diff options
author | Torbjorn Granlund <tg@gmplib.org> | 2019-10-02 21:06:48 +0200 |
---|---|---|
committer | Torbjorn Granlund <tg@gmplib.org> | 2019-10-02 21:06:48 +0200 |
commit | a52b2338c910ffe6027b7ecbe953ff60bcdcc56a (patch) | |
tree | bac4b207d8a9bf3de69c16bbce76b3c47e8eb993 /mpn/sparc64 | |
parent | 3469ff8feea233875097a5de0b2a342347b08066 (diff) | |
download | gmp-a52b2338c910ffe6027b7ecbe953ff60bcdcc56a.tar.gz |
New tuneup files.
Diffstat (limited to 'mpn/sparc64')
-rw-r--r-- | mpn/sparc64/ultrasparct45/gmp-mparam.h | 173 |
1 files changed, 173 insertions, 0 deletions
diff --git a/mpn/sparc64/ultrasparct45/gmp-mparam.h b/mpn/sparc64/ultrasparct45/gmp-mparam.h new file mode 100644 index 000000000..2fecdba32 --- /dev/null +++ b/mpn/sparc64/ultrasparct45/gmp-mparam.h @@ -0,0 +1,173 @@ +/* Sparc64 T4-T5 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 + +/* 3600 MHz ultrasparct5 running GNU/Linux */ +/* FFT tuning limit = 0.5 M */ +/* Generated by tuneup.c, 2019-10-01, gcc 7.4 */ + +#define DIVREM_1_NORM_THRESHOLD 3 +#define DIVREM_1_UNNORM_THRESHOLD 3 +#define MOD_1_1P_METHOD 2 /* 0.34% faster than 1 */ +#define MOD_1_NORM_THRESHOLD 0 /* always */ +#define MOD_1_UNNORM_THRESHOLD 3 +#define MOD_1N_TO_MOD_1_1_THRESHOLD 6 +#define MOD_1U_TO_MOD_1_1_THRESHOLD 6 +#define MOD_1_1_TO_MOD_1_2_THRESHOLD 8 +#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */ +#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 13 +#define USE_PREINV_DIVREM_1 1 +#define DIV_QR_1N_PI1_METHOD 2 /* 27.84% faster than 1 */ +#define DIV_QR_1_NORM_THRESHOLD 3 +#define DIV_QR_1_UNNORM_THRESHOLD 2 +#define DIV_QR_2_PI2_THRESHOLD 5 +#define DIVEXACT_1_THRESHOLD 0 /* always (native) */ +#define BMOD_1_TO_MOD_1_THRESHOLD 19 + +#define DIV_1_VS_MUL_1_PERCENT 654 + +#define MUL_TOOM22_THRESHOLD 40 +#define MUL_TOOM33_THRESHOLD 129 +#define MUL_TOOM44_THRESHOLD 372 +#define MUL_TOOM6H_THRESHOLD 494 +#define MUL_TOOM8H_THRESHOLD 656 + +#define MUL_TOOM32_TO_TOOM43_THRESHOLD 126 +#define MUL_TOOM32_TO_TOOM53_THRESHOLD 247 +#define MUL_TOOM42_TO_TOOM53_THRESHOLD 225 +#define MUL_TOOM42_TO_TOOM63_THRESHOLD 219 +#define MUL_TOOM43_TO_TOOM54_THRESHOLD 188 + +#define SQR_BASECASE_THRESHOLD 20 +#define SQR_TOOM2_THRESHOLD 59 +#define SQR_TOOM3_THRESHOLD 107 +#define SQR_TOOM4_THRESHOLD 298 +#define SQR_TOOM6_THRESHOLD 399 +#define SQR_TOOM8_THRESHOLD 562 + +#define MULMID_TOOM42_THRESHOLD 48 + +#define MULMOD_BNM1_THRESHOLD 25 +#define SQRMOD_BNM1_THRESHOLD 23 + +#define MUL_FFT_MODF_THRESHOLD 555 /* k = 5 */ +#define MUL_FFT_TABLE3 \ + { { 555, 5}, { 29, 6}, { 31, 7}, { 31, 8}, \ + { 17, 7}, { 36, 8}, { 19, 7}, { 39, 8}, \ + { 21, 7}, { 43, 8}, { 29, 9}, { 15, 8}, \ + { 31, 7}, { 63, 8}, { 35, 9}, { 19, 8}, \ + { 43, 9}, { 23, 8}, { 51, 9}, { 27, 8}, \ + { 57,10}, { 15, 8}, { 61, 9}, { 31, 8}, \ + { 67, 9}, { 35, 8}, { 71, 9}, { 39, 8}, \ + { 81, 9}, { 43,10}, { 23, 9}, { 59,11}, \ + { 15,10}, { 31, 9}, { 71,10}, { 39, 9}, \ + { 87,10}, { 47, 9}, { 99,10}, { 55, 9}, \ + { 115,11}, { 31,10}, { 63, 9}, { 131,10}, \ + { 87,11}, { 47,10}, { 111, 9}, { 223,12}, \ + { 31,11}, { 63,10}, { 135,11}, { 79,10}, \ + { 159,11}, { 95,10}, { 191,11}, { 111,12}, \ + { 63,11}, { 143,10}, { 287,11}, { 159,12}, \ + { 95,11}, { 191,10}, { 383, 9}, { 767,13}, \ + { 8192,14}, { 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 75 +#define MUL_FFT_THRESHOLD 5760 + +#define SQR_FFT_MODF_THRESHOLD 372 /* k = 5 */ +#define SQR_FFT_TABLE3 \ + { { 372, 5}, { 23, 6}, { 12, 5}, { 25, 6}, \ + { 25, 7}, { 13, 6}, { 27, 7}, { 25, 8}, \ + { 13, 7}, { 28, 8}, { 15, 7}, { 31, 8}, \ + { 27, 9}, { 15, 8}, { 35, 9}, { 19, 8}, \ + { 41, 9}, { 23, 8}, { 47, 9}, { 27,10}, \ + { 15, 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}, { 79,11}, { 47,10}, { 95,12}, \ + { 31,11}, { 63,10}, { 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, 9}, { 607,11}, \ + { 159,10}, { 319, 9}, { 639,12}, { 95,11}, \ + { 191,10}, { 383, 9}, { 767,11}, { 207,13}, \ + { 8192,14}, { 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 75 +#define SQR_FFT_THRESHOLD 3776 + +#define MULLO_BASECASE_THRESHOLD 0 /* always */ +#define MULLO_DC_THRESHOLD 35 +#define MULLO_MUL_N_THRESHOLD 11278 +#define SQRLO_BASECASE_THRESHOLD 0 /* always */ +#define SQRLO_DC_THRESHOLD 168 +#define SQRLO_SQR_THRESHOLD 7511 + +#define DC_DIV_QR_THRESHOLD 36 +#define DC_DIVAPPR_Q_THRESHOLD 103 +#define DC_BDIV_QR_THRESHOLD 28 +#define DC_BDIV_Q_THRESHOLD 88 + +#define INV_MULMOD_BNM1_THRESHOLD 78 +#define INV_NEWTON_THRESHOLD 181 +#define INV_APPR_THRESHOLD 118 + +#define BINV_NEWTON_THRESHOLD 296 +#define REDC_1_TO_REDC_2_THRESHOLD 4 +#define REDC_2_TO_REDC_N_THRESHOLD 79 + +#define MU_DIV_QR_THRESHOLD 1970 +#define MU_DIVAPPR_Q_THRESHOLD 1970 +#define MUPI_DIV_QR_THRESHOLD 82 +#define MU_BDIV_QR_THRESHOLD 1528 +#define MU_BDIV_Q_THRESHOLD 1970 + +#define POWM_SEC_TABLE 1,58,102,1509 + +#define GET_STR_DC_THRESHOLD 15 +#define GET_STR_PRECOMPUTE_THRESHOLD 29 +#define SET_STR_DC_THRESHOLD 686 +#define SET_STR_PRECOMPUTE_THRESHOLD 2717 + +#define FAC_DSC_THRESHOLD 336 +#define FAC_ODD_THRESHOLD 24 + +#define MATRIX22_STRASSEN_THRESHOLD 32 +#define HGCD2_DIV1_METHOD 1 /* 0.66% faster than 3 */ +#define HGCD_THRESHOLD 57 +#define HGCD_APPR_THRESHOLD 50 +#define HGCD_REDUCE_THRESHOLD 3389 +#define GCD_DC_THRESHOLD 386 +#define GCDEXT_DC_THRESHOLD 288 +#define JACOBI_BASE_METHOD 4 /* 2.50% faster than 3 */ |