[Gmp-commit] /var/hg/gmp: Retune (mainly for DIV_1_VS_MUL_1_PERCENT).
mercurial at gmplib.org
mercurial at gmplib.org
Tue Jan 3 19:41:07 UTC 2017
details: /var/hg/gmp/rev/f7e1104aaaa5
changeset: 17201:f7e1104aaaa5
user: Torbjorn Granlund <tg at gmplib.org>
date: Tue Jan 03 20:41:02 2017 +0100
description:
Retune (mainly for DIV_1_VS_MUL_1_PERCENT).
diffstat:
mpn/arm/v7a/cora5/gmp-mparam.h | 2 +
mpn/powerpc32/p7/gmp-mparam.h | 2 +
mpn/x86_64/coreibwl/gmp-mparam.h | 228 +++++++++++++++-----------------------
mpn/x86_64/skylake/gmp-mparam.h | 2 +
4 files changed, 94 insertions(+), 140 deletions(-)
diffs (truncated from 310 to 300 lines):
diff -r 5825c659d76a -r f7e1104aaaa5 mpn/arm/v7a/cora5/gmp-mparam.h
--- a/mpn/arm/v7a/cora5/gmp-mparam.h Tue Jan 03 20:05:28 2017 +0100
+++ b/mpn/arm/v7a/cora5/gmp-mparam.h Tue Jan 03 20:41:02 2017 +0100
@@ -50,6 +50,8 @@
#define DIVEXACT_1_THRESHOLD 0 /* always (native) */
#define BMOD_1_TO_MOD_1_THRESHOLD 51
+#define DIV_1_VS_MUL_1_PERCENT 178
+
#define MUL_TOOM22_THRESHOLD 45
#define MUL_TOOM33_THRESHOLD 149
#define MUL_TOOM44_THRESHOLD 242
diff -r 5825c659d76a -r f7e1104aaaa5 mpn/powerpc32/p7/gmp-mparam.h
--- a/mpn/powerpc32/p7/gmp-mparam.h Tue Jan 03 20:05:28 2017 +0100
+++ b/mpn/powerpc32/p7/gmp-mparam.h Tue Jan 03 20:41:02 2017 +0100
@@ -48,6 +48,8 @@
#define DIVEXACT_1_THRESHOLD 0 /* always */
#define BMOD_1_TO_MOD_1_THRESHOLD 34
+#define DIV_1_VS_MUL_1_PERCENT 318
+
#define MUL_TOOM22_THRESHOLD 20
#define MUL_TOOM33_THRESHOLD 89
#define MUL_TOOM44_THRESHOLD 130
diff -r 5825c659d76a -r f7e1104aaaa5 mpn/x86_64/coreibwl/gmp-mparam.h
--- a/mpn/x86_64/coreibwl/gmp-mparam.h Tue Jan 03 20:05:28 2017 +0100
+++ b/mpn/x86_64/coreibwl/gmp-mparam.h Tue Jan 03 20:41:02 2017 +0100
@@ -35,9 +35,9 @@
#undef HAVE_NATIVE_mpn_mul_2
#undef HAVE_NATIVE_mpn_addmul_2
-/* 2100 MHz Intel i3-5100 */
-/* FFT tuning limit = 200 M */
-/* Generated by tuneup.c, 2015-10-12, gcc 4.8 */
+/* 3400 MHz Intel Xeon Broadwell E3-1285Lv4 */
+/* FFT tuning limit = 0.5 M */
+/* Generated by tuneup.c, 2017-01-03, gcc 6.2 */
#define MOD_1_NORM_THRESHOLD 0 /* always */
#define MOD_1_UNNORM_THRESHOLD 0 /* always */
@@ -53,172 +53,120 @@
#define DIVEXACT_1_THRESHOLD 0 /* always (native) */
#define BMOD_1_TO_MOD_1_THRESHOLD 20
-#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 DIV_1_VS_MUL_1_PERCENT 485
-#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 MUL_TOOM22_THRESHOLD 29
+#define MUL_TOOM33_THRESHOLD 38
+#define MUL_TOOM44_THRESHOLD 324
+#define MUL_TOOM6H_THRESHOLD 430
+#define MUL_TOOM8H_THRESHOLD 644
+
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 77
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 207
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 75
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 84
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 109
#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
#define SQR_TOOM2_THRESHOLD 38
-#define SQR_TOOM3_THRESHOLD 113
+#define SQR_TOOM3_THRESHOLD 117
#define SQR_TOOM4_THRESHOLD 442
#define SQR_TOOM6_THRESHOLD 517
-#define SQR_TOOM8_THRESHOLD 572
+#define SQR_TOOM8_THRESHOLD 597
-#define MULMID_TOOM42_THRESHOLD 46
+#define MULMID_TOOM42_THRESHOLD 48
#define MULMOD_BNM1_THRESHOLD 16
-#define SQRMOD_BNM1_THRESHOLD 17
+#define SQRMOD_BNM1_THRESHOLD 18
-#define MUL_FFT_MODF_THRESHOLD 428 /* k = 5 */
+#define MUL_FFT_MODF_THRESHOLD 424 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 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}, \
+ { { 424, 5}, { 19, 6}, { 11, 5}, { 23, 6}, \
+ { 12, 5}, { 25, 6}, { 23, 7}, { 12, 6}, \
+ { 25, 7}, { 21, 8}, { 11, 7}, { 24, 8}, \
+ { 13, 7}, { 27, 8}, { 15, 7}, { 31, 8}, \
+ { 17, 7}, { 36, 8}, { 19, 7}, { 39, 8}, \
+ { 21, 9}, { 11, 8}, { 23, 7}, { 47, 8}, \
+ { 25, 7}, { 51, 8}, { 27, 9}, { 15, 8}, \
{ 35, 9}, { 19, 8}, { 41, 9}, { 23, 8}, \
- { 49, 9}, { 27,10}, { 15, 9}, { 39,10}, \
+ { 51, 9}, { 27,10}, { 15, 9}, { 31, 8}, \
+ { 63, 9}, { 39, 8}, { 79, 9}, { 43,10}, \
{ 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}, { 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}, { 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
+ { 71,10}, { 39, 9}, { 87,10}, { 47, 9}, \
+ { 99,10}, { 55,11}, { 31,10}, { 63, 9}, \
+ { 135,10}, { 87,11}, { 47,10}, { 103,12}, \
+ { 31,11}, { 63,10}, { 135, 9}, { 271,10}, \
+ { 143, 8}, { 575, 9}, { 303,11}, { 79,10}, \
+ { 159, 8}, { 639,10}, { 175, 8}, { 703, 9}, \
+ { 367,11}, { 95, 9}, { 383, 8}, { 767, 9}, \
+ { 399, 8}, { 799, 9}, { 415,11}, { 111,12}, \
+ { 63,11}, { 127, 9}, { 511,10}, { 271, 9}, \
+ { 543,11}, { 143,10}, { 287, 9}, { 575,11}, \
+ { 159,10}, { 319, 9}, { 639,11}, { 175,12}, \
+ { 95,11}, { 191,10}, { 383, 9}, { 767,10}, \
+ { 399,13}, { 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 104
+#define MUL_FFT_THRESHOLD 5760
#define SQR_FFT_MODF_THRESHOLD 396 /* k = 5 */
#define SQR_FFT_TABLE3 \
- { { 396, 5}, { 23, 6}, { 12, 5}, { 25, 6}, \
- { 25, 7}, { 13, 6}, { 27, 7}, { 14, 6}, \
- { 29, 7}, { 15, 6}, { 31, 7}, { 25, 8}, \
- { 13, 7}, { 28, 8}, { 15, 7}, { 32, 8}, \
+ { { 396, 5}, { 23, 6}, { 29, 7}, { 15, 6}, \
+ { 31, 7}, { 25, 8}, { 13, 7}, { 28, 8}, \
+ { 15, 7}, { 31, 8}, { 17, 7}, { 35, 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, 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}, { 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}, \
- { 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}, { 703,12}, { 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
+ { 31,11}, { 63,10}, { 135,11}, { 79,10}, \
+ { 159,11}, { 95,12}, { 63,11}, { 127, 9}, \
+ { 511, 8}, { 1023, 9}, { 543,10}, { 287, 9}, \
+ { 607,11}, { 159,10}, { 319, 9}, { 671,12}, \
+ { 95,10}, { 383, 9}, { 767,13}, { 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 66
+#define SQR_FFT_THRESHOLD 3712
#define MULLO_BASECASE_THRESHOLD 0 /* always */
-#define MULLO_DC_THRESHOLD 27
-#define MULLO_MUL_N_THRESHOLD 8648
-#define SQRLO_BASECASE_THRESHOLD 9
-#define SQRLO_DC_THRESHOLD 172
-#define SQRLO_SQR_THRESHOLD 7487
-
-#define DC_DIV_QR_THRESHOLD 56
-#define DC_DIVAPPR_Q_THRESHOLD 191
-#define DC_BDIV_QR_THRESHOLD 86
-#define DC_BDIV_Q_THRESHOLD 188
-
-#define INV_MULMOD_BNM1_THRESHOLD 70
-#define INV_NEWTON_THRESHOLD 179
-#define INV_APPR_THRESHOLD 181
+#define MULLO_DC_THRESHOLD 29
+#define MULLO_MUL_N_THRESHOLD 10950
+#define SQRLO_BASECASE_THRESHOLD 8
+#define SQRLO_DC_THRESHOLD 177
+#define SQRLO_SQR_THRESHOLD 7269
-#define BINV_NEWTON_THRESHOLD 309
-#define REDC_1_TO_REDC_2_THRESHOLD 33
-#define REDC_2_TO_REDC_N_THRESHOLD 78
+#define DC_DIV_QR_THRESHOLD 58
+#define DC_DIVAPPR_Q_THRESHOLD 195
+#define DC_BDIV_QR_THRESHOLD 101
+#define DC_BDIV_Q_THRESHOLD 204
-#define MU_DIV_QR_THRESHOLD 1718
-#define MU_DIVAPPR_Q_THRESHOLD 1718
-#define MUPI_DIV_QR_THRESHOLD 79
-#define MU_BDIV_QR_THRESHOLD 1652
-#define MU_BDIV_Q_THRESHOLD 1718
+#define INV_MULMOD_BNM1_THRESHOLD 58
+#define INV_NEWTON_THRESHOLD 183
+#define INV_APPR_THRESHOLD 179
-#define POWM_SEC_TABLE 1,9,191,779,839
+#define BINV_NEWTON_THRESHOLD 375
+#define REDC_1_TO_REDC_2_THRESHOLD 32
+#define REDC_2_TO_REDC_N_THRESHOLD 92
-#define GET_STR_DC_THRESHOLD 14
-#define GET_STR_PRECOMPUTE_THRESHOLD 20
-#define SET_STR_DC_THRESHOLD 711
-#define SET_STR_PRECOMPUTE_THRESHOLD 1664
+#define MU_DIV_QR_THRESHOLD 1589
+#define MU_DIVAPPR_Q_THRESHOLD 1589
+#define MUPI_DIV_QR_THRESHOLD 82
+#define MU_BDIV_QR_THRESHOLD 1597
+#define MU_BDIV_Q_THRESHOLD 1747
-#define FAC_DSC_THRESHOLD 810
-#define FAC_ODD_THRESHOLD 23
+#define POWM_SEC_TABLE 1,16,194,579,779,2387
+
+#define GET_STR_DC_THRESHOLD 12
+#define GET_STR_PRECOMPUTE_THRESHOLD 19
+#define SET_STR_DC_THRESHOLD 1055
+#define SET_STR_PRECOMPUTE_THRESHOLD 2170
+
+#define FAC_DSC_THRESHOLD 668
+#define FAC_ODD_THRESHOLD 44
#define MATRIX22_STRASSEN_THRESHOLD 19
#define HGCD_THRESHOLD 63
diff -r 5825c659d76a -r f7e1104aaaa5 mpn/x86_64/skylake/gmp-mparam.h
--- a/mpn/x86_64/skylake/gmp-mparam.h Tue Jan 03 20:05:28 2017 +0100
More information about the gmp-commit
mailing list