[Gmp-commit] /var/hg/gmp: 5 new changesets
mercurial at gmplib.org
mercurial at gmplib.org
Thu Nov 24 12:43:28 CET 2011
details: /var/hg/gmp/rev/352b9dcae2ac
changeset: 14471:352b9dcae2ac
user: Torbjorn Granlund <tege at gmplib.org>
date: Thu Nov 24 12:13:26 2011 +0100
description:
(tune_mu_div, tune_mu_bdiv): Up min_size to karatsuba's threshold.
details: /var/hg/gmp/rev/7bc2d0a2e916
changeset: 14472:7bc2d0a2e916
user: Torbjorn Granlund <tege at gmplib.org>
date: Thu Nov 24 12:17:47 2011 +0100
description:
Add power7/32 tuning file.
details: /var/hg/gmp/rev/5e8b8939b35d
changeset: 14473:5e8b8939b35d
user: Torbjorn Granlund <tege at gmplib.org>
date: Thu Nov 24 12:19:09 2011 +0100
description:
Retune.
details: /var/hg/gmp/rev/af85fae90e54
changeset: 14474:af85fae90e54
user: Torbjorn Granlund <tege at gmplib.org>
date: Thu Nov 24 12:39:37 2011 +0100
description:
*** empty log message ***
details: /var/hg/gmp/rev/dd533e46ca69
changeset: 14475:dd533e46ca69
user: Torbjorn Granlund <tege at gmplib.org>
date: Thu Nov 24 12:41:46 2011 +0100
description:
*** empty log message ***
diffstat:
ChangeLog | 7 +
mpn/powerpc32/p5/gmp-mparam.h | 139 ++++++++++++------------
mpn/powerpc32/p6/gmp-mparam.h | 192 ++++++++++++++++++----------------
mpn/powerpc32/p7/gmp-mparam.h | 149 +++++++++++++++++++++++++++
mpn/powerpc64/mode64/p3/gmp-mparam.h | 71 +++++++-----
mpn/powerpc64/mode64/p6/gmp-mparam.h | 42 +++---
mpn/s390_64/README | 77 ++++++++++++++
tune/tuneup.c | 8 +-
8 files changed, 470 insertions(+), 215 deletions(-)
diffs (truncated from 898 to 300 lines):
diff -r 9ae501782004 -r dd533e46ca69 ChangeLog
--- a/ChangeLog Tue Nov 22 22:05:25 2011 +0100
+++ b/ChangeLog Thu Nov 24 12:41:46 2011 +0100
@@ -1,3 +1,10 @@
+2011-11-24 Torbjorn Granlund <tege at gmplib.org>
+
+ * mpn/powerpc32/p7/gmp-mparam.h: New file.
+
+ * tune/tuneup.c (tune_mu_div, tune_mu_bdiv): Up min_size to karatsuba's
+ threshold.
+
2011-11-22 Torbjorn Granlund <tege at gmplib.org>
* mpn/powerpc64/mode64/p6/aorsmul_1.asm: New file.
diff -r 9ae501782004 -r dd533e46ca69 mpn/powerpc32/p5/gmp-mparam.h
--- a/mpn/powerpc32/p5/gmp-mparam.h Tue Nov 22 22:05:25 2011 +0100
+++ b/mpn/powerpc32/p5/gmp-mparam.h Thu Nov 24 12:41:46 2011 +0100
@@ -30,114 +30,117 @@
#define MOD_1_UNNORM_THRESHOLD 0 /* always */
#define MOD_1N_TO_MOD_1_1_THRESHOLD 8
#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 46
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 15
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 9
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD 50
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 18
#define USE_PREINV_DIVREM_1 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 62
+#define BMOD_1_TO_MOD_1_THRESHOLD 61
#define MUL_TOOM22_THRESHOLD 22
-#define MUL_TOOM33_THRESHOLD 78
+#define MUL_TOOM33_THRESHOLD 57
#define MUL_TOOM44_THRESHOLD 130
-#define MUL_TOOM6H_THRESHOLD 206
-#define MUL_TOOM8H_THRESHOLD 260
+#define MUL_TOOM6H_THRESHOLD 189
+#define MUL_TOOM8H_THRESHOLD 309
#define MUL_TOOM32_TO_TOOM43_THRESHOLD 89
#define MUL_TOOM32_TO_TOOM53_THRESHOLD 99
-#define MUL_TOOM42_TO_TOOM53_THRESHOLD 85
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 83
#define MUL_TOOM42_TO_TOOM63_THRESHOLD 88
-#define SQR_BASECASE_THRESHOLD 0 /* always */
-#define SQR_TOOM2_THRESHOLD 42
+#define SQR_BASECASE_THRESHOLD 6
+#define SQR_TOOM2_THRESHOLD 40
#define SQR_TOOM3_THRESHOLD 77
-#define SQR_TOOM4_THRESHOLD 169
-#define SQR_TOOM6_THRESHOLD 246
-#define SQR_TOOM8_THRESHOLD 381
+#define SQR_TOOM4_THRESHOLD 124
+#define SQR_TOOM6_THRESHOLD 140
+#define SQR_TOOM8_THRESHOLD 238
+
+#define MULMID_TOOM42_THRESHOLD 40
#define MULMOD_BNM1_THRESHOLD 15
-#define SQRMOD_BNM1_THRESHOLD 18
+#define SQRMOD_BNM1_THRESHOLD 16
-#define MUL_FFT_MODF_THRESHOLD 380 /* k = 5 */
+#define POWM_SEC_TABLE 4,29,252,840,2080
+
+#define MUL_FFT_MODF_THRESHOLD 412 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 380, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \
- { 13, 5}, { 27, 6}, { 21, 7}, { 11, 6}, \
- { 25, 7}, { 13, 6}, { 27, 7}, { 15, 6}, \
- { 31, 7}, { 21, 8}, { 11, 7}, { 27, 8}, \
+ { { 412, 5}, { 21, 6}, { 11, 5}, { 23, 6}, \
+ { 12, 5}, { 25, 6}, { 21, 7}, { 11, 6}, \
+ { 25, 7}, { 13, 6}, { 27, 7}, { 21, 8}, \
+ { 11, 7}, { 27, 8}, { 15, 7}, { 33, 8}, \
+ { 19, 7}, { 39, 8}, { 23, 7}, { 47, 8}, \
+ { 27, 9}, { 15, 8}, { 39, 9}, { 23, 8}, \
+ { 51,10}, { 15, 9}, { 31, 8}, { 67, 9}, \
+ { 39, 8}, { 79, 9}, { 55,10}, { 31, 9}, \
+ { 79,10}, { 47, 9}, { 95,11}, { 31,10}, \
+ { 63, 9}, { 135,10}, { 79, 9}, { 159,10}, \
+ { 95,11}, { 63,10}, { 127, 9}, { 255,10}, \
+ { 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}, { 671,10}, { 351, 9}, \
+ { 703,11}, { 191,10}, { 383, 9}, { 767,10}, \
+ { 415, 9}, { 831,11}, { 223,12}, { 4096,13}, \
+ { 8192,14}, { 16384,15}, { 32768,16} }
+#define MUL_FFT_TABLE3_SIZE 71
+#define MUL_FFT_THRESHOLD 4736
+
+#define SQR_FFT_MODF_THRESHOLD 340 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 340, 5}, { 21, 6}, { 11, 5}, { 23, 6}, \
+ { 21, 7}, { 11, 6}, { 24, 7}, { 13, 6}, \
+ { 27, 7}, { 21, 8}, { 11, 7}, { 27, 8}, \
{ 15, 7}, { 33, 8}, { 19, 7}, { 39, 8}, \
{ 23, 7}, { 47, 8}, { 27, 9}, { 15, 8}, \
- { 39, 9}, { 23, 8}, { 51,10}, { 15, 9}, \
- { 31, 8}, { 67, 9}, { 39, 8}, { 79, 9}, \
- { 47,10}, { 31, 9}, { 79,10}, { 47,11}, \
- { 31,10}, { 63, 9}, { 135,10}, { 79, 9}, \
+ { 39, 9}, { 23, 8}, { 47,10}, { 15, 9}, \
+ { 31, 8}, { 67, 9}, { 47,10}, { 31, 9}, \
+ { 71,10}, { 47,11}, { 31,10}, { 63, 9}, \
+ { 127, 8}, { 255, 9}, { 135,10}, { 79, 9}, \
{ 159,10}, { 95, 9}, { 191,11}, { 63,10}, \
- { 127, 9}, { 255,10}, { 143, 9}, { 287, 8}, \
- { 575,10}, { 159,11}, { 95, 9}, { 383,12}, \
- { 63,11}, { 127,10}, { 255, 9}, { 511,10}, \
- { 271, 9}, { 543,10}, { 287, 9}, { 575,11}, \
- { 159,10}, { 319, 9}, { 639,10}, { 335, 9}, \
- { 671,10}, { 351,11}, { 191,10}, { 383, 9}, \
- { 767,10}, { 415, 9}, { 831,11}, { 223,12}, \
- { 4096,13}, { 8192,14}, { 16384,15}, { 32768,16} }
-#define MUL_FFT_TABLE3_SIZE 76
-#define MUL_FFT_THRESHOLD 4736
-
-#define SQR_FFT_MODF_THRESHOLD 316 /* k = 5 */
-#define SQR_FFT_TABLE3 \
- { { 316, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \
- { 21, 7}, { 11, 6}, { 24, 7}, { 13, 6}, \
- { 27, 7}, { 15, 6}, { 31, 7}, { 21, 8}, \
- { 11, 7}, { 27, 8}, { 15, 7}, { 33, 8}, \
- { 19, 6}, { 77, 7}, { 39, 8}, { 23, 7}, \
- { 47, 8}, { 27, 9}, { 15, 8}, { 39, 9}, \
- { 23, 8}, { 47,10}, { 15, 7}, { 121, 9}, \
- { 31, 8}, { 67, 9}, { 39, 8}, { 79, 9}, \
- { 47,10}, { 31, 9}, { 79,10}, { 47,11}, \
- { 31,10}, { 63, 9}, { 127, 8}, { 255,10}, \
- { 79, 9}, { 159, 8}, { 319, 9}, { 175,10}, \
- { 95, 9}, { 191, 8}, { 383,11}, { 63,10}, \
{ 127, 9}, { 255, 8}, { 511, 9}, { 271,10}, \
{ 143, 9}, { 287, 8}, { 575, 9}, { 303,10}, \
- { 159, 9}, { 319,10}, { 175,11}, { 95,10}, \
- { 191, 9}, { 383,10}, { 207,12}, { 63,11}, \
+ { 159,11}, { 95,10}, { 191,12}, { 63,11}, \
{ 127,10}, { 255, 9}, { 511,10}, { 271, 9}, \
{ 543,10}, { 287, 9}, { 575,10}, { 303,11}, \
{ 159,10}, { 319, 9}, { 639,10}, { 335, 9}, \
{ 671,10}, { 351,11}, { 191,10}, { 383, 9}, \
{ 767,10}, { 415,11}, { 223,10}, { 447,12}, \
{ 4096,13}, { 8192,14}, { 16384,15}, { 32768,16} }
-#define SQR_FFT_TABLE3_SIZE 88
+#define SQR_FFT_TABLE3_SIZE 76
#define SQR_FFT_THRESHOLD 3712
#define MULLO_BASECASE_THRESHOLD 2
#define MULLO_DC_THRESHOLD 68
#define MULLO_MUL_N_THRESHOLD 9236
-#define DC_DIV_QR_THRESHOLD 70
-#define DC_DIVAPPR_Q_THRESHOLD 238
+#define DC_DIV_QR_THRESHOLD 69
+#define DC_DIVAPPR_Q_THRESHOLD 220
#define DC_BDIV_QR_THRESHOLD 75
#define DC_BDIV_Q_THRESHOLD 188
#define INV_MULMOD_BNM1_THRESHOLD 54
-#define INV_NEWTON_THRESHOLD 250
-#define INV_APPR_THRESHOLD 246
+#define INV_NEWTON_THRESHOLD 230
+#define INV_APPR_THRESHOLD 230
-#define BINV_NEWTON_THRESHOLD 375
+#define BINV_NEWTON_THRESHOLD 278
#define REDC_1_TO_REDC_N_THRESHOLD 87
-#define MU_DIV_QR_THRESHOLD 1334
-#define MU_DIVAPPR_Q_THRESHOLD 1387
-#define MUPI_DIV_QR_THRESHOLD 114
-#define MU_BDIV_QR_THRESHOLD 1078
-#define MU_BDIV_Q_THRESHOLD 1334
+#define MU_DIV_QR_THRESHOLD 1210
+#define MU_DIVAPPR_Q_THRESHOLD 1308
+#define MUPI_DIV_QR_THRESHOLD 106
+#define MU_BDIV_QR_THRESHOLD 1017
+#define MU_BDIV_Q_THRESHOLD 1210
#define MATRIX22_STRASSEN_THRESHOLD 14
-#define HGCD_THRESHOLD 104
-#define GCD_DC_THRESHOLD 424
-#define GCDEXT_DC_THRESHOLD 321
+#define HGCD_THRESHOLD 110
+#define HGCD_APPR_THRESHOLD 138
+#define HGCD_REDUCE_THRESHOLD 2578
+#define GCD_DC_THRESHOLD 408
+#define GCDEXT_DC_THRESHOLD 298
#define JACOBI_BASE_METHOD 4
-#define GET_STR_DC_THRESHOLD 12
-#define GET_STR_PRECOMPUTE_THRESHOLD 23
-#define SET_STR_DC_THRESHOLD 454
-#define SET_STR_PRECOMPUTE_THRESHOLD 1074
+#define GET_STR_DC_THRESHOLD 13
+#define GET_STR_PRECOMPUTE_THRESHOLD 24
+#define SET_STR_DC_THRESHOLD 527
+#define SET_STR_PRECOMPUTE_THRESHOLD 1090
diff -r 9ae501782004 -r dd533e46ca69 mpn/powerpc32/p6/gmp-mparam.h
--- a/mpn/powerpc32/p6/gmp-mparam.h Tue Nov 22 22:05:25 2011 +0100
+++ b/mpn/powerpc32/p6/gmp-mparam.h Thu Nov 24 12:41:46 2011 +0100
@@ -29,115 +29,127 @@
#define MOD_1_NORM_THRESHOLD 3
#define MOD_1_UNNORM_THRESHOLD 0 /* always */
#define MOD_1N_TO_MOD_1_1_THRESHOLD 3
-#define MOD_1U_TO_MOD_1_1_THRESHOLD 8
-#define MOD_1_1_TO_MOD_1_2_THRESHOLD 0 /* never mpn_mod_1_1p */
-#define MOD_1_2_TO_MOD_1_4_THRESHOLD 15
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 9
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 3
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD MP_SIZE_T_MAX
+#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
+#define DIV_QR_2_PI2_THRESHOLD MP_SIZE_T_MAX /* never */
#define DIVEXACT_1_THRESHOLD 0 /* always */
#define BMOD_1_TO_MOD_1_THRESHOLD MP_SIZE_T_MAX /* never */
-#define MUL_TOOM22_THRESHOLD 34
-#define MUL_TOOM33_THRESHOLD 70
-#define MUL_TOOM44_THRESHOLD 187
-#define MUL_TOOM6H_THRESHOLD 286
-#define MUL_TOOM8H_THRESHOLD 321
+#define MUL_TOOM22_THRESHOLD 19
+#define MUL_TOOM33_THRESHOLD 55
+#define MUL_TOOM44_THRESHOLD 88
+#define MUL_TOOM6H_THRESHOLD 137
+#define MUL_TOOM8H_THRESHOLD 181
-#define MUL_TOOM32_TO_TOOM43_THRESHOLD 110
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 118
-#define MUL_TOOM42_TO_TOOM53_THRESHOLD 107
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 145
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 57
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 56
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 57
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 56
#define SQR_BASECASE_THRESHOLD 0 /* always */
-#define SQR_TOOM2_THRESHOLD 68
-#define SQR_TOOM3_THRESHOLD 113
-#define SQR_TOOM4_THRESHOLD 312
-#define SQR_TOOM6_THRESHOLD 330
-#define SQR_TOOM8_THRESHOLD 357
+#define SQR_TOOM2_THRESHOLD 30
+#define SQR_TOOM3_THRESHOLD 56
+#define SQR_TOOM4_THRESHOLD 130
+#define SQR_TOOM6_THRESHOLD 189
+#define SQR_TOOM8_THRESHOLD 296
-#define MULMOD_BNM1_THRESHOLD 19
-#define SQRMOD_BNM1_THRESHOLD 20
+#define MULMID_TOOM42_THRESHOLD 26
-#define MUL_FFT_MODF_THRESHOLD 304 /* k = 5 */
+#define MULMOD_BNM1_THRESHOLD 7
+#define SQRMOD_BNM1_THRESHOLD 12
+
+#define POWM_SEC_TABLE 2,26,127,453,1068
+
+#define MUL_FFT_MODF_THRESHOLD 212 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 304, 5}, { 17, 6}, { 9, 5}, { 19, 6}, \
- { 10, 5}, { 21, 6}, { 17, 7}, { 9, 6}, \
- { 20, 7}, { 11, 6}, { 24, 7}, { 13, 8}, \
- { 7, 7}, { 21, 8}, { 11, 7}, { 27, 9}, \
- { 7, 8}, { 15, 7}, { 33, 8}, { 19, 7}, \
- { 41, 8}, { 23, 7}, { 47, 8}, { 27, 9}, \
+ { { 212, 5}, { 13, 6}, { 7, 5}, { 15, 6}, \
+ { 13, 7}, { 7, 6}, { 16, 7}, { 9, 6}, \
+ { 19, 7}, { 13, 8}, { 7, 7}, { 19, 8}, \
+ { 11, 7}, { 25, 9}, { 7, 8}, { 15, 7}, \
+ { 31, 8}, { 19, 7}, { 39, 8}, { 23, 9}, \
{ 15, 8}, { 39, 9}, { 23, 8}, { 47,10}, \
- { 15, 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}, { 127, 8}, { 255, 9}, { 135,10}, \
- { 79, 9}, { 159, 8}, { 319,10}, { 95, 9}, \
- { 191, 8}, { 383,11}, { 63,10}, { 127, 9}, \
- { 255, 8}, { 511, 9}, { 271,10}, { 143, 9}, \
- { 287,10}, { 159, 9}, { 319,11}, { 95,10}, \
- { 191, 9}, { 383,12}, { 63,11}, { 127,10}, \
- { 255, 9}, { 511,10}, { 271, 9}, { 543,10}, \
- { 287,11}, { 159,10}, { 319, 9}, { 639,10}, \
- { 351,11}, { 191,10}, { 383, 9}, { 767,10}, \
- { 415,11}, { 223,10}, { 447,12}, { 4096,13}, \
- { 8192,14}, { 16384,15}, { 32768,16} }
-#define MUL_FFT_TABLE3_SIZE 83
-#define MUL_FFT_THRESHOLD 4736
+ { 15, 9}, { 31, 8}, { 63, 9}, { 39, 8}, \
+ { 79, 9}, { 47,10}, { 31, 9}, { 63, 8}, \
+ { 127, 9}, { 71, 8}, { 143, 7}, { 287, 9}, \
+ { 79,10}, { 47,11}, { 31,10}, { 63, 9}, \
+ { 127, 8}, { 255, 7}, { 511, 9}, { 143, 8}, \
More information about the gmp-commit
mailing list