From 11da511c784eca003deb90c23570f0873954e0de Mon Sep 17 00:00:00 2001 From: Duncan Wilkie Date: Sat, 18 Nov 2023 06:11:09 -0600 Subject: Initial commit. --- gmp-6.3.0/mpn/x86/bt2/gmp-mparam.h | 214 +++++++++++++++++++++++++++++++++++++ 1 file changed, 214 insertions(+) create mode 100644 gmp-6.3.0/mpn/x86/bt2/gmp-mparam.h (limited to 'gmp-6.3.0/mpn/x86/bt2/gmp-mparam.h') diff --git a/gmp-6.3.0/mpn/x86/bt2/gmp-mparam.h b/gmp-6.3.0/mpn/x86/bt2/gmp-mparam.h new file mode 100644 index 0000000..f936cb7 --- /dev/null +++ b/gmp-6.3.0/mpn/x86/bt2/gmp-mparam.h @@ -0,0 +1,214 @@ +/* x86/bobcat 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 + +/* NOTE: In a fat binary build SQR_TOOM2_THRESHOLD here cannot be greater than + the value in mpn/x86/k7/gmp-mparam.h. The latter is used as a hard limit in + k7/sqr_basecase.asm. */ + +/* 2050 MHz AMD Jaguar/Kabini */ +/* FFT tuning limit = 67,000,000 */ +/* Generated by tuneup.c, 2019-10-24, gcc 8.3 */ + +#define MOD_1_NORM_THRESHOLD 4 +#define MOD_1_UNNORM_THRESHOLD 6 +#define MOD_1N_TO_MOD_1_1_THRESHOLD 4 +#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 9 +#define USE_PREINV_DIVREM_1 1 /* native */ +#define DIV_QR_1N_PI1_METHOD 1 /* 47.53% faster than 2 */ +#define DIV_QR_1_NORM_THRESHOLD MP_SIZE_T_MAX /* never */ +#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 27 + +#define DIV_1_VS_MUL_1_PERCENT 243 + +#define MUL_TOOM22_THRESHOLD 32 +#define MUL_TOOM33_THRESHOLD 90 +#define MUL_TOOM44_THRESHOLD 154 +#define MUL_TOOM6H_THRESHOLD 286 +#define MUL_TOOM8H_THRESHOLD 478 + +#define MUL_TOOM32_TO_TOOM43_THRESHOLD 97 +#define MUL_TOOM32_TO_TOOM53_THRESHOLD 152 +#define MUL_TOOM42_TO_TOOM53_THRESHOLD 103 +#define MUL_TOOM42_TO_TOOM63_THRESHOLD 113 +#define MUL_TOOM43_TO_TOOM54_THRESHOLD 154 + +#define SQR_BASECASE_THRESHOLD 0 /* always (native) */ +#define SQR_TOOM2_THRESHOLD 38 +#define SQR_TOOM3_THRESHOLD 126 +#define SQR_TOOM4_THRESHOLD 220 +#define SQR_TOOM6_THRESHOLD 318 +#define SQR_TOOM8_THRESHOLD 502 + +#define MULMID_TOOM42_THRESHOLD 68 + +#define MULMOD_BNM1_THRESHOLD 19 +#define SQRMOD_BNM1_THRESHOLD 25 + +#define MUL_FFT_MODF_THRESHOLD 570 /* k = 5 */ +#define MUL_FFT_TABLE3 \ + { { 570, 5}, { 25, 6}, { 13, 5}, { 27, 6}, \ + { 15, 5}, { 31, 6}, { 28, 7}, { 15, 6}, \ + { 33, 7}, { 17, 6}, { 35, 7}, { 19, 6}, \ + { 39, 7}, { 23, 6}, { 47, 7}, { 27, 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}, { 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}, { 159,11}, { 95,10}, { 191,12}, \ + { 63,11}, { 127,10}, { 255, 9}, { 511,10}, \ + { 271, 9}, { 543,10}, { 287,11}, { 159,10}, \ + { 319, 9}, { 639,10}, { 335, 9}, { 671,11}, \ + { 191,10}, { 383, 9}, { 767,10}, { 399, 9}, \ + { 799,10}, { 415,11}, { 223,12}, { 127,11}, \ + { 255,10}, { 543,11}, { 287,10}, { 607, 9}, \ + { 1215,11}, { 319,10}, { 671,11}, { 351,12}, \ + { 191,11}, { 383,10}, { 799,11}, { 415,13}, \ + { 127,12}, { 255,11}, { 543,10}, { 1087,11}, \ + { 607,10}, { 1215,12}, { 319,11}, { 671,10}, \ + { 1343,11}, { 735,10}, { 1471,12}, { 383,11}, \ + { 799,10}, { 1599,11}, { 863,12}, { 447,11}, \ + { 991,13}, { 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}, { 959,14}, \ + { 255,13}, { 511,12}, { 1215,13}, { 639,12}, \ + { 1471,13}, { 767,12}, { 1727,13}, { 895,12}, \ + { 1919,14}, { 511,13}, { 1023,12}, { 2111,13}, \ + { 1151,12}, { 2431,13}, { 1407,14}, { 767,13}, \ + { 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}, { 3967,15}, { 1023,14}, \ + { 2047,13}, { 4479,14}, { 2303,13}, { 4991,12}, \ + { 9983,14}, { 2815,13}, { 5887,15}, { 1535,14}, \ + { 3839,16} } +#define MUL_FFT_TABLE3_SIZE 153 +#define MUL_FFT_THRESHOLD 5760 + +#define SQR_FFT_MODF_THRESHOLD 530 /* k = 5 */ +#define SQR_FFT_TABLE3 \ + { { 530, 5}, { 27, 6}, { 15, 5}, { 31, 6}, \ + { 28, 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}, \ + { 79, 9}, { 47, 8}, { 95, 9}, { 55,10}, \ + { 31, 9}, { 79,10}, { 47, 9}, { 95,11}, \ + { 31,10}, { 63, 9}, { 135,10}, { 95,11}, \ + { 63,10}, { 143, 9}, { 287,10}, { 159,11}, \ + { 95,12}, { 63,11}, { 127,10}, { 255, 9}, \ + { 511,10}, { 271, 9}, { 543,10}, { 287,11}, \ + { 159,10}, { 319, 9}, { 639,10}, { 335, 9}, \ + { 671,10}, { 351,11}, { 191,10}, { 383, 9}, \ + { 767,10}, { 399, 9}, { 799,12}, { 127,11}, \ + { 255,10}, { 543,11}, { 287,10}, { 607, 9}, \ + { 1215,11}, { 319,10}, { 671,11}, { 351,12}, \ + { 191,11}, { 383,10}, { 799,11}, { 415,10}, \ + { 831,13}, { 127,12}, { 255,11}, { 543,10}, \ + { 1087,11}, { 607,10}, { 1215,12}, { 319,11}, \ + { 671,10}, { 1343,11}, { 735,10}, { 1471,12}, \ + { 383,11}, { 799,10}, { 1599,11}, { 863,12}, \ + { 447,11}, { 991,13}, { 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}, \ + { 1215,13}, { 639,12}, { 1471,13}, { 767,12}, \ + { 1727,13}, { 895,12}, { 1919,14}, { 511,13}, \ + { 1023,12}, { 2111,13}, { 1151,12}, { 2495,13}, \ + { 1407,14}, { 767,13}, { 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}, \ + { 3967,15}, { 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 151 +#define SQR_FFT_THRESHOLD 4736 + +#define MULLO_BASECASE_THRESHOLD 8 +#define MULLO_DC_THRESHOLD 44 +#define MULLO_MUL_N_THRESHOLD 11278 +#define SQRLO_BASECASE_THRESHOLD 13 +#define SQRLO_DC_THRESHOLD 62 +#define SQRLO_SQR_THRESHOLD 8907 + +#define DC_DIV_QR_THRESHOLD 79 +#define DC_DIVAPPR_Q_THRESHOLD 228 +#define DC_BDIV_QR_THRESHOLD 75 +#define DC_BDIV_Q_THRESHOLD 136 + +#define INV_MULMOD_BNM1_THRESHOLD 90 +#define INV_NEWTON_THRESHOLD 260 +#define INV_APPR_THRESHOLD 236 + +#define BINV_NEWTON_THRESHOLD 294 +#define REDC_1_TO_REDC_N_THRESHOLD 80 + +#define MU_DIV_QR_THRESHOLD 1787 +#define MU_DIVAPPR_Q_THRESHOLD 1718 +#define MUPI_DIV_QR_THRESHOLD 118 +#define MU_BDIV_QR_THRESHOLD 1442 +#define MU_BDIV_Q_THRESHOLD 1652 + +#define POWM_SEC_TABLE 1,16,96,615,865,1442 + +#define GET_STR_DC_THRESHOLD 16 +#define GET_STR_PRECOMPUTE_THRESHOLD 27 +#define SET_STR_DC_THRESHOLD 252 +#define SET_STR_PRECOMPUTE_THRESHOLD 638 + +#define FAC_DSC_THRESHOLD 141 +#define FAC_ODD_THRESHOLD 39 + +#define MATRIX22_STRASSEN_THRESHOLD 19 +#define HGCD2_DIV1_METHOD 1 /* 13.65% faster than 3 */ +#define HGCD_THRESHOLD 81 +#define HGCD_APPR_THRESHOLD 66 +#define HGCD_REDUCE_THRESHOLD 3389 +#define GCD_DC_THRESHOLD 531 +#define GCDEXT_DC_THRESHOLD 345 +#define JACOBI_BASE_METHOD 1 /* 0.84% faster than 4 */ + +/* Tuneup completed successfully, took 103818 seconds */ -- cgit v1.2.3