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/bd4/gmp-mparam.h | 225 ++++++++++++++++++++++++++++++ 1 file changed, 225 insertions(+) create mode 100644 vendor/gmp-6.3.0/mpn/x86/bd4/gmp-mparam.h (limited to 'vendor/gmp-6.3.0/mpn/x86/bd4') diff --git a/vendor/gmp-6.3.0/mpn/x86/bd4/gmp-mparam.h b/vendor/gmp-6.3.0/mpn/x86/bd4/gmp-mparam.h new file mode 100644 index 0000000..6c20d0f --- /dev/null +++ b/vendor/gmp-6.3.0/mpn/x86/bd4/gmp-mparam.h @@ -0,0 +1,225 @@ +/* AMD bd4 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 + +/* 3800-4200 MHz Excavator/Bristol Ridge */ +/* FFT tuning limit = 67,000,000 */ +/* Generated by tuneup.c, 2019-10-23, gcc 8.3 */ + +#define MOD_1_NORM_THRESHOLD 0 /* always */ +#define MOD_1_UNNORM_THRESHOLD 0 /* always */ +#define MOD_1N_TO_MOD_1_1_THRESHOLD 8 +#define MOD_1U_TO_MOD_1_1_THRESHOLD 6 +#define MOD_1_1_TO_MOD_1_2_THRESHOLD 27 +#define MOD_1_2_TO_MOD_1_4_THRESHOLD 50 +#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 13 +#define USE_PREINV_DIVREM_1 1 /* native */ +#define DIV_QR_1N_PI1_METHOD 1 /* 28.45% faster than 2 */ +#define DIV_QR_1_NORM_THRESHOLD 4 +#define DIV_QR_1_UNNORM_THRESHOLD MP_SIZE_T_MAX /* never */ +#define DIV_QR_2_PI2_THRESHOLD 13 +#define DIVEXACT_1_THRESHOLD 0 /* always (native) */ +#define BMOD_1_TO_MOD_1_THRESHOLD 28 + +#define DIV_1_VS_MUL_1_PERCENT 314 + +#define MUL_TOOM22_THRESHOLD 32 +#define MUL_TOOM33_THRESHOLD 73 +#define MUL_TOOM44_THRESHOLD 166 +#define MUL_TOOM6H_THRESHOLD 270 +#define MUL_TOOM8H_THRESHOLD 357 + +#define MUL_TOOM32_TO_TOOM43_THRESHOLD 69 +#define MUL_TOOM32_TO_TOOM53_THRESHOLD 114 +#define MUL_TOOM42_TO_TOOM53_THRESHOLD 103 +#define MUL_TOOM42_TO_TOOM63_THRESHOLD 121 +#define MUL_TOOM43_TO_TOOM54_THRESHOLD 154 + +#define SQR_BASECASE_THRESHOLD 0 /* always (native) */ +#define SQR_TOOM2_THRESHOLD 42 +#define SQR_TOOM3_THRESHOLD 89 +#define SQR_TOOM4_THRESHOLD 208 +#define SQR_TOOM6_THRESHOLD 306 +#define SQR_TOOM8_THRESHOLD 454 + +#define MULMID_TOOM42_THRESHOLD 68 + +#define MULMOD_BNM1_THRESHOLD 19 +#define SQRMOD_BNM1_THRESHOLD 18 + +#define MUL_FFT_MODF_THRESHOLD 570 /* k = 5 */ +#define MUL_FFT_TABLE3 \ + { { 570, 5}, { 25, 6}, { 13, 5}, { 27, 6}, \ + { 25, 7}, { 13, 6}, { 27, 7}, { 15, 6}, \ + { 32, 7}, { 17, 6}, { 35, 7}, { 19, 6}, \ + { 39, 7}, { 27, 8}, { 15, 7}, { 35, 8}, \ + { 19, 7}, { 41, 8}, { 23, 7}, { 47, 8}, \ + { 27, 9}, { 15, 8}, { 31, 7}, { 63, 8}, \ + { 39, 9}, { 23, 8}, { 51,10}, { 15, 9}, \ + { 31, 8}, { 67, 9}, { 39, 8}, { 79, 9}, \ + { 47, 8}, { 95,10}, { 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, 6}, { 2303, 5}, \ + { 4735, 4}, { 9471, 5}, { 4863, 7}, { 1279, 9}, \ + { 335, 8}, { 671, 9}, { 351, 8}, { 703,10}, \ + { 191,12}, { 63,11}, { 127,10}, { 255, 9}, \ + { 511,10}, { 271, 9}, { 543,11}, { 159,10}, \ + { 319, 9}, { 639,10}, { 335, 9}, { 671, 8}, \ + { 1343,10}, { 351, 9}, { 703,10}, { 367, 9}, \ + { 735,11}, { 191,10}, { 383, 9}, { 767,10}, \ + { 399, 9}, { 799, 8}, { 1599,10}, { 415,11}, \ + { 223,12}, { 127,11}, { 255,10}, { 543, 9}, \ + { 1087,11}, { 287,10}, { 607, 9}, { 1215,11}, \ + { 319,10}, { 671, 9}, { 1343,11}, { 351,12}, \ + { 191,11}, { 383,10}, { 799,11}, { 415,10}, \ + { 863,13}, { 127,12}, { 255,11}, { 543,10}, \ + { 1087,11}, { 607,10}, { 1215, 9}, { 2431,12}, \ + { 319,11}, { 671,10}, { 1343,11}, { 735,10}, \ + { 1471, 9}, { 2943,12}, { 383,11}, { 799,10}, \ + { 1599,11}, { 863,10}, { 1727,12}, { 447,11}, \ + { 959,10}, { 1919,13}, { 255,12}, { 511,11}, \ + { 1087,12}, { 575,11}, { 1215,10}, { 2431,12}, \ + { 639,11}, { 1343,12}, { 703,11}, { 1471,10}, \ + { 2943,13}, { 383,12}, { 767,11}, { 1599,12}, \ + { 831,11}, { 1727,10}, { 3455,12}, { 959,11}, \ + { 1919,10}, { 3839,13}, { 511,12}, { 1087,11}, \ + { 2239,12}, { 1215,11}, { 2431,13}, { 639,12}, \ + { 1471,11}, { 2943,10}, { 5887,13}, { 767,12}, \ + { 1727,11}, { 3455,13}, { 895,12}, { 1919,11}, \ + { 3839,14}, { 511,13}, { 1023,12}, { 2239,13}, \ + { 1151,12}, { 2431,13}, { 1279,12}, { 2559,13}, \ + { 1407,12}, { 2943,11}, { 5887,14}, { 767,13}, \ + { 1663,12}, { 3455,13}, { 1919,12}, { 3839,15}, \ + { 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 MUL_FFT_TABLE3_SIZE 192 +#define MUL_FFT_THRESHOLD 5760 + +#define SQR_FFT_MODF_THRESHOLD 476 /* k = 5 */ +#define SQR_FFT_TABLE3 \ + { { 476, 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}, { 29, 8}, { 15, 7}, { 35, 8}, \ + { 19, 7}, { 41, 8}, { 23, 7}, { 47, 8}, \ + { 27, 9}, { 15, 8}, { 39, 9}, { 23, 8}, \ + { 51, 9}, { 31, 8}, { 67, 9}, { 39, 8}, \ + { 79, 9}, { 47, 8}, { 95,10}, { 31, 9}, \ + { 79,10}, { 47, 9}, { 95,11}, { 31,10}, \ + { 63, 9}, { 135,10}, { 95, 9}, { 191,10}, \ + { 111,11}, { 63,10}, { 127, 9}, { 255,10}, \ + { 143, 9}, { 287, 8}, { 575,10}, { 159,11}, \ + { 95,10}, { 191,12}, { 63,10}, { 255, 9}, \ + { 511,10}, { 271, 9}, { 543,10}, { 287, 9}, \ + { 575,11}, { 159,10}, { 319, 9}, { 639,10}, \ + { 335, 9}, { 671,10}, { 351, 9}, { 735,11}, \ + { 191,10}, { 383, 9}, { 767,10}, { 399, 9}, \ + { 799,10}, { 415, 9}, { 863,12}, { 127,11}, \ + { 255,10}, { 511, 9}, { 1023,10}, { 543,11}, \ + { 287,10}, { 607, 9}, { 1215,11}, { 319,10}, \ + { 671, 9}, { 1343,11}, { 351,10}, { 735,12}, \ + { 191,11}, { 383,10}, { 799,11}, { 415,10}, \ + { 863,13}, { 127,12}, { 255,11}, { 511,10}, \ + { 1055,11}, { 543,10}, { 1087,11}, { 607,10}, \ + { 1215,12}, { 319,11}, { 671,10}, { 1343,11}, \ + { 735,10}, { 1471,12}, { 383,11}, { 799,10}, \ + { 1599,11}, { 863,10}, { 1727,12}, { 447,11}, \ + { 959,13}, { 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}, { 959,11}, \ + { 1919,14}, { 255,13}, { 511,12}, { 1023,11}, \ + { 2047,12}, { 1087,11}, { 2239,12}, { 1215,11}, \ + { 2431,13}, { 639,12}, { 1471,11}, { 2943,13}, \ + { 767,12}, { 1727,13}, { 895,12}, { 1983,14}, \ + { 511,13}, { 1023,12}, { 2239,13}, { 1151,12}, \ + { 2431,13}, { 1279,12}, { 2559,13}, { 1407,12}, \ + { 2943,14}, { 767,13}, { 1663,12}, { 3455,13}, \ + { 1919,12}, { 3839,15}, { 511,14}, { 1023,13}, \ + { 2175,12}, { 4479,13}, { 2431,14}, { 1279,13}, \ + { 2943,12}, { 5887,14}, { 1535,13}, { 3455,14}, \ + { 1791,13}, { 3967,15}, { 1023,14}, { 2047,13}, \ + { 4479,14}, { 2303,13}, { 4991,12}, { 9983,14}, \ + { 2815,13}, { 5887,15}, { 1535,14}, { 3839,16} } +#define SQR_FFT_TABLE3_SIZE 176 +#define SQR_FFT_THRESHOLD 4736 + +#define MULLO_BASECASE_THRESHOLD 3 +#define MULLO_DC_THRESHOLD 54 +#define MULLO_MUL_N_THRESHOLD 10950 +#define SQRLO_BASECASE_THRESHOLD 10 +#define SQRLO_DC_THRESHOLD 77 +#define SQRLO_SQR_THRESHOLD 9449 + +#define DC_DIV_QR_THRESHOLD 84 +#define DC_DIVAPPR_Q_THRESHOLD 252 +#define DC_BDIV_QR_THRESHOLD 79 +#define DC_BDIV_Q_THRESHOLD 80 + +#define INV_MULMOD_BNM1_THRESHOLD 71 +#define INV_NEWTON_THRESHOLD 254 +#define INV_APPR_THRESHOLD 266 + +#define BINV_NEWTON_THRESHOLD 294 +#define REDC_1_TO_REDC_N_THRESHOLD 79 + +#define MU_DIV_QR_THRESHOLD 1652 +#define MU_DIVAPPR_Q_THRESHOLD 1528 +#define MUPI_DIV_QR_THRESHOLD 122 +#define MU_BDIV_QR_THRESHOLD 1387 +#define MU_BDIV_Q_THRESHOLD 1528 + +#define POWM_SEC_TABLE 1,16,96,480,960 + +#define GET_STR_DC_THRESHOLD 12 +#define GET_STR_PRECOMPUTE_THRESHOLD 19 +#define SET_STR_DC_THRESHOLD 264 +#define SET_STR_PRECOMPUTE_THRESHOLD 542 + +#define FAC_DSC_THRESHOLD 91 +#define FAC_ODD_THRESHOLD 29 + +#define MATRIX22_STRASSEN_THRESHOLD 19 +#define HGCD2_DIV1_METHOD 1 /* 9.73% faster than 3 */ +#define HGCD_THRESHOLD 55 +#define HGCD_APPR_THRESHOLD 50 +#define HGCD_REDUCE_THRESHOLD 3389 +#define GCD_DC_THRESHOLD 562 +#define GCDEXT_DC_THRESHOLD 416 +#define JACOBI_BASE_METHOD 4 /* 16.50% faster than 1 */ + +/* Tuneup completed successfully, took 49179 seconds */ -- cgit v1.2.3