FLINT_FFT_SMALL_ROUND_USE_NATIVE, FLINT_ROUND_MUL_USE_ROUND, FLINT_ROUND_MUL_USE_MAGIC
Synopsis
#include <flint/machine_vectors.h>FLINT_FFT_SMALL_ROUND_USE_NATIVEsourceFLINT_ROUND_MUL_USE_ROUNDFLINT_ROUND_MUL_USE_MAGICFLINT_FFT_SMALL_ROUND_USE_NATIVE is set in the flint-mparam.h of each target: 0 (magic constant) for most Intel targets, 1 (native rounding) for AMD, ARM and generic targets. The header defaults it to 1. Defining FLINT_ROUND_MUL_USE_ROUND or FLINT_ROUND_MUL_USE_MAGIC forces either choice, for testing.
Cite this page
The FLINT team, “FLINT_FFT_SMALL_ROUND_USE_NATIVE, FLINT_ROUND_MUL_USE_ROUND, FLINT_ROUND_MUL_USE_MAGIC (machine_vectors.h),” FLINT: Fast Library for Number Theory, documentation, version 3.7.0-dev, 2026. https://flintlib.org/doc/machine_vectors/FLINT_FFT_SMALL_ROUND_USE_NATIVE.html (generated 2026-10-20).
@misc{flint-doc-machine-vectors-FLINT-FFT-SMALL-ROUND-USE-NATIVE,
author = {{The FLINT team}},
title = {{FLINT\_FFT\_SMALL\_ROUND\_USE\_NATIVE, FLINT\_ROUND\_MUL\_USE\_ROUND, FLINT\_ROUND\_MUL\_USE\_MAGIC (machine\_vectors.h)}},
howpublished = {FLINT: Fast Library for Number Theory, documentation, version 3.7.0-dev},
year = {2026},
url = {https://flintlib.org/doc/machine_vectors/FLINT_FFT_SMALL_ROUND_USE_NATIVE.html},
note = {Generated 2026-10-20}
}