Nvidia GPU

Home Products GSA Support News About Us Contact Us Tracking

My Account | Live Chat | My Cart

Products

Special

1U Server Special

Hot Deal

PDF

About Us

Brochure

Product Line

Feature

Low in cost
Requires less power and reduced cooling
Cluster can easily fit in small space
Maximum Performance delivered by hundreds of parallel CUDA cores
Easy-to-deploy preconfigured Tesla GPU clusters customizable to your needs
Performance Advantages
515 Gigaflops double precision performance on Tesla C2050, M2050, and S2050 products
Large on-board memory with faster PCIe communication
NVIDIA GPU Direct for faster communication with infiniband
Optimized drivers for both Linux and Windows platforms
ECC protection for memories provide uncompromised data reliability
NVIDIA® Parallel DataCache™ Technology, accelerating algorithms such as physics solvers, ray-tracing, and sparse matrix multiplication where data addresses are not known beforehand
NVIDIA® GigaThread™ Engine, maximizing throughput with faster context switching, concurrent kernel execution, and improved thread block scheduling
CUDA programming environment with broad support of programming languages and APIs, including C, C++, OpenCL, DirectCompute, or Fortran
L1/L2 cache for improved bandwidth and efficient data sharing

Full double precision floating point performance
515 GigaFlops on Tesla C2050, M2050, and S2050 products
Higher double precision than consumer products
Faster PCIe communication
The only NVIDIA product with two DMA engines for bi-directional PCIe communication
Higher performance on technical applications with large data sets
Larger on-board memory (3 Gigabyte and 6 Gigabyte)
Faster communication with InfiniBand using NVIDIA GPUDirect™
Special Linux patch, InfiniBand driver, and CUDA driver
Higher performance CUDA driver for Windows OS
TCC driver reduces CUDA kernel overhead and enables Windows Remote Desktop and Windows Services

	GPU-Mini
	System Hardware
Nodes	4 Nvidia Tesla S2050/C2070
GPU	16 Nvidia Tesla 20-series C2050/C2070
CPU	64-bit Quad-core Intel Xeon E5620 @ 2.4 GHz Stepping: B1
Cache	12 MB Intel Smart Cache per processor
FLOPs Peak performance	Up to 515G double precision flops per GPU Up to 1.03T single precision flops per GPU
Main Memory	Up to 192 GB ECC DDR3 (1333/1066/800MHz) per node
GPU Memory	48 GB GDDR5
Interconnect	Gigabit Ethernet QDR 40 Gbps Infiniband
Network Switch	16-port Gigabit Ethernet 24-port Infiniband QDR Switch
File System	Linux EXT3 for /Root and /Temp, NFS
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	Red Hat CentOS
Message Passing Libraries	Microsoft MPI library
Rack Cabinet	24U 19”
	System Software
Cluster Management options	Clustercorp Rocks+ Cluster Rolls Software for CUDATM
Job Scheduler & Resource Manager Options	Torque/Maui Moab SGE SLURM PBS Pro Platform LSF
Compiler options	Intel Cluster Toolkit PGI PathScale
Debugger options	CUDA C/C++/Fortran OpenCL DirectCompute Toolkits NVIDIA Parallel Nsight
	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.

	GPU-Max
	System Hardware
Nodes	8 Nvidia Tesla S2050/C2070
GPU	32 Nvidia Tesla 20-series C2050/C2070
CPU	32 Quad-core Intel Xeon E5620 @ 2.4 GHz Stepping: B1
Cache	12 MB Intel Smart Cache per processor
FLOPs Peak performance	Up to 515G double precision flops per GPU Up to 1.03T single precision flops per GPU
Main Memory	Up to 192 GB ECC DDR3 (1333/1066/800MHz) per node
GPU Memory	48 GB GDDR5
Interconnect	Gigabit Ethernet QDR 40 Gbps Infiniband
Network Switch	24-port Gigabit Ethernet 36-port Infiniband QDR Switch
File System	Linux EXT3 for /Root and /Temp, NFS
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	Red Hat CentOS
Message Passing Libraries	MVAPICH MPICH2 LAM/MPI OpenMPI
Rack Cabinet	36U 19”
	System Software
Cluster Management options	Clustercorp Rocks+ Cluster Rolls Software for CUDATM
Job Scheduler & Resource Manager Options	Torque/Maui Moab SGE SLURM PBS Pro Platform LSF
Compiler options	Intel Cluster Toolkit PGI PathScale
Debugger options	CUDA C/C++/Fortran OpenCL DirectCompute Toolkits NVIDIA Parallel Nsight
	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.

Home Products GSA Support News About Us Contact Us Tracking