Silicon Graphics International and Intel recently announced plans to reach exascale levels of computational power within ten years. Exascale computing amounts to computers that are capable of delivering 1,000+ petaflops (One exaflop is 1000 petaflops) of computational horsepower to process quintillions of calculations. To put that in perspective, today’s supercomputers are just now breaking into the level of single-digit petaflop performance, with the fastest supercomputer delivering 8.16 petaflops. It is capable of this thanks to many thousands of eight core CPUs, whereas other top 500 supercomputers are starting to utilize a CPU and GPU combination in order to achieve petaflop performance.

Intel Hopes For Exaflop Capable Supercomputers Within 10 Years - Systems 2

The Aubrey Isle Silicon Inside Knights Corner

This partnering of Central Processing Unit (CPU) and GPU (or other accelerator) allows high performance supercomputers to achieve much higher performance than with CPUs alone. Intel CPUs power close to 80% of the top 500 Supercomputers; however, they have begun to realize that specialized accelerators are able to speed up highly parallel computing tasks. Specifically, Intel plans to combine Xeon processors with successors to their Knights Corner Many Integrated Core accelerator to reach exascale performance levels when combined with other data transfer and inter-core communication advancements. Knights Corner is an upcoming successor to the Knights Ferry and Larrabee processors.

Computer World quotes Eng Lim Goh, the CTO of SGI, in stating that “Accelerators such as graphics processors (GPUs) are currently being used with CPUs to execute more calculations per second. While some accelerators achieve desired results, many are not satisfied with the performance related to the time and cost spent porting applications to work with accelerators.”

Knights corner will be able to run x86 based software and features 50 cores based on a 22nm manufacturing process.  Each core will run four threads at 1.2 GHz, have 8 MB of cache, and will be supported by 512 bit vector processing units.  It’s predecessor, Knights Ferry is based on 32 45nm cores and eight contained in a Xeon server and are capable of 7.4 teraflops. Their MIC chip is aimed directly at NVIDIA’s CUDA and AMD’s OpenCL graphics processors, and is claimed to offer performance in addition to ease of use as they are capable of running traditional x86 based software.

It looks like the CPU-only supercomputers will be seeing more competition from GPU and MIC accelerated supercomputers, and will eventually be replaced at the exascale level. AMD and NVIDIA are betting heavily on their OpenCL and CUDA programmable graphics cards while Intel is going with a chip capable of running less specialized but widely used x86 programmable chips.  It remains to be seen which platform will be victorious; however, the increased competition should hasten the advancement of high performance computing power.  You can read more about Intel’s plan for Many Integrated Core accelerated supercomputing here.