standards , range , accuracy trigonometric functions

[RBato]

Dear Intel Community

How is standards , range , accuracy trigonometric functions in Intel C++ Compiler ? How is Your advise ?

[RBato]

Thank You for Your Answered

How is code of floating-point number in Intel processors series ?

Best Regards

Rafał Bator

[Bernard]

I presume that you are talking about the floating point representation of the encoded numbers. So then it is based on IEEE 754 standard.

http://en.wikipedia.org/wiki/IEEE_floating_point

Regarding my previous post , one correction is needed. All that FP transcendental computation is usually performed by micro-code executed by microcode sequencer. Intel calls it Microcode Assists.

[RBato]

Thank You for Your answer .

I read in it  as is listed and not coded . How is coded ?

Best Regards

Rafał Bator

[Bernard]

Rafał B. wrote:

Thank You for Your answer .

I read in it  as is listed and not coded . How is coded ?

Best Regards

Rafał Bator

I think that Intel will not disclose microcode implementation of x87 machine code instructions, but you may look at this paper written by AMD "Hierarchical microcode implementation of floating point instructions on microprocessor". You can find it on Google Patents.