Dell today announced it continues to push the boundaries of high-performance computing (HPC) and big data by unveiling the PowerEdge C6320, the latest addition in its 13th generation Dell PowerEdge server portfolio. The PowerEdge C6320 delivers up to two times performance improvement on the leading HPC performance benchmark(1), and has the right mix of cost-efficient compute and storage in a compact, 2U chassis for HPC and hyper-converged solutions and appliances, allowing customers to meet demanding workload needs.
The notion of aligning HPC and big data has steadily gained traction over the past few years. As analytics and big data continue to be top of mind for organizations of all sizes and industries, traditional IT departments are considering HPC solutions to help provide rapid and reliable information to business owners so they can make more informed decisions. As Dell’s latest future-ready HPC solution, the Dell PowerEdge C6320 helps power the discoveries and insights being made by top research organizations and enterprises around the world.
Additionally, as hyper-converged systems such as Dell Engineered Solutions for VMware EVO: RAIL and Dell’s XC Series of Web-scale Converged Appliances now make up the fastest growing part of the overall converged infrastructure market, the PowerEdge C6320 along with its embedded management software is an ideal platform for these appliances. According to IDC, sales of hyper-converged systems are expected to increase 116.2 percent in 2015 over the previous year to $806.8 million (USD). The market is expected to experience a 59.7 percent compound annual growth rate (CAGR) from 2014 to 2019, when it will generate more than $3.9 billion (USD) in total sales(2).
Dell PowerEdge C6320, purpose-built for high-performance computing fields
The PowerEdge C6320 is designed to offer four independent server nodes in a 2U chassis. Compared to the previous generation, it provides up to two times the performance improvement on the LinPack spec(1), up to 45 percent improvement on the SPECint_rate benchmark(3) and up to 28 percent better power efficiency on the Spec_Power benchmark(4). This allows customers to optimize application performance and productivity while conserving energy use and saving traditional datacenter space.
The PowerEdge C6320 features the latest generation of Intel Xeon E5-2600 v3 processors and provides up to 18 cores per socket (144 cores per 2U chassis), up to 512GB of DDR4 memory and up to 72TB of flexible local storage. In addition, the PowerEdge C6320 now comes integrated with iDRAC8 with Lifecycle Controller. By leveraging iDRAC8, customers can automate many routine management tasks and reduce the time and number of steps to deploy, monitor and update their servers throughout their lifecycle.
For the most demanding HPC and big data workloads, customers can pair the PowerEdge C6320 with the accelerator-optimized PowerEdge C4130. As organizations are increasingly turning to GPUs for workload acceleration, the PowerEdge C4130 is a GPU dense and flexible rack server purpose-built to speed the most demanding workloads. The PowerEdge C4130 delivers up to 33 percent better GPU/accelerator density than its closest competitors(5) and 400 percent more PCIe GPU/accelerators per processor per rack U than a comparable HP system(6). The PowerEdge C4130 can also achieve over 7.2 Teraflops on a single 1U server and has a performance/watt ratio of up to 4.17 Gigaflops per watt(7).
Dell PowerEdge C6320 powers Comet
Comet is a new petascale supercomputer designed to transform advanced scientific computing by expanding access and capacity among traditional as well as research domains. Deployed at the San Diego Supercomputer Center (SDSC) at the University of California, San Diego, Comet includes 27 racks of PowerEdge C6320 compute nodes and is designed to optimize capacity for modest-scale jobs. Totaling 1,944 nodes or 46,656 cores, Comet provides a five-fold increase in compute capacity versus SDSC’s previous HPC system.
“We like to say that Comet provides ‘HPC for the 99 percent’ – essentially it’s about providing high-performance computing to a much larger research community and serving as a gateway to discovery,” said SDSC director Michael Norman, principal investigator for the Comet project. “In order to provide research to a larger community of users, we needed to start with a solid hardware foundation. We chose the Dell PowerEdge C6320s over competitive solutions because of Dell’s reputation in the HPC space, its leading hardware design and innovations, and for its ease of deployment. We’re excited to be working with Dell as we expand access to researchers who have not traditionally relied on supercomputers to help accelerate discovery.”
Dell PowerEdge C6320 for hyper-converged
Dell provides hyper-converged solutions with pre-configured software and hardware integrated together to target specific solutions for the software defined era. Designed as a modular scale out platform, the PowerEdge C6320 is an ideal hardware platform for these solutions including Dell Engineered Solutions for VMware EVO: RAIL and Dell XC Series of Web-scale Converged Appliances. The PowerEdge C6320 provides the right mix of processor performance, compute nodes and local storage options with leading agent-free server management tools enabling customers to quickly deploy, maintain and manage their solutions.
“As organizations continue to be inundated with information, there’s an increasing correlation between data analytics and high performance computing,” said Ashley Gorakhpurwalla, vice president and general manager, Dell Server Solutions. “From powering the revolutionary discoveries being made by top research organizations to helping accelerate product and service deployment for leading IT organizations, the PowerEdge C6320 is the latest example of Dell’s commitment to helping organizations future-proof their business while enabling companies to leverage information for competitive advantage.”
“More and more IT professionals are turning to Dell’s engineered and hyper-converged solutions as a method to simplify and streamline IT capabilities while delivering both rapid time-to-value and business results,” said Jim Ganthier, vice president and general manager, Dell Engineered Solutions and Cloud. “As the Dell Engineered Solutions portfolio continues to evolve, the PowerEdge C6320 will play an integral role. Its flexible, modular platform with automated management makes it an ideal platform for appliances such as the Dell Engineered Solutions for VMware EVO:RAIL, Dell XC Series of Web-scale Converged Appliances and our HPC offerings. The exceptional mix of features and capabilities gives our customers best-in-class performance, price and power efficiencies in a way that meets their business requirements both now and into the future.”
Dell Inc. listens to customers and delivers innovative technology and services that give them the power to do more. For more information, visit www.dell.com.
(1) Based on the LinPack benchmark, the Dell PowerEdge C6320 achieved 999 Gflops using two Intel Xeon E5-2699 processors. Dell PowerEdge C6220 achieved 498 GFlops using two Intel Xeon E5-2697 processors on the same benchmark. Based on testing by Dell Labs in June 2015.
(2) According to IDC Worldwide Hyperconverged Systems 2015–2019 Forecast, April 2015.
(3) SPEC® and the benchmark name SPECint® are registered trademarks of the Standard Performance Evaluation Corporation. Based on testing by Dell Labs in June 2015. The Dell PowerEdge C6320 achieved a SPECint_rate of 1,3320 using two Xeon E5-2699 processors. The Dell PowerEdge C6220 achieved a SPECint_rate of 919 using two Xeon E5-2697 processors. For latest SPEC CPU2006 benchmark results, visit www.spec.org.
(4) SPEC® and the benchmark name SPECpower_ssj are trademarks of the Standard Performance Evaluation Corporation. Based on testing by Dell Labs in June 2015. The 4 node Dell PowerEdge C6320 cluster achieved a SPECpower_ssj2008 result of 3,235,764 overall ssj_ops/Node, compared to the 4 node Dell PowerEdge C6220 cluster with a SPECpower_ssj2008 result of 1,678,974 overall ssj_ops/Node score. For the latest SPECpower_ssj2008 benchmark results, visit www.spec.org.
(5) Based on Dell internal analysis of number of GPUs per 1U of rack space performed against SuperMicro SYS 1028GR-TR and HP SL250s Gen8 (SL6500) in November 2014.
(6) Based on Dell internal analysis performed November 2014.
(7) Based on Dell Labs testing performed November 2014 using the High Performance LinPack (HPL) benchmark test. Actual performance will vary with configuration, usage and manufacturing variability.