What are gigaFLOPS (GFLOPS)?

A gigaFLOPS (GFLOPS) is a unit in computer science that’s equivalent to one billion floating point operations per second. FLOPS are used to measure the computing power of processors, especially those used for scientific applications, machine learning and high-performance computers.

What are FLOPS and what are they used for?

FLOPS is short for floating point operations per second and indicates how many calculations with floating point numbers a computer can perform in one second. Floating point operations are essential for different scientific and technical applications, as they make it possible to process both very large and very small numbers with high precision. They are essential in areas like physics, computer science and machine learning.

FLOPS are crucial for applications that require complex calculations, for example weather forecasts, climate modeling, the simulation of physical processes, machine learning and artificial intelligence. Processors with high FLOPS values can work quickly and efficiently in those areas.

Special benchmark tests are performed to determine the FLOPS value of a processor. The tests evaluate how many floating point operations the system can complete in one second. Different types of calculations are often included in order to get an accurate picture of the performance of a processor.

How many FLOPS are in one gigaFLOPS?

FLOPS units are based on the decimal system and thus correspond to powers of ten. One GFLOPS is 10⁹ FLOPS, meaning that a processor with the value of 1 GFLOPS can perform one billion (1,000,000,000) floating point operations per second.

What are the other FLOPS units?

In addition to GFLOPS, there are other FLOPS units that allow you to compare the performance of CPUs and GPUs. You can convert other FLOPS units into GFLOPS as follows:

How many FLOPS do modern computers and GPUs reach?

The computing power of modern computers, especially high-performance GPUs, has increased immensely in recent years. Modern graphics cards and super computers reach values ranging from several TFLOPS up to even exaFLOPS.

For example, NVIDIA H100 is a high-performance GPU for AI and data center applications. It reaches peak performance at 989 teraFLOPS for FP32 Tensor Core calculations. The NVIDIA A30, which was designed primarily for high performance computing and AI inferences, works at 10.3 teraFLOPS for FP32 calculations.

The fastest supercomputer in the world, the Frontier, can now reach values of over one exaFLOPS, meaning it can process trillions of FLOPS without a problem.