Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | New mpn_div_qr_1n_pi1 variants, DIV_QR_1N_METHOD 3 and 4. | Niels Möller | 2021-07-01 | 1 | -2/+4 |
| | | | | Not enabled, but hooked into the speed and tuneup programs. | ||||
* | Measure variant 4 and 5 of HGCD2_DIV1_METHOD. | Torbjorn Granlund | 2019-09-23 | 1 | -5/+13 |
| | |||||
* | Make tuning of hgcd and gcd take hgcd2 choice into account | Niels M?ller | 2019-09-23 | 1 | -12/+15 |
| | | | | | | | | | | | | | | | | * gmp-impl.h (hgcd2_func_t) [TUNE_PROGRAM_BUILD]: New typedef. (hgcd2_func) [TUNE_PROGRAM_BUILD]: New function pointer. * tune/hgcd2.c (mpn_hgcd2): New file, with a redefined function to invoke an implementation via the hgcd2_func function pointer. Initially points to the default implementation in mpn/generic/hgcd2.c. * tune/Makefile.am (tuneup_SOURCES): Add hgcd2.c. * tune/tuneup.c (one_method): Return index of selected function. (tune_hgcd2): Set hgcd2_func to point to selected function. So that the later tuning of mpn_hgcd and mpn_gcd uses the right implementation of hgcd2. | ||||
* | tuneup: Add missing comment for the one_method helper function. | Niels M?ller | 2019-09-16 | 1 | -0/+5 |
| | |||||
* | Fix use of TMP_ALLOC in tuneup.c | Niels M?ller | 2019-09-15 | 1 | -1/+1 |
| | |||||
* | Rename HGCD2_METHOD --> HGCD2_DIV1_METHOD. | Niels M?ller | 2019-09-14 | 1 | -1/+1 |
| | |||||
* | New tuneup helper function, to measure several functions for a fix size. | Niels M?ller | 2019-09-13 | 1 | -101/+71 |
| | |||||
* | For hgcd2, add a div1 function handling q <= 7 specially. | Niels M?ller | 2019-09-05 | 1 | -8/+38 |
| | | | | | | | | | | | | | | * mpn/generic/hgcd2.c (div1): Return both r and q as a mp_double_limb_t, replacing the DIV1 macro. (div1) [HGCD2_METHOD == 3]: New implementation handling q <= 7 specially and without branches. Based on Torbj?rn's mail to the gmp-devel list. * tune/speed.c, tune/speed.h, tune/common.c, tune/Makefile.am: Add corresponding speed support. * tune/hgcd2-3.c: New file. * tune/tuneup.c (print_define_with_speedup): New function, to output a comment with speedup compared to next-best method. (tune_hgcd2): Update tuning. | ||||
* | Tuneup support for HGCD2_METHOD, controlling div1 usage in mpn_hgcd2. | Niels M?ller | 2019-09-04 | 1 | -0/+27 |
| | | | | | | | | | | | * mpn/generic/hgcd2.c (HGCD2_METHOD): New parameter. (DIV1): New macro, using either the div1 function or plain division, depending on the value of HGCD2_METHOD. (mpn_hgcd2): Use DIV1. * tune/speed.c, tune/speed.h, tune/common.c, tune/Makefile.am: Add measuring of mpn_hgcd2 methods. * tune/hgcd2-1.c, tune/hgcd2-2.c: New files. * tune/tuneup.c: Tune HGCD2_METHOD. | ||||
* | (tune_sqrlo): For SQRLO_BASECASE_THRESHOLD start at 2. | Torbjorn Granlund | 2017-07-02 | 1 | -1/+1 |
| | |||||
* | (tune_mullo): For MULLO_BASECASE_THRESHOLD start at 2. | Torbjorn Granlund | 2017-07-02 | 1 | -1/+1 |
| | |||||
* | Amend last change: Tweak pi1_bdiv_q_1 / divexact_1 criterion. | Torbjorn Granlund | 2017-02-08 | 1 | -2/+2 |
| | |||||
* | (relspeed_div_1_vs_mul_1): Prefer mpn_pi1_bdiv_q_1. | Torbjorn Granlund | 2017-02-07 | 1 | -7/+20 |
| | |||||
* | Amend last change. | Torbjorn Granlund | 2017-01-25 | 1 | -1/+1 |
| | |||||
* | Break out and optimise powtab computation from mpn/generic/get_str.c and ↵ | Torbjorn Granlund | 2017-01-24 | 1 | -2/+3 |
| | | | | mpn/generic/set_str.c. | ||||
* | (relspeed_div_1_vs_mul_1): New function. | Torbjorn Granlund | 2016-12-31 | 1 | -1/+45 |
| | |||||
* | Include just gmp-impl.h, make gmp-impl.h grab gmp.h. | Torbjorn Granlund | 2016-08-29 | 1 | -1/+0 |
| | |||||
* | (tune_mu_bdiv): Start at measured BDIV_DC_ thresholds. | Torbjorn Granlund | 2015-10-14 | 1 | -2/+2 |
| | |||||
* | tune/tuneup.c (tune_mullo): Set MULLO_MUL_N_THRESHOLD to never | Marco Bodrato | 2015-08-25 | 1 | -11/+12 |
| | | | | whenever the FFT threshold does not exist. | ||||
* | Tuning code for SQRLO_*:THRESHOLDs. | Marco Bodrato | 2015-08-25 | 1 | -0/+50 |
| | |||||
* | mpn/generic/invertappr.c (mpn_ni_invertappr): Reduce memory used (and ↵ | Marco Bodrato | 2015-05-15 | 1 | -3/+3 |
| | | | | related updates) | ||||
* | (all): Make GCD tuning last since it is not robust. | Torbjorn Granlund | 2015-05-01 | 1 | -7/+7 |
| | |||||
* | Add 'static' and 'const' for the benefit of C++. | Torbjorn Granlund | 2014-11-15 | 1 | -2/+0 |
| | |||||
* | Fix typo in last change. | Torbjorn Granlund | 2014-11-14 | 1 | -0/+7 |
| | |||||
* | Add casts for C++ compatibility. | Torbjorn Granlund | 2014-11-13 | 1 | -16/+18 |
| | |||||
* | Ensure DIV_QR_1_NORM_THRESHOLD, DIV_QR_1_UNNORM_THRESHOLD >= 1. | Niels M?ller | 2014-02-17 | 1 | -0/+4 |
| | |||||
* | mpn_sec_powm: Replace exponent limb count argument with a bit count. | Niels M?ller | 2014-02-11 | 1 | -8/+3 |
| | |||||
* | Fixed off-by-one problem in tuning of mpn_sec_powm. | Niels M?ller | 2014-02-09 | 1 | -2/+12 |
| | |||||
* | Update library files license to use LGPL3+ and GPL2+. | Torbjorn Granlund | 2014-01-27 | 1 | -7/+18 |
| | |||||
* | Canonicalise copyright headers. | Torbjorn Granlund | 2014-01-19 | 1 | -3/+3 |
| | |||||
* | Get rid of BYTES_PER_MP_LIMB, most files affected. | Torbjorn Granlund | 2014-01-19 | 1 | -1/+1 |
| | |||||
* | Rename mpn_blah_sec to mpn_sec_blah. | Torbjorn Granlund | 2013-12-26 | 1 | -3/+3 |
| | |||||
* | Use https to link to GNU license. | Torbjorn Granlund | 2013-12-02 | 1 | -1/+1 |
| | |||||
* | Collapse copyright years. | Torbjorn Granlund | 2013-11-28 | 1 | -2/+1 |
| | |||||
* | Implemented tuning of mpn_div_qr_1. | Niels M?ller | 2013-10-20 | 1 | -3/+60 |
| | |||||
* | Fix typos. | Torbjorn Granlund | 2013-07-22 | 1 | -1/+1 |
| | |||||
* | typos in previous commit (was 32-bit only) | Marco Bodrato | 2012-05-07 | 1 | -1/+1 |
| | |||||
* | tune/tuneup.c: Update minimal threshold for FAC_DSC. | Marco Bodrato | 2012-05-07 | 1 | -1/+1 |
| | |||||
* | tune/tuneup.c (tune_fac_u): Update DSC_THRESHOLD minimum. | Marco Bodrato | 2012-05-05 | 1 | -1/+1 |
| | |||||
* | Measure POWM_SEC_TABLE after the REDC thresholds. | Torbjorn Granlund | 2012-05-04 | 1 | -5/+3 |
| | |||||
* | Better handle situation where redc_2 is never faster. | Torbjorn Granlund | 2012-03-07 | 1 | -9/+17 |
| | |||||
* | Clean out __GMP_PROTO. | Torbjorn Granlund | 2012-03-03 | 1 | -7/+4 |
| | |||||
* | Tuneup support for MUL_TOOM43_TO_TOOM54_THRESHOLD. | Niels Möller | 2012-02-15 | 1 | -0/+10 |
| | |||||
* | Remove unused tuneup variables. | Torbjorn Granlund | 2012-01-25 | 1 | -2/+0 |
| | |||||
* | mpz_fac_ui: Less memory, less divisions. | Marco Bodrato | 2012-01-16 | 1 | -1/+1 |
| | |||||
* | Correct miminum for FAC_DSC. | Marco Bodrato | 2012-01-10 | 1 | -1/+1 |
| | |||||
* | tune_fac_ui: ignore fluctuations on small values. | Marco Bodrato | 2012-01-05 | 1 | -0/+1 |
| | |||||
* | tune_fac_ui: FAC_ODD_THRESHOLD can be "always". | Marco Bodrato | 2012-01-05 | 1 | -1/+2 |
| | |||||
* | Small correction to fac_ui thresholds computation. | Marco Bodrato | 2012-01-02 | 1 | -9/+8 |
| | |||||
* | Tune fac_ui thresholds. | Marco Bodrato | 2011-12-31 | 1 | -1/+32 |
| |