summaryrefslogtreecommitdiff
path: root/tune
Commit message (Collapse)AuthorAgeFilesLines
* Copyright yearsMarco Bodrato2022-02-213-3/+3
|
* tune/: tune/speed support for mpn_{mul,sqr}mod_bknp1Marco Bodrato2022-02-153-0/+125
|
* tune/speed.c: Add FLAG_NODATA for gmp_primesieveMarco Bodrato2022-01-121-1/+1
|
* Copyright yearsMarco Bodrato2021-11-072-2/+2
|
* Add speed support for gmp_primesieve.Marco Bodrato2021-10-143-0/+36
|
* Add speed support for mpn_addaddmul_1msb0.Niels Möller2021-10-073-0/+41
| | | | | | * tune/speed.h (SPEED_ROUTINE_MPN_ADDADDMUL1_MSB0): New macro. * tune/common.c (speed_mpn_addaddmul_1msb0): New function. * tune/speed.c (routine): Add mpn_addaddmul_1msb0 to list.
* Fix missing declaration, to unbreak tuneup.Niels Möller2021-07-021-0/+1
|
* New mpn_div_qr_1n_pi1 variants, DIV_QR_1N_METHOD 3 and 4.Niels Möller2021-07-018-5/+103
| | | | Not enabled, but hooked into the speed and tuneup programs.
* tune: Add support for the function mpz_prevprime() to tune/speed (by Troisi)Marco Bodrato2020-11-233-0/+16
|
* (main): Cast printf args to right type.Torbjorn Granlund2020-11-191-6/+8
|
* (main): Cast printf args to right type.Torbjorn Granlund2020-11-191-1/+1
|
* tune: New mesurable speed, mpz_nextprime_1.Marco Bodrato2020-03-203-0/+54
|
* (main): Use %zu for size_t printing.Torbjorn Granlund2020-01-101-1/+1
|
* tune/speed.c (routine): Add mpn_hgcd2_[45].Marco Bodrato2019-12-201-0/+2
|
* tune: Small optimisations to recent changes.Marco Bodrato2019-11-163-11/+11
|
* tune/: tune/speed support for mpz_nextprime (by Seth Troisi)Marco Bodrato2019-11-163-0/+50
|
* tune/: tune/speed support for mpn_perfect_{power,square}_p (by Seth Troisi)Marco Bodrato2019-11-163-0/+69
|
* tune/speed*: add optional r flag for mpz_powmMarco Bodrato2019-11-092-2/+5
|
* Measure variant 4 and 5 of HGCD2_DIV1_METHOD.Torbjorn Granlund2019-09-236-12/+109
|
* Make tuning of hgcd and gcd take hgcd2 choice into accountNiels M?ller2019-09-233-13/+65
| | | | | | | | | | | | | | | | * 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?ller2019-09-161-0/+5
|
* Fix use of TMP_ALLOC in tuneup.cNiels M?ller2019-09-151-1/+1
|
* Rename HGCD2_METHOD --> HGCD2_DIV1_METHOD.Niels M?ller2019-09-144-7/+7
|
* New tuneup helper function, to measure several functions for a fix size.Niels M?ller2019-09-131-101/+71
|
* For hgcd2, add a div1 function handling q <= 7 specially.Niels M?ller2019-09-056-9/+87
| | | | | | | | | | | | | | * 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?ller2019-09-047-0/+125
| | | | | | | | | | | * 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.
* Speed support for mpn_hgcd2.Niels M?ller2019-09-043-0/+42
| | | | | | * tune/speed.h (SPEED_ROUTINE_MPN_HGCD2): New macro. * tune/common.c (speed_mpn_hgcd2): New function. * tune/speed.c (routine): Add mpn_hgcd2.
* Speed support for gcd_22.Niels M?ller2019-08-163-0/+13
| | | | | | | Calls mpn_gcd_22(al, al, bl, bl), so that B+1 is a common factor. * tune/speed.h (SPEED_ROUTINE_MPN_GCD_22): New macro. * tune/speed.c (routine): Add mpn_gcd_22. * tune/common.c (speed_mpn_gcd_22): New function.
* tune/speed: Support mpn_gcd_11.Niels M?ller2019-08-063-0/+11
|
* Copyright yearsMarco Bodrato2018-05-161-1/+1
|
* tune/speed.c (run_gnuplot): Set termoption, as suggested by Paul.Marco Bodrato2018-03-181-0/+3
|
* tune/Makefile.am: Disallow parallel make (thanks Vincent Lefevre)Marco Bodrato2018-02-181-0/+3
|
* Purge definitions of obsolete UMUL_TIME and UDIV_TIME constants.Niels M?ller2017-07-231-3/+0
|
* Measure mpn_sbpi1_bdiv_r.Torbjorn Granlund2017-07-213-2/+50
|
* (tune_sqrlo): For SQRLO_BASECASE_THRESHOLD start at 2.Torbjorn Granlund2017-07-021-1/+1
|
* (tune_mullo): For MULLO_BASECASE_THRESHOLD start at 2.Torbjorn Granlund2017-07-021-1/+1
|
* (AM_LDFLAGS): Define. (Thanks to Emmanuel Thom?? and Vincent Lefevre.)Torbjorn Granlund2017-06-281-0/+1
|
* tune/common.c (speed_mpn_sqrlo_basecase): Avoid crash when out of range.Marco Bodrato2017-04-181-1/+3
|
* Amend last change: Tweak pi1_bdiv_q_1 / divexact_1 criterion.Torbjorn Granlund2017-02-081-2/+2
|
* (relspeed_div_1_vs_mul_1): Prefer mpn_pi1_bdiv_q_1.Torbjorn Granlund2017-02-071-7/+20
|
* Amend last change.Torbjorn Granlund2017-01-251-1/+1
|
* Break out and optimise powtab computation from mpn/generic/get_str.c and ↵Torbjorn Granlund2017-01-243-4/+3
| | | | mpn/generic/set_str.c.
* (relspeed_div_1_vs_mul_1): New function.Torbjorn Granlund2016-12-311-1/+45
|
* tune/: support mpz_invertMarco Bodrato2016-12-303-0/+43
|
* tune/speed: support mpz_mfac_uiuiMarco Bodrato2016-12-283-5/+37
|
* (cgt_works_p): Add a missing verbosity check.Torbjorn Granlund2016-11-271-2/+2
|
* Include just gmp-impl.h, make gmp-impl.h grab gmp.h.Torbjorn Granlund2016-08-2939-39/+0
|
* tune/speed: Support mpz_primorial_ui.Marco Bodrato2015-11-223-0/+8
|
* (tune_mu_bdiv): Start at measured BDIV_DC_ thresholds.Torbjorn Granlund2015-10-141-2/+2
|
* tune/tuneup.c (tune_mullo): Set MULLO_MUL_N_THRESHOLD to neverMarco Bodrato2015-08-251-11/+12
| | | | whenever the FFT threshold does not exist.