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/pentium4/sse2/gmp-mparam.h | 213 +++++++++++++++++++++++++++ 1 file changed, 213 insertions(+) create mode 100644 gmp-6.3.0/mpn/x86/pentium4/sse2/gmp-mparam.h (limited to 'gmp-6.3.0/mpn/x86/pentium4/sse2/gmp-mparam.h') diff --git a/gmp-6.3.0/mpn/x86/pentium4/sse2/gmp-mparam.h b/gmp-6.3.0/mpn/x86/pentium4/sse2/gmp-mparam.h new file mode 100644 index 0000000..a047a51 --- /dev/null +++ b/gmp-6.3.0/mpn/x86/pentium4/sse2/gmp-mparam.h @@ -0,0 +1,213 @@ +/* Intel Pentium-4 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 + +/* 2600 MHz P4 Northwood */ +/* FFT tuning limit = 23,700,309 */ +/* Generated by tuneup.c, 2019-11-09, gcc 8.2 */ + +#define MOD_1_NORM_THRESHOLD 5 +#define MOD_1_UNNORM_THRESHOLD 14 +#define MOD_1N_TO_MOD_1_1_THRESHOLD 7 +#define MOD_1U_TO_MOD_1_1_THRESHOLD 5 +#define MOD_1_1_TO_MOD_1_2_THRESHOLD 13 +#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */ +#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 7 +#define USE_PREINV_DIVREM_1 1 /* native */ +#define DIV_QR_1N_PI1_METHOD 2 /* 4.36% faster than 1 */ +#define DIV_QR_1_NORM_THRESHOLD 16 +#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 21 + +#define DIV_1_VS_MUL_1_PERCENT 358 + +#define MUL_TOOM22_THRESHOLD 26 +#define MUL_TOOM33_THRESHOLD 101 +#define MUL_TOOM44_THRESHOLD 284 +#define MUL_TOOM6H_THRESHOLD 406 +#define MUL_TOOM8H_THRESHOLD 592 + +#define MUL_TOOM32_TO_TOOM43_THRESHOLD 101 +#define MUL_TOOM32_TO_TOOM53_THRESHOLD 191 +#define MUL_TOOM42_TO_TOOM53_THRESHOLD 189 +#define MUL_TOOM42_TO_TOOM63_THRESHOLD 195 +#define MUL_TOOM43_TO_TOOM54_THRESHOLD 151 + +#define SQR_BASECASE_THRESHOLD 0 /* always (native) */ +#define SQR_TOOM2_THRESHOLD 51 +#define SQR_TOOM3_THRESHOLD 163 +#define SQR_TOOM4_THRESHOLD 254 +#define SQR_TOOM6_THRESHOLD 614 +#define SQR_TOOM8_THRESHOLD 842 + +#define MULMID_TOOM42_THRESHOLD 58 + +#define MULMOD_BNM1_THRESHOLD 19 +#define SQRMOD_BNM1_THRESHOLD 23 + +#define MUL_FFT_MODF_THRESHOLD 824 /* k = 5 */ +#define MUL_FFT_TABLE3 \ + { { 824, 5}, { 29, 6}, { 15, 5}, { 33, 6}, \ + { 17, 5}, { 36, 6}, { 19, 5}, { 39, 6}, \ + { 29, 7}, { 15, 6}, { 32, 7}, { 17, 6}, \ + { 36, 7}, { 19, 6}, { 39, 7}, { 21, 6}, \ + { 43, 7}, { 23, 6}, { 48, 7}, { 29, 8}, \ + { 15, 7}, { 37, 8}, { 19, 7}, { 43, 8}, \ + { 23, 7}, { 49, 8}, { 27, 7}, { 55, 8}, \ + { 31, 7}, { 63, 8}, { 43, 9}, { 23, 8}, \ + { 55, 9}, { 31, 8}, { 67, 9}, { 39, 8}, \ + { 79, 9}, { 47, 8}, { 99, 9}, { 55,10}, \ + { 31, 9}, { 79,10}, { 47, 9}, { 103,11}, \ + { 31,10}, { 63, 9}, { 143,10}, { 79, 9}, \ + { 167,10}, { 95, 9}, { 191,10}, { 111,11}, \ + { 63,10}, { 127, 9}, { 255,10}, { 159,11}, \ + { 95,10}, { 191,12}, { 63,11}, { 127,10}, \ + { 271,11}, { 159,10}, { 319, 9}, { 639,10}, \ + { 335,11}, { 191,10}, { 383, 9}, { 799,10}, \ + { 415,11}, { 223,12}, { 127,11}, { 255,10}, \ + { 527,11}, { 287,10}, { 607, 9}, { 1215,11}, \ + { 319,10}, { 671,12}, { 191,11}, { 383,10}, \ + { 799,11}, { 415,10}, { 863,13}, { 127,12}, \ + { 255,11}, { 543,10}, { 1119, 9}, { 2239,11}, \ + { 607,10}, { 1215,12}, { 319,11}, { 671,10}, \ + { 1343,11}, { 735,10}, { 1471, 9}, { 2943,12}, \ + { 383,11}, { 799,10}, { 1599,11}, { 863,12}, \ + { 447,11}, { 927,10}, { 1855,11}, { 959,13}, \ + { 255,12}, { 511,11}, { 1119,12}, { 575,11}, \ + { 1215,10}, { 2431,11}, { 1247,12}, { 639,11}, \ + { 1343,12}, { 703,11}, { 1471,10}, { 2943,13}, \ + { 383,12}, { 767,11}, { 1599,12}, { 831,11}, \ + { 1727,10}, { 3455,12}, { 895,14}, { 255,13}, \ + { 511,12}, { 1087,11}, { 2239,10}, { 4479,12}, \ + { 1215,11}, { 2431,13}, { 639,12}, { 1343,11}, \ + { 2687,12}, { 1471,11}, { 2943,13}, { 767,12}, \ + { 1727,11}, { 3455,13}, { 895,12}, { 1983,14}, \ + { 511,13}, { 1023,12}, { 2239,13}, { 1151,12}, \ + { 2495,11}, { 4991,13}, { 1407,12}, { 2943,14}, \ + { 767,13}, { 1535,12}, { 3135,13}, { 1663,12}, \ + { 3455,13}, { 1919,12}, { 3967,15}, { 511,14}, \ + { 1023,13}, { 2175,12}, { 4479,13}, { 2431,12}, \ + { 4991,14}, { 1279,13}, { 2687,12}, { 5503,13}, \ + { 8192,14}, { 16384,15}, { 32768,16} } +#define MUL_FFT_TABLE3_SIZE 167 +#define MUL_FFT_THRESHOLD 7808 + +#define SQR_FFT_MODF_THRESHOLD 560 /* k = 5 */ +#define SQR_FFT_TABLE3 \ + { { 560, 5}, { 33, 6}, { 17, 5}, { 35, 6}, \ + { 33, 7}, { 17, 6}, { 36, 7}, { 19, 6}, \ + { 39, 7}, { 35, 8}, { 19, 7}, { 43, 8}, \ + { 23, 7}, { 47, 8}, { 27, 7}, { 55, 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}, { 111,11}, { 63,10}, { 143, 9}, \ + { 287,10}, { 159,11}, { 95,10}, { 191,12}, \ + { 63,11}, { 127, 9}, { 511, 8}, { 1023, 9}, \ + { 527,11}, { 159,10}, { 319, 9}, { 639,10}, \ + { 351,11}, { 191,10}, { 431,11}, { 223,12}, \ + { 127,11}, { 255,10}, { 543,11}, { 287,10}, \ + { 607, 9}, { 1215,11}, { 319,10}, { 639,11}, \ + { 351,12}, { 191,11}, { 383,10}, { 767,11}, \ + { 415,10}, { 831,13}, { 127,12}, { 255,11}, \ + { 543,10}, { 1119,11}, { 607,12}, { 319,11}, \ + { 671,10}, { 1343,11}, { 735,12}, { 383,11}, \ + { 799,10}, { 1599,11}, { 863,12}, { 447,11}, \ + { 927,10}, { 1855,11}, { 991,13}, { 255,12}, \ + { 511,11}, { 1055,10}, { 2111,11}, { 1087,12}, \ + { 575,11}, { 1215,10}, { 2431,12}, { 639,11}, \ + { 1343,12}, { 703,11}, { 1407,13}, { 383,12}, \ + { 767,11}, { 1599,12}, { 831,11}, { 1727,10}, \ + { 3455,12}, { 895,11}, { 1855,12}, { 959,14}, \ + { 255,13}, { 511,12}, { 1087,11}, { 2239,12}, \ + { 1215,11}, { 2431,13}, { 639,12}, { 1471,11}, \ + { 2943,13}, { 767,12}, { 1727,11}, { 3455,13}, \ + { 895,12}, { 1983,14}, { 511,13}, { 1023,12}, \ + { 2239,13}, { 1151,12}, { 2495,11}, { 4991,13}, \ + { 1279,12}, { 2623,13}, { 1407,12}, { 2943,14}, \ + { 767,13}, { 1663,12}, { 3455,13}, { 1919,12}, \ + { 3839,15}, { 511,14}, { 1023,13}, { 2175,12}, \ + { 4479,13}, { 2431,12}, { 4991,14}, { 1279,13}, \ + { 2687,12}, { 5503,13}, { 8192,14}, { 16384,15}, \ + { 32768,16} } +#define SQR_FFT_TABLE3_SIZE 149 +#define SQR_FFT_THRESHOLD 4800 + +#define MULLO_BASECASE_THRESHOLD 12 +#define MULLO_DC_THRESHOLD 44 +#define MULLO_MUL_N_THRESHOLD 14281 +#define SQRLO_BASECASE_THRESHOLD 13 +#define SQRLO_DC_THRESHOLD 42 +#define SQRLO_SQR_THRESHOLD 9449 + +#define DC_DIV_QR_THRESHOLD 38 +#define DC_DIVAPPR_Q_THRESHOLD 105 +#define DC_BDIV_QR_THRESHOLD 52 +#define DC_BDIV_Q_THRESHOLD 83 + +#define INV_MULMOD_BNM1_THRESHOLD 50 +#define INV_NEWTON_THRESHOLD 158 +#define INV_APPR_THRESHOLD 118 + +#define BINV_NEWTON_THRESHOLD 342 +#define REDC_1_TO_REDC_N_THRESHOLD 67 + +#define MU_DIV_QR_THRESHOLD 2130 +#define MU_DIVAPPR_Q_THRESHOLD 1895 +#define MUPI_DIV_QR_THRESHOLD 60 +#define MU_BDIV_QR_THRESHOLD 1652 +#define MU_BDIV_Q_THRESHOLD 2089 + +#define POWM_SEC_TABLE 1,22,96,446,723,1378 + +#define GET_STR_DC_THRESHOLD 13 +#define GET_STR_PRECOMPUTE_THRESHOLD 20 +#define SET_STR_DC_THRESHOLD 298 +#define SET_STR_PRECOMPUTE_THRESHOLD 960 + +#define FAC_DSC_THRESHOLD 212 +#define FAC_ODD_THRESHOLD 71 + +#define MATRIX22_STRASSEN_THRESHOLD 26 +#define HGCD2_DIV1_METHOD 3 /* 0.68% faster than 1 */ +#define HGCD_THRESHOLD 80 +#define HGCD_APPR_THRESHOLD 138 +#define HGCD_REDUCE_THRESHOLD 4455 +#define GCD_DC_THRESHOLD 365 +#define GCDEXT_DC_THRESHOLD 245 +#define JACOBI_BASE_METHOD 4 /* 23.41% faster than 1 */ + +/* Tuneup completed successfully, took 63807 seconds */ -- cgit v1.2.3