[Gmp-commit] /var/hg/gmp: Retune.
mercurial at gmplib.org
mercurial at gmplib.org
Sat Mar 22 14:42:27 UTC 2014
details: /var/hg/gmp/rev/05e6f6b1c3a8
changeset: 16350:05e6f6b1c3a8
user: Torbjorn Granlund <tege at gmplib.org>
date: Sat Mar 22 15:42:23 2014 +0100
description:
Retune.
diffstat:
mpn/sparc64/ultrasparc34/gmp-mparam.h | 141 ++++++++++----------
mpn/x86/coreinhm/gmp-mparam.h | 227 ++++++++++++++++++++++-----------
mpn/x86_64/coreinhm/gmp-mparam.h | 179 ++++++++++++++++----------
3 files changed, 331 insertions(+), 216 deletions(-)
diffs (truncated from 678 to 300 lines):
diff -r 7a022f693cad -r 05e6f6b1c3a8 mpn/sparc64/ultrasparc34/gmp-mparam.h
--- a/mpn/sparc64/ultrasparc34/gmp-mparam.h Mon Mar 17 22:44:30 2014 +0100
+++ b/mpn/sparc64/ultrasparc34/gmp-mparam.h Sat Mar 22 15:42:23 2014 +0100
@@ -1,7 +1,7 @@
/* ultrasparc3/4 gmp-mparam.h -- Compiler/machine parameter header file.
-Copyright 1991, 1993, 1994, 1999-2002, 2004, 2006, 2008-2010 Free Software
-Foundation, Inc.
+Copyright 1991, 1993, 1994, 1999-2002, 2004, 2006, 2008-2010, 2014 Free
+Software Foundation, Inc.
This file is part of the GNU MP Library.
@@ -33,7 +33,7 @@
#define GMP_LIMB_BYTES 8
/* 1593 MHz ultrasparc3 running Solaris 10 (swift.nada.kth.se) */
-/* FFT tuning limit = 25000000 */
+/* FFT tuning limit = 60000000 */
/* Generated by tuneup.c, 2014-03-14, gcc 3.4 */
#define DIVREM_1_NORM_THRESHOLD 0 /* always */
@@ -78,98 +78,103 @@
#define MULMOD_BNM1_THRESHOLD 15
#define SQRMOD_BNM1_THRESHOLD 9
-#define MUL_FFT_MODF_THRESHOLD 248 /* k = 5 */
+#define MUL_FFT_MODF_THRESHOLD 220 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 248, 5}, { 13, 6}, { 17, 7}, { 9, 6}, \
+ { { 220, 5}, { 13, 6}, { 17, 7}, { 9, 6}, \
{ 19, 7}, { 17, 8}, { 9, 7}, { 20, 8}, \
{ 11, 7}, { 24, 8}, { 13, 9}, { 7, 8}, \
{ 19, 9}, { 11, 8}, { 25,10}, { 7, 9}, \
{ 15, 8}, { 33, 9}, { 19, 8}, { 39, 9}, \
{ 23, 8}, { 47, 9}, { 27,10}, { 15, 9}, \
{ 39,10}, { 23, 9}, { 47,11}, { 15,10}, \
- { 31, 9}, { 63, 8}, { 127, 9}, { 67,10}, \
- { 39, 9}, { 79, 8}, { 159, 7}, { 319, 9}, \
+ { 31, 9}, { 63, 8}, { 127, 7}, { 255, 9}, \
+ { 67,10}, { 39, 9}, { 79, 8}, { 159, 9}, \
{ 83,10}, { 47, 9}, { 95, 8}, { 191, 7}, \
{ 383,10}, { 55,11}, { 31,10}, { 63, 9}, \
- { 127, 8}, { 255,10}, { 71, 9}, { 143, 8}, \
- { 287, 7}, { 575,10}, { 79, 9}, { 159, 8}, \
- { 319,11}, { 47,10}, { 95, 9}, { 191, 8}, \
- { 383,10}, { 103, 9}, { 207, 8}, { 415,12}, \
- { 31,11}, { 63,10}, { 127, 9}, { 255,10}, \
- { 143, 9}, { 287, 8}, { 575,11}, { 79,10}, \
- { 159, 9}, { 319, 8}, { 639, 9}, { 351,11}, \
- { 95, 9}, { 383,10}, { 207, 9}, { 415,10}, \
- { 223, 9}, { 447,12}, { 63,11}, { 127,10}, \
- { 255,11}, { 143,10}, { 287, 9}, { 575,11}, \
- { 159,10}, { 319, 9}, { 639,11}, { 175,10}, \
- { 351,12}, { 95,11}, { 191,10}, { 383,11}, \
- { 207,10}, { 415,11}, { 223,10}, { 447,13}, \
- { 63,12}, { 127,11}, { 287,10}, { 575,12}, \
- { 159,11}, { 351,10}, { 703, 9}, { 1407,12}, \
- { 191,11}, { 415,12}, { 223,11}, { 447,13}, \
- { 127,12}, { 287,11}, { 575,12}, { 351,11}, \
- { 703,13}, { 191,12}, { 447,14}, { 127,13}, \
- { 255,12}, { 575,13}, { 319,12}, { 703,13}, \
+ { 127, 8}, { 255, 7}, { 511,10}, { 71, 9}, \
+ { 143, 8}, { 287, 7}, { 575,10}, { 79, 9}, \
+ { 159, 8}, { 319,11}, { 47,10}, { 95, 9}, \
+ { 191, 8}, { 383,10}, { 103, 9}, { 207, 8}, \
+ { 415,10}, { 111,12}, { 31,11}, { 63,10}, \
+ { 127, 9}, { 255,10}, { 143, 9}, { 287, 8}, \
+ { 575,11}, { 79,10}, { 175, 9}, { 351,11}, \
+ { 95,10}, { 191, 9}, { 383,10}, { 207, 9}, \
+ { 415,11}, { 111,10}, { 223,12}, { 63,11}, \
+ { 127,10}, { 255,11}, { 143,10}, { 287, 9}, \
+ { 575, 8}, { 1151,11}, { 159,10}, { 319, 9}, \
+ { 639,11}, { 175,10}, { 351, 9}, { 703,12}, \
+ { 95,11}, { 191,10}, { 383,11}, { 207,10}, \
+ { 415,11}, { 223,10}, { 447,13}, { 63,12}, \
+ { 127,11}, { 287,10}, { 575,12}, { 159,11}, \
+ { 351,10}, { 703,12}, { 191,11}, { 415,12}, \
+ { 223,11}, { 479,13}, { 127,12}, { 287,11}, \
+ { 575,12}, { 351,13}, { 191,12}, { 415,11}, \
+ { 831,12}, { 479,14}, { 127,13}, { 255,12}, \
+ { 575,13}, { 319,12}, { 703,11}, { 1407,13}, \
{ 383,12}, { 831,13}, { 447,12}, { 895,14}, \
{ 255,13}, { 511,12}, { 1023,13}, { 575,12}, \
- { 1151,13}, { 639,12}, { 1279,13}, { 703,12}, \
- { 1407,14}, { 383,13}, { 895,15}, { 255,14}, \
- { 511,13}, { 1151,14}, { 639,13}, { 1407,14}, \
- { 767,13}, { 1663,14}, { 895,13}, { 1791,15}, \
- { 511,14}, { 1023,13}, { 2047,14}, { 1151,13}, \
- { 2303,14}, { 1407,15}, { 32768,16}, { 65536,17}, \
- { 131072,18}, { 262144,19}, { 524288,20}, {1048576,21}, \
- {2097152,22}, {4194304,23}, {8388608,24} }
-#define MUL_FFT_TABLE3_SIZE 159
+ { 1215,13}, { 703,14}, { 383,13}, { 831,12}, \
+ { 1663,13}, { 895,15}, { 255,14}, { 511,13}, \
+ { 1151,14}, { 639,13}, { 1407,14}, { 767,13}, \
+ { 1663,14}, { 895,13}, { 1791,15}, { 511,14}, \
+ { 1023,13}, { 2047,14}, { 1151,13}, { 2303,14}, \
+ { 1407,15}, { 767,14}, { 1791,16}, { 511,15}, \
+ { 1023,14}, { 2303,15}, { 1279,14}, { 2815,15}, \
+ { 1535,14}, { 3199,15}, { 1791,14}, { 3583,16}, \
+ { 65536,17}, { 131072,18}, { 262144,19}, { 524288,20}, \
+ {1048576,21}, {2097152,22}, {4194304,23}, {8388608,24} }
+#define MUL_FFT_TABLE3_SIZE 172
#define MUL_FFT_THRESHOLD 2240
#define SQR_FFT_MODF_THRESHOLD 244 /* k = 5 */
#define SQR_FFT_TABLE3 \
{ { 244, 5}, { 8, 4}, { 17, 5}, { 15, 6}, \
{ 8, 5}, { 17, 6}, { 17, 7}, { 9, 6}, \
- { 19, 7}, { 17, 8}, { 9, 7}, { 20, 8}, \
- { 11, 7}, { 23, 8}, { 13, 9}, { 7, 8}, \
+ { 19, 7}, { 10, 6}, { 21, 7}, { 17, 8}, \
+ { 9, 7}, { 20, 8}, { 11, 7}, { 23, 8}, \
{ 21, 9}, { 11, 8}, { 25, 9}, { 15, 8}, \
- { 31, 9}, { 19, 8}, { 39, 9}, { 23,10}, \
+ { 31, 9}, { 19, 8}, { 39, 9}, { 27,10}, \
{ 15, 9}, { 39,10}, { 23, 9}, { 47,11}, \
- { 15,10}, { 31, 9}, { 63,10}, { 39, 9}, \
- { 79,10}, { 55,11}, { 31,10}, { 63, 9}, \
- { 127, 8}, { 255,10}, { 71, 9}, { 143, 8}, \
- { 287, 7}, { 575,10}, { 79, 9}, { 159,11}, \
- { 47,10}, { 95, 9}, { 191, 8}, { 383, 7}, \
- { 767, 9}, { 207,12}, { 31,11}, { 63,10}, \
- { 127, 9}, { 255, 8}, { 511, 9}, { 271,10}, \
- { 143, 9}, { 287, 8}, { 575,11}, { 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}, \
- { 831,10}, { 223,12}, { 63,11}, { 127,10}, \
- { 271,11}, { 143,10}, { 287, 9}, { 575,11}, \
+ { 15,10}, { 31, 9}, { 67,10}, { 39, 9}, \
+ { 79,10}, { 47, 9}, { 95,10}, { 55,11}, \
+ { 31,10}, { 63, 9}, { 127, 8}, { 255,10}, \
+ { 71, 9}, { 143, 8}, { 287, 7}, { 575,10}, \
+ { 79, 9}, { 159, 8}, { 319,11}, { 47, 9}, \
+ { 191, 8}, { 383, 7}, { 767, 9}, { 207,12}, \
+ { 31,11}, { 63,10}, { 127, 9}, { 255, 8}, \
+ { 511, 9}, { 271,10}, { 143, 9}, { 287, 8}, \
+ { 575,11}, { 79,10}, { 159, 9}, { 319, 8}, \
+ { 639,10}, { 175, 9}, { 351, 8}, { 703,10}, \
+ { 191, 9}, { 383, 8}, { 767,10}, { 207, 9}, \
+ { 415, 8}, { 831,10}, { 223, 9}, { 447, 8}, \
+ { 895,12}, { 63,11}, { 127,10}, { 271,11}, \
+ { 143,10}, { 287, 9}, { 575, 8}, { 1215,11}, \
{ 159,10}, { 319, 9}, { 639,11}, { 175,10}, \
- { 351, 9}, { 703, 8}, { 1407,12}, { 95,11}, \
- { 191,10}, { 383,11}, { 207,10}, { 415, 9}, \
- { 831,11}, { 223,13}, { 63,12}, { 127,11}, \
- { 271,10}, { 543,11}, { 287,10}, { 575, 9}, \
+ { 351, 9}, { 703,11}, { 191,10}, { 383,11}, \
+ { 207,10}, { 415, 9}, { 831, 8}, { 1663,10}, \
+ { 447,13}, { 63,12}, { 127,11}, { 271,10}, \
+ { 543, 9}, { 1087,11}, { 287,10}, { 575, 9}, \
{ 1151,12}, { 159,11}, { 319,10}, { 639,11}, \
{ 351,10}, { 703,12}, { 191,11}, { 415,10}, \
- { 831,12}, { 223,11}, { 479,10}, { 959,13}, \
- { 127,12}, { 255,11}, { 511,10}, { 1023,12}, \
- { 287,11}, { 575,10}, { 1151,11}, { 607,12}, \
+ { 831,12}, { 223,11}, { 447,13}, { 127,12}, \
+ { 255,11}, { 543,12}, { 287,11}, { 607,12}, \
{ 319,11}, { 639,12}, { 351,11}, { 703,13}, \
{ 191,12}, { 415,11}, { 831,12}, { 479,14}, \
{ 127,13}, { 255,12}, { 607,13}, { 319,12}, \
- { 639,11}, { 1279,12}, { 703,13}, { 383,12}, \
- { 831,13}, { 447,12}, { 959,14}, { 255,13}, \
- { 511,12}, { 1087,13}, { 575,12}, { 1151,13}, \
- { 703,14}, { 383,13}, { 831,12}, { 1663,13}, \
- { 895,15}, { 255,14}, { 511,13}, { 1087,12}, \
- { 2175,13}, { 1215,14}, { 639,13}, { 1407,14}, \
- { 767,13}, { 1663,14}, { 895,13}, { 1791,15}, \
- { 511,14}, { 1023,13}, { 2047,14}, { 1151,13}, \
- { 2303,14}, { 1407,15}, { 32768,16}, { 65536,17}, \
+ { 703,11}, { 1407,13}, { 383,12}, { 831,13}, \
+ { 447,12}, { 959,14}, { 255,13}, { 511,12}, \
+ { 1023,13}, { 575,12}, { 1151,13}, { 639,12}, \
+ { 1279,13}, { 703,14}, { 383,13}, { 831,12}, \
+ { 1663,13}, { 895,15}, { 255,14}, { 511,13}, \
+ { 1151,14}, { 639,13}, { 1407,14}, { 767,13}, \
+ { 1663,14}, { 895,13}, { 1791,15}, { 511,14}, \
+ { 1023,13}, { 2047,14}, { 1151,13}, { 2303,14}, \
+ { 1407,15}, { 767,14}, { 1791,16}, { 511,15}, \
+ { 1023,14}, { 2303,15}, { 1279,14}, { 2815,15}, \
+ { 1535,14}, { 3199,15}, { 1791,16}, { 65536,17}, \
{ 131072,18}, { 262144,19}, { 524288,20}, {1048576,21}, \
{2097152,22}, {4194304,23}, {8388608,24} }
-#define SQR_FFT_TABLE3_SIZE 175
+#define SQR_FFT_TABLE3_SIZE 183
#define SQR_FFT_THRESHOLD 1728
#define MULLO_BASECASE_THRESHOLD 19
diff -r 7a022f693cad -r 05e6f6b1c3a8 mpn/x86/coreinhm/gmp-mparam.h
--- a/mpn/x86/coreinhm/gmp-mparam.h Mon Mar 17 22:44:30 2014 +0100
+++ b/mpn/x86/coreinhm/gmp-mparam.h Sat Mar 22 15:42:23 2014 +0100
@@ -1,6 +1,6 @@
/* x86/coreinhm gmp-mparam.h -- Compiler/machine parameter header file.
-Copyright 1991, 1993, 1994, 2000-2011 Free Software Foundation, Inc.
+Copyright 1991, 1993, 1994, 2000-2011, 2014 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
@@ -31,121 +31,194 @@
#define GMP_LIMB_BITS 32
#define GMP_LIMB_BYTES 4
-/* Generated by tuneup.c, 2011-11-25, gcc 4.5 */
+/* 2667 MHz Core i7 Nehalem */
+/* FFT tuning limit = 100000000 */
+/* Generated by tuneup.c, 2014-03-19, gcc 4.5 */
-#define MOD_1_NORM_THRESHOLD 24
+#define MOD_1_NORM_THRESHOLD 25
#define MOD_1_UNNORM_THRESHOLD 15
#define MOD_1N_TO_MOD_1_1_THRESHOLD 8
#define MOD_1U_TO_MOD_1_1_THRESHOLD 7
#define MOD_1_1_TO_MOD_1_2_THRESHOLD 11
#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 5
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 3
#define USE_PREINV_DIVREM_1 1 /* native */
+#define DIV_QR_1N_PI1_METHOD 1
+#define DIV_QR_1_NORM_THRESHOLD 18
+#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 16
+#define BMOD_1_TO_MOD_1_THRESHOLD 15
-#define MUL_TOOM22_THRESHOLD 28
-#define MUL_TOOM33_THRESHOLD 81
+#define MUL_TOOM22_THRESHOLD 26
+#define MUL_TOOM33_THRESHOLD 89
#define MUL_TOOM44_THRESHOLD 214
-#define MUL_TOOM6H_THRESHOLD 306
-#define MUL_TOOM8H_THRESHOLD 454
+#define MUL_TOOM6H_THRESHOLD 327
+#define MUL_TOOM8H_THRESHOLD 466
-#define MUL_TOOM32_TO_TOOM43_THRESHOLD 137
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 148
-#define MUL_TOOM42_TO_TOOM53_THRESHOLD 132
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 131
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 97
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 159
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 95
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 101
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 142
#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
-#define SQR_TOOM2_THRESHOLD 42
-#define SQR_TOOM3_THRESHOLD 149
-#define SQR_TOOM4_THRESHOLD 226
-#define SQR_TOOM6_THRESHOLD 333
-#define SQR_TOOM8_THRESHOLD 494
+#define SQR_TOOM2_THRESHOLD 44
+#define SQR_TOOM3_THRESHOLD 145
+#define SQR_TOOM4_THRESHOLD 232
+#define SQR_TOOM6_THRESHOLD 342
+#define SQR_TOOM8_THRESHOLD 502
#define MULMID_TOOM42_THRESHOLD 78
#define MULMOD_BNM1_THRESHOLD 17
#define SQRMOD_BNM1_THRESHOLD 21
-#define POWM_SEC_TABLE 2,33,294,1298,2870
-
#define MUL_FFT_MODF_THRESHOLD 606 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 606, 5}, { 28, 6}, { 15, 5}, { 33, 6}, \
- { 29, 7}, { 15, 6}, { 33, 7}, { 17, 6}, \
- { 36, 7}, { 19, 6}, { 39, 7}, { 23, 6}, \
- { 47, 7}, { 29, 8}, { 15, 7}, { 37, 8}, \
- { 19, 7}, { 41, 8}, { 23, 7}, { 47, 8}, \
+ { { 606, 5}, { 25, 6}, { 13, 5}, { 28, 6}, \
+ { 15, 5}, { 33, 6}, { 29, 7}, { 15, 6}, \
+ { 33, 7}, { 17, 6}, { 36, 7}, { 19, 6}, \
+ { 39, 7}, { 23, 6}, { 47, 7}, { 35, 8}, \
+ { 19, 7}, { 43, 8}, { 23, 7}, { 49, 8}, \
{ 31, 7}, { 63, 8}, { 43, 9}, { 23, 8}, \
{ 51, 9}, { 31, 8}, { 67, 9}, { 39, 8}, \
- { 79, 9}, { 47, 8}, { 95,10}, { 31, 9}, \
- { 79,10}, { 47, 9}, { 95,11}, { 31,10}, \
- { 63, 9}, { 135,10}, { 79, 9}, { 159,10}, \
- { 95, 9}, { 191,11}, { 63,10}, { 159,11}, \
- { 95,10}, { 191,12}, { 63,11}, { 127,10}, \
- { 255, 9}, { 511,10}, { 271,11}, { 159,10}, \
- { 319, 9}, { 639,10}, { 335,11}, { 191,10}, \
- { 383, 9}, { 767,10}, { 399,12}, { 4096,13}, \
- { 8192,14}, { 16384,15}, { 32768,16} }
-#define MUL_FFT_TABLE3_SIZE 63
-#define MUL_FFT_THRESHOLD 6784
-
-#define SQR_FFT_MODF_THRESHOLD 505 /* k = 5 */
-#define SQR_FFT_TABLE3 \
- { { 505, 5}, { 28, 6}, { 15, 5}, { 33, 6}, \
- { 17, 5}, { 35, 6}, { 29, 7}, { 15, 6}, \
- { 33, 7}, { 17, 6}, { 36, 7}, { 19, 6}, \
- { 39, 7}, { 23, 6}, { 47, 7}, { 29, 8}, \
More information about the gmp-commit
mailing list