Ensures that the math library functions produce consistent results across different implementations of the same architecture.
IDE Equivalent
NoneArchitectures
IA-32, Intel® 64 architectures
Syntax
Linux and Mac OS X: | -fimf-arch-consistency=value[:funclist] |
Windows: | /Qimf-arch-consistency:value[:funclist] |
Arguments
value |
Is one of the logical values "true" or "false". |
funclist |
Is an optional list of one or more math library functions to which the attribute should be applied. If you specify more than one function, they must be separated with commas. |
Default
OFF |
The compiler uses default heuristics when calling math library functions. |
Description
This option ensures that the math library functions produce consistent results across different implementations of the same architecture.
If -fimf-arch-consistency=true (Linux and Mac OS X) or /Qimf-arch-consistency:true is specified, it takes precedence over precision settings in the following options:
-fimf-absolute-error (Linux* OS and Mac OS* X) or /Qimf-absolute-error (Windows* OS)
-
-fimf-accuracy-bits (Linux OS and Mac OS X) or /Qimf-accuracy-bits (Windows OS)
-fimf-max-error (Linux OS and Mac OS X) or /Qimf-max-error (Windows OS)
-
-fimf-precision (Linux OS and Mac OS X) or /Qimf-precision (Windows OS)
The -fimf-arch-consistency (Linux* OS and Mac OS* X) and /Qimf-arch-consistency (Windows* OS) option may decrease run-time performance, but the option will provide bit-wise consistent results on all Intel® processors and compatible, non-Intel processors, regardless of micro-architecture. This option may not provide bit-wise consistent results between different architectures, for example, between IA-32 and Intel® 64 architectures.
Note
Many routines in libraries LIBM (Math Library) and SVML (Short Vector Math Library) are more highly optimized for Intel® microprocessors than for non-Intel microprocessors.
Alternate Options
None