Computes hyperbolic cosine of vector elements.
Buffer API:
void cosh(queue& exec_queue, int64_t n, buffer<T,1>& a, buffer<T,1>& y, uint64_t mode = mode::not_defined, error_handler<T> errhandler = {} );
USM API:
event cosh(queue& exec_queue, int64_t n, T* a, T* y, vector_class<event>* depends, uint64_t mode = mode::not_defined, error_handler<T> errhandler = {} );
cosh supports the following precisions and devices:
T | Devices supported |
---|---|
float | Host, CPU, and GPU |
double | Host, CPU, and GPU |
std::complex<float> | Host |
std::complex<double> | Host |
The cosh(a) function computes hyperbolic cosine of vector elements.
Data Type | Threshold Limitations on Input Parameters |
---|---|
single precision | -Log(FLT_MAX)-Log2 <a[i] < Log(FLT_MAX)+Log2 |
double precision | -Log(DBL_MAX)-Log2 <a[i] < Log(DBL_MAX)+Log2 |
Argument | Result | Error Code |
---|---|---|
+0 | +1 | |
-0 | +1 | |
X > overflow | +∞ | status::overflow |
X < -overflow | +∞ | status::overflow |
+∞ | +∞ | |
-∞ | +∞ | |
QNAN | QNAN | |
SNAN | QNAN |
RE(a) i·IM(a) |
-∞
|
-X
|
-0
|
+0
|
+X
|
+∞
|
NAN
|
---|---|---|---|---|---|---|---|
+i·∞ | +∞+i·QNAN |
QNAN+i·QNAN |
QNAN-i·0 |
QNAN+i·0 |
QNAN+i·QNAN |
+∞+i·QNAN |
QNAN+i·QNAN |
+i·Y | +∞·Cos(Y)- i·∞·Sin(Y) |
+∞·CIS(Y) |
QNAN+i·QNAN |
||||
+i·0 | +∞-i·0 | +1-i·0 | +1+i·0 | +∞+i·0 | QNAN+i·0 |
||
-i·0 | +∞+i·0 | +1+i·0 | +1-i·0 | +∞-i·0 | QNAN-i·0 |
||
-i·Y | +∞·Cos(Y)- i·∞·Sin(Y) |
+∞·CIS(Y) |
QNAN+i·QNAN |
||||
-i·∞ | +∞+i·QNAN |
QNAN+i·QNAN |
QNAN+i·0 |
QNAN-i·0 |
QNAN+i·QNAN |
+∞+i·QNAN |
QNAN+i·QNAN |
+i·NAN | +∞+i·QNAN |
QNAN+i·QNAN |
QNAN+i·QNAN |
QNAN-i·QNAN |
QNAN+i·QNAN |
+∞+i·QNAN |
QNAN+i·QNAN |
Notes:
The complex cosh(a) function sets the VM Error Status to status::overflow in the case of overflow, that is, when RE(a), IM(a) are finite non-zero numbers, but the real or imaginary part of the exact result is so large that it does not meet the target precision.
cosh(CONJ(a))=CONJ(cosh(a))
cosh(-a)=cosh(a).
Buffer API:
The queue where the routine should be executed.
Specifies the number of elements to be calculated.
The buffer a containing 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.
Sets local error handling mode for this function call. See the create_error_handler function for arguments and their descriptions. This is an optional parameter. The local error handler is disabled by default.
USM API:
The queue where the routine should be executed.
Specifies the number of elements to be calculated.
Pointer a to the 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.
Sets local error handling mode for this function call. See the create_error_handler function for arguments and their descriptions. This is an optional parameter. The local error handler is disabled by default.
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 coshcan be found in the Intel® oneMKL installation directory, under:
examples/sycl/vml/vcosh.cpp