Computes four-quadrant inverse tangent of elements of two vectors.
Buffer API:
void atan2(queue& exec_queue, int64_t n, buffer<T,1>& a, buffer<T,1>& b, buffer<T,1>& y, uint64_t mode = mode::not_defined );
USM API:
event atan2(queue& exec_queue, int64_t n, T* a, T* b, T* y, vector_class<event>* depends, uint64_t mode = mode::not_defined );
ad2d supports the following precisions and devices:
T | Devices supported |
---|---|
float | Host, CPU, and GPU |
double | Host, CPU, and GPU |
The atan2(a,b) function computes four-quadrant inverse tangent of elements of two vectors.
The elements of the output vectory are computed as the four-quadrant arctangent of a[i] / b[i].
Argument 1 | Argument 2 | Result | Error Code |
---|---|---|---|
-∞ | -∞ | -3*π/4 | |
-∞ | b < +0 | -π/2 | |
-∞ | -0 | -π/2 | |
-∞ | +0 | -π/2 | |
-∞ | b > +0 | -π/2 | |
-∞ | +∞ | -π/4 | |
a < +0 | -∞ | -π | |
a < +0 | -0 | -π/2 | |
a < +0 | +0 | -π/2 | |
a < +0 | +∞ | -0 | |
-0 | -∞ | -π | |
-0 | b < +0 | -π | |
-0 | -0 | -π | |
-0 | +0 | -0 | |
-0 | b > +0 | -0 | |
-0 | +∞ | -0 | |
+0 | -∞ | +π | |
+0 | b < +0 | +π | |
+0 | -0 | +π | |
+0 | +0 | +0 | |
+0 | b > +0 | +0 | |
+0 | +∞ | +0 | |
a > +0 | -∞ | +π | |
a > +0 | -0 | +π/2 | |
a > +0 | +0 | +π/2 | |
a > +0 | +∞ | +0 | |
+∞ | -∞ | +3*π/4 | |
+∞ | b < +0 | +π/2 | |
+∞ | -0 | +π/2 | |
+∞ | +0 | +π/2 | |
+∞ | b > +0 | +π/2 | |
+∞ | +∞ | +π/4 | |
a > +0 | QNAN | QNAN | |
a > +0 | SNAN | QNAN | |
QNAN | b > +0 | QNAN | |
SNAN | b > +0 | QNAN | |
QNAN | QNAN | QNAN | |
QNAN | SNAN | QNAN | |
SNAN | QNAN | QNAN | |
SNAN | SNAN | QNAN |
The atan2(a,b) function does not generate any errors.
Buffer API:
The queue where the routine should be executed.
Specifies the number of elements to be calculated.
The buffer a containing 1st input vector of size n.
The buffer b containing 2nd input vector of size n.
Overrides the global VM mode setting for this function call. See set_mode function for possible values and their description. This is an optional parameter. The default value is mode::not_defined.
USM API:
The queue where the routine should be executed.
Specifies the number of elements to be calculated.
Pointer a to the 1st input vector of size n.
Pointer b to the 2nd input vector of size n.
Vector of dependent events (to wait for input data to be ready).
Overrides the global VM mode setting for this function call. See the set_mode function for possible values and their description. This is an optional parameter. The default value is mode::not_defined.
Buffer API:
The buffer y containing the output vector of size n.
USM API:
Pointer y to the output vector of size n.
Function end event.
An example of how to use atan2can be found in the Intel® oneMKL installation directory, under:
examples/sycl/vml/vatan2.cpp