[Gmp-commit] /var/hg/gmp: 3 new changesets
mercurial at gmplib.org
mercurial at gmplib.org
Thu Sep 5 02:00:41 CEST 2013
details: /var/hg/gmp/rev/a88e54d52a9b
changeset: 15971:a88e54d52a9b
user: Torbjorn Granlund <tege at gmplib.org>
date: Thu Sep 05 01:54:32 2013 +0200
description:
Extend FFT tables.
details: /var/hg/gmp/rev/b9c897951cdb
changeset: 15972:b9c897951cdb
user: Torbjorn Granlund <tege at gmplib.org>
date: Thu Sep 05 01:56:10 2013 +0200
description:
Retune.
details: /var/hg/gmp/rev/fb4b3934029f
changeset: 15973:fb4b3934029f
user: Torbjorn Granlund <tege at gmplib.org>
date: Thu Sep 05 02:00:18 2013 +0200
description:
Streamline.
diffstat:
mpn/powerpc32/gmp-mparam.h | 137 ++++++++----------------
mpn/x86_64/bd1/gmp-mparam.h | 136 ++++++++++++------------
mpn/x86_64/bobcat/gmp-mparam.h | 139 ++++++++++++-------------
mpn/x86_64/coreihwl/aorsmul_1.asm | 19 +-
mpn/x86_64/coreihwl/gmp-mparam.h | 108 +++++++++++++------
mpn/x86_64/coreinhm/gmp-mparam.h | 209 ++++++++++++++++---------------------
6 files changed, 357 insertions(+), 391 deletions(-)
diffs (truncated from 1006 to 300 lines):
diff -r fd4d46ab4503 -r fb4b3934029f mpn/powerpc32/gmp-mparam.h
--- a/mpn/powerpc32/gmp-mparam.h Wed Sep 04 12:45:17 2013 +0200
+++ b/mpn/powerpc32/gmp-mparam.h Thu Sep 05 02:00:18 2013 +0200
@@ -59,12 +59,12 @@
#define MUL_TOOM42_TO_TOOM63_THRESHOLD 72
#define MUL_TOOM43_TO_TOOM54_THRESHOLD 82
-#define SQR_BASECASE_THRESHOLD 4
-#define SQR_TOOM2_THRESHOLD 26
-#define SQR_TOOM3_THRESHOLD 77
-#define SQR_TOOM4_THRESHOLD 136
+#define SQR_BASECASE_THRESHOLD 0 /* always */
+#define SQR_TOOM2_THRESHOLD 22
+#define SQR_TOOM3_THRESHOLD 73
+#define SQR_TOOM4_THRESHOLD 130
#define SQR_TOOM6_THRESHOLD 189
-#define SQR_TOOM8_THRESHOLD 284
+#define SQR_TOOM8_THRESHOLD 309
#define MULMID_TOOM42_THRESHOLD 32
@@ -73,101 +73,58 @@
#define MUL_FFT_MODF_THRESHOLD 284 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 284, 5}, { 17, 6}, { 9, 5}, { 19, 6}, \
- { 13, 7}, { 7, 6}, { 17, 7}, { 9, 6}, \
- { 20, 7}, { 11, 6}, { 23, 7}, { 13, 8}, \
- { 7, 7}, { 19, 8}, { 11, 7}, { 25, 9}, \
- { 7, 8}, { 15, 7}, { 33, 8}, { 19, 7}, \
- { 39, 8}, { 23, 7}, { 47, 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}, { 71, 8}, \
- { 143, 9}, { 79,10}, { 47, 9}, { 95,11}, \
- { 31,10}, { 63, 9}, { 127, 8}, { 255, 9}, \
- { 135, 8}, { 271, 9}, { 143,10}, { 79, 9}, \
- { 159, 8}, { 319, 9}, { 175,10}, { 95, 9}, \
- { 191, 8}, { 383, 9}, { 207, 8}, { 415,11}, \
- { 63,10}, { 127, 9}, { 255, 8}, { 511, 9}, \
- { 271,10}, { 143, 9}, { 287, 8}, { 575,10}, \
- { 159, 9}, { 319,10}, { 175,11}, { 95,10}, \
- { 191, 9}, { 383,10}, { 207, 9}, { 415, 8}, \
- { 831,12}, { 63,11}, { 127,10}, { 255, 9}, \
- { 511,10}, { 271, 9}, { 543, 8}, { 1087,10}, \
- { 287, 9}, { 575,11}, { 159,10}, { 319, 9}, \
- { 639,10}, { 351, 9}, { 703,11}, { 191,10}, \
- { 415, 9}, { 831,11}, { 223,10}, { 447, 9}, \
- { 895,10}, { 479, 9}, { 959,12}, { 127,11}, \
- { 255,10}, { 543, 9}, { 1087,11}, { 287,10}, \
- { 607,11}, { 319,10}, { 639,11}, { 351,10}, \
- { 703, 9}, { 1407,12}, { 191,11}, { 383,10}, \
- { 767,11}, { 415,10}, { 831,11}, { 447,10}, \
- { 895,11}, { 479,10}, { 959,13}, { 127,12}, \
- { 255,11}, { 543,10}, { 1087,11}, { 607,12}, \
- { 319,11}, { 639,10}, { 1279,11}, { 703,10}, \
- { 1407,12}, { 383,11}, { 831,12}, { 447,11}, \
- { 959,10}, { 1919,13}, { 255,12}, { 511,11}, \
- { 1087,12}, { 575,11}, { 1215,10}, { 2431,12}, \
- { 639,11}, { 1279,12}, { 703,11}, { 1407,13}, \
- { 383,12}, { 959,11}, { 1919,14}, { 255,13}, \
- { 511,12}, { 1215,11}, { 2431,13}, { 639,12}, \
- { 1471,13}, { 767,12}, { 1599,13}, { 895,12}, \
- { 1919,14}, { 511,13}, { 1023,12}, { 2111,13}, \
- { 1151,12}, { 2431,13}, { 1407,14}, { 767,13}, \
- { 1535,12}, { 3071,13}, { 1919,12}, { 3839,15}, \
- { 32768,16} }
-#define MUL_FFT_TABLE3_SIZE 165
-#define MUL_FFT_THRESHOLD 3392
-
-#define SQR_FFT_MODF_THRESHOLD 236 /* k = 5 */
-#define SQR_FFT_TABLE3 \
- { { 248, 5}, { 17, 6}, { 9, 5}, { 19, 6}, \
+ { { 284, 5}, { 15, 6}, { 8, 5}, { 17, 6}, \
{ 17, 7}, { 9, 6}, { 20, 7}, { 11, 6}, \
{ 23, 7}, { 13, 8}, { 7, 7}, { 19, 8}, \
{ 11, 7}, { 25, 9}, { 7, 8}, { 15, 7}, \
{ 33, 8}, { 19, 7}, { 39, 8}, { 23, 7}, \
{ 47, 8}, { 27, 9}, { 15, 8}, { 39, 9}, \
{ 23, 8}, { 47,10}, { 15, 9}, { 31, 8}, \
- { 63, 9}, { 39, 8}, { 79, 9}, { 47,10}, \
- { 31, 9}, { 63, 8}, { 127, 9}, { 71, 8}, \
- { 143, 9}, { 79,10}, { 47, 9}, { 95,11}, \
- { 31,10}, { 63, 9}, { 127, 8}, { 255, 7}, \
- { 511, 9}, { 143,10}, { 79, 9}, { 159, 8}, \
- { 319, 9}, { 175, 8}, { 351,10}, { 95, 9}, \
- { 191, 8}, { 383, 9}, { 207, 8}, { 415,11}, \
- { 63,10}, { 127, 9}, { 255, 8}, { 511,10}, \
+ { 67, 9}, { 39, 8}, { 79, 9}, { 47, 8}, \
+ { 95,10}, { 31, 9}, { 71, 8}, { 143, 9}, \
+ { 79,10}, { 47, 9}, { 95,11}, { 31,10}, \
+ { 63, 9}, { 127, 8}, { 255, 9}, { 135, 8}, \
+ { 271, 9}, { 143,10}, { 79, 9}, { 159, 8}, \
+ { 319, 9}, { 175,10}, { 95, 9}, { 191, 8}, \
+ { 383, 9}, { 207, 8}, { 415,11}, { 63,10}, \
+ { 127, 9}, { 255, 8}, { 511, 9}, { 271,10}, \
{ 143, 9}, { 287, 8}, { 575,10}, { 159, 9}, \
- { 319,10}, { 175, 9}, { 351,11}, { 95,10}, \
- { 191, 9}, { 383,10}, { 207, 9}, { 415, 8}, \
- { 831,12}, { 63,11}, { 127,10}, { 255, 9}, \
- { 511,10}, { 271, 9}, { 543,10}, { 287, 9}, \
- { 575,11}, { 159,10}, { 319, 9}, { 639,10}, \
- { 351, 9}, { 703, 8}, { 1407, 9}, { 735,11}, \
- { 191,10}, { 415, 9}, { 831,11}, { 223,10}, \
- { 447, 9}, { 895,10}, { 479,12}, { 127,11}, \
- { 255,10}, { 543,11}, { 287,10}, { 607,11}, \
- { 319,10}, { 639,11}, { 351,10}, { 703, 9}, \
- { 1407,12}, { 191,11}, { 383,13}, { 127,12}, \
- { 255,11}, { 543,10}, { 1087,11}, { 575,10}, \
- { 1151,12}, { 319,11}, { 703,10}, { 1407,12}, \
- { 383,11}, { 831,12}, { 447,11}, { 959,13}, \
- { 255,12}, { 511,11}, { 1087,12}, { 575,11}, \
- { 1215,12}, { 639,11}, { 1279,12}, { 703,11}, \
- { 1407,13}, { 383,12}, { 959,14}, { 255,13}, \
- { 511,12}, { 1215,11}, { 2431,13}, { 639,12}, \
- { 1471,13}, { 767,12}, { 1599,13}, { 895,12}, \
- { 1919,14}, { 511,13}, { 1023,12}, { 2111,13}, \
- { 1151,12}, { 2431,13}, { 1407,12}, { 2815,14}, \
- { 767,13}, { 1535,12}, { 3199,13}, { 1919,15}, \
- { 32768,16} }
-#define SQR_FFT_TABLE3_SIZE 153
-#define SQR_FFT_THRESHOLD 2368
+ { 319,10}, { 175,11}, { 95,10}, { 191, 9}, \
+ { 383,10}, { 207, 9}, { 415, 8}, { 831,12}, \
+ { 4096,13}, { 8192,14}, { 16384,15}, { 32768,16} }
+#define MUL_FFT_TABLE3_SIZE 76
+#define MUL_FFT_THRESHOLD 3712
+
+#define SQR_FFT_MODF_THRESHOLD 248 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 248, 5}, { 17, 6}, { 9, 5}, { 19, 6}, \
+ { 17, 7}, { 9, 6}, { 20, 7}, { 11, 6}, \
+ { 23, 7}, { 13, 8}, { 7, 7}, { 19, 8}, \
+ { 11, 7}, { 25, 9}, { 7, 8}, { 15, 7}, \
+ { 33, 8}, { 19, 7}, { 39, 8}, { 27, 9}, \
+ { 15, 8}, { 39, 9}, { 23, 8}, { 47,10}, \
+ { 15, 9}, { 31, 8}, { 63, 9}, { 39, 8}, \
+ { 79, 9}, { 47,10}, { 31, 9}, { 63, 8}, \
+ { 127, 9}, { 71, 8}, { 143, 9}, { 79,10}, \
+ { 47, 9}, { 95,11}, { 31,10}, { 63, 9}, \
+ { 127, 8}, { 255, 7}, { 511, 9}, { 143,10}, \
+ { 79, 9}, { 159, 8}, { 319, 9}, { 175, 8}, \
+ { 351,10}, { 95, 9}, { 191, 8}, { 383, 9}, \
+ { 207, 8}, { 415, 7}, { 831,11}, { 63,10}, \
+ { 127, 9}, { 255, 8}, { 511,10}, { 143, 9}, \
+ { 287, 8}, { 575,10}, { 159, 9}, { 319,10}, \
+ { 175, 9}, { 351,11}, { 95,10}, { 191, 9}, \
+ { 383,10}, { 207, 9}, { 415, 8}, { 831,12}, \
+ { 4096,13}, { 8192,14}, { 16384,15}, { 32768,16} }
+#define SQR_FFT_TABLE3_SIZE 76
+#define SQR_FFT_THRESHOLD 2688
#define MULLO_BASECASE_THRESHOLD 0 /* always */
#define MULLO_DC_THRESHOLD 45
#define MULLO_MUL_N_THRESHOLD 6633
#define DC_DIV_QR_THRESHOLD 43
-#define DC_DIVAPPR_Q_THRESHOLD 153
+#define DC_DIVAPPR_Q_THRESHOLD 148
#define DC_BDIV_QR_THRESHOLD 54
#define DC_BDIV_Q_THRESHOLD 124
@@ -181,10 +138,10 @@
#define MU_DIV_QR_THRESHOLD 998
#define MU_DIVAPPR_Q_THRESHOLD 1037
#define MUPI_DIV_QR_THRESHOLD 84
-#define MU_BDIV_QR_THRESHOLD 748
-#define MU_BDIV_Q_THRESHOLD 942
+#define MU_BDIV_QR_THRESHOLD 872
+#define MU_BDIV_Q_THRESHOLD 1078
-#define POWM_SEC_TABLE 4,23,164,616,1812
+#define POWM_SEC_TABLE 2,20,103,429,1379
#define MATRIX22_STRASSEN_THRESHOLD 11
#define HGCD_THRESHOLD 118
diff -r fd4d46ab4503 -r fb4b3934029f mpn/x86_64/bd1/gmp-mparam.h
--- a/mpn/x86_64/bd1/gmp-mparam.h Wed Sep 04 12:45:17 2013 +0200
+++ b/mpn/x86_64/bd1/gmp-mparam.h Thu Sep 05 02:00:18 2013 +0200
@@ -23,124 +23,126 @@
#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 3
-#define MOD_1_1_TO_MOD_1_2_THRESHOLD 24
+#define MOD_1N_TO_MOD_1_1_THRESHOLD 4
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 4
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 21
#define MOD_1_2_TO_MOD_1_4_THRESHOLD 34
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 11
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 10
#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 20
-#define MUL_TOOM22_THRESHOLD 16
+#define MUL_TOOM22_THRESHOLD 18
#define MUL_TOOM33_THRESHOLD 57
#define MUL_TOOM44_THRESHOLD 154
#define MUL_TOOM6H_THRESHOLD 250
-#define MUL_TOOM8H_THRESHOLD 309
+#define MUL_TOOM8H_THRESHOLD 406
#define MUL_TOOM32_TO_TOOM43_THRESHOLD 97
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 108
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 115
#define MUL_TOOM42_TO_TOOM53_THRESHOLD 105
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 109
-#define MUL_TOOM43_TO_TOOM54_THRESHOLD 143
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 113
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 154
#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
-#define SQR_TOOM2_THRESHOLD 24
-#define SQR_TOOM3_THRESHOLD 139
-#define SQR_TOOM4_THRESHOLD 218
-#define SQR_TOOM6_THRESHOLD 318
-#define SQR_TOOM8_THRESHOLD 434
+#define SQR_TOOM2_THRESHOLD 20
+#define SQR_TOOM3_THRESHOLD 81
+#define SQR_TOOM4_THRESHOLD 202
+#define SQR_TOOM6_THRESHOLD 303
+#define SQR_TOOM8_THRESHOLD 430
-#define MULMID_TOOM42_THRESHOLD 22
+#define MULMID_TOOM42_THRESHOLD 20
-#define MULMOD_BNM1_THRESHOLD 11
-#define SQRMOD_BNM1_THRESHOLD 13
+#define MULMOD_BNM1_THRESHOLD 12
+#define SQRMOD_BNM1_THRESHOLD 14
-#define MUL_FFT_MODF_THRESHOLD 396 /* k = 5 */
+#define MUL_FFT_MODF_THRESHOLD 340 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 380, 5}, { 21, 6}, { 11, 5}, { 23, 6}, \
- { 23, 7}, { 12, 6}, { 25, 7}, { 13, 6}, \
- { 27, 7}, { 15, 6}, { 31, 7}, { 25, 8}, \
+ { { 340, 5}, { 11, 4}, { 23, 5}, { 19, 6}, \
+ { 10, 5}, { 21, 6}, { 11, 5}, { 23, 6}, \
+ { 21, 7}, { 11, 6}, { 24, 7}, { 15, 6}, \
+ { 31, 7}, { 21, 8}, { 11, 7}, { 25, 8}, \
{ 13, 7}, { 27, 8}, { 15, 7}, { 32, 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}, { 31, 8}, { 63, 9}, { 35, 8}, \
- { 71, 9}, { 39,10}, { 23, 9}, { 51,11}, \
+ { 15, 9}, { 39,10}, { 23, 9}, { 51,11}, \
{ 15,10}, { 31, 9}, { 71,10}, { 39, 9}, \
- { 87,10}, { 47, 9}, { 99,10}, { 55,11}, \
- { 31,10}, { 87,11}, { 47,10}, { 103,12}, \
+ { 83,10}, { 47, 9}, { 99,10}, { 55,11}, \
+ { 31,10}, { 79,11}, { 47,10}, { 95,12}, \
{ 31,11}, { 63,10}, { 135,11}, { 79,10}, \
- { 167,11}, { 95,12}, { 63,11}, { 127,10}, \
- { 255,11}, { 143,10}, { 287, 9}, { 575,10}, \
+ { 167,11}, { 95, 9}, { 383,11}, { 111,12}, \
+ { 63,11}, { 127,10}, { 255,11}, { 143,10}, \
{ 303,11}, { 159,12}, { 95,11}, { 191,13}, \
{ 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 75
-#define MUL_FFT_THRESHOLD 4736
+#define MUL_FFT_THRESHOLD 3712
-#define SQR_FFT_MODF_THRESHOLD 340 /* k = 5 */
+#define SQR_FFT_MODF_THRESHOLD 348 /* k = 5 */
#define SQR_FFT_TABLE3 \
- { { 332, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \
- { 11, 5}, { 23, 6}, { 25, 7}, { 25, 8}, \
+ { { 348, 5}, { 11, 4}, { 23, 5}, { 19, 6}, \
+ { 11, 5}, { 23, 6}, { 21, 7}, { 11, 6}, \
+ { 25, 7}, { 21, 8}, { 11, 7}, { 25, 8}, \
{ 13, 7}, { 27, 8}, { 15, 7}, { 31, 8}, \
- { 21, 9}, { 11, 8}, { 27, 9}, { 15, 8}, \
- { 33, 9}, { 19, 8}, { 41, 9}, { 23, 8}, \
- { 47, 9}, { 27,10}, { 15, 9}, { 39,10}, \
- { 23, 9}, { 47,11}, { 15,10}, { 31, 9}, \
- { 67,10}, { 39, 9}, { 79,10}, { 47, 9}, \
- { 95,10}, { 55,11}, { 31,10}, { 79,11}, \
+ { 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}, { 51,11}, \
+ { 15,10}, { 31, 9}, { 67,10}, { 39, 9}, \
+ { 79,10}, { 47,11}, { 31,10}, { 79,11}, \
{ 47,10}, { 95,12}, { 31,11}, { 63,10}, \
{ 127, 9}, { 255,10}, { 135,11}, { 79,10}, \
- { 159,11}, { 95,10}, { 191,12}, { 63,11}, \
- { 127,10}, { 255, 9}, { 511,10}, { 271,11}, \
- { 143,10}, { 303,11}, { 159,10}, { 319,12}, \
- { 95,11}, { 191,10}, { 383,11}, { 207,13}, \
- { 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 71
More information about the gmp-commit
mailing list