AuroraMiddleware/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2024-12-16 08:00:05 +00:00
Code Issues Packages Projects Releases Wiki Activity
424c4f60ed
glibc/sysdeps/ieee754
History
Szabolcs Nagy 424c4f60ed Add new pow implementation 
The algorithm is exp(y * log(x)), where log(x) is computed with about
1.3*2^-68 relative error (1.5*2^-68 without fma), returning the result
in two doubles, and the exp part uses the same algorithm (and lookup
tables) as exp, but takes the input as two doubles and a sign (to handle
negative bases with odd integer exponent).  The __exp1 internal symbol
is no longer necessary.

There is separate code path when fma is not available but the worst case
error is about 0.54 ULP in both cases.  The lookup table and consts for
log are 4168 bytes.  The .rodata+.text is decreased by 37908 bytes on
aarch64.  The non-nearest rounding error is less than 1 ULP.

Improvements on Cortex-A72 compared to current glibc master:
pow thruput: 2.40x in [0.01 11.1]x[0.01 11.1]
pow latency: 1.84x in [0.01 11.1]x[0.01 11.1]

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

	* NEWS: Mention pow improvements.
	* math/Makefile (type-double-routines): Add e_pow_log_data.
	* sysdeps/generic/math_private.h (__exp1): Remove.
	* sysdeps/i386/fpu/e_pow_log_data.c: New file.
	* sysdeps/ia64/fpu/e_pow_log_data.c: New file.
	* sysdeps/ieee754/dbl-64/Makefile (CFLAGS-e_pow.c): Allow fma
	contraction.
	* sysdeps/ieee754/dbl-64/e_exp.c (__exp1): Remove.
	(exp_inline): Remove.
	(__ieee754_exp): Only single double input is handled.
	* sysdeps/ieee754/dbl-64/e_pow.c: Rewrite.
	* sysdeps/ieee754/dbl-64/e_pow_log_data.c: New file.
	* sysdeps/ieee754/dbl-64/math_config.h (issignaling_inline): Define.
	(__pow_log_data): Define.
	* sysdeps/ieee754/dbl-64/upow.h: Remove.
	* sysdeps/ieee754/dbl-64/upow.tbl: Remove.
	* sysdeps/m68k/m680x0/fpu/e_pow_log_data.c: New file.
	* sysdeps/x86_64/fpu/multiarch/Makefile (CFLAGS-e_pow-fma.c): Allow fma
	contraction.
	(CFLAGS-e_pow-fma4.c): Likewise.
2018-09-19 10:04:51 +01:00
..
dbl-64 Add new pow implementation 2018-09-19 10:04:51 +01:00
float128 Use ceil functions not __ceil functions in glibc libm. 2018-09-17 20:42:06 +00:00
flt-32 Use ceil functions not __ceil functions in glibc libm. 2018-09-17 20:42:06 +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 Use ceil functions not __ceil functions in glibc libm. 2018-09-17 20:42:06 +00:00
ldbl-128 Use ceil functions not __ceil functions in glibc libm. 2018-09-17 20:42:06 +00:00
ldbl-128ibm Fix ldbl-128ibm ceill, floorl inlining of ceil, floor. 2018-09-18 13:24:14 +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 Use rint functions not __rint functions in glibc libm. 2018-09-14 13:10:39 +00:00
k_standardf.c Update copyright dates with scripts/update-copyrights. 2018-01-01 00:32:25 +00:00
k_standardl.c Use rint functions not __rint functions in glibc libm. 2018-09-14 13:10:39 +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