How to Use floating-point in a Sentence

floating-point

adjective

• There’s an awful lot of bit patterns in floating-point arithmetic no one ever uses.
  — IEEE Spectrum, 25 Sep. 2022
• And why are the numbers for floating-point operations per second so much lower?
  — IEEE Spectrum, 25 June 2018
• The bill applies only to models trained with more than 10^26 floating-point operations or with a compute cost above $100 million.
  — Jason Snyder, Forbes.com, 24 May 2026
• Nvidia’s recently announced Hopper GPU includes support for even smaller, 8-bit floating-point numbers.
  — Dina Genkina, IEEE Spectrum, 18 Oct. 2022
• Exascale supercomputers can, by definition, surpass an exaflop—more than a quintillion floating-point operations per second.
  — IEEE Spectrum, 18 Dec. 2022
• For digital signal processing, floating-point arithmetic simplifies the job of maintaining precision, a near-impossible burden in the most demanding algorithms.
  — IEEE Spectrum, 30 June 2025
• The chip has 8-bit floating-point capabilities, but so far the smallest precision the company has engaged on the chip for MLPerf training purposes is bfloat 16.
  — IEEE Spectrum, 17 Nov. 2022
• One popular approach is known as quantization, which reduces data requirements by representing weights using fewer bits—for instance, using 8-bit floating-point numbers rather than 32-bit.
  — Edd Gent, IEEE Spectrum, 31 Mar. 2023
• Typically for training, the computer must be able to calculate with relatively high precision, often using 32-bit floating-point operations.
  — IEEE Spectrum, 29 Dec. 2016
• Our research shows that starting at around 10 16 floating-point operations per second (tens of petaflops) the superconducting computer handily becomes more power efficient than its classical cousin.
  — IEEE Spectrum, 15 May 2024
• Total computational resources in the economy could eventually reach 10⁵⁴ floating-point operations per second.
  — Nick Lichtenberg, Fortune, 4 Apr. 2026
• In parallel with the development of DSP2, Jim led a new architecture, DSP32, which used floating-point arithmetic.
  — IEEE Spectrum, 30 June 2025
• For reference, a PFLOPS represents one quadrillion (10^15) floating-point operations per second (1,000 trillion).
  — Christopher McFadden, Interesting Engineering, 20 Dec. 2025
• Nuclear weapon simulators, cryptographers, and others want exascale supercomputers, capable of 1,000 petaflops—1 million trillion floating-point operations per second—or greater.
  — IEEE Spectrum, 24 Feb. 2016
• Their speed is measured in FLOPS, floating-point operations per second, and the biggest systems now sustain exaFLOPS on a rigorous test called LINPACK (HPL).
  — Kaif Shaikh, Interesting Engineering, 2 Sep. 2025
• According to the Ministry of Industry and Information Technology (MIIT), China has achieved 1,882 exaflops – short for exa floating-point operations per second – which translates to 1,882 quintillion, or billion billion, calculations per second, reported SCMP.
  — Prabhat Ranjan Mishra, Interesting Engineering, 23 Apr. 2026