Glossary High Performance Computing

High-Performance Computing (HPC): High-performance computing uses supercomputers and other compute clusters to solve particularly complex, computationally intensive tasks. Supercomputers are large, classical computers, often with thousands of CPU and GPU cores

CPU: CPU is the central processing unit, the main processor of a computer that processes instructions.

GPU: the graphics unit or graphics processor, is a processor specialized and optimized for the calculation of

graphics for various devices.

FLOPS: Floating Point Operations per Second is a measure of the performance of computers or processors and
refers to the number of floating-point operations that a computing unit can perform per second.

PetaFLOPS: Peta Floating Point Operations per Second is the processing speed of computers. A Petaflop is equal to
one quadrillion or 1,000 trillion floating point operations per second (10 15 FLOPS).

ExaFLOPS: Exa Floating Point Operations per Second is the processing speed of computers. If you want to abbreviate a
trillion units, a number with 18 zeros, the abbreviation Exa stands for it. One exaflop corresponds to one
trillion floating point operations per second (10 18 FLOPS).

Exascale computing systems analyze and perform 1,000,000,000,000,000,000 floating-point operations per
second, while simulating the methods and interactions of the fundamental forces in the universe.