AuroraMiddleware/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2024-11-25 22:40:05 +00:00
Code Issues Packages Projects Releases Wiki Activity
221e4babca
glibc/sysdeps/ieee754
History
Szabolcs Nagy 3e08ff544b Add new log2 implementation 
Similar algorithm is used as in log: log2(2^k x) = k + log2(c) + log2(x/c)
where the last term is approximated by a polynomial of x/c - 1, the first
order coefficient is about 1/ln2 in this case.

There is separate code path when fma instruction is not available for
computing x/c - 1 precisely, for which the table size is doubled.

The worst case error is 0.547 ULP (0.55 without fma), the read only
global data size is 1168 bytes (2192 without fma) on aarch64.  The
non-nearest rounding error is less than 1 ULP.

Improvements on Cortex-A72 compared to current glibc master:
log2 thruput: 2.00x in [0.01 11.1]
log2 latency: 2.04x in [0.01 11.1]
log2 thruput: 2.17x in [0.999 1.001]
log2 latency: 2.88x in [0.999 1.001]

Tested on
aarch64-linux-gnu (defined __FP_FAST_FMA)
arm-linux-gnueabihf (!defined __FP_FAST_FMA)
x86_64-linux-gnu (!defined __FP_FAST_FMA)
powerpc64le-linxu-gnu (defined __FP_FAST_FMA)
targets.

	* NEWS: Mention log2 improvements.
	* math/Makefile (type-double-routines): Add e_log2_data.
	* sysdeps/i386/fpu/e_log2_data.c: New file.
	* sysdeps/ia64/fpu/e_log2_data.c: New file.
	* sysdeps/ieee754/dbl-64/e_log2.c: Rewrite.
	* sysdeps/ieee754/dbl-64/e_log2_data.c: New file.
	* sysdeps/ieee754/dbl-64/math_config.h (__log2_data): Add.
	* sysdeps/ieee754/dbl-64/wordsize-64/e_log2.c: Remove.
	* sysdeps/m68k/m680x0/fpu/e_log2_data.c: New file.
2018-09-12 17:36:33 +01:00
..
dbl-64 Add new log2 implementation 2018-09-12 17:36:33 +01:00
float128 Do not include fenv_private.h in math_private.h. 2018-09-03 21:09:04 +00:00
flt-32 Move fenv.h soft-float inlines from fenv_private.h to include/fenv.h. 2018-09-04 19:52:06 +00:00
ldbl-64-128 Don't include math.h/math_private.h in math_ldbl_opt.h. 2018-03-10 15:18:08 -05:00
ldbl-96 Move fenv.h soft-float inlines from fenv_private.h to include/fenv.h. 2018-09-04 19:52:06 +00:00
ldbl-128 Move fenv.h soft-float inlines from fenv_private.h to include/fenv.h. 2018-09-04 19:52:06 +00:00
ldbl-128ibm Move fenv.h soft-float inlines from fenv_private.h to include/fenv.h. 2018-09-04 19:52:06 +00:00
ldbl-128ibm-compat ldbl-128ibm-compat: Add printf_size 2018-07-02 10:51:01 -03:00
ldbl-opt Add a generic significand implementation 2018-06-20 18:15:06 -03:00
soft-fp Add narrowing divide functions. 2018-05-17 00:40:52 +00:00
ieee754.h Update copyright dates with scripts/update-copyrights. 2018-01-01 00:32:25 +00:00
k_standard.c Prefer new libm function wrappers for !LIBM_SVID_COMPAT. 2017-09-05 23:35:55 +00:00
k_standardf.c Update copyright dates with scripts/update-copyrights. 2018-01-01 00:32:25 +00:00
k_standardl.c Move fenv.h soft-float inlines from fenv_private.h to include/fenv.h. 2018-09-04 19:52:06 +00:00
Makefile Avoid -Wno-write-strings for k_standard.c. 2015-02-26 22:50:54 +00:00
s_lib_version.c Simplify math-svid-compat code. 2017-08-28 15:19:52 +00:00
s_matherr.c Obsolete matherr, _LIB_VERSION, libieee.a. 2017-08-21 17:45:10 +00:00
s_signgam.c Fix lgamma setting signgam for ISO C (bug 15421). 2015-11-20 22:49:59 +00:00