diff options
author | Thomas Voss <mail@thomasvoss.com> | 2024-06-21 23:36:36 +0200 |
---|---|---|
committer | Thomas Voss <mail@thomasvoss.com> | 2024-06-21 23:42:26 +0200 |
commit | a89a14ef5da44684a16b204e7a70460cc8c4922a (patch) | |
tree | b23b4c6b155977909ef508fdae2f48d33d802813 /vendor/gmp-6.3.0/mpn/x86/goldmont | |
parent | 1db63fcedab0b288820d66e100b1877b1a5a8851 (diff) |
Basic constant folding implementation
Diffstat (limited to 'vendor/gmp-6.3.0/mpn/x86/goldmont')
-rw-r--r-- | vendor/gmp-6.3.0/mpn/x86/goldmont/gmp-mparam.h | 219 |
1 files changed, 219 insertions, 0 deletions
diff --git a/vendor/gmp-6.3.0/mpn/x86/goldmont/gmp-mparam.h b/vendor/gmp-6.3.0/mpn/x86/goldmont/gmp-mparam.h new file mode 100644 index 0000000..3d37fa3 --- /dev/null +++ b/vendor/gmp-6.3.0/mpn/x86/goldmont/gmp-mparam.h @@ -0,0 +1,219 @@ +/* Intel Goldmont/32 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 + +/* 2200 MHz Intel Atom C3758 Goldmont/Denverton */ +/* FFT tuning limit = 67,000,000 */ +/* Generated by tuneup.c, 2019-10-22, gcc 8.3 */ + +#define MOD_1_NORM_THRESHOLD 7 +#define MOD_1_UNNORM_THRESHOLD 12 +#define MOD_1N_TO_MOD_1_1_THRESHOLD 9 +#define MOD_1U_TO_MOD_1_1_THRESHOLD 7 +#define MOD_1_1_TO_MOD_1_2_THRESHOLD 10 +#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 /* 32.79% faster than 2 */ +#define DIV_QR_1_NORM_THRESHOLD 32 +#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 23 + +#define DIV_1_VS_MUL_1_PERCENT 228 + +#define MUL_TOOM22_THRESHOLD 18 +#define MUL_TOOM33_THRESHOLD 81 +#define MUL_TOOM44_THRESHOLD 193 +#define MUL_TOOM6H_THRESHOLD 286 +#define MUL_TOOM8H_THRESHOLD 399 + +#define MUL_TOOM32_TO_TOOM43_THRESHOLD 81 +#define MUL_TOOM32_TO_TOOM53_THRESHOLD 138 +#define MUL_TOOM42_TO_TOOM53_THRESHOLD 125 +#define MUL_TOOM42_TO_TOOM63_THRESHOLD 137 +#define MUL_TOOM43_TO_TOOM54_THRESHOLD 185 + +#define SQR_BASECASE_THRESHOLD 0 /* always (native) */ +#define SQR_TOOM2_THRESHOLD 32 +#define SQR_TOOM3_THRESHOLD 113 +#define SQR_TOOM4_THRESHOLD 280 +#define SQR_TOOM6_THRESHOLD 399 +#define SQR_TOOM8_THRESHOLD 547 + +#define MULMID_TOOM42_THRESHOLD 60 + +#define MULMOD_BNM1_THRESHOLD 13 +#define SQRMOD_BNM1_THRESHOLD 15 + +#define MUL_FFT_MODF_THRESHOLD 368 /* k = 5 */ +#define MUL_FFT_TABLE3 \ + { { 368, 5}, { 21, 6}, { 11, 5}, { 23, 6}, \ + { 21, 7}, { 11, 6}, { 25, 7}, { 13, 6}, \ + { 27, 7}, { 15, 6}, { 31, 7}, { 21, 8}, \ + { 11, 7}, { 27, 8}, { 15, 7}, { 33, 8}, \ + { 19, 7}, { 39, 8}, { 23, 7}, { 47, 8}, \ + { 27, 9}, { 15, 8}, { 39, 9}, { 23, 8}, \ + { 47,10}, { 15, 9}, { 31, 8}, { 63, 9}, \ + { 39, 8}, { 79, 9}, { 47,10}, { 31, 9}, \ + { 79,10}, { 47, 9}, { 95,11}, { 31,10}, \ + { 63, 9}, { 127, 8}, { 255, 9}, { 135,10}, \ + { 79, 9}, { 159,10}, { 95, 9}, { 191,11}, \ + { 63,10}, { 127, 9}, { 255, 8}, { 511,10}, \ + { 143, 9}, { 287, 8}, { 575, 9}, { 303,10}, \ + { 159,11}, { 95,10}, { 191,12}, { 63,11}, \ + { 127,10}, { 255, 9}, { 511,10}, { 271, 9}, \ + { 543,10}, { 287, 9}, { 575,10}, { 303, 9}, \ + { 607,11}, { 159,10}, { 319, 9}, { 639,10}, \ + { 351, 9}, { 703,11}, { 191,10}, { 383, 9}, \ + { 767,10}, { 415, 9}, { 831,11}, { 223,10}, \ + { 447,12}, { 127,11}, { 255,10}, { 543, 9}, \ + { 1087,11}, { 287,10}, { 607, 9}, { 1215,11}, \ + { 319,10}, { 671,11}, { 351,10}, { 703,12}, \ + { 191,11}, { 383,10}, { 767,11}, { 415,10}, \ + { 831,11}, { 447,13}, { 127,12}, { 255,11}, \ + { 543,10}, { 1087,11}, { 607,10}, { 1215,12}, \ + { 319,11}, { 671,10}, { 1343,11}, { 703,10}, \ + { 1407,11}, { 735,12}, { 383,11}, { 831,12}, \ + { 447,11}, { 959,13}, { 255,12}, { 511,11}, \ + { 1087,12}, { 575,11}, { 1215,10}, { 2431,12}, \ + { 639,11}, { 1343,12}, { 703,11}, { 1407,13}, \ + { 383,12}, { 831,11}, { 1663,12}, { 959,11}, \ + { 1919,14}, { 255,13}, { 511,12}, { 1215,11}, \ + { 2431,13}, { 639,12}, { 1471,11}, { 2943,13}, \ + { 767,12}, { 1727,13}, { 895,12}, { 1919,11}, \ + { 3839,14}, { 511,13}, { 1023,12}, { 2111,13}, \ + { 1151,12}, { 2431,13}, { 1407,12}, { 2943,14}, \ + { 767,13}, { 1663,12}, { 3455,13}, { 1919,12}, \ + { 3839,15}, { 511,14}, { 1023,13}, { 2431,14}, \ + { 1279,13}, { 2943,12}, { 5887,14}, { 1535,13}, \ + { 3455,14}, { 1791,13}, { 3839,12}, { 7679,15}, \ + { 1023,14}, { 2303,13}, { 4991,12}, { 9983,14}, \ + { 2559,13}, { 5119,14}, { 2815,13}, { 5887,15}, \ + { 1535,14}, { 3839,13}, { 7679,16} } +#define MUL_FFT_TABLE3_SIZE 171 +#define MUL_FFT_THRESHOLD 3712 + +#define SQR_FFT_MODF_THRESHOLD 340 /* k = 5 */ +#define SQR_FFT_TABLE3 \ + { { 340, 5}, { 21, 6}, { 11, 5}, { 23, 6}, \ + { 12, 5}, { 25, 6}, { 21, 7}, { 11, 6}, \ + { 25, 7}, { 13, 6}, { 27, 7}, { 15, 6}, \ + { 31, 7}, { 21, 8}, { 11, 7}, { 27, 8}, \ + { 15, 7}, { 33, 8}, { 19, 7}, { 39, 8}, \ + { 23, 7}, { 47, 8}, { 27, 9}, { 15, 8}, \ + { 39, 9}, { 23, 8}, { 47,10}, { 15, 9}, \ + { 31, 8}, { 67, 9}, { 39, 8}, { 79, 9}, \ + { 47,10}, { 31, 9}, { 79,10}, { 47,11}, \ + { 31,10}, { 63, 9}, { 127, 8}, { 255,10}, \ + { 79, 9}, { 159, 8}, { 319,10}, { 95, 9}, \ + { 191,11}, { 63,10}, { 127, 9}, { 255, 8}, \ + { 511, 9}, { 271,10}, { 143, 9}, { 287, 8}, \ + { 575, 9}, { 303, 8}, { 607, 9}, { 319,11}, \ + { 95,10}, { 191,12}, { 63,11}, { 127,10}, \ + { 255, 9}, { 511,10}, { 271, 9}, { 543,10}, \ + { 287, 9}, { 575,10}, { 303, 9}, { 607,11}, \ + { 159,10}, { 319, 9}, { 639,10}, { 335, 9}, \ + { 671,10}, { 351, 9}, { 703,11}, { 191,10}, \ + { 383, 9}, { 767,10}, { 415, 9}, { 831,11}, \ + { 223,10}, { 479,12}, { 127,11}, { 255,10}, \ + { 543, 9}, { 1087,11}, { 287,10}, { 607, 9}, \ + { 1215,11}, { 319,10}, { 671,11}, { 351,10}, \ + { 703,12}, { 191,11}, { 383,10}, { 767,11}, \ + { 415,10}, { 831,11}, { 479,13}, { 127,12}, \ + { 255,11}, { 543,10}, { 1087,11}, { 607,10}, \ + { 1215,12}, { 319,11}, { 671,10}, { 1343,11}, \ + { 735,12}, { 383,11}, { 831,12}, { 447,11}, \ + { 959,13}, { 255,12}, { 511,11}, { 1087,12}, \ + { 575,11}, { 1215,12}, { 639,11}, { 1343,12}, \ + { 703,11}, { 1471,13}, { 383,12}, { 831,11}, \ + { 1663,12}, { 959,11}, { 1919,14}, { 255,13}, \ + { 511,12}, { 1215,13}, { 639,12}, { 1471,11}, \ + { 2943,13}, { 767,12}, { 1727,13}, { 895,12}, \ + { 1919,14}, { 511,13}, { 1023,12}, { 2111,13}, \ + { 1151,12}, { 2431,13}, { 1407,12}, { 2943,14}, \ + { 767,13}, { 1663,12}, { 3455,13}, { 1919,15}, \ + { 511,14}, { 1023,13}, { 2431,14}, { 1279,13}, \ + { 2943,12}, { 5887,14}, { 1535,13}, { 3455,14}, \ + { 1791,13}, { 3839,12}, { 7679,15}, { 1023,14}, \ + { 2047,13}, { 4095,14}, { 2303,13}, { 4991,12}, \ + { 9983,14}, { 2815,13}, { 5887,15}, { 1535,14}, \ + { 3839,13}, { 7679,16} } +#define SQR_FFT_TABLE3_SIZE 170 +#define SQR_FFT_THRESHOLD 3520 + +#define MULLO_BASECASE_THRESHOLD 5 +#define MULLO_DC_THRESHOLD 50 +#define MULLO_MUL_N_THRESHOLD 6633 +#define SQRLO_BASECASE_THRESHOLD 0 /* always */ +#define SQRLO_DC_THRESHOLD 95 +#define SQRLO_SQR_THRESHOLD 6633 + +#define DC_DIV_QR_THRESHOLD 68 +#define DC_DIVAPPR_Q_THRESHOLD 204 +#define DC_BDIV_QR_THRESHOLD 64 +#define DC_BDIV_Q_THRESHOLD 108 + +#define INV_MULMOD_BNM1_THRESHOLD 34 +#define INV_NEWTON_THRESHOLD 276 +#define INV_APPR_THRESHOLD 226 + +#define BINV_NEWTON_THRESHOLD 298 +#define REDC_1_TO_REDC_N_THRESHOLD 65 + +#define MU_DIV_QR_THRESHOLD 1528 +#define MU_DIVAPPR_Q_THRESHOLD 1589 +#define MUPI_DIV_QR_THRESHOLD 140 +#define MU_BDIV_QR_THRESHOLD 1334 +#define MU_BDIV_Q_THRESHOLD 1499 + +#define POWM_SEC_TABLE 3,16,96,428,1317 + +#define GET_STR_DC_THRESHOLD 13 +#define GET_STR_PRECOMPUTE_THRESHOLD 18 +#define SET_STR_DC_THRESHOLD 704 +#define SET_STR_PRECOMPUTE_THRESHOLD 1358 + +#define FAC_DSC_THRESHOLD 95 +#define FAC_ODD_THRESHOLD 29 + +#define MATRIX22_STRASSEN_THRESHOLD 15 +#define HGCD2_DIV1_METHOD 1 /* 5.53% faster than 3 */ +#define HGCD_THRESHOLD 172 +#define HGCD_APPR_THRESHOLD 204 +#define HGCD_REDUCE_THRESHOLD 2479 +#define GCD_DC_THRESHOLD 610 +#define GCDEXT_DC_THRESHOLD 443 +#define JACOBI_BASE_METHOD 4 /* 6.53% faster than 3 */ + +/* Tuneup completed successfully, took 101563 seconds */ |