Jaguar, which is located at the Department of Energy’s Oak Ridge Leadership Computing Facility and was upgraded earlier this year, posted a 1.75 petaflop/s performance speed running the Linpack benchmark. Jaguar roared ahead with new processors bringing the theoretical peak capability to 2.3 petaflop/s and nearly a quarter of a million cores. One petaflop/s refers to one quadrillion calculations per second.

Also of note is the new Tianhe-1 in China which pairs Xeons with AMD GPUs. Yes, this is probably as big of news as the top placed computer as this is the first time I've seen a CPU/GPU box on the list.

Rounding out the top 5 positions is the new Tianhe-1 (meaning River in Sky) system installed at the National Super Computer Center in Tianjin, China and to be used to address research problems in petroleum exploration and the simulation of large aircraft designs. The highest ranked Chinese system ever, Tianhe-1 is a hybrid design with Intel Xeon processors and AMD GPUs used as accelerators. Each node consists of two AMD GPUs attached to two Intel Xeon processors.

The machine has become the first academic system to surpass a quadrillion floating-point operations per second, or one petaFLOPS. The upgrade also puts the Kraken among the top five supercomputers in the world. The system came online on 5th October with a peak performance of 1.03 petaFLOPS. It features more than 16,000 six-core 2.6-GHz AMD Istanbul processors with nearly 100,000 compute cores.

The end result is that servers based on a quad hex-core Opteron are about 20% to 50% faster, and at the same time consume 20% less than Intel hex-core. The E7450 has a slightly better performance/watt ratio, but simple mathematics show that no matter which hex-core Xeon you chose, it is going to look bad for the Intel six-core. The X7460 and its brothers are toast. The Intel quad platform will not be attractive until the Nehalem EX arrives.

Until then, we have a landslide victory for the AMD quad Opteron platform, if only the pesky dual Xeon X5570 wouldn't spoil the party. Servers based on the X55xx series are the most expensive of the dual socket market, but still cost about half (or even less than half) as much than the quad hex-core Opterons based servers. The memory slot advantage is also shrinking: an X55xx based server can realistically use 18 x 4GB or 72GB (maximum: 144GB). A quad Opteron based server typically has 32 slots and can house up to 128GB of RAM if you use affordable 4 GB DIMMs (maximum: 256GB).

The new Coates Cluster consists of 1,200 HP dual-quad core computer nodes with a total of 9,000 AMD processors, organized into sub-clusters, each with a different memory and storage configuration. All nodes have 10 gigabit Ethernet (10GigE) within a network infrastructure running Cisco Nexus data center switches and Chelsio iWARP Ethernet remote direct memory access adapters. The nodes will run Red Hat Enterprise Linux 5 and use Altair Engineering's PBSPro 10.x for resource and job management.

I'm guessing that 9,000 processors actually means 9,000 cores. For a tech site Campus Techology was pretty light on details.

Socket F is a DDR2 design and C32 is DDR3. Having interchangeable processors and memories would mean a massive test matrix that OEMs might find difficult to support. Eventually you’ll have to switch over to the new design. Based on the fact that we expect Socket F to end up with ~5 years of life in it from 2006 to 2011, we feel it has served the market well and we don’t want to be focusing the new generation of processor into a 4 year old platform.