MareNostrum 4 will unite x86, Power9 and ARM chips; deliver 13.7 PF performance
MareNostrum is a supercomputer in the Barcelona Supercomputing Center, the most powerful in Spain and one of seven supercomputers in the Spanish Supercomputing Network. It was presented by IBM and María Jesús San Segundo.
The MareNostrum 4 the next successor of the MareNistrum is being built by the Barcelona Supercomputing Center will have an unusual configuration. One of the interesting thing about this supercomputer is that, Instead of selecting a single architecture for the new machine that powers the system, it will consists of multiple platforms, incorporating a diverse set of technologies from IBM, Lenovo, Fujitsu, Intel and NVIDIA.
For once, there will be a ceasefire in the war between major chip architectures x86, ARM and Power9, which will all be used in a supercomputer. There will be three clusters, each of which will house Intel x86, ARM and Power9 chips. Those clusters will be linked to form a supercomputer that will deliver up to 13.7 PetaFlops of performance.
Never in the history of the Supercomputing all three architectures have never been implemented together not even in any servers. So, of course the questions is how these architectures will interoperate??
Obviously, all three chip architectures are fundamentally different. So, any application written to take advantage of a specific architecture won’t work on another. But here’s one thing server architectures are changing so different types of systems can coexist. Linux supports x86, ARM and Power9, so it’s possible to write applications to work across the architectures.
The system will share common networking and storage assets. Lenovo is providing server and chip technologies for MareNostrum 4. Basically company’s aim is that to make such supercomputer using emerging technologies that can be used for all kinds of scientific calculations.
However, the performance of MareNostrum 4 isn’t overwhelming, especially when compared to China’s Sunway TaihuLight, which is the world’s fastest computer. TaihuLight delivers 93 petaflops of peak performance where as MareNostrum 4 delivers only 13.7.
According to the BSC press announcement (via top500), the 13.7 petaflop MareNostrum 4 will be split into two parts. The “general purpose” part will be a standard cluster provided by Lenovo, consisting of 48 racks (3,400 nodes) of Intel Xeon-based servers. Peak performance is anticipated to be 11 petaflops. That’s 10 times more powerful, flops-wise, than the current MareNostrum 3 supercomputer, an IBM iDataPlex machine installed in 2012. and upgraded in 2013.
The second part of the new supercomputer will be made up of three different clusters, each of which will incorporate a different set of “emerging technologies.”
The other ingredients of MareNostrum 4 include Lenovo server cabinets with Intel’s current Xeon Phi supercomputing chip, code-named Knights Landing, and upcoming chip code-named Knights Hill. It will also have racks of computing nodes with IBM Power9 chips, which will ship next year. It will have storage capacity of 24 petabytes.
The supercomputer will be implemented in phases, and replace the existing MareNostrum 3. BSC has not specified a timeframe for installation of the various clusters, but given their reliance on future processors not expected to be commercially available until the second half of 2017, it’s unlikely that the project will be complete before the end of next year, at the earliest.
Uniting more than one chips in supercomputer would bring new horizon of Supercomputing? What you think abuot it? Let us know in a comment below.