This thread has been locked.
If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.
Call one of these functions from the compiler RTS library ...
float sqrtf(float); double sqrt (double); long double sqrtl(long double);
Thanks and regards,
-George
Hi George,
srqt() works fine for scalar values. But we want to do it for Vector values.
Vector square root is what we are looking for. float16 to be precise
The __recip_sqrt intrinsic does not return a precise reciprocal of the square root, but an approximation. This approximation can be refined with further calculation. Unfortunately, we compiler experts do not have an example to share. I'll refer this thread to the device experts. They may have an example in one of the software packages they support.
Thanks and regards,
-George
Hi,
You can look at VXLIB_oneBySqrtXVecF32 and VXLIB_oneBySqrtXVecD64 APIs at <sdkInstallPath>\vision_apps\kernels\park_assist\c7x\VXLIB_inlines.h for reference.
Regards,
Parth