mirror/glibc - mirror of git://sourceware.org/git/glibc.git

	Commit message (Collapse)	Author	Age	Files	Lines
*	powerpc: Remove f{max,min}{f} assembly implementations	Adhemerval Zanella	2016-12-27	1	-1/+0
\| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \|	This patch removes the powerpc assembly implementation of fmax/fmin. Based on benchtests, the assembly ones shows: $ ./testrun.sh benchtests/bench-fmax "fmax": { "": { "duration": 5.07586e+09, "iterations": 2.01676e+09, "max": 1350.39, "min": 2.073, "mean": 2.51684 }, "qNaN": { "duration": 5.09315e+09, "iterations": 8.4568e+08, "max": 2788, "min": 5.806, "mean": 6.02255 }, "sNaN": { "duration": 5.09073e+09, "iterations": 8.42316e+08, "max": 4215.84, "min": 5.737, "mean": 6.04373 } And $ ./testrun.sh benchtests/bench-fmin "fmin": { "": { "duration": 5.07711e+09, "iterations": 2.02982e+09, "max": 497.094, "min": 2.073, "mean": 2.50126 }, "qNaN": { "duration": 5.09134e+09, "iterations": 8.46968e+08, "max": 2255.14, "min": 5.807, "mean": 6.01125 }, "sNaN": { "duration": 5.09122e+09, "iterations": 8.4746e+08, "max": 1969.38, "min": 5.729, "mean": 6.00763 } } The default implementation (math/s_f{max.min}_template.c) shows slight better latency for all cases: $ ./testrun.sh benchtests/bench-fmax "fmax": { "": { "duration": 5.07044e+09, "iterations": 2.38695e+09, "max": 2048.58, "min": 2.073, "mean": 2.12423 }, "qNaN": { "duration": 5.09004e+09, "iterations": 9.45428e+08, "max": 3306.93, "min": 5.138, "mean": 5.38385 }, "sNaN": { "duration": 5.08458e+09, "iterations": 1.15959e+09, "max": 972.008, "min": 3.321, "mean": 4.3848 } } And: $ ./testrun.sh benchtests/bench-fmin "fmin": { "": { "duration": 5.06817e+09, "iterations": 2.3913e+09, "max": 1177.9, "min": 2.073, "mean": 2.11942 }, "qNaN": { "duration": 5.08857e+09, "iterations": 9.45656e+08, "max": 2658.83, "min": 5.09, "mean": 5.38099 }, "sNaN": { "duration": 5.08093e+09, "iterations": 1.16725e+09, "max": 1030.74, "min": 3.323, "mean": 4.3529 } } Both were run with GCC 5.4 (ubuntu 16 default installation) using default compiler flags on POWER8E 3.4GHz (powerpc64le-linux-gnu).
*	Update.	Ulrich Drepper	1999-10-10	1	-0/+1
	* nss/getXXbyYY_r.c (do_weak_alias): Remove unnecessary parenthesis. * sysdeps/powerpc/s_copysign.S: Move to... * sysdeps/powerpc/fpu/s_copysign.S: ...here. Use portable asm syntax. * sysdeps/powerpc/s_copysignf.S: Move to... * sysdeps/powerpc/fpu/s_copysignf.S: ...here. * sysdeps/powerpc/s_fabs.S: Move to... * sysdeps/powerpc/fpu/s_fabs.S: ...here. Use portable asm syntax. * sysdeps/powerpc/s_fabsf.S: Move to... * sysdeps/powerpc/fpu/s_fabsf.S: ...here. * sysdeps/powerpc/s_fdim.c: Move to... * sysdeps/powerpc/fpu/s_fdim.c: ...here. * sysdeps/powerpc/s_fdimf.c: Move to... * sysdeps/powerpc/fpu/s_fdimf.c: ...here. * sysdeps/powerpc/s_fmax.S: Move to... * sysdeps/powerpc/fpu/s_fmax.S: ...here. Use portable asm syntax. * sysdeps/powerpc/s_fmaxf.S: Move to... * sysdeps/powerpc/fpu/s_fmaxf.S: ...here. * sysdeps/powerpc/s_fmin.S: Move to... * sysdeps/powerpc/fpu/s_fmin.S: ...here. Use portable asm syntax. * sysdeps/powerpc/s_fminf.S: Move to... * sysdeps/powerpc/fpu/s_fminf.S: ...here. * sysdeps/powerpc/s_isnan.S: Move to... * sysdeps/powerpc/fpu/s_isnan.c: ...here. * sysdeps/powerpc/s_isnanf.S: Move to... * sysdeps/powerpc/fpu/s_isnanf.S: ...here. * sysdeps/powerpc/s_llrint.c: Move to... * sysdeps/powerpc/fpu/s_llrint.c: ...here. * sysdeps/powerpc/s_llrintf.c: Move to... * sysdeps/powerpc/fpu/s_llrintf.c: ...here. * sysdeps/powerpc/s_llround.c: Move to... * sysdeps/powerpc/fpu/s_llround.c: ...here. * sysdeps/powerpc/s_llroundf.c: Move to... * sysdeps/powerpc/fpu/s_llroundf.c: ...here. * sysdeps/powerpc/s_lrint.c: Move to... * sysdeps/powerpc/fpu/s_lrint.c: ...here. * sysdeps/powerpc/s_lrintf.S: Move to... * sysdeps/powerpc/fpu/s_lrintf.S: ...here. * sysdeps/powerpc/s_lround.c: Move to... * sysdeps/powerpc/fpu/s_lround.c: ...here. * sysdeps/powerpc/s_lroundf.c: Move to... * sysdeps/powerpc/fpu/s_lroundf.c: ...here. * sysdeps/powerpc/s_rint.c: Move to... * sysdeps/powerpc/fpu/s_rint.c: ...here. * sysdeps/powerpc/s_rintf.c: Move to... * sysdeps/powerpc/fpu/s_rintf.c: ...here. * sysdeps/powerpc/t_sqrt.c: Move to... * sysdeps/powerpc/fpu/t_sqrt: ...here. * sysdeps/powerpc/w_sqrt.c: Move to... * sysdeps/powerpc/fpu/w_sqrt.c: ...here. * sysdeps/powerpc/w_sqrtf.c: Move to... * sysdeps/powerpc/fpu/w_sqrtf.c: ...here. * configure.in: Support platforms which have no .text pseudo-op. Patches partly by Jimi X <jimix@pobox.com>.