aboutsummaryrefslogtreecommitdiff
path: root/vendor/gmp-6.3.0/mpn/x86/coreibwl
diff options
context:
space:
mode:
authorThomas Voss <mail@thomasvoss.com> 2024-06-21 23:36:36 +0200
committerThomas Voss <mail@thomasvoss.com> 2024-06-21 23:42:26 +0200
commita89a14ef5da44684a16b204e7a70460cc8c4922a (patch)
treeb23b4c6b155977909ef508fdae2f48d33d802813 /vendor/gmp-6.3.0/mpn/x86/coreibwl
parent1db63fcedab0b288820d66e100b1877b1a5a8851 (diff)
Basic constant folding implementation
Diffstat (limited to 'vendor/gmp-6.3.0/mpn/x86/coreibwl')
-rw-r--r--vendor/gmp-6.3.0/mpn/x86/coreibwl/gmp-mparam.h216
1 files changed, 216 insertions, 0 deletions
diff --git a/vendor/gmp-6.3.0/mpn/x86/coreibwl/gmp-mparam.h b/vendor/gmp-6.3.0/mpn/x86/coreibwl/gmp-mparam.h
new file mode 100644
index 0000000..7b58cad
--- /dev/null
+++ b/vendor/gmp-6.3.0/mpn/x86/coreibwl/gmp-mparam.h
@@ -0,0 +1,216 @@
+/* x86/coreibwl 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
+
+/* 3400-3800 MHz Intel Xeon E3-1285Lv4 Broadwell */
+/* FFT tuning limit = 67,000,000 */
+/* Generated by tuneup.c, 2019-10-20, gcc 8.3 */
+
+#define MOD_1_NORM_THRESHOLD 15
+#define MOD_1_UNNORM_THRESHOLD 16
+#define MOD_1N_TO_MOD_1_1_THRESHOLD 10
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 8
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 0 /* never mpn_mod_1_1p */
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD 10
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 11
+#define USE_PREINV_DIVREM_1 1 /* native */
+#define DIV_QR_1N_PI1_METHOD 1 /* 21.34% faster than 2 */
+#define DIV_QR_1_NORM_THRESHOLD 14
+#define DIV_QR_1_UNNORM_THRESHOLD MP_SIZE_T_MAX /* never */
+#define DIV_QR_2_PI2_THRESHOLD 29
+#define DIVEXACT_1_THRESHOLD 0 /* always (native) */
+#define BMOD_1_TO_MOD_1_THRESHOLD 19
+
+#define DIV_1_VS_MUL_1_PERCENT 295
+
+#define MUL_TOOM22_THRESHOLD 26
+#define MUL_TOOM33_THRESHOLD 97
+#define MUL_TOOM44_THRESHOLD 220
+#define MUL_TOOM6H_THRESHOLD 306
+#define MUL_TOOM8H_THRESHOLD 454
+
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 93
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 153
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 154
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 169
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 136
+
+#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
+#define SQR_TOOM2_THRESHOLD 44
+#define SQR_TOOM3_THRESHOLD 134
+#define SQR_TOOM4_THRESHOLD 242
+#define SQR_TOOM6_THRESHOLD 342
+#define SQR_TOOM8_THRESHOLD 502
+
+#define MULMID_TOOM42_THRESHOLD 98
+
+#define MULMOD_BNM1_THRESHOLD 20
+#define SQRMOD_BNM1_THRESHOLD 23
+
+#define MUL_FFT_MODF_THRESHOLD 540 /* k = 5 */
+#define MUL_FFT_TABLE3 \
+ { { 540, 5}, { 29, 6}, { 15, 5}, { 31, 6}, \
+ { 16, 5}, { 33, 6}, { 17, 5}, { 36, 6}, \
+ { 25, 7}, { 13, 6}, { 29, 7}, { 15, 6}, \
+ { 33, 7}, { 17, 6}, { 36, 7}, { 19, 6}, \
+ { 39, 7}, { 21, 6}, { 43, 7}, { 23, 6}, \
+ { 47, 7}, { 29, 8}, { 15, 7}, { 35, 8}, \
+ { 19, 7}, { 43, 8}, { 23, 7}, { 49, 8}, \
+ { 27, 7}, { 55, 9}, { 15, 8}, { 31, 7}, \
+ { 63, 8}, { 43, 9}, { 23, 8}, { 55,10}, \
+ { 15, 9}, { 31, 8}, { 67, 9}, { 39, 8}, \
+ { 83, 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, 9}, { 191,10}, { 111,11}, \
+ { 63,10}, { 143, 9}, { 287,10}, { 159,11}, \
+ { 95, 7}, { 1599, 8}, { 831, 9}, { 431, 8}, \
+ { 863, 9}, { 447,10}, { 239, 9}, { 479,10}, \
+ { 255, 9}, { 511,10}, { 287,11}, { 159,10}, \
+ { 319, 9}, { 639,10}, { 335, 9}, { 671,11}, \
+ { 191,10}, { 383, 9}, { 767,10}, { 399,11}, \
+ { 223,12}, { 127,11}, { 255,10}, { 511, 9}, \
+ { 1023,11}, { 287,10}, { 607,11}, { 319,10}, \
+ { 671,11}, { 351,12}, { 191,11}, { 383,10}, \
+ { 799,11}, { 415,13}, { 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}, \
+ { 959,13}, { 255,12}, { 511,11}, { 1119,12}, \
+ { 575,11}, { 1215,12}, { 639,11}, { 1343,12}, \
+ { 703,11}, { 1407,13}, { 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}, { 2239,13}, \
+ { 1151,12}, { 2431,13}, { 1279,12}, { 2623,13}, \
+ { 1407,12}, { 2815,14}, { 767,13}, { 1535,12}, \
+ { 3135,13}, { 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}, { 3839,15}, \
+ { 1023,14}, { 2047,13}, { 4479,14}, { 2303,13}, \
+ { 4991,12}, { 9983,14}, { 2559,13}, { 5247,14}, \
+ { 2815,13}, { 5887,15}, { 1535,14}, { 3839,16} }
+#define MUL_FFT_TABLE3_SIZE 172
+#define MUL_FFT_THRESHOLD 7424
+
+#define SQR_FFT_MODF_THRESHOLD 472 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 472, 5}, { 29, 6}, { 15, 5}, { 33, 6}, \
+ { 37, 7}, { 19, 6}, { 40, 7}, { 29, 8}, \
+ { 15, 7}, { 35, 8}, { 19, 7}, { 43, 8}, \
+ { 23, 7}, { 49, 8}, { 27, 9}, { 15, 8}, \
+ { 31, 7}, { 63, 8}, { 43, 9}, { 23, 8}, \
+ { 55,10}, { 15, 9}, { 31, 8}, { 67, 9}, \
+ { 39, 8}, { 83, 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}, \
+ { 127, 9}, { 255,10}, { 143, 9}, { 287,10}, \
+ { 159,11}, { 95,12}, { 63,11}, { 127,10}, \
+ { 271, 9}, { 543, 6}, { 4479, 7}, { 2431, 8}, \
+ { 1247, 7}, { 2495, 8}, { 1279,10}, { 351,11}, \
+ { 191,10}, { 399, 9}, { 799,10}, { 415,12}, \
+ { 127,11}, { 255,10}, { 543,11}, { 287,10}, \
+ { 607,11}, { 319,10}, { 639,11}, { 351,12}, \
+ { 191,11}, { 383,10}, { 799,11}, { 415,10}, \
+ { 831,13}, { 127,12}, { 255,11}, { 511,10}, \
+ { 1023,11}, { 543,10}, { 1087,11}, { 607,12}, \
+ { 319,11}, { 671,10}, { 1343,11}, { 735,12}, \
+ { 383,11}, { 799,10}, { 1599,11}, { 863,12}, \
+ { 447,11}, { 927,13}, { 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}, { 1663,12}, \
+ { 895,11}, { 1855,14}, { 255,13}, { 511,12}, \
+ { 1023,11}, { 2047,12}, { 1087,11}, { 2239,12}, \
+ { 1215,13}, { 639,12}, { 1471,13}, { 767,12}, \
+ { 1663,13}, { 895,12}, { 1983,14}, { 511,13}, \
+ { 1023,12}, { 2239,13}, { 1151,12}, { 2495,13}, \
+ { 1279,12}, { 2623,13}, { 1407,14}, { 767,13}, \
+ { 1535,12}, { 3135,13}, { 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}, \
+ { 3839,15}, { 1023,14}, { 2047,13}, { 4479,14}, \
+ { 2303,13}, { 4991,12}, { 9983,14}, { 2815,13}, \
+ { 5887,15}, { 1535,14}, { 3327,13}, { 6783,14}, \
+ { 3839,16} }
+#define SQR_FFT_TABLE3_SIZE 157
+#define SQR_FFT_THRESHOLD 5568
+
+#define MULLO_BASECASE_THRESHOLD 16
+#define MULLO_DC_THRESHOLD 37
+#define MULLO_MUL_N_THRESHOLD 14281
+#define SQRLO_BASECASE_THRESHOLD 0 /* always */
+#define SQRLO_DC_THRESHOLD 137
+#define SQRLO_SQR_THRESHOLD 10821
+
+#define DC_DIV_QR_THRESHOLD 54
+#define DC_DIVAPPR_Q_THRESHOLD 146
+#define DC_BDIV_QR_THRESHOLD 98
+#define DC_BDIV_Q_THRESHOLD 218
+
+#define INV_MULMOD_BNM1_THRESHOLD 50
+#define INV_NEWTON_THRESHOLD 173
+#define INV_APPR_THRESHOLD 165
+
+#define BINV_NEWTON_THRESHOLD 278
+#define REDC_1_TO_REDC_N_THRESHOLD 79
+
+#define MU_DIV_QR_THRESHOLD 1787
+#define MU_DIVAPPR_Q_THRESHOLD 1787
+#define MUPI_DIV_QR_THRESHOLD 78
+#define MU_BDIV_QR_THRESHOLD 1589
+#define MU_BDIV_Q_THRESHOLD 1830
+
+#define POWM_SEC_TABLE 1,16,126,416,932
+
+#define GET_STR_DC_THRESHOLD 11
+#define GET_STR_PRECOMPUTE_THRESHOLD 17
+#define SET_STR_DC_THRESHOLD 306
+#define SET_STR_PRECOMPUTE_THRESHOLD 894
+
+#define FAC_DSC_THRESHOLD 141
+#define FAC_ODD_THRESHOLD 34
+
+#define MATRIX22_STRASSEN_THRESHOLD 20
+#define HGCD2_DIV1_METHOD 3 /* 5.97% faster than 1 */
+#define HGCD_THRESHOLD 73
+#define HGCD_APPR_THRESHOLD 123
+#define HGCD_REDUCE_THRESHOLD 3664
+#define GCD_DC_THRESHOLD 562
+#define GCDEXT_DC_THRESHOLD 465
+#define JACOBI_BASE_METHOD 1 /* 31.16% faster than 3 */
+
+/* Tuneup completed successfully, took 35114 seconds */