[Gmp-commit] /var/hg/gmp: 3 new changesets
mercurial at gmplib.org
mercurial at gmplib.org
Sun Oct 18 16:16:20 UTC 2015
details: /var/hg/gmp/rev/94fe2722a985
changeset: 16885:94fe2722a985
user: Torbjorn Granlund <torbjorng at google.com>
date: Sun Oct 18 18:15:37 2015 +0200
description:
Retune.
details: /var/hg/gmp/rev/74abdbe3176a
changeset: 16886:74abdbe3176a
user: Torbjorn Granlund <torbjorng at google.com>
date: Sun Oct 18 18:16:00 2015 +0200
description:
Add tuning file for arm64.
details: /var/hg/gmp/rev/e2bbc8385e19
changeset: 16887:e2bbc8385e19
user: Torbjorn Granlund <torbjorng at google.com>
date: Sun Oct 18 18:16:16 2015 +0200
description:
ChangeLog
diffstat:
ChangeLog | 4 +
mpn/arm64/gmp-mparam.h | 184 ++++++++++++++++++++++++++++
mpn/x86_64/bd1/gmp-mparam.h | 287 ++++++++++++++++++++++---------------------
3 files changed, 334 insertions(+), 141 deletions(-)
diffs (truncated from 558 to 300 lines):
diff -r fc0ce695e2fa -r e2bbc8385e19 ChangeLog
--- a/ChangeLog Sun Oct 18 15:30:24 2015 +0200
+++ b/ChangeLog Sun Oct 18 18:16:16 2015 +0200
@@ -1,3 +1,7 @@
+2015-10-18 Torbjörn Granlund <torbjorng at google.com>
+
+ * mpn/arm64/gmp-mparam.h: New file.
+
2015-10-18 Marco Bodrato <bodrato at mail.dm.unipi.it>
* Makefile.am (LIBGMP_LT_*, LIBGMPXX_LT_*): Bump version info.
diff -r fc0ce695e2fa -r e2bbc8385e19 mpn/arm64/gmp-mparam.h
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/arm64/gmp-mparam.h Sun Oct 18 18:16:16 2015 +0200
@@ -0,0 +1,184 @@
+/* gmp-mparam.h -- Compiler/machine parameter header file.
+
+Copyright 2015 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
+
+/* 2400 MHz AppliedMicro X-Gene */
+/* FFT tuning limit = 0.5 M */
+/* Generated by tuneup.c, 2015-10-18, gcc 4.8 */
+
+#define DIVREM_1_NORM_THRESHOLD 0 /* always */
+#define DIVREM_1_UNNORM_THRESHOLD 0 /* always */
+#define MOD_1_1P_METHOD 1
+#define MOD_1_NORM_THRESHOLD 0 /* always */
+#define MOD_1_UNNORM_THRESHOLD 0 /* always */
+#define MOD_1N_TO_MOD_1_1_THRESHOLD 7
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 6
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 0 /* never mpn_mod_1_1p */
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD 28
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 13
+#define USE_PREINV_DIVREM_1 1
+#define DIV_QR_1N_PI1_METHOD 1
+#define DIV_QR_1_NORM_THRESHOLD 1
+#define DIV_QR_1_UNNORM_THRESHOLD 1
+#define DIV_QR_2_PI2_THRESHOLD MP_SIZE_T_MAX /* never */
+#define DIVEXACT_1_THRESHOLD 0 /* always */
+#define BMOD_1_TO_MOD_1_THRESHOLD 30
+
+#define MUL_TOOM22_THRESHOLD 14
+#define MUL_TOOM33_THRESHOLD 97
+#define MUL_TOOM44_THRESHOLD 154
+#define MUL_TOOM6H_THRESHOLD 206
+#define MUL_TOOM8H_THRESHOLD 309
+
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 89
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 103
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 89
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 103
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 130
+
+#define SQR_BASECASE_THRESHOLD 6
+#define SQR_TOOM2_THRESHOLD 28
+#define SQR_TOOM3_THRESHOLD 93
+#define SQR_TOOM4_THRESHOLD 148
+#define SQR_TOOM6_THRESHOLD 214
+#define SQR_TOOM8_THRESHOLD 284
+
+#define MULMID_TOOM42_THRESHOLD 38
+
+#define MULMOD_BNM1_THRESHOLD 9
+#define SQRMOD_BNM1_THRESHOLD 13
+
+#define MUL_FFT_MODF_THRESHOLD 308 /* k = 5 */
+#define MUL_FFT_TABLE3 \
+ { { 308, 5}, { 13, 6}, { 7, 5}, { 15, 6}, \
+ { 8, 5}, { 17, 6}, { 15, 7}, { 8, 6}, \
+ { 17, 7}, { 17, 8}, { 9, 7}, { 20, 8}, \
+ { 11, 7}, { 24, 8}, { 13, 7}, { 27, 9}, \
+ { 7, 8}, { 15, 7}, { 31, 8}, { 17, 7}, \
+ { 35, 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}, { 55,11}, { 15,10}, \
+ { 31, 9}, { 71,10}, { 39, 9}, { 83,10}, \
+ { 47, 9}, { 99,10}, { 55,11}, { 31,10}, \
+ { 63, 9}, { 127,10}, { 79, 9}, { 159,11}, \
+ { 47,10}, { 95, 9}, { 191, 8}, { 383,10}, \
+ { 103,12}, { 31,11}, { 63,10}, { 127, 9}, \
+ { 255, 8}, { 511,10}, { 135, 9}, { 287,11}, \
+ { 79,10}, { 159, 9}, { 319, 8}, { 639,10}, \
+ { 175, 9}, { 351, 8}, { 703,11}, { 95,10}, \
+ { 191, 9}, { 383, 8}, { 767,10}, { 207, 9}, \
+ { 415, 8}, { 831,11}, { 111,10}, { 223,12}, \
+ { 63,11}, { 127,10}, { 255, 9}, { 511,10}, \
+ { 271, 9}, { 543,10}, { 287, 9}, { 575,11}, \
+ { 159,10}, { 319, 9}, { 639,11}, { 175,10}, \
+ { 351, 9}, { 703,12}, { 95,11}, { 191,10}, \
+ { 383, 9}, { 767,11}, { 207,10}, { 415, 9}, \
+ { 831,11}, { 223,10}, { 447,13}, { 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 110
+#define MUL_FFT_THRESHOLD 3520
+
+#define SQR_FFT_MODF_THRESHOLD 272 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 272, 5}, { 13, 6}, { 7, 5}, { 15, 6}, \
+ { 17, 7}, { 9, 6}, { 19, 7}, { 17, 8}, \
+ { 9, 7}, { 20, 8}, { 11, 7}, { 23, 8}, \
+ { 13, 9}, { 7, 8}, { 15, 7}, { 31, 8}, \
+ { 19, 9}, { 11, 8}, { 27, 9}, { 15, 8}, \
+ { 33, 9}, { 19, 8}, { 39, 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}, { 63, 8}, \
+ { 255,10}, { 71, 9}, { 143, 8}, { 287,10}, \
+ { 79,11}, { 47,10}, { 95, 9}, { 191,12}, \
+ { 31,11}, { 63, 9}, { 255, 8}, { 511,10}, \
+ { 143, 9}, { 287,11}, { 79,10}, { 159, 9}, \
+ { 319, 8}, { 639,10}, { 175, 9}, { 351, 8}, \
+ { 703,11}, { 95,10}, { 191, 9}, { 383, 8}, \
+ { 767,10}, { 207, 9}, { 415,12}, { 63,10}, \
+ { 255, 9}, { 511,11}, { 143,10}, { 287, 9}, \
+ { 575, 8}, { 1151,11}, { 159,10}, { 319, 9}, \
+ { 639,11}, { 175,10}, { 351, 9}, { 703,12}, \
+ { 95,11}, { 191,10}, { 383, 9}, { 767,11}, \
+ { 207,10}, { 415, 9}, { 831,11}, { 223,13}, \
+ { 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 99
+#define SQR_FFT_THRESHOLD 2496
+
+#define MULLO_BASECASE_THRESHOLD 0 /* always */
+#define MULLO_DC_THRESHOLD 43
+#define MULLO_MUL_N_THRESHOLD 7035
+#define SQRLO_BASECASE_THRESHOLD 4
+#define SQRLO_DC_THRESHOLD 106
+#define SQRLO_SQR_THRESHOLD 4972
+
+#define DC_DIV_QR_THRESHOLD 51
+#define DC_DIVAPPR_Q_THRESHOLD 167
+#define DC_BDIV_QR_THRESHOLD 47
+#define DC_BDIV_Q_THRESHOLD 50
+
+#define INV_MULMOD_BNM1_THRESHOLD 26
+#define INV_NEWTON_THRESHOLD 226
+#define INV_APPR_THRESHOLD 199
+
+#define BINV_NEWTON_THRESHOLD 246
+#define REDC_1_TO_REDC_N_THRESHOLD 59
+
+#define MU_DIV_QR_THRESHOLD 1234
+#define MU_DIVAPPR_Q_THRESHOLD 1234
+#define MUPI_DIV_QR_THRESHOLD 114
+#define MU_BDIV_QR_THRESHOLD 889
+#define MU_BDIV_Q_THRESHOLD 1210
+
+#define POWM_SEC_TABLE 3,28,194,712,2245
+
+#define GET_STR_DC_THRESHOLD 11
+#define GET_STR_PRECOMPUTE_THRESHOLD 22
+#define SET_STR_DC_THRESHOLD 1095
+#define SET_STR_PRECOMPUTE_THRESHOLD 3333
+
+#define FAC_DSC_THRESHOLD 300
+#define FAC_ODD_THRESHOLD 26
+
+#define MATRIX22_STRASSEN_THRESHOLD 15
+#define HGCD_THRESHOLD 145
+#define HGCD_APPR_THRESHOLD 168
+#define HGCD_REDUCE_THRESHOLD 2121
+#define GCD_DC_THRESHOLD 525
+#define GCDEXT_DC_THRESHOLD 382
+#define JACOBI_BASE_METHOD 4
diff -r fc0ce695e2fa -r e2bbc8385e19 mpn/x86_64/bd1/gmp-mparam.h
--- a/mpn/x86_64/bd1/gmp-mparam.h Sun Oct 18 15:30:24 2015 +0200
+++ b/mpn/x86_64/bd1/gmp-mparam.h Sun Oct 18 18:16:16 2015 +0200
@@ -1,7 +1,7 @@
/* AMD bd1 gmp-mparam.h -- Compiler/machine parameter header file.
-Copyright 1991, 1993, 1994, 2000-2010, 2012, 2014 Free Software Foundation,
-Inc.
+Copyright 1991, 1993, 1994, 2000-2010, 2012, 2014, 2015 Free Software
+Foundation, Inc.
This file is part of the GNU MP Library.
@@ -33,16 +33,16 @@
#define GMP_LIMB_BYTES 8
/* 3600 MHz Bulldozer Zambezi */
-/* FFT tuning limit = 40000000 */
-/* Generated by tuneup.c, 2014-03-13, gcc 4.5 */
+/* FFT tuning limit = 100 M */
+/* Generated by tuneup.c, 2015-10-14, gcc 4.8 */
#define MOD_1_NORM_THRESHOLD 0 /* always */
#define MOD_1_UNNORM_THRESHOLD 0 /* always */
#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 13
-#define MOD_1_2_TO_MOD_1_4_THRESHOLD 28
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 11
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 3
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 18
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD 31
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 10
#define USE_PREINV_DIVREM_1 1 /* native */
#define DIV_QR_1_NORM_THRESHOLD 1
#define DIV_QR_1_UNNORM_THRESHOLD MP_SIZE_T_MAX /* never */
@@ -51,96 +51,96 @@
#define BMOD_1_TO_MOD_1_THRESHOLD 22
#define MUL_TOOM22_THRESHOLD 20
-#define MUL_TOOM33_THRESHOLD 59
+#define MUL_TOOM33_THRESHOLD 57
#define MUL_TOOM44_THRESHOLD 166
#define MUL_TOOM6H_THRESHOLD 274
-#define MUL_TOOM8H_THRESHOLD 333
+#define MUL_TOOM8H_THRESHOLD 339
#define MUL_TOOM32_TO_TOOM43_THRESHOLD 97
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 107
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 108
#define MUL_TOOM42_TO_TOOM53_THRESHOLD 105
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 115
-#define MUL_TOOM43_TO_TOOM54_THRESHOLD 150
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 113
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 148
#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
-#define SQR_TOOM2_THRESHOLD 22
-#define SQR_TOOM3_THRESHOLD 85
-#define SQR_TOOM4_THRESHOLD 242
+#define SQR_TOOM2_THRESHOLD 21
+#define SQR_TOOM3_THRESHOLD 81
+#define SQR_TOOM4_THRESHOLD 232
#define SQR_TOOM6_THRESHOLD 318
-#define SQR_TOOM8_THRESHOLD 478
+#define SQR_TOOM8_THRESHOLD 430
#define MULMID_TOOM42_THRESHOLD 22
#define MULMOD_BNM1_THRESHOLD 11
-#define SQRMOD_BNM1_THRESHOLD 14
+#define SQRMOD_BNM1_THRESHOLD 15
-#define MUL_FFT_MODF_THRESHOLD 404 /* k = 5 */
+#define MUL_FFT_MODF_THRESHOLD 412 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 404, 5}, { 19, 6}, { 11, 5}, { 23, 6}, \
- { 19, 7}, { 10, 6}, { 25, 7}, { 15, 6}, \
- { 31, 7}, { 25, 8}, { 13, 7}, { 27, 8}, \
- { 15, 7}, { 31, 8}, { 17, 7}, { 35, 8}, \
- { 19, 7}, { 39, 8}, { 27, 9}, { 15, 8}, \
- { 35, 9}, { 19, 8}, { 41, 9}, { 23, 8}, \
- { 47, 9}, { 27,10}, { 15, 9}, { 39,10}, \
- { 23, 9}, { 55,11}, { 15,10}, { 31, 9}, \
- { 67,10}, { 39, 9}, { 83,10}, { 47, 9}, \
- { 95,10}, { 55,11}, { 31,10}, { 79,11}, \
- { 47,10}, { 103,12}, { 31,11}, { 63,10}, \
- { 135,11}, { 79,10}, { 167,11}, { 95,10}, \
- { 191,11}, { 111,12}, { 63,11}, { 127,10}, \
- { 255,11}, { 143,10}, { 287, 9}, { 575,10}, \
- { 303,11}, { 159,12}, { 95,11}, { 191,10}, \
- { 383,11}, { 207,13}, { 63,12}, { 127,11}, \
- { 255,10}, { 511,11}, { 271,10}, { 543,11}, \
- { 287,10}, { 575,11}, { 303,12}, { 159,11}, \
- { 319, 9}, { 1279,11}, { 367,12}, { 191,11}, \
- { 383,10}, { 767,11}, { 415,12}, { 223,11}, \
- { 447,10}, { 895,13}, { 127,12}, { 255,11}, \
- { 511,10}, { 1023,11}, { 543,12}, { 287,11}, \
- { 575,10}, { 1151,11}, { 607,10}, { 1215,12}, \
- { 319,10}, { 1279,11}, { 671,12}, { 351,11}, \
+ { { 412, 5}, { 21, 6}, { 11, 5}, { 23, 6}, \
More information about the gmp-commit
mailing list