NOVATTE

P10K - Xeon Phi based Clusters

NOVATTE P10K Xeon Phi^TM Cluster Appliance is APAC best preconfigured HPC system which brings plug-and-play simplicity for small to large deployments.

Using unified NOVATTE architecture, P10K Xeon Phi Cluster can be easily scaled from small research-lab cluster to large-scale several hundreds TFlops Supercomputer with almost linear performance increase.

To get best performance from the Intel® Xeon Phi™ Coprocessors Intel recommends to use Intel® Parallel Studio XE or Intel® Cluster Studio XE.

 Buy Intel Software together with NOVATTE Xeon Phi™ products and get 10% discount on your Software purchase!

Intel Xeon Phi Coprocessors

Utilize x86 architecture of Xeon Phi coprocessors to quickly integrate them into your existing workloads and code. Intel equipped Xeon Phis with their own embedded Linux OS making Xeon Phis in essence stand-alone x86 computers that interact with the host through fairly thin and simple drivers. That kind of unified HW and SW architecture brings a great benefit to the HPC Cluster users.

Intel Cluster Ready

All NOVATTE Xeon Phi Cluster Appliances are officially certified by Intel for Intel Cluster Ready program. Be confident your cluster will work as it should, right away, without worrying if components will work together or not.

High Performance and Scalability

Being agile and first to market, NOVATTE uses the latest possible technologies to accelerate its HPC Clusters and bring performance to the maximum. Directly connecting computing and management nodes with storage through non-blocking 56Gbps FDR InfiniBand network, NOVATTE unifies system architecture to decrease protocol bottlenecks and allow NOVATTE HPC Cluster almost linear performance scalability of up to several PFlops. Unification of NOVATTE architecture makes it easy to convert default NFS storage file system to Lustre Parallel File System for maximum performance, scale and failover.

Great Value, Low TCO

Due to the shorter “Technology Vendor – NOVATTE – End User” value chain and thus lower overheads and costs, NOVATTE P10K Cluster Appliance provides extremely attractive Price per GFlop and GFlops per kW figures. Excellent investment protection, increased CPU utilization rates, high density and simplified cluster management delivers an attractive total cost of ownership while fully addressing the big data requirements of even the most compute-intensive technical applications.

Exclusive benefits:

    - Intel Xeon Phi coprocessors based systems
    - Turnkey pre-installed complete solution - switch it on and start working

    - High scalability and flexibility through unified system architecture

    - Intel Cluster Ready certified

    - Easy to use Admin-friendly intuitive cluster management system

    - Highly competent instant support from the most experienced HPC engineers and practitioners in Asia

Sample configurations (X4000 Phi server with 4 x Xeon Phi 5110P)

	Base	Quarter	Half	Full	Extension
Nodes	2	4	8	16	19
TFlop per system (Rpeak)	9	17.8	35.3	70.3	83,399.2
kW per system	3.5	6.3	11.9	23.3	27.6
GFlops per kW	2,645.17	2,817.01	2,962.55	3,015.82	3,021.71
GB per Node	32	32	32	32	32
Storage	NFS, optional: NLA - NOVATTE Lustre Appliance

Specifications

Xeon Phi coprocessors

Intel® Xeon Phi^TM cards for NOVATTE Servers and Workstations

Speed up your calculations with combined power of Intel^® Xeon processors and Intel^® Xeon Phi^TM coprocessors.
 
Example: SAXPY


Utilize x86 architecture of Xeon Phi coprocessors to quickly integrate them into your existing workloads and code. Intel equipped Xeon Phis with their own embedded Linux OS making Xeon Phis in essence stand-alone x86 computers that interact with the host through fairly thin and simple drivers. That kind of unified HW and SW architecture brings a great benefit to the HPC Cluster users.

To get best performance from the Intel® Xeon Phi™ Coprocessors Intel recommends to use Intel® Parallel Studio XE or Intel® Cluster Studio XE.

	Xeon Phi  7120P	Xeon Phi  5110P	Xeon Phi  3120A and 3120P
Frequency	1.24 GHz	1.053 GHz	1.1 GHz
Cores	61	60	57
Memory size (GDDR5)	16 GB	8 GB	6 GB
Power Consumption	300 W	225 W	300 W
Performance Rpeak Double Precision	1.208 TFlops	1.011 TFlops	1.003 TFlops

Try Intel Xeon Phi coprocessors today on NODE

Buy Intel Software together with one of NOVATTE products and get 10% discount on your Software purchase!

More information on Intel® Software Development Tools can be found here.

X2000 Phi Server

NOVATTE Server Phi server portfolio - the collection of powerful and efficient Xeon Phi compute building blocks, purposely built for NOVATTE High Performance Computing Cluster Appliance .

Speed up your analysis and research with the dense and efficient Xeon Phi solution. Whichever system you choose, performance, efficiency and professional responsive support are the trademarks of all Xeon Phi rack server solutions.

To get best performance from the Intel® Xeon Phi™ Coprocessors Intel recommends to use Intel® Parallel Studio XE or Intel® Cluster Studio XE.

Buy Intel Software together with NOVATTE Xeon Phi™ products and get 10% discount on your Software purchase!

Architecture:

- Size: 1U chassis
- Xeon Phi: Up to two Intel® Xeon Phi^TM coprocessors
- CPU: One Intel® Xeon® E5 family processor
- Performance: Up to 2,194.8 TFlops of double precision performance
- Memory: Up to 256 GB 1600/1333MHz ECC Registered memory
- Storage: Up to 3x 3.5'' or 6x2.5" SATA hot-swap HDDs or SSDs
- Power: 1,400W High-efficiency Platinum level redundant power supply with PMBus
- Fans: Advanced fan speed control
- OS: Linux: CentOS, RHEL

Dimensions:

Power System:
 - Power consumption: 1,400 W

Warranty:
 - 3 Years