From a89a14ef5da44684a16b204e7a70460cc8c4922a Mon Sep 17 00:00:00 2001 From: Thomas Voss Date: Fri, 21 Jun 2024 23:36:36 +0200 Subject: Basic constant folding implementation --- vendor/gmp-6.3.0/mpn/x86/bd2/gmp-mparam.h | 214 ++++++++++++++++++++++++++++++ 1 file changed, 214 insertions(+) create mode 100644 vendor/gmp-6.3.0/mpn/x86/bd2/gmp-mparam.h (limited to 'vendor/gmp-6.3.0/mpn/x86/bd2') diff --git a/vendor/gmp-6.3.0/mpn/x86/bd2/gmp-mparam.h b/vendor/gmp-6.3.0/mpn/x86/bd2/gmp-mparam.h new file mode 100644 index 0000000..6893da7 --- /dev/null +++ b/vendor/gmp-6.3.0/mpn/x86/bd2/gmp-mparam.h @@ -0,0 +1,214 @@ +/* AMD bd2 gmp-mparam.h -- Compiler/machine parameter header file. + +Copyright 2019 Free Software Foundation, Inc. + +This file is part of the GNU MP Library. + +The GNU MP Library is free software; you can redistribute it and/or modify +it under the terms of either: + + * the GNU Lesser General Public License as published by the Free + Software Foundation; either version 3 of the License, or (at your + option) any later version. + +or + + * the GNU General Public License as published by the Free Software + Foundation; either version 2 of the License, or (at your option) any + later version. + +or both in parallel, as here. + +The GNU MP Library is distributed in the hope that it will be useful, but +WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +for more details. + +You should have received copies of the GNU General Public License and the +GNU Lesser General Public License along with the GNU MP Library. If not, +see https://www.gnu.org/licenses/. */ + +#define GMP_LIMB_BITS 32 +#define GMP_LIMB_BYTES 4 + +/* 4000-4200 MHz Piledriver Vishera */ +/* FFT tuning limit = 67,000,000 */ +/* Generated by tuneup.c, 2019-10-23, gcc 8.3 */ + +#define MOD_1_NORM_THRESHOLD 3 +#define MOD_1_UNNORM_THRESHOLD 4 +#define MOD_1N_TO_MOD_1_1_THRESHOLD 6 +#define MOD_1U_TO_MOD_1_1_THRESHOLD 4 +#define MOD_1_1_TO_MOD_1_2_THRESHOLD 18 +#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */ +#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 12 +#define USE_PREINV_DIVREM_1 1 /* native */ +#define DIV_QR_1N_PI1_METHOD 1 /* 40.87% faster than 2 */ +#define DIV_QR_1_NORM_THRESHOLD 5 +#define DIV_QR_1_UNNORM_THRESHOLD MP_SIZE_T_MAX /* never */ +#define DIV_QR_2_PI2_THRESHOLD MP_SIZE_T_MAX /* never */ +#define DIVEXACT_1_THRESHOLD 0 /* always (native) */ +#define BMOD_1_TO_MOD_1_THRESHOLD 24 + +#define DIV_1_VS_MUL_1_PERCENT 254 + +#define MUL_TOOM22_THRESHOLD 32 +#define MUL_TOOM33_THRESHOLD 73 +#define MUL_TOOM44_THRESHOLD 151 +#define MUL_TOOM6H_THRESHOLD 222 +#define MUL_TOOM8H_THRESHOLD 351 + +#define MUL_TOOM32_TO_TOOM43_THRESHOLD 85 +#define MUL_TOOM32_TO_TOOM53_THRESHOLD 110 +#define MUL_TOOM42_TO_TOOM53_THRESHOLD 100 +#define MUL_TOOM42_TO_TOOM63_THRESHOLD 110 +#define MUL_TOOM43_TO_TOOM54_THRESHOLD 130 + +#define SQR_BASECASE_THRESHOLD 0 /* always (native) */ +#define SQR_TOOM2_THRESHOLD 44 +#define SQR_TOOM3_THRESHOLD 93 +#define SQR_TOOM4_THRESHOLD 212 +#define SQR_TOOM6_THRESHOLD 318 +#define SQR_TOOM8_THRESHOLD 466 + +#define MULMID_TOOM42_THRESHOLD 66 + +#define MULMOD_BNM1_THRESHOLD 20 +#define SQRMOD_BNM1_THRESHOLD 23 + +#define MUL_FFT_MODF_THRESHOLD 595 /* k = 5 */ +#define MUL_FFT_TABLE3 \ + { { 595, 5}, { 27, 6}, { 29, 7}, { 15, 6}, \ + { 33, 7}, { 17, 6}, { 35, 7}, { 19, 6}, \ + { 39, 7}, { 23, 6}, { 47, 7}, { 29, 8}, \ + { 15, 7}, { 35, 8}, { 19, 7}, { 41, 8}, \ + { 23, 7}, { 49, 8}, { 31, 7}, { 63, 8}, \ + { 39, 9}, { 23, 8}, { 55, 9}, { 31, 8}, \ + { 67, 9}, { 39, 8}, { 83, 9}, { 47, 8}, \ + { 95, 9}, { 55,10}, { 31, 9}, { 79,10}, \ + { 47, 9}, { 95,11}, { 31,10}, { 63, 9}, \ + { 135,10}, { 79, 9}, { 159,10}, { 95, 9}, \ + { 191,11}, { 63,10}, { 143, 7}, { 1215, 9}, \ + { 319, 8}, { 639, 9}, { 335, 8}, { 671, 9}, \ + { 351,10}, { 191,12}, { 63,11}, { 127,10}, \ + { 271,11}, { 159,10}, { 319, 9}, { 639,10}, \ + { 335,11}, { 191,10}, { 399,11}, { 223,12}, \ + { 127,11}, { 255,10}, { 543,11}, { 287,10}, \ + { 607,11}, { 319,10}, { 671,12}, { 191,11}, \ + { 383,10}, { 799,11}, { 415,13}, { 127,12}, \ + { 255,11}, { 543,10}, { 1087,11}, { 607,12}, \ + { 319,11}, { 671,10}, { 1343,11}, { 735,10}, \ + { 1471,12}, { 383,11}, { 799,10}, { 1599,11}, \ + { 863,12}, { 447,11}, { 895,13}, { 255,12}, \ + { 511,11}, { 1087,12}, { 575,11}, { 1215,12}, \ + { 639,11}, { 1343,12}, { 703,11}, { 1471,13}, \ + { 383,12}, { 767,11}, { 1599,12}, { 831,11}, \ + { 1727,12}, { 895,14}, { 255,13}, { 511,12}, \ + { 1087,11}, { 2239,12}, { 1215,13}, { 639,12}, \ + { 1471,11}, { 2943,13}, { 767,12}, { 1727,13}, \ + { 895,12}, { 1919,14}, { 511,13}, { 1023,12}, \ + { 2239,13}, { 1151,12}, { 2431,13}, { 1279,12}, \ + { 2623,13}, { 1407,12}, { 2943,14}, { 767,13}, \ + { 1535,12}, { 3135,13}, { 1663,12}, { 3455,13}, \ + { 1919,15}, { 511,14}, { 1023,13}, { 2175,12}, \ + { 4479,13}, { 2431,14}, { 1279,13}, { 2943,12}, \ + { 5887,14}, { 1535,13}, { 3455,14}, { 1791,13}, \ + { 3967,12}, { 7935,11}, { 15871,15}, { 1023,14}, \ + { 2047,13}, { 4479,14}, { 2303,13}, { 4991,12}, \ + { 9983,14}, { 2815,13}, { 5887,15}, { 1535,14}, \ + { 3839,13}, { 7935,12}, { 15871,16} } +#define MUL_FFT_TABLE3_SIZE 155 +#define MUL_FFT_THRESHOLD 6784 + +#define SQR_FFT_MODF_THRESHOLD 555 /* k = 5 */ +#define SQR_FFT_TABLE3 \ + { { 555, 5}, { 28, 6}, { 15, 5}, { 31, 6}, \ + { 16, 5}, { 33, 6}, { 29, 7}, { 15, 6}, \ + { 33, 7}, { 17, 6}, { 36, 7}, { 19, 6}, \ + { 39, 7}, { 23, 6}, { 47, 7}, { 29, 8}, \ + { 15, 7}, { 35, 8}, { 19, 7}, { 43, 8}, \ + { 23, 7}, { 49, 8}, { 31, 7}, { 63, 8}, \ + { 43, 9}, { 23, 8}, { 55, 9}, { 31, 8}, \ + { 67, 9}, { 39, 8}, { 79, 9}, { 47, 8}, \ + { 95, 9}, { 55,10}, { 31, 9}, { 79,10}, \ + { 47, 9}, { 95,11}, { 31,10}, { 63, 9}, \ + { 135,10}, { 79, 9}, { 159,10}, { 95,11}, \ + { 63,10}, { 143, 9}, { 287,10}, { 159,11}, \ + { 95,10}, { 191, 6}, { 3071, 5}, { 6399, 6}, \ + { 3455, 7}, { 1791, 8}, { 959,10}, { 255, 9}, \ + { 511,10}, { 271,11}, { 159,10}, { 319, 9}, \ + { 639,10}, { 335, 9}, { 671,10}, { 351,11}, \ + { 191,10}, { 399, 9}, { 799,10}, { 415,11}, \ + { 223,12}, { 127,11}, { 255,10}, { 543,11}, \ + { 287,10}, { 607,11}, { 319,10}, { 671,11}, \ + { 351,12}, { 191,11}, { 383,10}, { 799,11}, \ + { 415,13}, { 127,12}, { 255,11}, { 543,10}, \ + { 1087,11}, { 607,12}, { 319,11}, { 671,10}, \ + { 1343,11}, { 735,12}, { 383,11}, { 799,10}, \ + { 1599,11}, { 863,12}, { 447,11}, { 927,13}, \ + { 255,12}, { 511,11}, { 1055,10}, { 2111,11}, \ + { 1087,12}, { 575,11}, { 1215,12}, { 639,11}, \ + { 1343,12}, { 703,13}, { 383,12}, { 767,11}, \ + { 1599,12}, { 831,11}, { 1727,10}, { 3455,12}, \ + { 959,14}, { 255,13}, { 511,12}, { 1023,11}, \ + { 2111,12}, { 1087,11}, { 2239,10}, { 4479,12}, \ + { 1215,13}, { 639,12}, { 1471,11}, { 2943,13}, \ + { 767,12}, { 1727,11}, { 3455,13}, { 895,12}, \ + { 1855,14}, { 511,13}, { 1023,12}, { 2239,13}, \ + { 1151,12}, { 2495,13}, { 1279,12}, { 2623,13}, \ + { 1407,12}, { 2943,14}, { 767,13}, { 1663,12}, \ + { 3455,13}, { 1791,15}, { 511,14}, { 1023,13}, \ + { 2175,12}, { 4479,13}, { 2431,14}, { 1279,13}, \ + { 2943,12}, { 5887,14}, { 1535,13}, { 3455,14}, \ + { 1791,13}, { 3967,12}, { 7935,15}, { 1023,14}, \ + { 2047,13}, { 4479,14}, { 2303,13}, { 4991,12}, \ + { 9983,14}, { 2815,13}, { 5887,15}, { 1535,14}, \ + { 3839,13}, { 7935,16} } +#define SQR_FFT_TABLE3_SIZE 166 +#define SQR_FFT_THRESHOLD 5760 + +#define MULLO_BASECASE_THRESHOLD 3 +#define MULLO_DC_THRESHOLD 34 +#define MULLO_MUL_N_THRESHOLD 13463 +#define SQRLO_BASECASE_THRESHOLD 8 +#define SQRLO_DC_THRESHOLD 43 +#define SQRLO_SQR_THRESHOLD 11278 + +#define DC_DIV_QR_THRESHOLD 75 +#define DC_DIVAPPR_Q_THRESHOLD 200 +#define DC_BDIV_QR_THRESHOLD 71 +#define DC_BDIV_Q_THRESHOLD 119 + +#define INV_MULMOD_BNM1_THRESHOLD 74 +#define INV_NEWTON_THRESHOLD 266 +#define INV_APPR_THRESHOLD 214 + +#define BINV_NEWTON_THRESHOLD 278 +#define REDC_1_TO_REDC_N_THRESHOLD 71 + +#define MU_DIV_QR_THRESHOLD 1652 +#define MU_DIVAPPR_Q_THRESHOLD 1589 +#define MUPI_DIV_QR_THRESHOLD 122 +#define MU_BDIV_QR_THRESHOLD 1442 +#define MU_BDIV_Q_THRESHOLD 1597 + +#define POWM_SEC_TABLE 1,22,96,289,1259 + +#define GET_STR_DC_THRESHOLD 11 +#define GET_STR_PRECOMPUTE_THRESHOLD 20 +#define SET_STR_DC_THRESHOLD 173 +#define SET_STR_PRECOMPUTE_THRESHOLD 454 + +#define FAC_DSC_THRESHOLD 90 +#define FAC_ODD_THRESHOLD 34 + +#define MATRIX22_STRASSEN_THRESHOLD 19 +#define HGCD2_DIV1_METHOD 1 /* 5.80% faster than 3 */ +#define HGCD_THRESHOLD 74 +#define HGCD_APPR_THRESHOLD 50 +#define HGCD_REDUCE_THRESHOLD 3389 +#define GCD_DC_THRESHOLD 456 +#define GCDEXT_DC_THRESHOLD 345 +#define JACOBI_BASE_METHOD 4 /* 17.07% faster than 1 */ + +/* Tuneup completed successfully, took 53914 seconds */ -- cgit v1.2.3