UNPKG

double-double

Version:

Pure double-double precision functions *with strict error bounds*.

16 lines (15 loc) 643 B
/** * Returns the result of subtracting the second given double-double-precision * floating point number from the first. * * * relative error bound: 3u^2 + 13u^3, i.e. fl(a-b) = (a-b)(1+ϵ), * where ϵ <= 3u^2 + 13u^3, u = 0.5 * Number.EPSILON * * the error bound is not sharp - the worst case that could be found by the * authors were 2.25u^2 * * ALGORITHM 6 of https://hal.archives-ouvertes.fr/hal-01351529v3/document * @param x a double-double precision floating point number * @param y another double-double precision floating point number */ declare function ddDiffDd(x: number[], y: number[]): number[]; export { ddDiffDd };