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

mercurial at gmplib.org mercurial at gmplib.org
Sun Mar 18 10:32:49 CET 2012


details:   /var/hg/gmp/rev/09ae258d7dc9
changeset: 14764:09ae258d7dc9
user:      Torbjorn Granlund <tege at gmplib.org>
date:      Sun Mar 18 10:31:35 2012 +0100
description:
Update, to get BMOD_1_TO_MOD_1_THRESHOLD defined for fat binaries.

details:   /var/hg/gmp/rev/0acae62fa162
changeset: 14765:0acae62fa162
user:      Torbjorn Granlund <tege at gmplib.org>
date:      Sun Mar 18 10:32:41 2012 +0100
description:
Remove forgotten x86_64 reference.

diffstat:

 ChangeLog               |    7 +
 mpn/x86/p6/gcd_1.asm    |    9 --
 mpn/x86/p6/gmp-mparam.h |  181 +++++++++++++++++++++++++++++++++++++++--------
 3 files changed, 156 insertions(+), 41 deletions(-)

diffs (238 lines):

diff -r 775523081472 -r 0acae62fa162 ChangeLog
--- a/ChangeLog	Sat Mar 17 23:53:55 2012 +0100
+++ b/ChangeLog	Sun Mar 18 10:32:41 2012 +0100
@@ -1,3 +1,10 @@
+2012-03-18  Torbjorn Granlund  <tege at gmplib.org>
+
+	* mpn/x86/p6/gcd_1.asm: Remove forgotten x86_64 reference.
+
+	* mpn/x86/p6/gmp-mparam.h: Update, to get BMOD_1_TO_MOD_1_THRESHOLD
+	defined for fat binaries.
+
 2012-03-17  Torbjorn Granlund  <tege at gmplib.org>
 
 	* mpn/x86/k7/gcd_1.asm: Rewrite.
diff -r 775523081472 -r 0acae62fa162 mpn/x86/p6/gcd_1.asm
--- a/mpn/x86/p6/gcd_1.asm	Sat Mar 17 23:53:55 2012 +0100
+++ b/mpn/x86/p6/gcd_1.asm	Sun Mar 18 10:32:41 2012 +0100
@@ -49,15 +49,6 @@
 define(`v0',    `%edx')
 
 
-C Undo some configure cleverness.
-C The problem is that C only defines the '1c' variant, and that configure
-C therefore considers modexact_1c to be the base function.  It then adds a
-C special fat rule for mpn_modexact_1_odd, messing up things when a cpudep
-C gcd_1 exists without a corresponding cpudep mode1o.
-ifdef(`WANT_FAT_BINARY', `
-  define(`mpn_modexact_1_odd', `MPN_PREFIX`modexact_1_odd_x86_64'')')
-
-
 ASM_START()
 	TEXT
 	ALIGN(16)
diff -r 775523081472 -r 0acae62fa162 mpn/x86/p6/gmp-mparam.h
--- a/mpn/x86/p6/gmp-mparam.h	Sat Mar 17 23:53:55 2012 +0100
+++ b/mpn/x86/p6/gmp-mparam.h	Sun Mar 18 10:32:41 2012 +0100
@@ -1,7 +1,7 @@
 /* Intel P6 gmp-mparam.h -- Compiler/machine parameter header file.
 
-Copyright 1991, 1993, 1994, 1999, 2000, 2001, 2002, 2003 Free Software
-Foundation, Inc.
+Copyright 1991, 1993, 1994, 1999, 2000, 2001, 2002, 2003, 2008, 2009, 2010 Free
+Software Foundation, Inc.
 
 This file is part of the GNU MP Library.
 
@@ -23,44 +23,161 @@
 #define BYTES_PER_MP_LIMB 4
 
 
-/* NOTE: In a fat binary build SQR_TOOM2_THRESHOLD here cannot be smaller than
-   the value in mpn/x86/p6/mmx/gmp-mparam.h.  The former is used as a hard
-   limit in mpn/x86/p6/sqr_basecase.asm, and that file will be run by the
-   p6/mmx cpus (pentium2, pentium3).  */
+/* NOTE: In a fat binary build SQR_TOOM2_THRESHOLD here cannot be more than the
+   value in mpn/x86/p6/gmp-mparam.h.  The latter is used as a hard limit in
+   mpn/x86/p6/sqr_basecase.asm.  */
 
 
-/* 200MHz Pentium Pro */
+/* 1867 MHz P6 model 13 */
 
-/* Generated by tuneup.c, 2003-02-12, gcc 2.95 */
+#define MOD_1_NORM_THRESHOLD                 4
+#define MOD_1_UNNORM_THRESHOLD               4
+#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        11
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD         0  /* never mpn_mod_1s_2p */
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD      8
+#define USE_PREINV_DIVREM_1                  1  /* native */
+#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           21
 
-#define MUL_TOOM22_THRESHOLD             23
-#define MUL_TOOM33_THRESHOLD            140
+#define MUL_TOOM22_THRESHOLD                20
+#define MUL_TOOM33_THRESHOLD                74
+#define MUL_TOOM44_THRESHOLD               181
+#define MUL_TOOM6H_THRESHOLD               252
+#define MUL_TOOM8H_THRESHOLD               363
 
-#define SQR_BASECASE_THRESHOLD            0  /* always */
-#define SQR_TOOM2_THRESHOLD              52
-#define SQR_TOOM3_THRESHOLD             189
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD      73
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD     114
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD     115
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD      80
 
-#define DIV_SB_PREINV_THRESHOLD           0  /* always */
-#define DIV_DC_THRESHOLD                116
-#define POWM_THRESHOLD                  131
+#define SQR_BASECASE_THRESHOLD               0  /* always (native) */
+#define SQR_TOOM2_THRESHOLD                 30
+#define SQR_TOOM3_THRESHOLD                101
+#define SQR_TOOM4_THRESHOLD                154
+#define SQR_TOOM6_THRESHOLD                222
+#define SQR_TOOM8_THRESHOLD                527
 
-#define GCD_ACCEL_THRESHOLD               3
-#define JACOBI_BASE_METHOD                1
+#define MULMID_TOOM42_THRESHOLD             58
 
-#define USE_PREINV_DIVREM_1               0
-#define USE_PREINV_MOD_1                  1  /* native */
-#define DIVREM_2_THRESHOLD                0  /* always */
-#define DIVEXACT_1_THRESHOLD              0  /* always */
-#define MODEXACT_1_ODD_THRESHOLD          0  /* always */
+#define MULMOD_BNM1_THRESHOLD               13
+#define SQRMOD_BNM1_THRESHOLD               17
 
-#define GET_STR_DC_THRESHOLD             18
-#define GET_STR_PRECOMPUTE_THRESHOLD     23
-#define SET_STR_THRESHOLD              6093
+#define POWM_SEC_TABLE  4,23,258,768,2388
 
-#define MUL_FFT_TABLE  { 464, 928, 1920, 3584, 10240, 40960, 0 }
-#define MUL_FFT_MODF_THRESHOLD          360
-#define MUL_FFT_THRESHOLD              2816
+#define MUL_FFT_MODF_THRESHOLD             565  /* k = 5 */
+#define MUL_FFT_TABLE3                                      \
+  { {    565, 5}, {     25, 6}, {     13, 5}, {     27, 6}, \
+    {     25, 7}, {     13, 6}, {     28, 7}, {     15, 6}, \
+    {     31, 7}, {     17, 6}, {     35, 7}, {     27, 8}, \
+    {     15, 7}, {     35, 8}, {     19, 7}, {     41, 8}, \
+    {     23, 7}, {     47, 8}, {     27, 9}, {     15, 8}, \
+    {     31, 7}, {     63, 8}, {     39, 9}, {     23, 5}, \
+    {    383, 4}, {    991, 5}, {    511, 6}, {    267, 7}, \
+    {    157, 8}, {     91, 9}, {     47, 8}, {    111, 9}, \
+    {     63, 8}, {    127, 9}, {     79,10}, {     47, 9}, \
+    {     95,11}, {     31,10}, {     63, 9}, {    135,10}, \
+    {     79, 9}, {    159,10}, {     95,11}, {     63,10}, \
+    {    143, 9}, {    287,10}, {    159,11}, {     95,10}, \
+    {    191,12}, {     63,11}, {    127,10}, {    255, 9}, \
+    {    511,10}, {    271, 9}, {    543,10}, {    287,11}, \
+    {    159,10}, {    335, 9}, {    671,11}, {    191,10}, \
+    {    383, 9}, {    767,10}, {    399, 9}, {    799,10}, \
+    {    415,11}, {    223,12}, {    127,11}, {    255,10}, \
+    {    543, 9}, {   1087,11}, {    287,10}, {    607,11}, \
+    {    319,10}, {    671,12}, {    191,11}, {    383,10}, \
+    {    799,11}, {    415,10}, {    831,13}, {    127,12}, \
+    {    255,11}, {    543,10}, {   1087,11}, {    607,10}, \
+    {   1215,12}, {    319,11}, {    671,10}, {   1343,11}, \
+    {    735,10}, {   1471,12}, {    383,11}, {    799,10}, \
+    {   1599,11}, {    863,12}, {    447,11}, {    959,13}, \
+    {    255,12}, {    511,11}, {   1087,12}, {    575,11}, \
+    {   1215,12}, {    639,11}, {   1343,12}, {    703,11}, \
+    {   1471,13}, {    383,12}, {    831,11}, {   1727,12}, \
+    {    959,14}, {    255,13}, {    511,12}, {   1215,13}, \
+    {    639,12}, {   1471,11}, {   2943,13}, {    767,12}, \
+    {   1727,13}, {    895,12}, {   1919,14}, {    511,13}, \
+    {   1023,12}, {   2111,13}, {   1151,12}, {   2431,13}, \
+    {   1407,12}, {   2815,14}, {    767,13}, {   1663,12}, \
+    {   3455,13}, {   8192,14}, {  16384,15}, {  32768,16} }
+#define MUL_FFT_TABLE3_SIZE 132
+#define MUL_FFT_THRESHOLD                 6784
 
-#define SQR_FFT_TABLE  { 528, 1184, 1920, 4608, 14336, 40960, 0 }
-#define SQR_FFT_MODF_THRESHOLD          440
-#define SQR_FFT_THRESHOLD              2816
+#define SQR_FFT_MODF_THRESHOLD             472  /* k = 5 */
+#define SQR_FFT_TABLE3                                      \
+  { {    472, 5}, {     25, 6}, {     13, 5}, {     27, 6}, \
+    {     25, 7}, {     13, 6}, {     27, 7}, {     15, 6}, \
+    {     31, 7}, {     17, 6}, {     35, 7}, {     27, 8}, \
+    {     15, 7}, {     35, 8}, {     19, 7}, {     41, 8}, \
+    {     23, 7}, {     49, 8}, {     27, 9}, {     15, 8}, \
+    {     39, 9}, {     23, 8}, {     51,10}, {     15, 9}, \
+    {     31, 8}, {     63, 4}, {   1023, 8}, {     67, 9}, \
+    {     39, 5}, {    639, 4}, {   1471, 6}, {    383, 7}, \
+    {    209, 8}, {    119, 9}, {     63, 7}, {    255, 8}, \
+    {    139, 9}, {     71, 8}, {    143, 9}, {     79,10}, \
+    {     47, 9}, {     95,11}, {     31,10}, {     63, 9}, \
+    {    135,10}, {     79, 9}, {    159, 8}, {    319, 9}, \
+    {    167,10}, {     95,11}, {     63,10}, {    143, 9}, \
+    {    287,10}, {    159,11}, {     95,10}, {    191,12}, \
+    {     63,11}, {    127,10}, {    255, 9}, {    543, 8}, \
+    {   1087,10}, {    287, 9}, {    575,11}, {    159,10}, \
+    {    319, 9}, {    639,10}, {    335, 9}, {    671,10}, \
+    {    351, 9}, {    703,11}, {    191,10}, {    383, 9}, \
+    {    767,10}, {    399, 9}, {    799,10}, {    415, 9}, \
+    {    831,11}, {    223,12}, {    127,11}, {    255,10}, \
+    {    543, 9}, {   1087,11}, {    287,10}, {    607, 9}, \
+    {   1215,11}, {    319,10}, {    671, 9}, {   1343,11}, \
+    {    351,10}, {    703,12}, {    191,11}, {    383,10}, \
+    {    799,11}, {    415,10}, {    831,13}, {    127,12}, \
+    {    255,11}, {    543,10}, {   1087,11}, {    607,12}, \
+    {    319,11}, {    671,10}, {   1343,11}, {    735,12}, \
+    {    383,11}, {    799,10}, {   1599,11}, {    863,12}, \
+    {    447,11}, {    959,13}, {    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}, {   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}, \
+    {   2111,13}, {   1151,12}, {   2431,13}, {   1407,14}, \
+    {    767,13}, {   1663,12}, {   3455,13}, {   8192,14}, \
+    {  16384,15}, {  32768,16} }
+#define SQR_FFT_TABLE3_SIZE 146
+#define SQR_FFT_THRESHOLD                 5760
+
+#define MULLO_BASECASE_THRESHOLD             0  /* always */
+#define MULLO_DC_THRESHOLD                  33
+#define MULLO_MUL_N_THRESHOLD            13463
+
+#define DC_DIV_QR_THRESHOLD                 20
+#define DC_DIVAPPR_Q_THRESHOLD              56
+#define DC_BDIV_QR_THRESHOLD                60
+#define DC_BDIV_Q_THRESHOLD                134
+
+#define INV_MULMOD_BNM1_THRESHOLD           38
+#define INV_NEWTON_THRESHOLD                66
+#define INV_APPR_THRESHOLD                  63
+
+#define BINV_NEWTON_THRESHOLD              250
+#define REDC_1_TO_REDC_N_THRESHOLD          63
+
+#define MU_DIV_QR_THRESHOLD               1164
+#define MU_DIVAPPR_Q_THRESHOLD             979
+#define MUPI_DIV_QR_THRESHOLD               38
+#define MU_BDIV_QR_THRESHOLD              1442
+#define MU_BDIV_Q_THRESHOLD               1470
+
+#define MATRIX22_STRASSEN_THRESHOLD         17
+#define HGCD_THRESHOLD                      64
+#define HGCD_APPR_THRESHOLD                105
+#define HGCD_REDUCE_THRESHOLD             3524
+#define GCD_DC_THRESHOLD                   386
+#define GCDEXT_DC_THRESHOLD                309
+#define JACOBI_BASE_METHOD                   1
+
+#define GET_STR_DC_THRESHOLD                13
+#define GET_STR_PRECOMPUTE_THRESHOLD        26
+#define SET_STR_DC_THRESHOLD               587
+#define SET_STR_PRECOMPUTE_THRESHOLD      1104


More information about the gmp-commit mailing list