# GCC -ffast-math and IEEE-754 Semantics

> -ffast-math changes floating-point assumptions around reassociation, NaN, infinity and signed zero; it is a numerical contract, not only a speed flag.

- Author: Muhammet Ali Köker
- Language: en
- Canonical: https://alikoker.com.tr/en/gcc-ffast-math-and-ieee-754-semantics
- Translation: https://alikoker.com.tr/gcc-ffast-math-ve-ieee-754-semantigi
- Published: 2021-06-15T12:00:00+03:00
- Modified: 2026-08-30T14:55:00+03:00
- Type: article

An algebraically valid transformation is not automatically equivalent under IEEE-754 floating point.

```text
(a+b)+c
```

and

```text
a+(b+c)
```

can differ because intermediate values are rounded. NaN, infinity and signed zero create additional observable behavior.

I therefore treat `-ffast-math` as a numerical-semantics decision, not simply a performance switch.

## It enables a group of assumptions

GCC uses `-ffast-math` to enable several optimization assumptions. The exact set is version-dependent, so I verify the compiler documentation used for the build.

## Reassociation changes results

Allowing reassociation can expose better vectorization but changes operation order. Whether the difference is acceptable depends on the application's error budget.

## NaN can be part of logic

Code may intentionally test `isnan()` or handle infinity. An optimization mode that assumes those values do not occur can invalidate such control flow.

## Signed zero is observable

`+0.0` and `-0.0` compare equal but can produce different reciprocal infinities. Code that relies on this distinction needs strict semantics.

## FMA may differ bit-for-bit

Fused multiply-add rounds once instead of rounding multiplication and addition separately. A different bit pattern is not necessarily less accurate; reproducibility requirements determine whether it is acceptable.

## SIMD makes relaxed semantics attractive

Relaxed rules can permit transformations useful for [SIMD](/en/wiki/simd). The speedup is valuable only if numerical deviation remains within a defined tolerance.

## Determinism needs extra care

Compiler version, ISA and FMA availability can change evaluation. In reproducible systems I record compiler flags and numerical tolerances as release inputs.

## How I test

I compare a reference build and optimized build on ordinary values, cancellation cases, extreme magnitudes, signed zeros and NaN/infinity where meaningful. I measure both speed and numerical deviation.

## Avoid blind global `-Ofast`

When the hot path is local, a narrow compilation scope is easier to validate than changing floating-point semantics across the entire application.

The engineering sequence is:

```text
measure
→ identify bottleneck
→ relax semantics deliberately
→ measure performance
→ measure numerical error
```

## References

- GCC Optimization Options
- IEEE Std 754-2019

## Cite This Work

Köker, M. A. (2021). GCC -ffast-math and IEEE-754 Semantics. alikoker.com.tr. https://alikoker.com.tr/en/gcc-ffast-math-and-ieee-754-semantics

- BibTeX: https://alikoker.com.tr/en/gcc-ffast-math-and-ieee-754-semantics.bib
- RIS: https://alikoker.com.tr/en/gcc-ffast-math-and-ieee-754-semantics.ris
- CSL-JSON: https://alikoker.com.tr/en/gcc-ffast-math-and-ieee-754-semantics.csl.json