P. 1
NVIDIA CUDA C Programming Guide 3.1

NVIDIA CUDA C Programming Guide 3.1

|Views: 738|Likes:
Published by 邱吉震

More info:

Published by: 邱吉震 on Sep 08, 2010
Copyright:Attribution Non-commercial


Read on Scribd mobile: iPhone, iPad and Android.
download as PDF, TXT or read online from Scribd
See more
See less





Functions from Section C.1 can be used in both host and device code whereas
functions from Section C.2 can only be used in device code.
Note that floating-point functions are overloaded, so that in general, there are three
prototypes for a given function :
(1) double (double), e.g. double log(double)
(2) float (float), e.g. float log(float)
(3) float f(float), e.g. float logf(float)
This means, in particular, that passing a float argument always results in a float
result (variants (2) and (3) above).

You're Reading a Free Preview

/*********** DO NOT ALTER ANYTHING BELOW THIS LINE ! ************/ var s_code=s.t();if(s_code)document.write(s_code)//-->