[Gmp-commit] /var/hg/gmp: Retune
mercurial at gmplib.org
mercurial at gmplib.org
Fri Jun 16 14:58:50 UTC 2017
details: /var/hg/gmp/rev/57a2a6ec16af
changeset: 17450:57a2a6ec16af
user: Torbjorn Granlund <tg at gmplib.org>
date: Fri Jun 16 14:17:53 2017 +0200
description:
Retune
diffstat:
mpn/x86_64/silvermont/gmp-mparam.h | 195 ++++++++++++++++++------------------
1 files changed, 100 insertions(+), 95 deletions(-)
diffs (241 lines):
diff -r a47a9191df84 -r 57a2a6ec16af mpn/x86_64/silvermont/gmp-mparam.h
--- a/mpn/x86_64/silvermont/gmp-mparam.h Fri Jun 16 00:40:03 2017 +0200
+++ b/mpn/x86_64/silvermont/gmp-mparam.h Fri Jun 16 14:17:53 2017 +0200
@@ -32,13 +32,13 @@
#define GMP_LIMB_BYTES 8
/* 2400 MHz Rangeley */
-/* Generated by tuneup.c, 2017-02-23, gcc 4.8 */
+/* Generated by tuneup.c, 2017-06-16, gcc 6.3 */
#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 2
-#define MOD_1_1_TO_MOD_1_2_THRESHOLD 66
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 3
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 54
#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */
#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 9
#define USE_PREINV_DIVREM_1 1 /* native */
@@ -48,123 +48,128 @@
#define DIVEXACT_1_THRESHOLD 0 /* always (native) */
#define BMOD_1_TO_MOD_1_THRESHOLD MP_SIZE_T_MAX /* never */
-#define DIV_1_VS_MUL_1_PERCENT 141
+#define DIV_1_VS_MUL_1_PERCENT 169
-#define MUL_TOOM22_THRESHOLD 20
-#define MUL_TOOM33_THRESHOLD 66
-#define MUL_TOOM44_THRESHOLD 169
-#define MUL_TOOM6H_THRESHOLD 254
+#define MUL_TOOM22_THRESHOLD 19
+#define MUL_TOOM33_THRESHOLD 113
+#define MUL_TOOM44_THRESHOLD 166
+#define MUL_TOOM6H_THRESHOLD 226
#define MUL_TOOM8H_THRESHOLD 333
-#define MUL_TOOM32_TO_TOOM43_THRESHOLD 113
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 107
#define MUL_TOOM32_TO_TOOM53_THRESHOLD 124
-#define MUL_TOOM42_TO_TOOM53_THRESHOLD 113
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 129
-#define MUL_TOOM43_TO_TOOM54_THRESHOLD 104
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 105
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 113
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 89
-#define SQR_BASECASE_THRESHOLD 6
-#define SQR_TOOM2_THRESHOLD 40
-#define SQR_TOOM3_THRESHOLD 61
-#define SQR_TOOM4_THRESHOLD 268
+#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
+#define SQR_TOOM2_THRESHOLD 26
+#define SQR_TOOM3_THRESHOLD 105
+#define SQR_TOOM4_THRESHOLD 244
#define SQR_TOOM6_THRESHOLD 0 /* always */
-#define SQR_TOOM8_THRESHOLD 333
-
-#define MULMID_TOOM42_THRESHOLD 28
+#define SQR_TOOM8_THRESHOLD 309
-#define MULMOD_BNM1_THRESHOLD 14
-#define SQRMOD_BNM1_THRESHOLD 14
+#define MULMID_TOOM42_THRESHOLD 24
-#define MUL_FFT_MODF_THRESHOLD 380 /* k = 5 */
+#define MULMOD_BNM1_THRESHOLD 13
+#define SQRMOD_BNM1_THRESHOLD 15
+
+#define MUL_FFT_MODF_THRESHOLD 340 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 380, 5}, { 15, 6}, { 8, 5}, { 17, 6}, \
- { 9, 5}, { 19, 6}, { 17, 7}, { 9, 6}, \
- { 19, 7}, { 11, 6}, { 23, 7}, { 17, 8}, \
- { 9, 7}, { 20, 8}, { 11, 7}, { 23, 8}, \
- { 13, 7}, { 27, 8}, { 15, 7}, { 31, 8}, \
- { 21, 9}, { 11, 8}, { 27, 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}, \
- { 67,10}, { 39, 9}, { 79,10}, { 47, 9}, \
- { 95,11}, { 31,10}, { 79,11}, { 47,10}, \
- { 95,12}, { 31,11}, { 63,10}, { 127, 9}, \
- { 255,11}, { 79,10}, { 159, 9}, { 319,10}, \
- { 167,11}, { 95,10}, { 191, 9}, { 383,12}, \
- { 63,11}, { 127, 9}, { 511,10}, { 271,11}, \
- { 143,10}, { 287, 9}, { 575,10}, { 319,12}, \
- { 95,11}, { 191,10}, { 383,11}, { 207,10}, \
- { 415,13}, { 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 80
-#define MUL_FFT_THRESHOLD 3520
+ { { 340, 5}, { 17, 6}, { 9, 5}, { 19, 6}, \
+ { 17, 7}, { 9, 6}, { 20, 7}, { 11, 6}, \
+ { 23, 7}, { 17, 8}, { 9, 7}, { 20, 8}, \
+ { 11, 7}, { 23, 8}, { 13, 7}, { 27, 8}, \
+ { 15, 7}, { 31, 8}, { 21, 9}, { 11, 8}, \
+ { 27, 9}, { 15, 8}, { 33, 9}, { 19, 8}, \
+ { 39, 9}, { 23, 8}, { 49, 9}, { 27,10}, \
+ { 15, 9}, { 39,10}, { 23, 9}, { 51,11}, \
+ { 15,10}, { 31, 9}, { 71,10}, { 39, 9}, \
+ { 83,10}, { 47, 9}, { 99,10}, { 55,11}, \
+ { 31,10}, { 71, 8}, { 287,10}, { 79,11}, \
+ { 47,10}, { 95, 9}, { 191,10}, { 103,12}, \
+ { 31,11}, { 63,10}, { 127, 8}, { 511,10}, \
+ { 135, 8}, { 543,10}, { 143,11}, { 79,10}, \
+ { 159, 9}, { 319,11}, { 95,10}, { 191, 9}, \
+ { 383,10}, { 207, 9}, { 415,11}, { 111,12}, \
+ { 63,11}, { 127,10}, { 255, 9}, { 511,10}, \
+ { 271,11}, { 143,10}, { 287, 9}, { 575,10}, \
+ { 319,11}, { 175,12}, { 95,11}, { 191,10}, \
+ { 383,11}, { 207,10}, { 415,13}, { 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 90
+#define MUL_FFT_THRESHOLD 3712
-#define SQR_FFT_MODF_THRESHOLD 280 /* k = 5 */
+#define SQR_FFT_MODF_THRESHOLD 308 /* k = 5 */
#define SQR_FFT_TABLE3 \
- { { 280, 5}, { 17, 6}, { 17, 7}, { 9, 6}, \
- { 19, 7}, { 17, 8}, { 9, 7}, { 20, 8}, \
- { 11, 7}, { 23, 8}, { 15, 7}, { 31, 8}, \
- { 21, 9}, { 11, 8}, { 27, 9}, { 15, 8}, \
- { 33, 9}, { 19, 8}, { 39, 9}, { 23, 8}, \
- { 47, 9}, { 27,10}, { 15, 9}, { 39,10}, \
+ { { 308, 5}, { 17, 6}, { 9, 5}, { 19, 6}, \
+ { 21, 7}, { 11, 6}, { 23, 7}, { 21, 8}, \
+ { 11, 7}, { 24, 8}, { 13, 7}, { 27, 8}, \
+ { 15, 7}, { 31, 8}, { 21, 9}, { 11, 8}, \
+ { 27, 9}, { 15, 8}, { 33, 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}, { 47, 9}, \
- { 95,11}, { 31,10}, { 79,11}, { 47,10}, \
- { 95,12}, { 31,11}, { 63, 9}, { 255, 8}, \
- { 511, 9}, { 271,10}, { 143,11}, { 79,10}, \
- { 159, 9}, { 319,10}, { 175, 9}, { 351,11}, \
- { 95,10}, { 191, 9}, { 383,10}, { 207, 9}, \
- { 415,12}, { 63,11}, { 127, 9}, { 511, 8}, \
- { 1023,10}, { 271,11}, { 143,10}, { 287, 9}, \
- { 575,11}, { 159,10}, { 319, 9}, { 639,11}, \
- { 175,10}, { 351,12}, { 95,11}, { 191,10}, \
- { 383, 9}, { 767,11}, { 207,10}, { 415, 9}, \
- { 831,13}, { 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 84
-#define SQR_FFT_THRESHOLD 3008
+ { 95,11}, { 31,10}, { 63, 9}, { 127,10}, \
+ { 79,11}, { 47,10}, { 95, 8}, { 383,10}, \
+ { 103,12}, { 31,11}, { 63,10}, { 127, 9}, \
+ { 255, 8}, { 511, 9}, { 271, 8}, { 543, 9}, \
+ { 287,11}, { 79,10}, { 159, 9}, { 319, 8}, \
+ { 639,10}, { 175, 9}, { 351,11}, { 95,10}, \
+ { 191, 9}, { 383,10}, { 207, 9}, { 415,11}, \
+ { 111,12}, { 63,11}, { 127,10}, { 255, 9}, \
+ { 511,10}, { 271, 9}, { 543,10}, { 287, 9}, \
+ { 575,10}, { 303,11}, { 159,10}, { 319, 9}, \
+ { 639,11}, { 175,10}, { 351,12}, { 95,11}, \
+ { 191,10}, { 383,11}, { 207,10}, { 415,13}, \
+ { 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 91
+#define SQR_FFT_THRESHOLD 2880
#define MULLO_BASECASE_THRESHOLD 0 /* always */
-#define MULLO_DC_THRESHOLD 53
+#define MULLO_DC_THRESHOLD 57
#define MULLO_MUL_N_THRESHOLD 6633
-#define SQRLO_BASECASE_THRESHOLD 0 /* always */
-#define SQRLO_DC_THRESHOLD 178
-#define SQRLO_SQR_THRESHOLD 5432
+#define SQRLO_BASECASE_THRESHOLD 8
+#define SQRLO_DC_THRESHOLD 11
+#define SQRLO_SQR_THRESHOLD 5558
-#define DC_DIV_QR_THRESHOLD 62
-#define DC_DIVAPPR_Q_THRESHOLD 216
-#define DC_BDIV_QR_THRESHOLD 58
-#define DC_BDIV_Q_THRESHOLD 133
+#define DC_DIV_QR_THRESHOLD 33
+#define DC_DIVAPPR_Q_THRESHOLD 232
+#define DC_BDIV_QR_THRESHOLD 31
+#define DC_BDIV_Q_THRESHOLD 152
-#define INV_MULMOD_BNM1_THRESHOLD 38
-#define INV_NEWTON_THRESHOLD 260
-#define INV_APPR_THRESHOLD 228
+#define INV_MULMOD_BNM1_THRESHOLD 36
+#define INV_NEWTON_THRESHOLD 226
+#define INV_APPR_THRESHOLD 220
-#define BINV_NEWTON_THRESHOLD 252
-#define REDC_1_TO_REDC_2_THRESHOLD 67
+#define BINV_NEWTON_THRESHOLD 220
+#define REDC_1_TO_REDC_2_THRESHOLD 59
#define REDC_2_TO_REDC_N_THRESHOLD 0 /* always */
-#define MU_DIV_QR_THRESHOLD 1334
-#define MU_DIVAPPR_Q_THRESHOLD 1334
-#define MUPI_DIV_QR_THRESHOLD 122
+#define MU_DIV_QR_THRESHOLD 1142
+#define MU_DIVAPPR_Q_THRESHOLD 1142
+#define MUPI_DIV_QR_THRESHOLD 89
#define MU_BDIV_QR_THRESHOLD 942
-#define MU_BDIV_Q_THRESHOLD 1241
+#define MU_BDIV_Q_THRESHOLD 1053
-#define POWM_SEC_TABLE 3,13,194,579,1867
+#define POWM_SEC_TABLE 3,34,194,642,1603
-#define GET_STR_DC_THRESHOLD 18
-#define GET_STR_PRECOMPUTE_THRESHOLD 34
-#define SET_STR_DC_THRESHOLD 270
-#define SET_STR_PRECOMPUTE_THRESHOLD 1290
+#define GET_STR_DC_THRESHOLD 21
+#define GET_STR_PRECOMPUTE_THRESHOLD 40
+#define SET_STR_DC_THRESHOLD 512
+#define SET_STR_PRECOMPUTE_THRESHOLD 2093
#define FAC_DSC_THRESHOLD 406
-#define FAC_ODD_THRESHOLD 29
+#define FAC_ODD_THRESHOLD 24
-#define MATRIX22_STRASSEN_THRESHOLD 16
-#define HGCD_THRESHOLD 115
-#define HGCD_APPR_THRESHOLD 159
-#define HGCD_REDUCE_THRESHOLD 1962
-#define GCD_DC_THRESHOLD 324
-#define GCDEXT_DC_THRESHOLD 306
+#define MATRIX22_STRASSEN_THRESHOLD 21
+#define HGCD_THRESHOLD 132
+#define HGCD_APPR_THRESHOLD 167
+#define HGCD_REDUCE_THRESHOLD 2121
+#define GCD_DC_THRESHOLD 440
+#define GCDEXT_DC_THRESHOLD 309
#define JACOBI_BASE_METHOD 3
More information about the gmp-commit
mailing list