libdevice User's Guide :: CUDA Toolkit Documentation

This document includes math equations (highlighted in red) which are best viewed with Firefox version 4.0 or higher, or another MathML-aware browser. There is also a PDF version of this document.

libdevice User's Guide (PDF) - v10.1.168 (older) - Last updated April 24, 2019 - Send Feedback

3.81. __nv_erfcx

Prototype:

double @__nv_erfcx(double %x)

Description:

Calculate the scaled complementary error function of the input argument x, $e^{x^{2}} \cdot erfc (x)$ .

Returns:

__nv_erfcx( $- \infty$ ) returns $+ \infty$
__nv_erfcx( $+ \infty$ ) returns +0
__nv_erfcx(x) returns $+ \infty$ if the correctly calculated value is outside the double floating point range.

Note:

For accuracy information for this function see the CUDA C Programming Guide, Appendix D.1, Table 7.

Library Availability:

Compute 2.0: Yes

Compute 3.0: Yes

Compute 3.5: Yes