Visible to Intel only — GUID: GUID-17006E2E-F821-4C88-926A-F8ADCFBE2694
Visible to Intel only — GUID: GUID-17006E2E-F821-4C88-926A-F8ADCFBE2694
InvSqrt
Computes inverse square root of each vector element.
Syntax
IppStatus ippsInvSqrt_32f_A11 (const Ipp32f* pSrc, Ipp32f* pDst, Ipp32s len);
IppStatus ippsInvSqrt_32f_A21 (const Ipp32f* pSrc, Ipp32f* pDst, Ipp32s len);
IppStatus ippsInvSqrt_32f_A24 (const Ipp32f* pSrc, Ipp32f* pDst, Ipp32s len);
IppStatus ippsInvSqrt_64f_A26 (const Ipp64f* pSrc, Ipp64f* pDst, Ipp32s len);
IppStatus ippsInvSqrt_64f_A50 (const Ipp64f* pSrc, Ipp64f* pDst, Ipp32s len);
IppStatus ippsInvSqrt_64f_A53 (const Ipp64f* pSrc, Ipp64f* pDst, Ipp32s len);
Include Files
ippvm.h
Domain Dependencies
Headers: ippcore.h
Libraries: ippcore.lib
Parameters
pSrc |
Pointer to the source vector. |
pDst |
Pointer to the destination vector. |
len |
Number of elements in the vectors. |
Description
This function computes inverse square root of each element of pSrc and stores the result in the corresponding element of pDst.
For single precision data:
function flavor ippsInvSqrt_32f_A11 guarantees 11 correctly rounded bits of significand, or at least 3 exact decimal digits;
function flavor ippsInvSqrt_32f_A21 guarantees 21 correctly rounded bits of significand, or 4 ulps, or about 6 exact decimal digits;
function flavor ippsInvSqrt_32f_A24 guarantees 24 correctly rounded bits of significand, including the implied bit, with the maximum guaranteed error within 1 ulp.
For double precision data:
function flavor ippsInvSqrt_64f_A26 guarantees 26 correctly rounded bits of significand, or 6.7E+7 ulps, or approximately 8 exact decimal digits;
function flavor ippsInvSqrt_64f_A50 guarantees 50 correctly rounded bits of significand, or 4 ulps, or approximately 15 exact decimal digits;
function flavor ippsInvSqrt_64f_A53 guarantees 53 correctly rounded bits of significand, including the implied bit, with the maximum guaranteed error within 1 ulp.
The computation is performed as follows:
pDst[n] = (pSrc[n])-1/2, 0 ≤ n < len.
Return Values
ippStsNoErr |
Indicates no error. |
ippStsNullPtrErr |
Indicates an error when pSrc or pDst pointer is NULL. |
ippStsSizeErr |
Indicates an error when len is less than or equal to 0. |
IppStsDomain |
Indicates a warning that the argument is out of the function domain, that is, at least one of the elements of pSrc is less than 0. |
IppStsSingularity |
Indicates a warning that the argument is the singularity point, that is, at least one of the elements of pSrc is equal to 0. |
Example
The example below shows how to use the function ippsInvSqrt.
IppStatus ippsInvSqrt_32f_A21_sample(void) { const Ipp32f x[4] = {7105.043, 5135.398, 3040.018, 149.944}; Ipp32f y[4]; IppStatus st = ippsInvSqrt_32f_A21( x, y, 4 ); printf(" ippsInvSqrt_32f_A21:\n"); printf(" x = %.3f %.3f %.3f %.3f \n", x[0], x[1], x[2], x[3]); printf(" y = %.3f %.3f %.3f %.3f \n", y[0], y[1], y[2], y[3]); return st; }
Output:
ippsInvSqrt_32f_A21: x = 7105.043 5135.398 3040.018 149.944 y = 0.012 0.014 0.018 0.082