|
| Home > Corporate Solutions > GPU Computing > GPU Clusters |
| Tesla™ Parallel High Performance Computing (HPC) Solutions |
 |
ACMA NVIDIA® Tesla™ S1070 Preconfigured Clusters
Supercharge your cluster with Tesla CUDA-based GPUs
ACMA is a leader in the HPC field, specializing in GPU Cluster Solutions. ACMA is one of only a few vendors in world that is backed by two giants in the cluster market space: Nvidia and Intel. ACMA is an Nvidia Tesla Prefer Provider and is also part of Intel's Cluster Ready Program. Together, this combined partnership allows ACMA to offer HPC clusters that are optimized to your environment.
ACMA’s GPU clusters are powered by the NVIDIA® Tesla™ S1070 Computing System, a four-teraflop 1U system that has the Tesla T10 GPUs based on the CUDA massively parallel architecture. With 4 GB of memory per GPU, support for IEEE 754 single & double floating point precision, and a fast 102 GB/sec GDDR3 interface to the memory, the S1070 1U speeds the transition to energy-efficient parallel computing and scales to solve the world's most important computing challenges with speed and accuracy. Successfully deployed at research institutes, universities, and enterprises – it powers the 29th most powerful supercomputer in the world.
|
 |
 |
 |
Feeding the HPC Industry’s Relentless Demand for Performance.
Keeps pace with the increasing demands of the toughest computing challenges - including drug research, oil and gas exploration and computational finance.
Many-core Architecture Delivers Optimum Scaling across HPC Applications.
 Parallel performance from 960 cores, capable of concurrent execution of thousands of computing threads, and scalable architecture meet the computational demands of those applications whose complexity has exceeded the CPU’s solving capabilities.
High Efficiency Computing Platform for Energy-conscious Organizations.
Higher performance and higher density for solving complex problems using less energy.
NVIDIA CUDA™ Technology Unlocks the Power of Tesla Many-core Computing Products.
 The only C language environment that unlocks the many-core processing power of GPUs to solve the world’s most computationally-intensive challenges.
|
ACMA offers several configurations of the Tesla preconfigured clusters and we can customize them to your needs:
| Model # |
Helios PGC-2504 |
Helios PGC-2508 |
| Configurations |
4 Tesla S1070 Preconfigured Cluster |
8 Tesla S1070 Preconfigured Cluster |
| GPUs |
16 Tesla T10 GPUs |
32 Tesla T10 GPUs |
| CPU Servers |
16 Dual-socket Quad-core Xeon E5620 2.4 GHz |
32 Dual-socket Quad-core Xeon E5620 2.4 GHz |
| Head Node Server |
2 Dual-socket Quad-core Xeon E5620 2.4 GHz |
2 Dual-socket Quad-core Xeon E5620 2.4 GHz |
| Memory |
64GB GPU memory, Up to 384GB 1333/1066/800MHz ECC Reg CPU memory |
128GB GPU memory, Up to 768GB DDR3 1333/1066/800MHz ECC Reg CPU memory |
| Storage |
Up to 32 TB SATA drives |
Up to 64 TB SATA drives |
| Network Connectivity |
QDR Infiniband on each node |
QDR Infiniband on each node |
| Network Switch |
Cisco 1U 20-port Gigabit Ethernet Switch |
Cisco 1U 20-port Gigabit Ethernet Switch |
| Infiniband Switch |
1U 36 4X QDR ports Infiniband switch |
1U 36 4X QDR ports Infiniband switch |
| Rocks+ Cluster Rolls Software for CUDA™ |
Rocks+ software with 1-year support, optional 3-year support service |
Rocks+ software with 1-year support, optional 3-year support service |
| Reference # |
Q145080 (Tesla S1070 & host servers) + Q145078 (Head Node) + Q145081 (Cluster Components) |
Q145077 (Tesla S1070 & host servers) + Q145078 (Head Node) + Q145079 (Cluster Components) |
TeslaT Parallel High Performance computing (HPC) Specifications
- Up to 17x lower cost, 21x lower power consumption, and 60% less space than traditional 1U servers
- Up to 86.94 Teraflops of single precision performance and7,266 Gigaflops of double precision performance per cluster
- Up to 336GB dedicated GPU memory and 8,568GB/sec memory bandwidth
- Up to 42 Quad-Core AMD or Intel processors on host systems
- Up to 126TB hot swap shared storage on host systems
- QDR InfiniBand fabric
- Real time InfiniBand diagnostics
Complete Cluster Distribution
- Free IPMI management suite
- Seamless standard and custom application integration & cluster installation
- Firmware upgrades
- BIOS modification
- Multiple Interconnect Options: InfiniBand, Fibre channel, Ethernet (Gigabit, 10GbE)
Clustered File Storage (from Terabyte to Petabyte)
- Hardware design & software stack
- Lustre / Open source file system (Redundancy across system nodes)
Complete Cluster Assembly and Set Up Services
- CUDA compatible clustering software and developer tools with up to three years of support
- Configuration of cluster nodes and the network
- Installation of applications and computers to offer a true replacement of the customers' IT department
Installed SoftwareThe AMAX Tesla preconfigured cluster comes with preinstalled with
- Redhat Enterprie Linux 5.x, 64-bit
- CUDA 2.2 Toolkit and SDK
- Clustering software (Rocks Roll or others)
GPU Software Development Tools
- Optional C-based software development tools and various libraries for GPUs
- Optional NVIDIA® RealityServer® 3.0 3D web services software suite
Click here to find out more about the C-based software development tools and various libraries for GPUs. |
| CUDA-based Tesla GPUs can increase the speed of applications by 250X on a wide range of applications – from MATLAB to computational fluid dynamics, molecular dynamics, quantum chemistry, imaging, signal processing, bio-informatics, and more.
|
 |
 |
 |
| Medical Imaging |
Digital Content Creation |
Computer-Aided Design /Engineering |
 |
 |
 |
| Fluid Simulation |
Seismic Exploration
Reservoir Simulation |
Computational Fluid
Dynamics (CFD) |
 |
 |
 |
| Computer Vision |
Protein Docking |
Molecular Dynamics |
 |
 |
 |
| Gene Sequencing |
Image Processing |
Multi-HD Stream Video Editing |
 |
 |
 |
| Finite Element Analysis |
Electro Dynamics |
Crash Modeling |
|
| Reference#:143228 |
 |
|
Careers