SCIENCE

New Powerful Parallel SuperComputing Systems Deliver 10X Higher Application Performance for Demanding HPC and Data Center Deployments

AMAX has announced the next-generation of AMAX ClusterMax SuperG cluster solutions, ServMax HPC building blocks, and ServMax server platforms are fully optimized for the latest NVIDIA Tesla M2090 GPU computing module. The new AMAX high performance GPU solutions  powered by the Tesla M2090 GPUs deliver 10X higher application performance than the latest multi-core CPU systems, providing unprecedented real-world scalability and breakthrough power-efficiency across a variety of HPC applications, including seismic processing, biochemistry simulations, weather and climate modeling, signal processing, computational finance, CAE, CFD, and data analysis. These highly configurable systems’ unparalleled performance, enable seamless integration of GPU computing for extreme performance, helping scientists and engineers solve the world's most complex computational problems.

The new Tesla M2090 GPUs boosts core count to 512 and deliver 1.33 Teraflop of single precision performance, providing AMAX’s comprehensive line of highly scalable HPC solutions with 30% more muscle to tackle larger, increasingly complex, and multithreaded applications, while outperforming previous generation systems and maintaining overall power efficiency. The systems offer the flexibility to set different power levels depending on customer usage, fueling blistering computational performance using even less power with greater reliability. AMAX is helping usher in a new generation of extreme performance and computing capabilities, in large part due to the exceptional performance capabilities of NVIDIA’s latest GPU technology, and enabling customers the flexibility in an ever-changing IT environment.

“By combining NVIDIA's powerful and efficient GPU architecture with AMAX’s unique engineering solution design, AMAX delivers breakthrough performance and compute efficiency for large scale-out HPC cluster deployments," said James Huang, Product Marketing Manager at AMAX. "The leading system-level power efficiency of our advanced HPC computing systems enables us to deliver performance-driven solutions that empower customers to grow, adapt and scale as their business demands evolve, while helping them reach their power consumption and green initiative goals."

Latest AMAX next-generation HPC solutions include:

• ClusterMax SuperG: Delivering an extremely powerful 65,536 Tesla M2090 GPU cores and 170.37 Teraflops of single precision performance in a 42U rack, the AMAX ClusterMax SuperG supercomputing cluster solutions offers superior performance and the full benefits of GPU computing while supporting a wide range of research initiatives including computational biology, molecular dynamics, structural biology and chemical biology simulation, amongst others.
• ServMax Xn-4101M: The AMAX ServMax Xn-4101M supports the new Tesla M2090 and is the fastest GPU server available, with up to 4,096 GPU cores, 10.65 Teraflops of single precision performance in a 4U chassis. The Xn-4101M seamlessly fits into existing HPC environments and is ideal for life sciences, molecular biology, visualization, financial modeling, and oil & gas application.
• ServMax Xn-1113M: Powered by the massively parallel CUDA architecture, the AMAX ServMax Xn-1113M HPC server delivers extreme computing power with up to 2.66 Teraflops of single precision performance and features two NVIDIA Tesla M2090 GPU cards and 1,024 CUDA cores in 1U chassis.
• ServMax H-1201M: The AMAX ServMax H-1201M 1U server solution delivers up to 12 AMD Opteron 6100 Series processing cores and four channels of DDR3 memory. Combined with the latest Tesla M2090 GPUs, the H-1201M provides a whopping 2.66 Teraflop of single precision performance, maintaining overall value.