[Gmp-commit] /var/hg/gmp: Retune.
mercurial at gmplib.org
mercurial at gmplib.org
Wed Oct 14 17:47:11 UTC 2015
details: /var/hg/gmp/rev/15ed2cbb2b45
changeset: 16860:15ed2cbb2b45
user: Torbjorn Granlund <torbjorng at google.com>
date: Wed Oct 14 19:47:08 2015 +0200
description:
Retune.
diffstat:
mpn/x86_64/coreibwl/gmp-mparam.h | 236 +++++++++++++++++++-------------------
1 files changed, 121 insertions(+), 115 deletions(-)
diffs (truncated from 307 to 300 lines):
diff -r a5fe546688db -r 15ed2cbb2b45 mpn/x86_64/coreibwl/gmp-mparam.h
--- a/mpn/x86_64/coreibwl/gmp-mparam.h Wed Oct 14 08:28:43 2015 +0200
+++ b/mpn/x86_64/coreibwl/gmp-mparam.h Wed Oct 14 19:47:08 2015 +0200
@@ -36,15 +36,15 @@
#undef HAVE_NATIVE_mpn_addmul_2
/* 2100 MHz Intel i3-5100 */
-/* FFT tuning limit = 100 M */
-/* Generated by tuneup.c, 2015-10-06, gcc 4.8 */
+/* FFT tuning limit = 200 M */
+/* Generated by tuneup.c, 2015-10-12, 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 4
#define MOD_1U_TO_MOD_1_1_THRESHOLD 3
#define MOD_1_1_TO_MOD_1_2_THRESHOLD 15
-#define MOD_1_2_TO_MOD_1_4_THRESHOLD 28
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD 26
#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 9
#define USE_PREINV_DIVREM_1 1 /* native */
#define DIV_QR_1_NORM_THRESHOLD 1
@@ -53,166 +53,172 @@
#define DIVEXACT_1_THRESHOLD 0 /* always (native) */
#define BMOD_1_TO_MOD_1_THRESHOLD 20
-#define MUL_TOOM22_THRESHOLD 24
-#define MUL_TOOM33_THRESHOLD 69
-#define MUL_TOOM44_THRESHOLD 202
-#define MUL_TOOM6H_THRESHOLD 418
-#define MUL_TOOM8H_THRESHOLD 0 /* always */
+#define MUL_TOOM22_THRESHOLD 28
+#define MUL_TOOM33_THRESHOLD 75
+#define MUL_TOOM44_THRESHOLD 218
+#define MUL_TOOM6H_THRESHOLD 354
+#define MUL_TOOM8H_THRESHOLD 434
-#define MUL_TOOM32_TO_TOOM43_THRESHOLD 129
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 160
-#define MUL_TOOM42_TO_TOOM53_THRESHOLD 137
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 138
-#define MUL_TOOM43_TO_TOOM54_THRESHOLD 185
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 75
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 163
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 147
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 149
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 215
#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
#define SQR_TOOM2_THRESHOLD 38
#define SQR_TOOM3_THRESHOLD 113
#define SQR_TOOM4_THRESHOLD 442
#define SQR_TOOM6_THRESHOLD 517
-#define SQR_TOOM8_THRESHOLD 597
+#define SQR_TOOM8_THRESHOLD 572
#define MULMID_TOOM42_THRESHOLD 46
#define MULMOD_BNM1_THRESHOLD 16
#define SQRMOD_BNM1_THRESHOLD 17
-#define MUL_FFT_MODF_THRESHOLD 404 /* k = 5 */
+#define MUL_FFT_MODF_THRESHOLD 428 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 404, 5}, { 21, 6}, { 11, 5}, { 23, 6}, \
- { 27, 7}, { 14, 6}, { 29, 7}, { 15, 6}, \
- { 31, 7}, { 25, 8}, { 13, 7}, { 29, 8}, \
- { 15, 7}, { 31, 8}, { 17, 7}, { 35, 8}, \
- { 19, 7}, { 39, 8}, { 21, 9}, { 11, 8}, \
- { 29, 9}, { 15, 8}, { 35, 9}, { 19, 8}, \
- { 41, 9}, { 23, 8}, { 49, 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}, { 87,11}, { 47,12}, { 31,11}, \
- { 63,10}, { 135,11}, { 79, 9}, { 319,10}, \
- { 167,11}, { 95,10}, { 191, 9}, { 383,11}, \
- { 111,12}, { 63,11}, { 127, 9}, { 511,11}, \
- { 143,10}, { 287, 9}, { 575,11}, { 159,12}, \
- { 95,11}, { 191,10}, { 383,13}, { 63,12}, \
- { 127,11}, { 255,10}, { 511,11}, { 271,10}, \
- { 543,11}, { 287,10}, { 575,12}, { 159,11}, \
- { 319,10}, { 639,11}, { 335,10}, { 671,11}, \
- { 351,10}, { 703,11}, { 367,12}, { 191,11}, \
- { 383,10}, { 767,11}, { 415,10}, { 831,11}, \
- { 447,13}, { 127,12}, { 255,11}, { 607,12}, \
- { 319,11}, { 703,13}, { 191,12}, { 383,11}, \
- { 799,12}, { 447,14}, { 127,13}, { 255,12}, \
- { 735,13}, { 383,12}, { 767,11}, { 1535,12}, \
- { 831,13}, { 447,12}, { 927,13}, { 511,12}, \
- { 1023,13}, { 575,12}, { 1151,13}, { 639,12}, \
- { 1279,13}, { 703,12}, { 1407,14}, { 383,13}, \
- { 767,12}, { 1535,13}, { 831,12}, { 1663,13}, \
- { 895,12}, { 1791,14}, { 511,13}, { 1087,12}, \
+ { { 428, 5}, { 23, 6}, { 25, 7}, { 13, 6}, \
+ { 27, 7}, { 14, 6}, { 29, 7}, { 24, 8}, \
+ { 13, 7}, { 29, 8}, { 15, 7}, { 31, 8}, \
+ { 17, 7}, { 35, 8}, { 19, 7}, { 39, 8}, \
+ { 21, 9}, { 11, 8}, { 27, 9}, { 15, 8}, \
+ { 35, 9}, { 19, 8}, { 41, 9}, { 23, 8}, \
+ { 49, 9}, { 27,10}, { 15, 9}, { 39,10}, \
+ { 23, 9}, { 55,11}, { 15,10}, { 31, 9}, \
+ { 67,10}, { 39, 9}, { 83,10}, { 47, 9}, \
+ { 99,10}, { 55,11}, { 31,10}, { 71, 6}, \
+ { 1215, 7}, { 639, 8}, { 335, 9}, { 179,12}, \
+ { 31,11}, { 63,10}, { 143,11}, { 79,10}, \
+ { 167,11}, { 111,12}, { 63,11}, { 127,10}, \
+ { 255, 9}, { 511,10}, { 271, 9}, { 543,10}, \
+ { 287, 9}, { 575,10}, { 303,11}, { 159,10}, \
+ { 319,12}, { 95,11}, { 191,10}, { 383,13}, \
+ { 63,12}, { 127,11}, { 255,10}, { 511,11}, \
+ { 271,10}, { 543,11}, { 287,10}, { 575,12}, \
+ { 159,11}, { 319,10}, { 639,11}, { 335,10}, \
+ { 671,11}, { 351,10}, { 703,12}, { 191,11}, \
+ { 383,10}, { 767,11}, { 415,10}, { 831,12}, \
+ { 223,11}, { 447,13}, { 127,11}, { 543,12}, \
+ { 287,11}, { 607,10}, { 1215,12}, { 319,11}, \
+ { 671,12}, { 351,11}, { 703,13}, { 191,12}, \
+ { 383,11}, { 799,12}, { 415,11}, { 831,12}, \
+ { 447,14}, { 127,13}, { 255,12}, { 543,11}, \
+ { 1087,12}, { 607,13}, { 319,12}, { 671,11}, \
+ { 1343,12}, { 735,13}, { 383,12}, { 831,13}, \
+ { 447,12}, { 959,13}, { 511,12}, { 1023,13}, \
+ { 575,12}, { 1151,13}, { 639,12}, { 1343,13}, \
+ { 703,12}, { 1407,14}, { 383,13}, { 831,12}, \
+ { 1663,13}, { 895,14}, { 511,13}, { 1087,12}, \
{ 2175,13}, { 1151,14}, { 639,13}, { 1343,12}, \
- { 2687,13}, { 1407,14}, { 767,13}, { 1599,12}, \
- { 3199,13}, { 1663,14}, { 895,13}, { 1791,15}, \
- { 511,14}, { 1023,13}, { 2175,14}, { 1151,13}, \
- { 2431,12}, { 4863,14}, { 1279,13}, { 2687,14}, \
- { 1407,15}, { 767,14}, { 1535,13}, { 3199,14}, \
- { 1663,13}, { 3455,12}, { 6911,14}, { 1791,16}, \
- { 511,15}, { 1023,14}, { 2431,13}, { 4863,15}, \
- { 1279,14}, { 2943,13}, { 5887,15}, { 1535,14}, \
- { 3455,13}, { 6911,15}, { 1791,14}, { 3839,16}, \
- { 1023,15}, { 2047,14}, { 4351,15}, { 2303,14}, \
+ { 2687,13}, { 1407,14}, { 767,13}, { 1535,12}, \
+ { 3199,13}, { 1663,14}, { 895,15}, { 511,14}, \
+ { 1023,13}, { 2175,14}, { 1151,13}, { 2431,12}, \
+ { 4863,14}, { 1279,13}, { 2687,14}, { 1407,13}, \
+ { 2943,15}, { 767,14}, { 1535,13}, { 3199,14}, \
+ { 1663,13}, { 3455,14}, { 1791,16}, { 511,15}, \
+ { 1023,14}, { 2175,13}, { 4479,14}, { 2431,13}, \
+ { 4863,15}, { 1279,14}, { 2943,13}, { 5887,15}, \
+ { 1535,14}, { 3455,15}, { 1791,14}, { 3839,16}, \
+ { 1023,15}, { 2047,14}, { 4479,15}, { 2303,14}, \
{ 4863,15}, { 2559,14}, { 5247,15}, { 2815,14}, \
- { 5887,16}, { 65536,17}, { 131072,18}, { 262144,19}, \
- { 524288,20}, {1048576,21}, {2097152,22}, {4194304,23}, \
- {8388608,24} }
-#define MUL_FFT_TABLE3_SIZE 177
+ { 5887,16}, { 1535,15}, { 3327,14}, { 6911,15}, \
+ { 3839,17}, { 1023,16}, { 2047,15}, { 4863,16}, \
+ { 2559,15}, { 5887,16}, { 65536,17}, { 131072,18}, \
+ { 262144,19}, { 524288,20}, {1048576,21}, {2097152,22}, \
+ {4194304,23}, {8388608,24} }
+#define MUL_FFT_TABLE3_SIZE 194
#define MUL_FFT_THRESHOLD 4736
#define SQR_FFT_MODF_THRESHOLD 396 /* k = 5 */
#define SQR_FFT_TABLE3 \
{ { 396, 5}, { 23, 6}, { 12, 5}, { 25, 6}, \
- { 27, 7}, { 14, 6}, { 29, 7}, { 15, 6}, \
- { 31, 7}, { 25, 8}, { 13, 7}, { 28, 8}, \
- { 15, 7}, { 32, 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}, { 55,11}, { 31,10}, { 79,11}, \
- { 47,10}, { 95,12}, { 31,11}, { 79,10}, \
+ { 25, 7}, { 13, 6}, { 27, 7}, { 14, 6}, \
+ { 29, 7}, { 15, 6}, { 31, 7}, { 25, 8}, \
+ { 13, 7}, { 28, 8}, { 15, 7}, { 32, 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}, { 51,11}, { 15,10}, { 31, 9}, \
+ { 67,10}, { 39, 9}, { 79,10}, { 55,11}, \
+ { 31,10}, { 79,11}, { 47,10}, { 95,12}, \
+ { 31, 9}, { 255,10}, { 135,11}, { 79,10}, \
{ 159,11}, { 95,10}, { 191, 9}, { 383,12}, \
{ 63,11}, { 127,10}, { 255, 9}, { 511,10}, \
{ 271,11}, { 143,10}, { 287, 9}, { 575,10}, \
- { 303, 9}, { 607,11}, { 159,10}, { 319,12}, \
- { 95,10}, { 383,13}, { 63,12}, { 127,11}, \
- { 255,10}, { 511,11}, { 271,10}, { 543,11}, \
- { 287,10}, { 575,11}, { 303,10}, { 607,12}, \
+ { 303, 9}, { 607,11}, { 159,10}, { 319, 9}, \
+ { 639,12}, { 95,10}, { 383, 9}, { 767,13}, \
+ { 63,12}, { 127,11}, { 255,10}, { 511,11}, \
+ { 271,10}, { 543,11}, { 287,10}, { 607,12}, \
{ 159,11}, { 319,10}, { 639,11}, { 335,10}, \
{ 671,11}, { 351,10}, { 703,11}, { 367,10}, \
{ 735,11}, { 383,10}, { 767,11}, { 415,10}, \
- { 831,12}, { 223,11}, { 447,13}, { 127,12}, \
+ { 831,12}, { 223,11}, { 479,13}, { 127,12}, \
{ 255,11}, { 543,12}, { 287,11}, { 607,12}, \
{ 319,11}, { 671,12}, { 351,11}, { 735,12}, \
{ 383,11}, { 767,12}, { 415,11}, { 831,12}, \
- { 479,14}, { 127,13}, { 255,12}, { 607,13}, \
- { 319,12}, { 735,13}, { 383,12}, { 831,13}, \
- { 447,12}, { 959,14}, { 255,13}, { 511,12}, \
+ { 447,11}, { 895,12}, { 479,14}, { 127,13}, \
+ { 255,12}, { 735,13}, { 383,12}, { 831,13}, \
+ { 447,12}, { 927,14}, { 255,13}, { 511,12}, \
{ 1023,13}, { 575,12}, { 1151,13}, { 639,12}, \
- { 1279,13}, { 703,14}, { 383,13}, { 767,12}, \
- { 1535,13}, { 831,12}, { 1663,13}, { 895,12}, \
- { 1791,13}, { 959,14}, { 511,13}, { 1087,12}, \
- { 2175,13}, { 1151,14}, { 639,13}, { 1343,12}, \
- { 2687,13}, { 1407,14}, { 767,13}, { 1535,12}, \
- { 3071,13}, { 1599,12}, { 3199,13}, { 1663,14}, \
- { 895,13}, { 1791,15}, { 511,14}, { 1023,13}, \
- { 2175,14}, { 1151,13}, { 2431,12}, { 4863,14}, \
- { 1279,13}, { 2687,14}, { 1407,15}, { 767,14}, \
- { 1535,13}, { 3199,14}, { 1663,13}, { 3455,14}, \
- { 1791,16}, { 511,15}, { 1023,14}, { 2431,13}, \
- { 4863,15}, { 1279,14}, { 2943,13}, { 5887,15}, \
- { 1535,14}, { 3455,15}, { 1791,14}, { 3839,16}, \
- { 1023,15}, { 2047,14}, { 4223,15}, { 2303,14}, \
- { 4863,15}, { 2559,14}, { 5247,15}, { 2815,14}, \
- { 5887,16}, { 65536,17}, { 131072,18}, { 262144,19}, \
- { 524288,20}, {1048576,21}, {2097152,22}, {4194304,23}, \
- {8388608,24} }
-#define SQR_FFT_TABLE3_SIZE 181
+ { 1279,13}, { 703,12}, { 1407,14}, { 383,13}, \
+ { 767,12}, { 1535,13}, { 831,12}, { 1663,13}, \
+ { 895,14}, { 511,13}, { 1087,12}, { 2175,13}, \
+ { 1151,14}, { 639,13}, { 1343,12}, { 2687,13}, \
+ { 1407,14}, { 767,13}, { 1599,12}, { 3199,13}, \
+ { 1663,14}, { 895,13}, { 1791,15}, { 511,14}, \
+ { 1023,13}, { 2175,14}, { 1151,13}, { 2431,12}, \
+ { 4863,14}, { 1279,13}, { 2687,14}, { 1407,15}, \
+ { 767,14}, { 1535,13}, { 3199,14}, { 1663,13}, \
+ { 3455,14}, { 1791,16}, { 511,15}, { 1023,14}, \
+ { 2431,13}, { 4863,15}, { 1279,14}, { 2943,13}, \
+ { 5887,15}, { 1535,14}, { 3455,15}, { 1791,14}, \
+ { 3839,16}, { 1023,15}, { 2047,14}, { 4223,15}, \
+ { 2303,14}, { 4863,15}, { 2559,14}, { 5119,15}, \
+ { 2815,14}, { 5887,16}, { 1535,15}, { 3327,14}, \
+ { 6911,15}, { 3839,17}, { 1023,16}, { 2047,15}, \
+ { 4863,16}, { 2559,15}, { 5887,16}, { 65536,17}, \
+ { 131072,18}, { 262144,19}, { 524288,20}, {1048576,21}, \
+ {2097152,22}, {4194304,23}, {8388608,24} }
+#define SQR_FFT_TABLE3_SIZE 191
#define SQR_FFT_THRESHOLD 3776
#define MULLO_BASECASE_THRESHOLD 0 /* always */
-#define MULLO_DC_THRESHOLD 39
-#define MULLO_MUL_N_THRESHOLD 9174
+#define MULLO_DC_THRESHOLD 27
+#define MULLO_MUL_N_THRESHOLD 8648
#define SQRLO_BASECASE_THRESHOLD 9
-#define SQRLO_DC_THRESHOLD 170
-#define SQRLO_SQR_THRESHOLD 7463
+#define SQRLO_DC_THRESHOLD 172
+#define SQRLO_SQR_THRESHOLD 7487
#define DC_DIV_QR_THRESHOLD 56
-#define DC_DIVAPPR_Q_THRESHOLD 189
+#define DC_DIVAPPR_Q_THRESHOLD 191
#define DC_BDIV_QR_THRESHOLD 86
-#define DC_BDIV_Q_THRESHOLD 171
+#define DC_BDIV_Q_THRESHOLD 188
#define INV_MULMOD_BNM1_THRESHOLD 70
#define INV_NEWTON_THRESHOLD 179
-#define INV_APPR_THRESHOLD 179
+#define INV_APPR_THRESHOLD 181
-#define BINV_NEWTON_THRESHOLD 276
+#define BINV_NEWTON_THRESHOLD 309
#define REDC_1_TO_REDC_2_THRESHOLD 33
-#define REDC_2_TO_REDC_N_THRESHOLD 84
+#define REDC_2_TO_REDC_N_THRESHOLD 78
-#define MU_DIV_QR_THRESHOLD 1620
+#define MU_DIV_QR_THRESHOLD 1718
#define MU_DIVAPPR_Q_THRESHOLD 1718
-#define MUPI_DIV_QR_THRESHOLD 77
-#define MU_BDIV_QR_THRESHOLD 1470
-#define MU_BDIV_Q_THRESHOLD 1752
+#define MUPI_DIV_QR_THRESHOLD 79
+#define MU_BDIV_QR_THRESHOLD 1652
+#define MU_BDIV_Q_THRESHOLD 1718
-#define POWM_SEC_TABLE 5,16,187,779,1035,1357
+#define POWM_SEC_TABLE 1,9,191,779,839
-#define GET_STR_DC_THRESHOLD 13
-#define GET_STR_PRECOMPUTE_THRESHOLD 19
-#define SET_STR_DC_THRESHOLD 632
-#define SET_STR_PRECOMPUTE_THRESHOLD 1658
+#define GET_STR_DC_THRESHOLD 14
+#define GET_STR_PRECOMPUTE_THRESHOLD 20
+#define SET_STR_DC_THRESHOLD 711
+#define SET_STR_PRECOMPUTE_THRESHOLD 1664
More information about the gmp-commit
mailing list