[Gmp-commit] /var/hg/gmp: 2 new changesets

mercurial at gmplib.org mercurial at gmplib.org
Thu Mar 17 19:50:52 CET 2022


details:   /var/hg/gmp/rev/b32f1a017aaf
changeset: 18328:b32f1a017aaf
user:      Torbjorn Granlund <tg at gmplib.org>
date:      Thu Mar 17 19:49:11 2022 +0100
description:
Alder Lake parameter file.

details:   /var/hg/gmp/rev/ba0d9b6f8c88
changeset: 18329:ba0d9b6f8c88
user:      Torbjorn Granlund <tg at gmplib.org>
date:      Thu Mar 17 19:50:49 2022 +0100
description:
Trivial merge.

diffstat:

 mpn/generic/mul_fft.c             |   28 ++++
 mpn/x86_64/alderlake/gmp-mparam.h |  225 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 253 insertions(+), 0 deletions(-)

diffs (274 lines):

diff -r a44f487c8d20 -r ba0d9b6f8c88 mpn/generic/mul_fft.c
--- a/mpn/generic/mul_fft.c	Fri Mar 11 21:13:20 2022 +0100
+++ b/mpn/generic/mul_fft.c	Thu Mar 17 19:50:49 2022 +0100
@@ -474,6 +474,7 @@
 mpn_fft_mul_modF_K (mp_ptr *ap, mp_ptr *bp, mp_size_t n, mp_size_t K)
 {
   int i;
+  unsigned k;
   int sqr = (ap == bp);
   TMP_DECL;
 
@@ -547,6 +548,33 @@
 	  (*ap)[n] = cy;
 	}
     }
+#if ! TUNE_PROGRAM_BUILD
+  else if (MPN_MULMOD_BKNP1_USABLE (n, k, MUL_FFT_MODF_THRESHOLD))
+    {
+      mp_ptr a;
+      mp_size_t n_k = n / k;
+
+      if (sqr)
+       {
+	 mp_ptr tp = TMP_SALLOC_LIMBS (mpn_sqrmod_bknp1_itch (n));
+         for (i = 0; i < K; i++)
+           {
+             a = *ap++;
+             mpn_sqrmod_bknp1 (a, a, n_k, k, tp);
+           }
+       }
+      else
+       {
+	 mp_ptr b, tp = TMP_SALLOC_LIMBS (mpn_mulmod_bknp1_itch (n));
+         for (i = 0; i < K; i++)
+           {
+             a = *ap++;
+             b = *bp++;
+             mpn_mulmod_bknp1 (a, a, b, n_k, k, tp);
+           }
+       }
+    }
+#endif
   else
     {
       mp_ptr a, b, tp, tpn;
diff -r a44f487c8d20 -r ba0d9b6f8c88 mpn/x86_64/alderlake/gmp-mparam.h
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/x86_64/alderlake/gmp-mparam.h	Thu Mar 17 19:50:49 2022 +0100
@@ -0,0 +1,225 @@
+/* Intel Alder Lake gmp-mparam.h -- Compiler/machine parameter header file.
+
+Copyright 2022 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
+
+/* 3700-4900 MHz Alder Lake */
+/* FFT tuning limit = 10,000,000 */
+/* Generated by tuneup.c, 2022-03-15, gcc 11.2 */
+
+#define MOD_1_NORM_THRESHOLD             MP_SIZE_T_MAX  /* never */
+#define MOD_1_UNNORM_THRESHOLD           MP_SIZE_T_MAX  /* never */
+#define MOD_1N_TO_MOD_1_1_THRESHOLD          5
+#define MOD_1U_TO_MOD_1_1_THRESHOLD          4
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD        12
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD        23
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD      8
+#define USE_PREINV_DIVREM_1                  1  /* native */
+#define DIV_QR_1_NORM_THRESHOLD             34
+#define DIV_QR_1_UNNORM_THRESHOLD        MP_SIZE_T_MAX  /* never */
+#define DIV_QR_2_PI2_THRESHOLD              30
+#define DIVEXACT_1_THRESHOLD                 0  /* always (native) */
+#define BMOD_1_TO_MOD_1_THRESHOLD           23
+
+#define DIV_1_VS_MUL_1_PERCENT             559
+
+#define MUL_TOOM22_THRESHOLD                13
+#define MUL_TOOM33_THRESHOLD                97
+#define MUL_TOOM44_THRESHOLD               148
+#define MUL_TOOM6H_THRESHOLD               562
+#define MUL_TOOM8H_THRESHOLD               608
+
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD      97
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD     259
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD      98
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD      98
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD     144
+
+#define SQR_BASECASE_THRESHOLD               0  /* always (native) */
+#define SQR_TOOM2_THRESHOLD                 24
+#define SQR_TOOM3_THRESHOLD                 86
+#define SQR_TOOM4_THRESHOLD                582
+#define SQR_TOOM6_THRESHOLD                  0  /* always */
+#define SQR_TOOM8_THRESHOLD                753
+
+#define MULMID_TOOM42_THRESHOLD             40
+
+#define MULMOD_BNM1_THRESHOLD               13
+#define SQRMOD_BNM1_THRESHOLD               16
+
+#define MUL_FFT_MODF_THRESHOLD             384  /* k = 5 */
+#define MUL_FFT_TABLE3                                      \
+  { {    384, 5}, {     21, 6}, {     11, 5}, {     23, 6}, \
+    {     21, 7}, {     11, 6}, {     24, 7}, {     24, 8}, \
+    {     13, 7}, {     27, 8}, {     15, 7}, {     31, 8}, \
+    {     23, 7}, {     47, 8}, {     27, 9}, {     15, 8}, \
+    {     33, 9}, {     19, 8}, {     39, 9}, {     23, 8}, \
+    {     49, 9}, {     27,10}, {     15, 9}, {     31, 8}, \
+    {     63, 9}, {     39,10}, {     23, 9}, {     51,11}, \
+    {     15,10}, {     31, 9}, {     71,10}, {     39, 9}, \
+    {     83,10}, {     47, 9}, {     95,10}, {     55,11}, \
+    {     31,10}, {     79,11}, {     47,10}, {     95,12}, \
+    {     31,11}, {     63,10}, {    127, 9}, {    255, 8}, \
+    {    511,10}, {    135,11}, {     79, 9}, {    319, 8}, \
+    {    639, 9}, {    335, 8}, {    671,11}, {     95,12}, \
+    {     63,11}, {    127,10}, {    255, 9}, {    511,10}, \
+    {    271, 9}, {    543, 8}, {   1087, 9}, {    575,10}, \
+    {    303, 9}, {    607,10}, {    319, 9}, {    639,10}, \
+    {    335, 9}, {    671,10}, {    351,12}, {     95,11}, \
+    {    191,10}, {    383,13}, {     63,12}, {    127,11}, \
+    {    255,10}, {    511,11}, {    271,10}, {    543, 9}, \
+    {   1087,11}, {    287,10}, {    575,11}, {    303,10}, \
+    {    607, 9}, {   1215,11}, {    319,10}, {    671,11}, \
+    {    351,10}, {    703,11}, {    367,10}, {    735, 9}, \
+    {   1471, 8}, {   2943,12}, {    191,11}, {    383,10}, \
+    {    767,11}, {    415,10}, {    831,12}, {    223,11}, \
+    {    447,10}, {    895,11}, {    479,10}, {    959,13}, \
+    {    127,12}, {    255,11}, {    511,10}, {   1023,11}, \
+    {    543,10}, {   1087, 9}, {   2175,12}, {    287,11}, \
+    {    575,10}, {   1151,11}, {    607,12}, {    319,11}, \
+    {    639,10}, {   1279,11}, {    671,12}, {    351,11}, \
+    {    703,10}, {   1407,11}, {    735,10}, {   1471, 9}, \
+    {   2943, 8}, {   5887,12}, {    383,11}, {    767,10}, \
+    {   1535,12}, {    415,11}, {    831,10}, {   1663,12}, \
+    {    447,11}, {    895,10}, {   1791,12}, {    479,11}, \
+    {    959,14}, {    127,13}, {    255,12}, {    511,11}, \
+    {   1023,12}, {    543,11}, {   1087,12}, {    575,11}, \
+    {   1151,12}, {    607,11}, {   1215,13}, {    319,12}, \
+    {    639,11}, {   1279,12}, {    671,11}, {   1343,12}, \
+    {    703,11}, {   1407,12}, {    735,11}, {   1471,10}, \
+    {   2943,13}, {    383,12}, {    767,11}, {   1535,12}, \
+    {    831,13}, {    447,12}, {    959,11}, {   1919,13}, \
+    {    511,12}, {   1087,13}, {    575,12}, {   1215,13}, \
+    {    639,12}, {   1343,13}, {    703,12}, {   1471,11}, \
+    {   2943,14}, {    383,13}, {    767,12}, {   1535,13}, \
+    {    831,12}, {   1663,13}, {    959,12}, {   1919,14}, \
+    {    511,13}, {   1087,12}, {   2175,13}, {   1215,14}, \
+    {  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 190
+#define MUL_FFT_THRESHOLD                 2496
+
+#define SQR_FFT_MODF_THRESHOLD             344  /* k = 5 */
+#define SQR_FFT_TABLE3                                      \
+  { {    344, 5}, {     21, 6}, {     11, 5}, {     23, 6}, \
+    {     25, 7}, {     13, 6}, {     27, 7}, {     25, 8}, \
+    {     13, 7}, {     27, 8}, {     15, 7}, {     31, 8}, \
+    {     21, 9}, {     11, 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}, \
+    {     63,10}, {     39, 9}, {     79,10}, {     47,11}, \
+    {     31,10}, {     79,11}, {     47,10}, {     95,12}, \
+    {     31,11}, {     63,10}, {    127, 9}, {    255, 8}, \
+    {    511,11}, {     79, 9}, {    319,11}, {     95,10}, \
+    {    191, 9}, {    383,12}, {     63,11}, {    127,10}, \
+    {    255, 9}, {    511,10}, {    271, 9}, {    543,11}, \
+    {    143,10}, {    287, 9}, {    575,10}, {    303, 9}, \
+    {    607,10}, {    319, 9}, {    639,12}, {     95,11}, \
+    {    191,10}, {    383,13}, {     63,12}, {    127,11}, \
+    {    255,10}, {    511,11}, {    271,10}, {    543,11}, \
+    {    287,10}, {    575,11}, {    303,10}, {    607,11}, \
+    {    319,10}, {    639,11}, {    335,10}, {    671,11}, \
+    {    351,10}, {    703,12}, {    191,11}, {    383,10}, \
+    {    767,11}, {    415,10}, {    831,12}, {    223,11}, \
+    {    447,10}, {    895,11}, {    479,10}, {    959,13}, \
+    {    127,12}, {    255,11}, {    511,10}, {   1023,11}, \
+    {    543,10}, {   1087,12}, {    287,11}, {    575,10}, \
+    {   1151,11}, {    607,10}, {   1215,12}, {    319,11}, \
+    {    639,10}, {   1279,11}, {    671,12}, {    351,11}, \
+    {    703,10}, {   1407,13}, {    191,12}, {    383,11}, \
+    {    767,12}, {    415,11}, {    831,12}, {    447,11}, \
+    {    895,12}, {    479,11}, {    959,10}, {   1919,14}, \
+    {    127,13}, {    255,12}, {    511,11}, {   1023,12}, \
+    {    543,11}, {   1087,12}, {    575,11}, {   1151,12}, \
+    {    607,11}, {   1215,13}, {    319,12}, {    639,11}, \
+    {   1279,12}, {    671,11}, {   1343,12}, {    703,11}, \
+    {   1407,13}, {    383,12}, {    831,13}, {    447,12}, \
+    {    959,14}, {    255,13}, {    511,12}, {   1087,13}, \
+    {    575,12}, {   1215,13}, {    639,12}, {   1343,13}, \
+    {    703,12}, {   1407,14}, {    383,13}, {    767,12}, \
+    {   1535,13}, {    831,12}, {   1663,13}, {    959,14}, \
+    {    511,13}, {   1087,12}, {   2175,13}, {   1215,14}, \
+    {  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 166
+#define SQR_FFT_THRESHOLD                 2240
+
+#define MULLO_BASECASE_THRESHOLD             0  /* always */
+#define MULLO_DC_THRESHOLD                  56
+#define MULLO_MUL_N_THRESHOLD             4940
+#define SQRLO_BASECASE_THRESHOLD            10
+#define SQRLO_DC_THRESHOLD                  73
+#define SQRLO_SQR_THRESHOLD               4392
+
+#define DC_DIV_QR_THRESHOLD                 19
+#define DC_DIVAPPR_Q_THRESHOLD             139
+#define DC_BDIV_QR_THRESHOLD                62
+#define DC_BDIV_Q_THRESHOLD                126
+
+#define INV_MULMOD_BNM1_THRESHOLD           24
+#define INV_NEWTON_THRESHOLD               108
+#define INV_APPR_THRESHOLD                 108
+
+#define BINV_NEWTON_THRESHOLD              208
+#define REDC_1_TO_REDC_2_THRESHOLD          36
+#define REDC_2_TO_REDC_N_THRESHOLD          53
+
+#define MU_DIV_QR_THRESHOLD                855
+#define MU_DIVAPPR_Q_THRESHOLD            1120
+#define MUPI_DIV_QR_THRESHOLD                0  /* always */
+#define MU_BDIV_QR_THRESHOLD               807
+#define MU_BDIV_Q_THRESHOLD               1470
+
+#define POWM_SEC_TABLE  1,11,70,702,2499
+
+#define GET_STR_DC_THRESHOLD                11
+#define GET_STR_PRECOMPUTE_THRESHOLD        17
+#define SET_STR_DC_THRESHOLD              2150
+#define SET_STR_PRECOMPUTE_THRESHOLD      2943
+
+#define FAC_DSC_THRESHOLD                  298
+#define FAC_ODD_THRESHOLD                   51
+
+#define MATRIX22_STRASSEN_THRESHOLD         17
+#define HGCD2_DIV1_METHOD                    1  /* 2.38% faster than 3 */
+#define HGCD_THRESHOLD                     142
+#define HGCD_APPR_THRESHOLD                159
+#define HGCD_REDUCE_THRESHOLD             2384
+#define GCD_DC_THRESHOLD                   483
+#define GCDEXT_DC_THRESHOLD                492
+#define JACOBI_BASE_METHOD                   1  /* 0.94% faster than 3 */


More information about the gmp-commit mailing list