PATCH: optimized libm single precision routines: erfcf, erff, expf for x86_64.

[Dmitrieva Liubov]

Hello All,

Here is a patch with the following optimized libm single precision
routines: erfcf, erff, expf for x86_64.

Our performance tests show (in the table here is a ratio: time of test
with libm from current master branch / time of test with libm from
current master branch after applying the patch.)

 	on Istanbul	on    on Atom   on Neha-lem     on AVX
erfcf  1.53	                1.26        1.81                  1.06
erff    1.52	                1.32        2.02                  1.08
expf   2.33                 1.40        2.57                  6.55



ChangeLog:

2012-02-06  Liubov Dmitrieva  <liubov.dmitrieva@gmail.com>

	* sysdeps/x86_64/fpu/s_erff.S: New file.
	* sysdeps/x86_64/fpu/s_erfcf.S: New file.
	* sysdeps/x86_64/fpu/e_expf.S: New file.


--
Liubov Dmitrieva
Software Engineer
Intel Corporation
-------------- next part --------------
A non-text attachment was scrubbed...
Name: single_precision_some_optimized_libm_routines.patch
Type: application/octet-stream
Size: 28417 bytes
Desc: not available
URL: <http://sourceware.org/pipermail/libc-alpha/attachments/20120206/f5a76242/attachment.obj>