
Maximum of 64 compute blades
Maximum of 64 HPE Slingshot switch blades

Single Cabinet - Doors Closed Without CDU

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 2

QuickSpecs HPE Cray Supercomputing EX

Overview

HPE Cray Supercomputing EX 2500 System Details

A single rack can accommodate up to 24 compute blade slots within 3 compute chassis. In this
configuration, the rack is not configured with any cooling fans. All cooling needs for the cabinet are
provided by direct liquid cooling and the CDUs. This approach to cooling provides greater efficiency for the
rack-level cooling, decreases power costs associated with cooling (no blowers) and utilizes a single water
source per CDU.
One rack supports the following:

Up to 3 compute chassis
Up to 3 power shelves with 4 rectifiers per shelf - 12 total 15kw rectifiers per rack.
Notes: 1 rectifier per shelf is used for redundancy

3 PDUs (1 per power shelf)

3 power input whips (3-phase)
Maximum of 24 compute blades
Maximum of 24 HPE Slingshot switch blades
Up to 2 in-rack CDUs for a max of 145KVA cooling capacity
Notes: 1 CDU is included by default in support of one compute chassis and will not show up as a line
item in the configuration. The second CDU will show up as a line item in the configuration once two or
more chassis are added to the configuration .

Single EX2500 rack - Doors Closed

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 3

QuickSpecs HPE Cray Supercomputing EX

Standard Features

Compute Chassis
The compute chassis is a mechanical assembly that provides power, cooling, system control, and network
fabric for up to 8 compute blade slots. 8 chassis are installed in the EX4000 and up to 3 chassis are
installed in the EX2500.

The features of the compute chassis are as follows:

8 compute blade slots

8 HPE Slingshot switch blade slots
One power/signal midplane

Compute and Accelerator Blades

Blades have three basic sections: computation, memory, and I/O and consume one blade slot in the
compute chassis. The following blades are designed for the HPE Cray EX Supercomputer

HPE Cray Supercomputing EX4252

The features of this compute blade are as follows:

Four 2-socket CPU nodes

AMD 4th Gen EPYCTM (Genoa - Zen4 up to 96 Cores
AMD 4th Gen EPYCTM (Bergamo - Zen4c up to 128 Cores)
AMD 5th Gen EPYCTM (Turin Dense 400W - Zen5/5c up to160 Cores)
12 DIMMs per CPU socket (1DPC)
Up to 64 GB DIMMs at up to 4800 MT/s for Genoa and Bergamo Processors
Up to 64 GB DIMMs at up to 6400 MT/s for Turin 400W Processors
Up to 8 HPE Slingshot 200Gbit/sec ports per blade
0 or 1 local NVMe M.2 SSD per node (up to 4 per blade)
1 Board Management Controllers (BMC) per blade
Cooled with cold plate

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 4

QuickSpecs HPE Cray Supercomputing EX

Standard Features
HPE Cray Supercomputing EX4252 Gen 2
The features of this compute blade are as follows:

Four 2-socket CPU nodes

AMD 4th Gen EPYCTM (Genoa - Zen4 up to 96 Cores)
AMD 4th Gen EPYCTM (Bergamo - Zen4c up to 128 Cores)
AMD 5th Gen EPYCTM (Turin Dense 400W - Zen5/5c up to 160 Cores)
AMD 5th Gen EPYCTM (Turin Dense 500W - Zen5/5c up to 192Cores)
12 DIMMs per CPU socket (1DPC)
Up to 64 GB DIMMs at up to 4800 MT/s for Genoa and Bergamo Processors
Up to 64 GB DIMMs at up to 6400 MT/s for Turin 400W / 500W Processors
Up to 8 HPE Slingshot 200Gbit/sec ports per blade
0 or 1 local NVMe M.2 SSD per node (up to 4 per blade)
1 Board Management Controllers (BMC) per blade
Cooled with cold plate

HPE Cray Supercomputing EX420

The features of this compute blade are as follows:

Four 2-socket CPU nodes

Support for the 4th Gen Intel Xeon scalable processor stack (XCC and HBM)
8 DIMMs per CPU socket (1DPC)
Up to 64 GB DIMMs at up to 4800 MT/s
Up to 8 HPE Slingshot 200Gbit/sec ports per blade
0 or 1 local NVMe M.2 SSD per node (up to 4 per blade)
2 Board Management Controllers (BMC) per blade
Cooled with cold plate

HPE Cray Supercomputing EX255a

The features of this accelerator blade are as follows:

Two 4-socket AMD InstinctTM MI300a Accelerator APU nodes

128GB HBM3 per APU
Up to 8 HPE Slingshot 200Gbit/sec ports per blade
0 or 1 local NVMe M.2 SSD per node (up to 2 per blade)
2 Board Management Controllers (BMC) per blade
Cooled with cold plate

HPE Cray Supercomputing EX254n

The features of this accelerator blade are as follows:

Two 4-socket Nvidia GH200 Grace Hopper Superchip nodes

96GB HBM3 per GPU; 120GB LPDDR per CPU
Up to 8 HPE Slingshot 200Gbit/sec ports per blade
0 or 1 local NVMe M.2 SSD per node (up to 2 per blade)
2 Board Management Controllers (BMC) per blade
Cooled with cold plate

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 5

QuickSpecs HPE Cray Supercomputing EX

Standard Features
Switch Chassis
The Slingshot switch blades are in the switch chassis and mounted to the rear of the compute chassis. The
purpose of the switch chassis is to provide a structure for orthogonally mounting the switch blades to the
compute chassis. There is no active backplane connecting the switches to the compute blades. Each
compute blade directly connects to one or more switch blades in the switch chassis using a cableless
connection. The switch chassis supports a maximum of eight Slingshot switch blades.

Compute Cabinet Rear View with Doors Open

HPE Slingshot Switch Blade

The following switch blade types are supported
The HPE Slingshot Switch blade is a 64 x, 200Gb/sec port switch designed for the switch chassis. Switch
blades are inserted into the rear of the cabinet and provide the high-speed network interface for the
compute blades. Each switch blade connects to all eight compute blades through orthogonal connectors
and provides fabric connections using copper and optical cables through its faceplate to expand the
network.
Each switch blade has 8 local connectors, with two ports per connector for a total of 16 downlink ports to
the eight compute blades. Each switch blade also has 24 QSFP-DD connectors with two 200 Gb/sec ports
per connector for a total of 48 copper or optical connections to the other switch blades in the cabinet and
other cabinets to create the high-speed fabric. The number of switch blades in a chassis depends on the
number of NIC injection points per compute node. For two-socket CPU blades such as the HPE Cray
EX425 or EX4252 or EX420, a typical configuration would be two switch blades in the switch chassis to
support the 4 nodes on the compute blade via the two port NIC Mezzanine card. These two switches
would service this configuration across all 8 compute blades in the chassis which consists of 32 nodes .
For GPU based blades, a typical configuration is four switch blades in order to server one NIC per GPU.

HPE Slingshot NIC Cards

Compute blades are outfitted with a mezzanine card that provides compute blade NIC connectivity to the
Slingshot switch blades. Each mezzanine card support two NICs through two PCIe buses. Each

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 6

QuickSpecs HPE Cray Supercomputing EX

Standard Features
mezzanine card is 100% direct liquid cooled through a cold plate. An "L0" copper cable connects each NIC
mezzanine card to the connector on the back of the compute blade. The compute blade will be the
determinant for which mezzanine cards are supported and the number of mezzanine cards that are
required per blade and whether there are options to configure the injection bandwidth per node (meaning
the number of NICs).
The following mezzanine card type are offered:
Dual port 100Gbit/sec Mellanox ConnectX-5 Ethernet Mezzanine Card
This mezzanine card is a two-port NIC design. Each of the two 100Gb/s Ethernet NIC port connects to a
host system using a PCIe Gen3 a x16 channel. Solutions with this NIC can utilize programming
environment support for HPE Cray MPI, OpenSHMEM, Chapel, UPC, as well as third-party software that
utilizes the RDMA-Over-Converged-Ethernet (RoCE) protocol.
Dual port 200 Gbit/sec HPE Slingshot Mezzanine Adapter
The HPE Slingshot 200 Gbit/sec mezzanine card is based on HPE silicon designed to deliver
supercomputer-class performance and scalability with the HPE Slingshot Switches. The NICs incorporate
hardware features that extensively offload message processing across the range of HPC workloads and
message sizes to ensure compute resources operate with high efficiency due to less interruption and
latency from message and communications processing. The NICs also seamlessly complement operation
with high performance networking technologies built into the Slingshot switches to optimize the end-to-end
solution for congestion management, fine grain flow control, and traffic classes. The host interface is PCIe
Gen4 x16 with support for extended speed mode at 25GT/s (where supported by the CPU or GPU).
A full suite of HPC and Ethernet features is supported including strong progression of MPI message
matching and data transfer, along with programming environment support for HPE Cray MPI,
OpenSHMEM, Chapel, UPC, and industry software that can support the HPE Slingshot NIC through the
Libfabric interface.

Topology
The HPE Cray Supercomputing EX Supercomputer operates using the dragonfly topology for the high-speed
network fabric created using the Slingshot switches. This provides a lower cost, efficient, and highly scalable
approach over alternative topology designs. Any two endpoints in even the largest supercomputer can be
reached with 3 or fewer switch to switch hops which reduces latency. The design maximizes use of high-
speed copper cables by utilizing all-to-all connected switches in an EX cabinet as a dragonfly "group", each
of which in turn uses optical cables to connect all the groups in different cabinets. This creates substantial
efficiency by reducing the use of expensive optical cables and enabling multiple paths to deliver very high
global bandwidth.
Various dragonfly switch group sizes are available and selected depending on the requirements to optimize
across lowest system cost (by maximizing the number of copper cables), maximum system scale, and the
desired scalable unit of deployment. For EX4000 configurations, it is typical to configure the entire cabinet
as one switch group. Here the two typical configurations are the 16 switch group (2 switches in each of the 8
chassis in a cabinet) or a 32 switch group 4 switches in each of the 8 chassis in a cabinet). It is possible to
implement more than one group in a cabinet, such as configuring a cabinet that had 4 switches in each of
the 8 chassis in the cabinet as two 16-switch groups instead of a single 32-switch group.
In the EX2500 cabinet, because the maximum system size is usually smaller than for EX4000. Therefore, it
is typical to configure each of the chassis as a group, although for larger systems build with EX2500, groups
sizes that aggregate switches in several chassis together - within the same or adjacent racks - are
supported.
The chart below provides a reference for the group sizes supported:

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 7

QuickSpecs HPE Cray Supercomputing EX

Standard Features
Switch Maximum Number Maximum scale Example Use In HPE Cray EX Supercomputers
es per of Groups (with no (here captured
group global bandwidth as number of
tapering) NIC endpoints)
2 33 1056 One EX 2500 chassis populated with CPU blades
4 49 3,136 One EX 2500 chassis populated with CPU blades
8 81 10,368 Multi-chassis group to use EX2500 for large
system
16 145 37,120 Fully populated (8 chassis) EX4000 cabinet with CPU
blades
32 257 263,168 Fully populated (8 chassis) EX4000 cabinet with GPU
blades

CDU (Cooling Distribution Unit) for EX4000 and EX2500

The cooling distribution unit (CDU) is a liquid-to-liquid heat exchanger that is used to remove heat from
HPE Cray EX Supercomputer. The CDU uses a secondary loop to circulate a heat transfer liquid to the
cold sinks. The heat captured in the secondary loop is transferred to the facilities primary loop via a liquid-
to-liquid heat exchanger.
The CDU is designed to circulate and control the heat transfer fluid to the manifolds that are in each
chassis in the cabinet. The in-row CDU is rated for 1.6MW of cooling. One CDU supports a maximum of
four cabinets. The 4U in-rack CDU is rated for 70kW of cooling and up to two (2) can be installed in an
EX2500 rack providing up to 140kW of cooling.
The CDU consists of a cabinet (or a 4U chassis) that includes a heat exchanger, circulating pumps, control
valve, sensors, controller, valves, and piping. The CDU monitors room conditions and prevents
condensation by maintaining the secondary loop at a temperature above the room's dew point.
All functions, such as switching pumps (if applicable), controlling water temperature, etc., are managed by
the controller using user defined settings.

In-Row CDU Side View with no Doors or In-Rack 4U CDU Side View (EX2500)
Skins (EX4000)

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 8

QuickSpecs HPE Cray Supercomputing EX

Standard Features

Software Stack
HPE Cray EX supercomputers are complete solutions with software and hardware that are tightly
integrated and performance-tuned to offer the best system performance while bringing new standards in
flexibility, manageability, and resiliency to supercomputing.
HPE Cray supercomputer software stacks address the needs of both system administrators, developers,
and end-users.
Administrative Software
HPE Cray Supercomputing EX supercomputer users now have the option to choose either HPE
Cray System Management or HPE Performance Cluster Manager.
HPE Cray System Management - a built-for-scale system management solution offering administrators all
functionalities they need to keep the HPE Cray EX system healthy, utilized to the maximum and
accommodating wide range of workload requirements via -aaS experience. The software is built to manage
systems which can scale to Exascale deployments featuring:

Comprehensive monitoring and management of all aspects of the system: CPU/GPU, network
(integrated HPE Slingshot Fabric Manager), storage as well as power management and monitoring
combined with provisioning for operational efficiency.
Partitioning and batch or container orchestration enable customers to run a variety of HPC/AI/HPDA
workloads the way that makes the best use of their system without logistical constraints.
REST APIs & standard protocols enable full interoperability with existing monitoring, management,
and automation toolsets.
HPE Performance Cluster Manager - a comprehensive, flexible HPC system management solution that
enables fast setup, provisioning and monitoring including the following features

Hardware discovery and Linux operating system installation for compute and service nodes
Inventory management
Telemetry data collection and analysis
Alert monitoring and component diagnosis
Power resource monitoring and management
Software image management Developer Software
HPE Cray Programming Environment - is a fully integrated software development suite offering
programmers comprehensive set of tools for developing, porting, debugging, and tuning of their
applications so they can shorten application development time and accelerate their performance.
The programming environment is designed to make porting of existing applications easier with minimal
recording and changes to the existing programming models to simplify transition to the new hardware
architectures and configurations, such as HPE Cray EX systems.

Operating System
HPE Cray OS is a compute operating system based on SLES with enhancements. The enhancements
provide customers with capabilities specific to supercomputing and high-performance computing fully
supported by HPE Services. These modifications don't alter the ability to run standard Linux applications,
but rather enhance it for performance, scale, and reliability. We integrate and test these materials together
and package releases.
Overall
While HPE Cray System Management and HPE Cray Operating System are designed to support HPE Cray
EX systems with HPE Slingshot, HPE Cray Programming Environment product also supports other HPE
and HPE Cray HPC systems (using InfiniBand interconnect).
The software stack is supported by HPE Services.

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 9

QuickSpecs HPE Cray Supercomputing EX

Standard Features
Features
HPE Cray Supercomputing EX Supercomputer
Operating system HPE Cray Operating System or RedHat RHEL (HPE Performance
Cluster Manager only)
System Management and HPE Cray System Management or HPE Performance Cluster
Fabric software Manager
HPE Slingshot Network Manager
Workload Management Altair® PBS Professional
and Orchestration Slurm Workload Manager
Containers: Singularity & Docker
Software and Application HPE Cray Programming Environment
Development Tools:
Development
− Compiling environment
− Communication Libraries: HPE Cray MPI, SHMEM
− Scientific Libraries: LAPACK, ScaLAPACK, BLAS, libsci, IRT,
FFTW 3.0
− I/O Libraries: NETCDF, HDF5
− 3rd party programming environments:
ο AMD ROCm and AOCC
ο NVIDIA HPC SDK
ο GNU Compilers

Performance analysis tools

− Tools for performance analysis and optimization - versions for both
experienced and novice users
− Code parallelization assistant for application optimization via code
restructuring
− Visualization tool for quick assessment of severity of issues
− Debuggers: GDB for HPC, Valgrind for HPC, tools for stack trace
analysis & abnormal termination processing
− 3rd party debugger support: Arm® Forge, TotalViewTM by Perforce
DL/AI Tools: Deep learning plugin

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 10

QuickSpecs HPE Cray Supercomputing EX

Services and Support

Product Warranty
HPE offers a 13-month warranty on all HPE Cray-branded hardware components that begins at the time
of shipment and provides replacement or repair of failed hardware at HPE's discretion. This warranty
provides only the most basic customer hardware support and is designed for highly skilled customers that
intend to maintain their own systems. This HPE limited warranty does not provide any support or warranty
obligation for software, even if sold, delivered, or installed by HPE.

Installation
The HPE Cray EX system requires the following installation services:

Pre-installation activities and solution implementation:

HPE and the Customer determine all installation activities that must be completed prior to System
installation. The Customer agrees to complete all of the pre-installation activities required.This
includes HPE site engineering work onsite as may be described in the HPE Cray Site Preparation
Guide.
Solution Implementation: upon completion of the pre-installation activities, HPE will provide the
software components as set forth in the applicable system purchase agreement or bill of materials.
Any additional software installation or configuration will need to be documented separately and will
incur additional charges. This configuration service does not include any customer specific
configuration, customization or testing unless otherwise specified.

System testing and performance validation:

The HPE installation personnel will conduct tests to verify the health and performance of the System. The
tests are not intended to demonstrate application performance; the tests verify that the system
infrastructure is working properly and delivering the intended performance level. HPE manufacturing tests
and diagnostics will be used by installation personnel while onsite to validate that all hardware is
functional, meeting the same performance and functional specifications as tested at the factory. Any
additional testing that is required should be specified in a separate mutually agreed writing.

Hardware Maintenance Service Features

The HPE Cray EX system benefits from HPE's highest level of support for high-performance compute
'HPE Complete Care - Cray' that may include HPE presence onsite.

This service level offers customers access to the HPE Cray customer portal. Case logging is
available 24x7 by telephone or via this customer portal.
There is a choice of two maintenance coverage windows: 9x5 or 24x7. Onsite response time options
are Next Business Day, 4 hours, 2 hours, or 1 hour. When an issue is reported, an HPE technical
representative will arrive onsite within the response time window to identify and begin resolving the
issue.
HPE provides critical spare parts to reduce any downtime associated with failures or maintenance.
Critical spare parts may be located either onsite or at professionally managed regional spare part
depots that provide rapid transportation of spare parts to customer sites. Customers may elect to
supplement the HPE-owned spare parts inventory by purchasing additional spare parts.
HPE Cray EX customers have access to the support snapshot analyzer that collects, analyzes, and
reports support information for HPE air cooled and liquid cooled HPC, and HPE Cray ClusterStor
systems.
HPE Remote Support provides remote access and support. Capabilities range from a customer
having full control of a remote screen-sharing session to the HPE Services team having the ability to
log in securely as needed to resolve issues and perform administrative functions.

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 11

QuickSpecs HPE Cray Supercomputing EX

Services and Support

Software Support Features

Support for HPE developed software includes the following features:

Access to self-help resources on customer portal

− Ability to open and submit a support case
− Access to HPE knowledge articles
− Ability to download:

ο Software releases and updates, including BIOS and FW

ο Software Patches

Notification of key operational items through the field notice (FN) process
Assistance from HPE Services Services to resolve issues within the service level coverage window
for the hardware contract; assistance includes:
− Triage to investigate/analyze issues
− Confirmation whether the issue is hardware or software
Confirmation if the issue is related to an HPE-supported product or a third-party-supported product. If the
issue is with a HPE-supported product, HPE Services Services may provide configuration
recommendations, possible work arounds, and directions to install a later version or patch, and/or submit a
bug to get the issue fixed. For HPE products, HPE reserves the right to determine whether and how an
issue will be resolved.

Customized Software
Support is provided for products sold by HPE and with a valid HPE Services Services support agreement.
Support for third-party products without a related HPE Services Services support agreement requires the
user to contact the third-party vendor for assistance. If customers modify HPE-delivered software without
authorization from HPE, any issues resulting from the unapproved modifications fall outside of the
standard support service agreement and HPE is not responsible for any resulting defects, damage, failure,
performance degradation, or issues of any kind, or correction or remedy of same. HPE may require the
user to remove custom modifications to confirm that a modification is not the source of the issue.
Customers may request that HPE Services Services assist in making modifications to a product. HPE
Services Services will do its best to implement the request via a billable statement of work (SOW).

API and CLI Support

Support is available for HPE published APIs. Unpublished APIs are not eligible for support. Documentation
outlining published API best practices and limitations is available at support.hpe.com , accessible either
directly or through the HPE Cray customer portal. HPE will assist in determining if the API is working
correctly, if the documentation is incorrect, or if the issue is an enhancement request.
HPE Application Programming Interface (API) and Command Line Interface (CLI) features allow the
flexibility to configure and customize your system to optimize operations in your environment. These tools
have the ability to significantly alter your system operations. If not properly tested and implemented in a
controlled manner, they can introduce significant problems in your environment. When using these
features or otherwise modifying or altering APIs, customers take on the responsibility to resolve or mitigate
any issues they have introduced into the system.
HPE Services Services is not available to provide support to resolve issues that arise from the use of CLIs
or APIs in a form not identical to those published by HPE.

Customer Training
Training courses are taught by HPE system experts and combine lectures with hands-on labs to enhance

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 12

QuickSpecs HPE Cray Supercomputing EX

Services and Support

understanding and retention. The courses cover all aspects of using and maintaining an HPE system, from
system administration to application development, porting, and optimization. A full listing of the standard
HPE Cray training courses, along with their descriptions, can be found at
https://education.hpe.com/ww/en/training/portfolio/servers.html.
Subject to separate ordering arrangement, classes are scheduled on regular cycles at the HPE training
facilities and can be scheduled for onsite delivery. HPE also offers customized training courses and can
provide quotes for these courses based on the customer's needs.

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 13

QuickSpecs HPE Cray Supercomputing EX

Technical Specifications

HPE Cray Supercomputing EX4000 Supercomputer (cabinet)

Dimensions with 98 x 46.5 x 68.5 in (H x W x D)
overhead cable trays 2489 x 1181 x 1740 mm (H x W x D)
Weight: (Maximum) Up to 8000 lbs. (3629kg)
Floor Loading (Flat 362 lbs./sq ft (1767 kg/qs m) (Operational)
Base)
Compute blade chassis 8 compute blade chassis with integrated compute trays, switches, and power
Up to 7 + 1 redundant 15kW power supplies per 2 compute blade chassis
Cooling Closed-loop airflow with direct liquid cooling for high wattage components and
room neutral up to 32°C data center supply water.
Power Requirements Up to 400KVA with 480V
(Max) Up to 350KVA with 400V

HPE Cray Supercomputing EX2500 Supercomputer (rack)

Dimensions with overhead cable trays 90.65 x 35.43 x 67.86 in (H x W x D)
2302 x 900 x 1719 mm (H x W x D)
Dimensions without cable trays 78.78 x 35.43 x 67.86 (H x W x D)
2000 x 900 x 1719 (H x W x D)
Weight: (Maximum) Up to 3225 lbs. (1462 kg)
Floor Loading (Flat Base) 806 lbs per caster (365 kg per caster)
Compute blade chassis 8 compute blade chassis with integrated compute trays,
switches, and power
Up to 3 + 1 redundant 15kW power supplies per compute
blade chassis
Cooling Closed-loop airflow with direct liquid cooling for high wattage
components and room neutral up to 32°C data center supply
water.
Power Requirements (Max) Up to 141 kVA with 480V
Up to 128kVA with 400V

Compute Blade Options - (HPE Cray Supercomputing EX4252)

Form factor single-slot blade for the HPE Cray EX4252 compute chassis assembly
Processors AMD 4th Gen EPYCTM (Genoa - Zen4 up to 96 Cores
AMD 4th Gen EPYCTM (Bergamo - Zen4c up to 128 Cores)
AMD 5th Gen EPYCTM (Turin Dense 400W - Zen5/5c up to160 Cores)
Compute blade Four 2-socket CPU nodes
Memory/blade Up to 1536 GB per node, 24 DIMM slots (12 per CPU socket) per node
Memory technology 16, 32, and 64 GB DDR5 4800 MT/s ECC Registered DIMMs
Local storage 0 or 1 local NVMe M.2 SSD per node (up to 4 per blade)
Fabric options HPE Slingshot (1 or 2 injection ports per node)

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 14

QuickSpecs HPE Cray Supercomputing EX

Technical Specifications
Compute Blade Options - (HPE Cray Supercomputing EX4252 Gen2)
Form factor single-slot blade for the HPE Cray EX425 compute chassis assembly
Processors AMD 4th Gen EPYCTM (Genoa - Zen4 up to 96 Cores)
AMD 4th Gen EPYCTM (Bergamo - Zen4c up to 128 Cores)
AMD 5th Gen EPYCTM (Turin Dense 400W - Zen5/5c up to 160 Cores)
AMD 5th Gen EPYCTM (Turin Dense 500W - Zen5/5c up to 192Cores)
Compute blade Four 2-socket CPU nodes
Memory/node Up to 1536 GB per node, 24 DIMM slots (12 per CPU socket) per node
Memory technology 32, and 64 GB DDR5 6400 MT/s ECC Registered DIMMs
Local storage 0 or 1 local NVMe M.2 SSD per node (up to 4 per blade)
Fabric options HPE Slingshot (1 or 2 injection ports per node)

Compute Blade Options - (HPE Cray Supercomputing EX420)

Form factor single-slot blade for the HPE Cray EX420 compute chassis assembly
Processors Intel 4th Gen Xeon scalable processor stack (XCC and HBM)
Compute blade Four 2-socket CPU nodes
Memory/blade Up to 1024 GB per node, 16 DIMM slots (8 per CPU socket) per node
Memory technology 16, 32, and 64 GB DDR5 4800 MT/s ECC Registered DIMMs
Local storage 0 or 1 local NVMe M.2 SSD per node (up to 4 per blade)
Fabric options HPE Slingshot (1 or 2 injection ports per node)

Compute Blade Options - (HPE Cray Supercomputing EX255a)

Form factor single-slot blade for the HPE Cray EX255 compute chassis assembly
Processors The AMD Instinct MI300A integrates 24 AMD 'Zen 4' x86 CPU cores
with 228 AMD CDNATM 3 high-throughput GPU compute units
Compute blade Two 4-socket AMD InstinctTM MI300a Accelerator APU nodes
Memory/blade 128GB per APU;1024 GB per blade utilizing HBM3 memory
Memory technology HBM3
Local storage 0 or 1 local NVMe M.2 SSD per node (up to 2 per blade)
Fabric options HPE Slingshot (4 injection ports per node)

Compute Blade Options - (HPE Cray Supercomputing EX254n)

Form factor single-slot blade for the HPE Cray EX254 compute chassis assembly
Processors Nvidia GH200 Grace Hopper Superchip
Compute blade Two 4-socket Nvidia GH200 Grace Hopper Superchip nodes
Memory/blade 768GB HBM3 and 960GB LPDDR
Memory technology HMB3 (GPU) and LPDDR (CPU)
Local storage 0 or 1 local NVMe M.2 SSD per node (up to 2 per blade)
Fabric options HPE Slingshot (4 injection ports per node)

Integrated HPE Slingshot Switch Blade

Ethernet Ports 64 Ethernet ports (16 Host; 48 QSFP-DD ports)
Port capability 100/200 Gb/s per port
Switch fabric 12.8Tb/s
capability
Messages/s capability 1.2B/s

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 15

QuickSpecs HPE Cray Supercomputing EX

Technical Specifications

HPE Slingshot 200Gb 2-port Mezzanine Adapter (R4K44A)

Form factor EX Blade Mezzanine form factor
Dimensions 3.311 x 7.362 (H x W) (84.09mm x 186.99)
Weight: 0.396lbs (180g)
Physical connectivity Two L0 connectors to blade switch ports
Host connectivity Two PCIe Gen 4 x16 (Supports ESM speeds depending on CPU or GPU
availability)
Port capability - 200 IEEE 802.3cd/bs (200 Gbps) Ethernet over 4 x 50 Gbps (PAM-4) lanes
Gbps Proprietary cabling
Throughput per port Line rate
Port status Depending on blade type
Power and cooling 48W max
30W typical
Liquid-cooled

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 16

QuickSpecs HPE Cray Supercomputing EX

Summary of Changes

Date Version Action Description of Change

History
05-May-2025 Version 20 Changed Updated EX2500 Chassis CDU requirements. Added EX4252
Gen2 blade added, Technical Specifications sections were
updated for EX4252 (added Turin 400W support) and EX255a
(clarified the AMD Instinct MI300A integrates 24 AMD 'Zen 4'
x86 CPU cores with 228 AMD CDNATM 3 high-throughput
GPU compute units) Deleted discontinued blades EX425,
EX235a and EX235n
06-May-2024 Version 19 Changed Standard Features, Service and Support and Technical
Specifications sections were updated.
Removed section "Generative AI for SC"
15-Apr-2024 Version 18 Changed Standard Features, Service and Support and Technical
Specifications sections were updated.
Added Table of Contents, Section on Generative AI for SC,
and 4U CDU for EX2500
18-Mar-2024 Version 17 Changed Updated Standard Features - revised specifications for
EX254n
04-Dec-2023 Version 16 Changed EX255a blade added. Product names updated to comply with
Branding Guidelines
Overview, Standard Features and Technical Specifications
sections were updated
02-Oct-2023 Version 15 Changed EX254n blade added. Standard Features and Technical
Specifications sections were updated
17-Apr-2023 Version 14 Changed Standard Features section was updated
03-Apr-2023 Version 13 Changed Standard Features section was updated
06-Mar-2023 Version 12 Changed Standard Features and Technical Specifications sections were
updated
19-Sep-2022 Version 11 Changed Service and Support and Technical Specifications sections
were updated.
06-Sep-2022 Version 10 Changed Added Cray EX2500 information
16-May-2022 Version 9 Changed Service and Support and Technical Specifications sections
were updated.
04-Apr-2022 Version 8 Changed Standard Features and Technical Specifications sections were
updated
04-Oct-2021 Version 7 Changed Standard Features section was updated
07-Sep-2021 Version 6 Changed Standard Features section was updated
06-Jul-2021 Version 5 Changed Updated Software Development Tools.
Standard Features and Technical Specifications sections were
updated.
17-May-2021 Version 4 Changed Standard Features section was updated
06-Apr-2021 Version 3 Changed Overview, Standard Features and Technical Specifications
sections were updated.
05-Oct-2020 Version 2 Changed Service and Support section was updated.
03-Aug-2020 Version 1 New New QuickSpecs

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 17

QuickSpecs HPE Cray Supercomputing EX

Copyright
Make the right purchase
decision. Contact our
presales specialists.

© Copyright 2025 Hewlett Packard Enterprise Development LP. The information contained
herein is subject to change without notice. The only warranties for Hewlett Packard
Enterprise products and services are set forth in the express warranty statements
accompanying such products and services. Nothing herein should be construed as
constituting an additional warranty. Hewlett Packard Enterprise shall not be liable for
technical or editorial errors or omissions contained herein.

For hard drives, 1GB = 1 billion bytes. Actual formatted capacity is less.

a00094635enw - 16619 - WorldWide - V20 - 05-May-2025

DA - 16619 Worldwide QuickSpecs — Version 20 — 5-5-2025 Page 18