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_64/bt1/gmp-mparam.h | 230 ++++++++++++++++++++++++++++++++++ 1 file changed, 230 insertions(+) create mode 100644 gmp-6.3.0/mpn/x86_64/bt1/gmp-mparam.h (limited to 'gmp-6.3.0/mpn/x86_64/bt1/gmp-mparam.h') diff --git a/gmp-6.3.0/mpn/x86_64/bt1/gmp-mparam.h b/gmp-6.3.0/mpn/x86_64/bt1/gmp-mparam.h new file mode 100644 index 0000000..977a209 --- /dev/null +++ b/gmp-6.3.0/mpn/x86_64/bt1/gmp-mparam.h @@ -0,0 +1,230 @@ +/* AMD 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 64 +#define GMP_LIMB_BYTES 8 + +/* Disable use of slow functions. FIXME: We should disable lib inclusion. */ +#undef HAVE_NATIVE_mpn_mul_2 +#undef HAVE_NATIVE_mpn_addmul_2 + +/* 1600 MHz AMD Bobcat/Zacate */ +/* FFT tuning limit = 110,472,704 */ +/* Generated by tuneup.c, 2019-10-12, 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 7 +#define MOD_1U_TO_MOD_1_1_THRESHOLD 3 +#define MOD_1_1_TO_MOD_1_2_THRESHOLD 31 +#define MOD_1_2_TO_MOD_1_4_THRESHOLD 71 +#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 14 +#define USE_PREINV_DIVREM_1 1 /* native */ +#define DIV_QR_1_NORM_THRESHOLD 1 +#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 20 + +#define DIV_1_VS_MUL_1_PERCENT 270 + +#define MUL_TOOM22_THRESHOLD 24 +#define MUL_TOOM33_THRESHOLD 66 +#define MUL_TOOM44_THRESHOLD 190 +#define MUL_TOOM6H_THRESHOLD 274 +#define MUL_TOOM8H_THRESHOLD 381 + +#define MUL_TOOM32_TO_TOOM43_THRESHOLD 129 +#define MUL_TOOM32_TO_TOOM53_THRESHOLD 138 +#define MUL_TOOM42_TO_TOOM53_THRESHOLD 127 +#define MUL_TOOM42_TO_TOOM63_THRESHOLD 131 +#define MUL_TOOM43_TO_TOOM54_THRESHOLD 100 + +#define SQR_BASECASE_THRESHOLD 0 /* always (native) */ +#define SQR_TOOM2_THRESHOLD 30 +#define SQR_TOOM3_THRESHOLD 101 +#define SQR_TOOM4_THRESHOLD 278 +#define SQR_TOOM6_THRESHOLD 372 +#define SQR_TOOM8_THRESHOLD 478 + +#define MULMID_TOOM42_THRESHOLD 22 + +#define MULMOD_BNM1_THRESHOLD 11 +#define SQRMOD_BNM1_THRESHOLD 13 + +#define MUL_FFT_MODF_THRESHOLD 444 /* k = 5 */ +#define MUL_FFT_TABLE3 \ + { { 444, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \ + { 11, 5}, { 23, 6}, { 21, 7}, { 11, 6}, \ + { 25, 7}, { 13, 6}, { 27, 7}, { 21, 8}, \ + { 11, 7}, { 25, 8}, { 13, 7}, { 28, 8}, \ + { 15, 7}, { 31, 8}, { 17, 7}, { 35, 8}, \ + { 19, 7}, { 39, 8}, { 27, 9}, { 15, 8}, \ + { 35, 9}, { 19, 8}, { 41, 9}, { 23, 8}, \ + { 49, 9}, { 27,10}, { 15, 9}, { 39,10}, \ + { 23, 9}, { 55,11}, { 15,10}, { 31, 9}, \ + { 71,10}, { 39, 9}, { 83, 5}, { 1343, 4}, \ + { 2687, 5}, { 1407, 6}, { 735, 7}, { 415, 8}, \ + { 223,10}, { 79,11}, { 47,10}, { 103,12}, \ + { 31,11}, { 63,10}, { 135,11}, { 79,10}, \ + { 167,11}, { 95,10}, { 191,11}, { 111,12}, \ + { 63,11}, { 127,10}, { 255,11}, { 143,10}, \ + { 287, 9}, { 575,11}, { 159,12}, { 95,11}, \ + { 191,10}, { 383,11}, { 207,10}, { 415,13}, \ + { 63,12}, { 127,11}, { 255,10}, { 511,11}, \ + { 271,10}, { 543,11}, { 287,10}, { 575,12}, \ + { 159,11}, { 319,10}, { 639,11}, { 351,10}, \ + { 703,12}, { 191,11}, { 383,10}, { 767,11}, \ + { 415,12}, { 223,13}, { 127,12}, { 255,11}, \ + { 543,12}, { 287,11}, { 607,12}, { 319,11}, \ + { 671,12}, { 351,11}, { 703,13}, { 191,12}, \ + { 383,11}, { 767,12}, { 415,11}, { 831,12}, \ + { 447,14}, { 127,13}, { 255,12}, { 607,13}, \ + { 319,12}, { 703,13}, { 383,12}, { 831,13}, \ + { 447,12}, { 959,14}, { 255,13}, { 511,12}, \ + { 1023,13}, { 575,12}, { 1151,13}, { 703,14}, \ + { 383,13}, { 831,12}, { 1663,13}, { 959,15}, \ + { 255,14}, { 511,13}, { 1087,12}, { 2175,13}, \ + { 1151,14}, { 639,13}, { 1343,12}, { 2687,13}, \ + { 1407,14}, { 767,13}, { 1599,12}, { 3199,13}, \ + { 1663,14}, { 895,15}, { 511,14}, { 1023,13}, \ + { 2175,14}, { 1151,13}, { 2431,12}, { 4863,14}, \ + { 1279,13}, { 2687,14}, { 1407,15}, { 767,14}, \ + { 1535,13}, { 3199,14}, { 1663,13}, { 3455,16}, \ + { 511,15}, { 1023,14}, { 2175,13}, { 4479,14}, \ + { 2431,13}, { 4863,15}, { 1279,14}, { 2943,13}, \ + { 5887,15}, { 1535,14}, { 3455,13}, { 6911,15}, \ + { 1791,14}, { 3839,16}, { 1023,15}, { 2047,14}, \ + { 4479,15}, { 2303,14}, { 4991,15}, { 2559,14}, \ + { 5247,15}, { 2815,14}, { 5887,16}, { 1535,15}, \ + { 3327,14}, { 16384,15}, { 32768,16}, { 65536,17}, \ + { 131072,18}, { 262144,19}, { 524288,20}, {1048576,21}, \ + {2097152,22}, {4194304,23}, {8388608,24} } +#define MUL_FFT_TABLE3_SIZE 183 +#define MUL_FFT_THRESHOLD 5760 + +#define SQR_FFT_MODF_THRESHOLD 380 /* k = 5 */ +#define SQR_FFT_TABLE3 \ + { { 380, 5}, { 21, 6}, { 11, 5}, { 23, 6}, \ + { 25, 7}, { 25, 8}, { 13, 7}, { 27, 8}, \ + { 15, 7}, { 31, 8}, { 17, 7}, { 35, 8}, \ + { 19, 7}, { 39, 8}, { 27, 9}, { 15, 8}, \ + { 35, 9}, { 19, 8}, { 41, 9}, { 23, 8}, \ + { 47, 9}, { 27,10}, { 15, 9}, { 31, 8}, \ + { 63, 9}, { 39,10}, { 23, 9}, { 51,11}, \ + { 15,10}, { 31, 9}, { 67,10}, { 39, 9}, \ + { 79,10}, { 47, 9}, { 95,10}, { 55,11}, \ + { 31,10}, { 63, 6}, { 1087, 7}, { 575, 8}, \ + { 303, 9}, { 159,10}, { 103,12}, { 31,11}, \ + { 63,10}, { 127, 9}, { 255,10}, { 135,11}, \ + { 79,10}, { 159, 9}, { 319,11}, { 95,10}, \ + { 191, 9}, { 383,11}, { 111,12}, { 63,11}, \ + { 127,10}, { 255, 9}, { 511,10}, { 271,11}, \ + { 143,10}, { 287, 9}, { 575,10}, { 303,11}, \ + { 159,10}, { 319,12}, { 95,11}, { 191,10}, \ + { 383,11}, { 207,13}, { 63,12}, { 127,11}, \ + { 255,10}, { 511,11}, { 271,10}, { 543,11}, \ + { 287,10}, { 575,11}, { 303,12}, { 159,11}, \ + { 319,10}, { 639,11}, { 335,10}, { 671,11}, \ + { 351,10}, { 703,12}, { 191,11}, { 383,10}, \ + { 767,11}, { 415,12}, { 223,11}, { 447,13}, \ + { 127,12}, { 255,11}, { 543,12}, { 287,11}, \ + { 607,12}, { 319,11}, { 671,12}, { 351,11}, \ + { 703,13}, { 191,12}, { 383,11}, { 767,12}, \ + { 415,11}, { 831,12}, { 479,14}, { 127,13}, \ + { 255,12}, { 607,13}, { 319,12}, { 703,13}, \ + { 383,12}, { 831,13}, { 447,12}, { 895,14}, \ + { 255,13}, { 511,12}, { 1023,13}, { 703,14}, \ + { 383,13}, { 831,12}, { 1663,13}, { 895,15}, \ + { 255,14}, { 511,13}, { 1087,12}, { 2175,13}, \ + { 1151,14}, { 639,13}, { 1343,12}, { 2687,13}, \ + { 1407,14}, { 767,13}, { 1599,12}, { 3199,13}, \ + { 1663,14}, { 895,15}, { 511,14}, { 1023,13}, \ + { 2175,14}, { 1151,13}, { 2431,12}, { 4863,14}, \ + { 1279,13}, { 2687,14}, { 1407,15}, { 767,14}, \ + { 1535,13}, { 3199,14}, { 1663,13}, { 3455,16}, \ + { 511,15}, { 1023,14}, { 2175,13}, { 4351,14}, \ + { 2431,13}, { 4863,15}, { 1279,14}, { 2943,13}, \ + { 5887,15}, { 1535,14}, { 3455,15}, { 1791,14}, \ + { 3839,16}, { 1023,15}, { 2047,14}, { 4479,15}, \ + { 2303,14}, { 4863,15}, { 2559,14}, { 5247,15}, \ + { 2815,14}, { 5887,16}, { 1535,15}, { 3327,14}, \ + { 16384,15}, { 32768,16}, { 65536,17}, { 131072,18}, \ + { 262144,19}, { 524288,20}, {1048576,21}, {2097152,22}, \ + {4194304,23}, {8388608,24} } +#define SQR_FFT_TABLE3_SIZE 186 +#define SQR_FFT_THRESHOLD 3712 + +#define MULLO_BASECASE_THRESHOLD 0 /* always */ +#define MULLO_DC_THRESHOLD 42 +#define MULLO_MUL_N_THRESHOLD 10950 +#define SQRLO_BASECASE_THRESHOLD 7 +#define SQRLO_DC_THRESHOLD 100 +#define SQRLO_SQR_THRESHOLD 7293 + +#define DC_DIV_QR_THRESHOLD 70 +#define DC_DIVAPPR_Q_THRESHOLD 204 +#define DC_BDIV_QR_THRESHOLD 59 +#define DC_BDIV_Q_THRESHOLD 148 + +#define INV_MULMOD_BNM1_THRESHOLD 46 +#define INV_NEWTON_THRESHOLD 246 +#define INV_APPR_THRESHOLD 236 + +#define BINV_NEWTON_THRESHOLD 252 +#define REDC_1_TO_REDC_2_THRESHOLD 67 +#define REDC_2_TO_REDC_N_THRESHOLD 0 /* always */ + +#define MU_DIV_QR_THRESHOLD 1589 +#define MU_DIVAPPR_Q_THRESHOLD 1589 +#define MUPI_DIV_QR_THRESHOLD 108 +#define MU_BDIV_QR_THRESHOLD 1442 +#define MU_BDIV_Q_THRESHOLD 1470 + +#define POWM_SEC_TABLE 1,16,194,960,1603,1811,2499 + +#define GET_STR_DC_THRESHOLD 20 +#define GET_STR_PRECOMPUTE_THRESHOLD 34 +#define SET_STR_DC_THRESHOLD 345 +#define SET_STR_PRECOMPUTE_THRESHOLD 1787 + +#define FAC_DSC_THRESHOLD 781 +#define FAC_ODD_THRESHOLD 104 + +#define MATRIX22_STRASSEN_THRESHOLD 17 +#define HGCD2_DIV1_METHOD 3 /* 3.20% faster than 5 */ +#define HGCD_THRESHOLD 110 +#define HGCD_APPR_THRESHOLD 50 +#define HGCD_REDUCE_THRESHOLD 2681 +#define GCD_DC_THRESHOLD 474 +#define GCDEXT_DC_THRESHOLD 293 +#define JACOBI_BASE_METHOD 2 /* 9.38% faster than 1 */ + +/* Tuneup completed successfully, took 358881 seconds */ -- cgit v1.2.3