at Supercomputing 2014 (SC14), the HPC conference in New Orleans, Louisiana, Dell launched its Dell PowerEdge C4130 servers with Intel Xeon Phi inside. As built for the HPC server rack focus effect dense and incredibly flexible GPU to accelerate the most demanding HPC workloads , the PowerEdge C4130 is an Intel Xeon 1U server E5-20v3 which offers up to four GPU / accelerators.
The Dell PowerEdge C4130 server would be able to reach more than 7.2 TeraFLOPS in a single 1U server , with a performance / watt to 4.17 gigaflops per watt. This allows customers to further optimize the performance and productivity Unshackling implementation constraints of the traditional data center space and energy use.
The integration of innovative technology from NVIDIA and Intel, the Dell PowerEdge C4130 server is available in five configurations designed sole that meet the flexibility to vary the characteristics of HPC workloads . This agility allows supercomputer scientific and medical research laboratories, financial companies, industrial companies and analysis or intensive computing data organizations must provide faster results and quickly adapt to changes the company's needs.
GPU higher density
The Dell PowerEdge C4130 adds up to two Intel Xeon server processors E5-20v3, 16 memory DIMMs DDR4 and up to two SATA SSD 1.8-inch startup disk in just 1U of rack space. With up to four 300W Intel Xeon Phi coprocessors or NVIDIA Tesla GPU accelerators , including the new NVIDIA Tesla K80 dual-GPU accelerator, the PowerEdge C4130 allow for transparent analysis and implementation of data more complex and computer intensive workloads.
"A majority of HPC users move GPU density higher configurations to drive discovery and innovation in seismic processing, signal processing and image, computational chemistry, and learning machine, "said Sumit Gupta, CEO of Tesla Accelerated Computing at NVIDIA ." the Dell PowerEdge C4130 server is a single platform that packs four Tesla K40 or K80 new Tesla dual-GPU accelerators in a compact 1U form factor with a highly flexible architecture that maximizes application performance with NVIDIA GPUDirect. "
0 Komentar