Windows HPC

Feature

Easy to deploy, manage and scale your cluster with existing Windows based infrastructure.
Lowers total cost of ownership due to readily available Windows expertise for both development and administration.
Can deliver performance equal or superior to Linux alternatives
Support for GPGPU’s enabled rack-mountable systems with Ethernet or Infiniband Interconnects.
Accelerates computation for Excel 2010 workbooks
Support for using idle cycles of workstation nodes for HPC computations
Built-in Diagnostics and Error reporting
Support for both batch oriented and service oriented architecture(SOA) applications
Highly optimized support for MPI, Networking and High Speed Interconnects
Integration with Active Directory provides enhanced security
Our servers provide up to 80% HPC system efficiency.
Microsoft HPC Server 2008 tool pack includes LIZARD® a push button benchmarking tool for your cluster

	Intel 8 Node Cluster
	System Hardware
Nodes	8 dual socket Intel Nodes
CPU	64-bit Quad-core Intel Xeon E5620 @ 2.4 GHz Stepping: B1
Cache	12 MB Intel Smart Cache per processor
FLOPs	614 Gflops Peak Performance per Cabinet
Main Memory	Up to 192 GB ECC DDR3 (1333/1066/800MHz) per node
Interconnect	Gigabit Ethernet QDR 40 Gbps Infiniband
Network Switch	16-port Gigabit Ethernet 18-port Infiniband QDR Switch
Storage Node	3U 14 bay rackmount server
Parallel File System options	Panasas Active Storage, GPFS, Lustre
Reliability Features (Hardware)	Full ECC memory protection Redundant power supplies Redundant cooling fans Redundant management servers Redundant management network Redundant Infiniband network Internal RAID1 disk capability
Reliability Features (Software)	Redundant management servers with software support for failover redundant I/O servers with software support for failover redundant management networks with software support for message retry and failover redundant Infiniband networks with software support for load balancing message retry and failover stateless management allows immediate recovery
Operating System	Head nodes: x64-based versions of Windows Server 2008 R2 Standard, Enterprise, Datacenter, or HPC Edition. Compute nodes: x64-based versions of Windows Server 2008 or Windows Server 2008 R2 Standard, Enterprise, Datacenter, or HPC Edition Broker nodes: x64-based versions of Windows Server 2008 R2 Standard, Enterprise, Datacenter, or HPC Edition Workstation nodes: x86-based or x64-based processors editions of Windows 7 Professional or Enterprise *Note: To enable failover clustered (aka High Availability or HA) the operating system for the head or broker nodes must use either Windows Server 2008 R2 Enterprise or Datacenter editions.
Message Passing Libraries	Microsoft MPI library
Rack Cabinet	15U 19”
	System Software
Cluster Management options	Microsoft HPC Cluster Manager
Job Scheduler & Resource Manager Options	Microsoft HPC Job Scheduler
Compiler options	Visual C++, C#, F#, Visual Basic PGI* PathScale*
Debugger options	Microsoft HPC Cluster Remote Debugger Allinea DDT* TotalView*
	Closed-Loop Services and Solution Management
Support and Services	Up-front consulting, pre-integration and testing with pre-sales and post-sales support Support for Linux operating environments with configurations that provide exceptional performance across a wide range of HPC applications.

	Intel 16 Node Cluster
	System Hardware
Nodes	16 dual socket Intel Nodes
CPU	64-bit Quad-core Intel Xeon E5620 @ 2.4 GHz Stepping: B1
Cache	12 MB Intel Smart Cache per processor
Main Memory	Up to 192 GB ECC DDR3 (1333/1066/800MHz) per node
Interconnect	Gigabit Ethernet QDR 40 Gbps Infiniband
Network Switch	24-port Gigabit Ethernet 24-port Infiniband QDR Switch
Storage Node	3U-4U 14/18 bay rackmount server
Parallel File System options	Panasas Active Storage, GPFS, Lustre
Reliability Features (Hardware)	Full ECC memory protection Redundant power supplies Redundant cooling fans Redundant management servers Redundant management network Redundant Infiniband network Internal RAID1 disk capability
Reliability Features (Software)	Redundant management servers with software support for failover redundant I/O servers with software support for failover redundant management networks with software support for message retry and failover redundant Infiniband networks with software support for load balancing message retry and failover stateless management allows immediate recovery
Operating System	Head nodes: x64-based versions of Windows Server 2008 R2 Standard, Enterprise, Datacenter, or HPC Edition. Compute nodes: x64-based versions of Windows Server 2008 or Windows Server 2008 R2 Standard, Enterprise, Datacenter, or HPC Edition Broker nodes: x64-based versions of Windows Server 2008 R2 Standard, Enterprise, Datacenter, or HPC Edition Workstation nodes: x86-based or x64-based processors editions of Windows 7 Professional or Enterprise *Note: To enable failover clustered (aka High Availability or HA) the operating system for the head or broker nodes must use either Windows Server 2008 R2 Enterprise or Datacenter editions.
Message Passing Libraries	Microsoft MPI library
Rack Cabinet	36U 19”
	System Software
Cluster Management options	Microsoft HPC Cluster Manager
Job Scheduler & Resource Manager Options	Microsoft HPC Job Scheduler
Compiler options	Visual C++, C#, F#, Visual Basic PGI* PathScale*
Debugger options	Microsoft HPC Cluster Remote Debugger Allinea DDT* TotalView*
	Closed-Loop Services and Solution Management
Support and Services	Up-front consulting, pre-integration and testing with pre-sales and post-sales support Support for Linux operating environments with configurations that provide exceptional performance across a wide range of HPC applications

	AMD 8 Node Cluster
	System Hardware
Nodes	8 dual socket AMD Nodes
CPU	64-bit Opteron Quad-core Lisbon @2.6 GHz 64-bit Opteron 6-core Lisbon @2.8 GHz 64-bit Opteron 8-core Magny-cours @2.4 GHz 64-bit Opteron 12-core Magny-cours @2.3 GHz
Cache	6M L3 Cache -Lisbon L2 – 512K/core, L3 - 12MB of shared L3 Cache-Magny-cours
Main Memory	Up to 64 GB Fully-buffered ECC DDR2 SDRAM per node
Interconnect	Gigabit Ethernet QDR 40 Gbps Infiniband
Network Switch	16-port Gigabit Ethernet 18-port Infiniband QDR Switch
Storage Node	3U 14 bay rackmount server
Parallel File System options	Panasas Active Storage, GPFS, Lustre
Reliability Features (Hardware)	Full ECC memory protection Redundant power supplies Redundant cooling fans Redundant management servers Redundant management network Redundant Infiniband network Internal RAID1 disk capability
Reliability Features (Software)	Redundant management servers with software support for failover redundant I/O servers with software support for failover redundant management networks with software support for message retry and failover redundant Infiniband networks with software support for load balancing message retry and failover stateless management allows immediate recovery
Operating System	Head nodes: x64-based versions of Windows Server 2008 R2 Standard, Enterprise, Datacenter, or HPC Edition. Compute nodes: x64-based versions of Windows Server 2008 or Windows Server 2008 R2 Standard, Enterprise, Datacenter, or HPC Edition Broker nodes: x64-based versions of Windows Server 2008 R2 Standard, Enterprise, Datacenter, or HPC Edition Workstation nodes: x86-based or x64-based processors editions of Windows 7 Professional or Enterprise *Note: To enable failover clustered (aka High Availability or HA) the operating system for the head or broker nodes must use either Windows Server 2008 R2 Enterprise or Datacenter editions.
Message Passing Libraries	Microsoft MPI library
Rack Cabinet	15U 19”
	System Software
Cluster Management options	Microsoft HPC Cluster Manager
Job Scheduler & Resource Manager Options	Microsoft HPC Job Scheduler
Compiler options	Visual C++, C#, F#, Visual Basic PGI* PathScale*
Debugger options	Microsoft HPC Cluster Remote Debugger Allinea DDT* TotalView*
	Closed-Loop Services and Solution Management
Support and Services	Up-front consulting, pre-integration and testing with pre-sales and post-sales support Support for Linux operating environments with configurations that provide exceptional performance across a wide range of HPC applications.

	AMD 16 Node Cluster
	System Hardware
Nodes	16 dual socket AMD Nodes
CPU	64-bit Opteron Quad-core Lisbon @2.6 GHz 64-bit Opteron 6-core Lisbon @2.8 GHz 64-bit Opteron 8-core Magny-cours @2.4 GHz 64-bit Opteron 12-core Magny-cours @2.3 GHz
Cache	6M L3 Cache -Lisbon L2 – 512K/core, L3 - 12MB of shared L3 Cache-Magny-cours
Main Memory	Up to 64 GB Fully-buffered ECC DDR2 SDRAM per node
Interconnect	Gigabit Ethernet QDR 40 Gbps Infiniband
Network Switch	24-port Gigabit Ethernet 24-port Infiniband QDR Switch
Storage Node	3U-4U 14/18 bay rackmount server
Parallel File System options	Panasas Active Storage, GPFS, Lustre
Reliability Features (Hardware)	Full ECC memory protection Redundant power supplies Redundant cooling fans Redundant management servers Redundant management network Redundant Infiniband network Internal RAID1 disk capability
Reliability Features (Software)	Redundant management servers with software support for failover redundant I/O servers with software support for failover redundant management networks with software support for message retry and failover redundant Infiniband networks with software support for load balancing message retry and failover stateless management allows immediate recovery
Operating System	Head nodes: x64-based versions of Windows Server 2008 R2 Standard, Enterprise, Datacenter, or HPC Edition. Compute nodes: x64-based versions of Windows Server 2008 or Windows Server 2008 R2 Standard, Enterprise, Datacenter, or HPC Edition Broker nodes: x64-based versions of Windows Server 2008 R2 Standard, Enterprise, Datacenter, or HPC Edition Workstation nodes: x86-based or x64-based processors editions of Windows 7 Professional or Enterprise *Note: To enable failover clustered (aka High Availability or HA) the operating system for the head or broker nodes must use either Windows Server 2008 R2 Enterprise or Datacenter editions.
Message Passing Libraries	Microsoft MPI library
Rack Cabinet	36U 19”
	System Software
Cluster Management options	Microsoft HPC Cluster Manager
Job Scheduler & Resource Manager Options	Microsoft HPC Job Scheduler
Compiler options	Visual C++, C#, F#, Visual Basic PGI* PathScale*
Debugger options	Microsoft HPC Cluster Remote Debugger Allinea DDT* TotalView*
	Closed-Loop Services and Solution Management
Support and Services	Up-front consulting, pre-integration and testing with pre-sales and post-sales support Support for Linux operating environments with configurations that provide exceptional performance across a wide range of HPC applications

For drivers and software support please use our FTP:
ftp.rackmountpro.com

Please contact our sales team for FTP credentials.