![intel c compiler svml math functions intel c compiler svml math functions](https://www.researchgate.net/publication/263049906/figure/fig1/AS:669093287981057@1536535679106/Left-runtime-performance-of-the-ALICE-simulation-An-overall-speed-up-of-7-percent-is_Q640.jpg)
Multiplies a number by 2 raised to a powerĭecomposes a number into integer and fractional parts Returns the nearest integer using current rounding mode with exception if the result differsĭecomposes a number into significand and a power of 2 Returns the nearest integer using current rounding mode Returns the nearest integer, rounding away from zero in halfway cases Returns the nearest integer not greater in magnitude than the given value Returns the nearest integer not greater than the given value Returns the nearest integer not less than the given value
INTEL C COMPILER SVML MATH FUNCTIONS PLUS
Returns e raised to the given power, minus oneĬomputes natural logarithm (to base e) of 1 plus the given numberĬomputes square root of the sum of the squares of two given numbersĬomputes arc tangent, using signs to determine quadrantsĬomputes natural logarithm of the absolute value of the gamma function Positive difference of two floating-point values Signed remainder as well as the three last bits of the division operation Signed remainder of the division operation
![intel c compiler svml math functions intel c compiler svml math functions](https://www.intel.com/content/dam/develop/external/us/en/images/umath1-741096.png)
Remainder of the floating-point division operation Ĭomputes absolute value of an integer valueĬomputes absolute value of a floating-point valueĬomputes the quotient and remainder of integer division Those functions are identified by f and l suffixes respectively. In C99, this shortcoming was fixed by introducing new sets of functions that work on float and long double arguments.
INTEL C COMPILER SVML MATH FUNCTIONS CODE
For those that are, the functions accept only type double for the floating-point arguments, leading to expensive type conversions in code that otherwise used single-precision float values. Not all of these functions are available in the C89 version of the standard. The functions that operate on integers, such as abs, labs, div, and ldiv, are instead defined in the header ( header in C++).Īny functions that operate on angles use radians as the unit of angle. Most of the mathematical functions are defined in ( header in C++).