Apr 14, 2011 14:28 GMT  ·  By

When GPU modules started to be used in supercomputing, Intel figured it would make something to battle them, leading to the appearance of the MIC architecture, which should start to be seriously tested soon.

With every new supercomputer, performance rises, and it looks like GPU computing modules have already been used in even the currently greatest of them.

Based on Intel Xeon chips and NVIDIA Tesla modules, the currently world's greatest HPC has a much greater prowess than ever and prompted Intel to get serious.

Basically, the Santa Clara, California-based company wants to step up its efforts regarding the MIC (Many integrated Core) architecture.

The code-named Knights Ferry MIC text platform has already been shipped to select developers and Intel wants more of them to test the technology, claiming that a unique advantage is given by x86 compatibility with x86 will (Instead of x86 and GPU modules).

"Think about Intel MIC as a co-processor. The advantage here is that you can use the same compilers, the same tools, the same [Intel] VTunes [performance profilers] that power around 90% of the Top 500.“ said Kirk Skaugen, vice president of the Intel architecture group and general manager of Intel's data center group.

“The next generation you run the compiler, it will optimize the workloads for the Intel cores, that are in the Xeon CPUs, and it will optimize on these new PCI Express cards that will have more than 50 cores and be on our 22nm process technology. So it will automatically balance that workload for the highest-parallel workloads on the planet,"

GPU computing modules like AMD FireStream and NVDIA Tesla don't replace the processors themselves, but they do deal better with special applications, highly parallel ones.

Intel claims that having x86 cores be complemented by MIC modules will boost performance even further.

“We are going to be expanding for you as software developers this to over 100 end-users by the end of the year, so you can begin experiencing the incredible performance here,” Skaugen said.