Visit additional Tabor Communication Publications
November 05, 2012
On Monday, AMD officially released its next-generation "Piledriver" Opteron 6300 series of x86 server CPUs. The news comes on the heels of the chipmaker's announcement to start offering 64-bit ARM-based Opterons by 2014 . As befitting its Opteron heritage, the 6300 series is aimed at performance-demanding workloads across the enterprise, web, and in HPC datacenters.
These latest processors represent an upgrade to the "Interlagos" Opteron 6200 CPUs that have been in circulation for about a year. Like its predecessor, the 6300 comes with up to 16 cores, 16MB of L3 cache, and four memory channels. Piledriver though, provides a tweaked microarchitecture for increased performance. Max clock frequency has been kicked up a notch, to 3.5 GHz, (the 6200 CPUs topped out at 3.3 GHz), but you only get four cores at that speed. The new 6300 CPUs use the same socket (G34) as the older 6200 and 6100 silicon, so in-place upgrades should be relatively painless.
Also like its 6200 processor, the 6300 sticks with the older PCIe 2.0 interface. Intel added support for PCIe 3.0 in its Sandy Bridge Xeon CPUs, which gives it a decided edge in data transfers for on-board devices that support the new standard, like the latest GPUs and SSDs. PCIe 3.0 delivers 8 gigatransfers per second, effectively doubling the data rate of the previous generation bus.
According to AMD, Indiana University has already installed a supercomputer outfitted with the new 6300 chips. For some reason though, the recently upgraded Cray XK7 Titan supercomputer at ORNL, which officially came on-line last week, was outfitted with the older 6200 CPUs. Whether this because the chips weren't available in time for the upgrade or because there was no particular advantage to adding a skosh more performance on the CPU side -- 90 percent of the FLOPS reside with the NVIDIA GPUs -- is unknown. Nevertheless, Cray announced it is going to support the 6300 in its XE6 and XE6m Opteron-only lines.
Besides Cray, SGI, Appro, Supermicro, AMAX, ASUS, ClusterVision, Colfax International, MEGWARE Computer, Microway, Penguin Computing, Silicon Mechanics, Tyan and ZT Systems will all be offering Opteron 6300-equipped HPC servers.
The news from AMD is not going to change the competitive landscape on the server front appreciably. Intel has been dominating the x86 server market rather handily for several years and a tweaked microarchitecture from its smaller competitor is unlikely to change that dynamic. Nevertheless, AMD will be able to press certain price-performance advantages over Intel, and the ability to upgrade servers seamlessly to the next-generation chips will continue to be a big draw to customers.
In quieter times, sounding the bell of funding big science with big systems tends to resonate further than when ears are already burning with sour economic and national security news. For exascale's future, however, the time could be ripe to instill some sense of urgency....
In a recent solicitation, the NSF laid out needs for furthering its scientific and engineering infrastructure with new tools to go beyond top performance, Having already delivered systems like Stampede and Blue Waters, they're turning an eye to solving data-intensive challenges. We spoke with the agency's Irene Qualters and Barry Schneider about..
Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.
In this demonstration of SGI DMF ZeroWatt disk solution, Dr. Eng Lim Goh, SGI CTO, discusses a function of SGI DMF software to reduce costs and power consumption in an exascale (Big Data) storage datacenter.
The Cray CS300-AC cluster supercomputer offers energy efficient, air-cooled design based on modular, industry-standard platforms featuring the latest processor and network technologies and a wide range of datacenter cooling requirements.