Linxe's eye

Impressive and elegant new German supercomputer: Specifications: HPC Cluster ("blizzard") IBM p575 "Power6" cluster water cooled 16 dual core CPUs per node Total size: 264 nodes, 8448 cores 249 compute nodes 12 I/O nodes 3 interactive nodes 18,8 GigaFlops/core Total system peak performance: 158 TeraFlops/s Top500: Rank 27 in 06/09 20 TeraByte memory 3 PetaByte GPFS file system (additional 3 PetaByte in 2011) 8 x Qlogic 288 port 4 x DDR Infiniband switches bandwidth: 16 GigaByte/s node to node (bidirectional ) 25.4 km Infiniband cables http://www.dkrz.de/dkrz/about/hardware/HPC_Cluster But Blizzard is connected to the Data archive: HPSS: High Performance Storage System 6 Sun StorageTek SL8500 tape libraries 8 robots per library 10 000 media slots per library 73 tape drives total capacity: 60 PetaByte. 60.000 media (T10000 A/B, LTO4, 9940B and 9840C ) 500 TeraByte disk cache projected fill rate: 10 PetaByte/year bidirectional bandwidth: 3...

IBM announced the new big project to build the next #1 supercomputer of the world, codename Sequoia, it's impressive the limit of 20 petaflops ... that's more than the combined power of all top 500 supercomputers (#1 is only 1 petaflops). The Sequoia will be powered by 1.6 million cores (specific 45-nanometer chips in development) and 1.6 petabytes of memory. It will be housed in 96 refrigerators spanning roughly 280 square meters. Of course the owner will be the USA gov, who's else? From: Gizmodo Image from: xkcd

So do you have some PS3 and you're boring of play and watch Blue-Ray movies? You must know the PS3 is the most accessible CELL- based machine, why not use this computer problem in other areas beyond entrainment . In this PS3 ClusterGuide you can build step-by-step your own cluster with PS3, the receipt: 1. Take some PS3. 2. Interconnect it in a LAN. 3. Install Fedora PPC in each one. 4. Install cluster utils . 5. Learn to code in CELL- SDK for a better experience and performance . I accept some PS3 for scientific probes ... really I just want one to play ...

This week the new fastest and most powerful computer of the world is the NCCS's Jaguar , a big cluster build by Cray and AMD, with a 1.64 petaflops of peak capacity. This means the return of the king of super-computers, Cray Inc . who was the reference for many years of the most powerful systems for computing. Now, with AMD build a cluster system (with Linux of course) and reclaim the Top 1. The cabinets also looks cool:

In this part we'll install and configure the other nodes, in the master node we have a DHCP server and a PXE network boot which serves the netboot system, so we just need to connect the net cable, a keyboard and a monitor to the node, turn on and wait to install the base system. Options include partition of the hda disk, we use the defaults and put all the system in a partition and default swap size. We add the general user named beagle and after rebooting, login, become root, change the password and install the SSH server: sudo su - passwd apt-get install openssh-server Repeat this for all the nodes. The next steps will be only from the master node. SSH access You need to create a pair of keys for each user to access any node without a password, first we create it in the general user beagle : ssh-keygen cp .ssh/id_pub .ssh/authorized_keys Root also need this keys, but we don't export the root's home, after you created the keys, you need to copy to all the nodes. This st...

This time I want to show how to build a HPC ( High Performance Computing ) cluster using Ubuntu Linux. Before to begin My Institute (Cinvestav - www.ira.cinvestav.mx) ask me to build a small cluster to general works and it'll be a learning system for bioinformatic. The cluster name is Beagle, they put the hardware and my friend LuisD and I the hard job. The design includes a master node to access, to check status and to send jobs, and 10 slaves nodes with /home exported with NFS, a job queque created with Sun Grid Engine, Ganglia is user to monitor the systems and also include MPI support. Hardware Master Node : AMD Athlon 64 X2 4200+, 2 Gb RAM, 1 hard disk IDE 80 Gb (hda), 1 hd SATA 320 Gb (sda), 1 external USB hd 1 Tb (sdb), network card nForce 10/100/1000 (eth1), network card PCI Realtek 10/100 (eth2). Slave Nodes X10 : AMD Athlon 64 X2 4200+, 2 Gb RAM, 1 hard disk IDE 80 Gb, network card nForce 10/100/1000 (eth0). Network Switch : 24 ports 10/100/1000. Many meters of network c...