Sets a new mode for VML functions according to the mode parameter and stores the previous VML mode to oldmode.
Include Files
The FORTRAN 77 interfaces are specified in the mkl_vml.f77 include file, the Fortran 90 interfaces are specified in the mkl_vml.f90 include file, and the C interfaces are specified in the mkl_vml_functions.h include file.
Input Parameters
Name |
Type |
Description |
|---|---|---|
mode |
FORTRAN 77: INTEGER*8 Fortran 90: INTEGER(KIND=8), INTENT(IN) C: const MKL_INT64 |
Specifies the VML mode to be set. |
Output Parameters
Name |
Type |
Description |
|---|---|---|
oldmode |
FORTRAN: INTEGER*8 Fortran 90: INTEGER(KIND=8) C: MKL_INT64 |
Specifies the former VML mode. |
Description
The SetMode function sets a new mode for VML functions according to the mode parameter and stores the previous VML mode to oldmode. The mode change has a global effect on all the VML functions within a thread.
Note
You can override the global mode setting and change the mode for a given VML function call by using a respective vm[s,d]<Func> variant of the function.
The mode parameter is designed to control accuracy, handling of denormalized numbers, and error handling. Table "Values of the mode Parameter" lists values of the mode parameter. You can obtain all other possible values of the mode parameter from the mode parameter values by using bitwise OR ( | ) operation to combine one value for accuracy, one value for handling of denormalized numbers, and one vlaue for error control options. The default value of the mode parameter is VML_HA | VML_FTZDAZ_OFF | VML_ERRMODE_DEFAULT.
The VML_FTZDAZ_ON mode is specifically designed to improve the performance of computations that involve denormalized numbers at the cost of reasonable accuracy loss. This mode changes the numeric behavior of the functions: denormalized input values are treated as zeros (DAZ = denormals-are-zero) and denormalized results are flushed to zero (FTZ = flush-to-zero). Accuracy loss may occur if input and/or output values are close to denormal range.
| Value of mode | Description |
|---|---|
| Accuracy Control | |
| VML_HA | high accuracy versions of VML functions |
| VML_LA | low accuracy versions of VML functions |
| VML_EP | enhanced performance accuracy versions of VML functions |
| Denormalized Numbers Handling Control | |
| VML_FTZDAZ_ON | Faster processing of denormalized inputs is enabled. |
| VML_FTZDAZ_OFF | Faster processing of denormalized inputs is disabled. |
| Error Mode Control | |
| VML_ERRMODE_IGNORE | No action is set for computation errors. |
| VML_ERRMODE_ERRNO | On error, the errno variable is set. |
| VML_ERRMODE_STDERR | On error, the error text information is written to stderr. |
| VML_ERRMODE_EXCEPT | On error, an exception is raised. |
| VML_ERRMODE_CALLBACK | On error, an additional error handler function is called. |
| VML_ERRMODE_DEFAULT | On error, the errno variable is set, an exception is raised, and an additional error handler function is called. |
Examples
The following example shows how to set low accuracy, fast processing for denormalized numbers and errno error mode in the Fortran and C languages:
- Fortran:
oldmode = vmlsetmode( VML_LA )
call vmlsetmode( IOR(VML_LA, VML_FTZDAZ_ON, VML_ERRMODE_ERRNO) )
- C:
vmlSetMode( VML_LA );
vmlSetMode( VML_LA | VML_FTZDAZ_ON | VML_ERRMODE_ERRNO );