[Gmp-commit] /var/hg/gmp: Retune (mainly for DIV_1_VS_MUL_1_PERCENT).
mercurial at gmplib.org
mercurial at gmplib.org
Fri Feb 3 13:29:35 UTC 2017
details: /var/hg/gmp/rev/e5173fed3ce9
changeset: 17221:e5173fed3ce9
user: Torbjorn Granlund <tg at gmplib.org>
date: Fri Feb 03 14:29:31 2017 +0100
description:
Retune (mainly for DIV_1_VS_MUL_1_PERCENT).
diffstat:
mpn/alpha/ev5/gmp-mparam.h | 92 +++++++++--------
mpn/x86/core2/gmp-mparam.h | 223 ++++++++++++++++++-------------------------
mpn/x86/p6/mmx/gmp-mparam.h | 100 +++++++++++-------
3 files changed, 203 insertions(+), 212 deletions(-)
diffs (truncated from 566 to 300 lines):
diff -r c23ab247bc13 -r e5173fed3ce9 mpn/alpha/ev5/gmp-mparam.h
--- a/mpn/alpha/ev5/gmp-mparam.h Sun Jan 29 23:36:58 2017 +0100
+++ b/mpn/alpha/ev5/gmp-mparam.h Fri Feb 03 14:29:31 2017 +0100
@@ -1,7 +1,6 @@
/* Alpha EV5 gmp-mparam.h -- Compiler/machine parameter header file.
-Copyright 1991, 1993, 1994, 1999-2002, 2004, 2005, 2008-2010, 2014 Free
-Software Foundation, Inc.
+Copyright 1991-2017 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
@@ -34,44 +33,46 @@
/* 600 MHz 21164A */
/* FFT tuning limit = 5000000 */
-/* Generated by tuneup.c, 2014-03-12, gcc 4.5 */
+/* Generated by tuneup.c, 2017-02-02, gcc 4.9 */
#define DIVREM_1_NORM_THRESHOLD 0 /* preinv always */
#define DIVREM_1_UNNORM_THRESHOLD 0 /* always */
#define MOD_1_1P_METHOD 2
#define MOD_1_NORM_THRESHOLD 0 /* always */
#define MOD_1_UNNORM_THRESHOLD 0 /* always */
-#define MOD_1N_TO_MOD_1_1_THRESHOLD 3
-#define MOD_1U_TO_MOD_1_1_THRESHOLD 6
+#define MOD_1N_TO_MOD_1_1_THRESHOLD 10
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 7
#define MOD_1_1_TO_MOD_1_2_THRESHOLD 22
#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 15
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 20
#define USE_PREINV_DIVREM_1 1 /* preinv always */
#define DIV_QR_1N_PI1_METHOD 1
#define DIV_QR_1_NORM_THRESHOLD MP_SIZE_T_MAX /* never */
#define DIV_QR_1_UNNORM_THRESHOLD MP_SIZE_T_MAX /* never */
#define DIV_QR_2_PI2_THRESHOLD MP_SIZE_T_MAX /* never */
#define DIVEXACT_1_THRESHOLD 0 /* always */
-#define BMOD_1_TO_MOD_1_THRESHOLD 76
+#define BMOD_1_TO_MOD_1_THRESHOLD 69
-#define MUL_TOOM22_THRESHOLD 14
+#define DIV_1_VS_MUL_1_PERCENT 181
+
+#define MUL_TOOM22_THRESHOLD 16
#define MUL_TOOM33_THRESHOLD 50
#define MUL_TOOM44_THRESHOLD 118
-#define MUL_TOOM6H_THRESHOLD 157
+#define MUL_TOOM6H_THRESHOLD 173
#define MUL_TOOM8H_THRESHOLD 236
-#define MUL_TOOM32_TO_TOOM43_THRESHOLD 73
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 77
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 49
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 84
#define MUL_TOOM42_TO_TOOM53_THRESHOLD 81
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 56
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 53
#define MUL_TOOM43_TO_TOOM54_THRESHOLD 70
#define SQR_BASECASE_THRESHOLD 0 /* always */
#define SQR_TOOM2_THRESHOLD 22
-#define SQR_TOOM3_THRESHOLD 73
+#define SQR_TOOM3_THRESHOLD 69
#define SQR_TOOM4_THRESHOLD 178
-#define SQR_TOOM6_THRESHOLD 0 /* always */
-#define SQR_TOOM8_THRESHOLD 260
+#define SQR_TOOM6_THRESHOLD 189
+#define SQR_TOOM8_THRESHOLD 357
#define MULMID_TOOM42_THRESHOLD 18
@@ -147,41 +148,44 @@
#define SQR_FFT_THRESHOLD 3968
#define MULLO_BASECASE_THRESHOLD 0 /* always */
-#define MULLO_DC_THRESHOLD 45
-#define MULLO_MUL_N_THRESHOLD 8397
+#define MULLO_DC_THRESHOLD 50
+#define MULLO_MUL_N_THRESHOLD 5558
+#define SQRLO_BASECASE_THRESHOLD 0 /* always */
+#define SQRLO_DC_THRESHOLD 78
+#define SQRLO_SQR_THRESHOLD 3597
#define DC_DIV_QR_THRESHOLD 47
-#define DC_DIVAPPR_Q_THRESHOLD 168
+#define DC_DIVAPPR_Q_THRESHOLD 167
#define DC_BDIV_QR_THRESHOLD 47
#define DC_BDIV_Q_THRESHOLD 110
-#define INV_MULMOD_BNM1_THRESHOLD 26
-#define INV_NEWTON_THRESHOLD 189
-#define INV_APPR_THRESHOLD 181
-
-#define BINV_NEWTON_THRESHOLD 196
-#define REDC_1_TO_REDC_N_THRESHOLD 51
-
-#define MU_DIV_QR_THRESHOLD 1558
-#define MU_DIVAPPR_Q_THRESHOLD 1558
-#define MUPI_DIV_QR_THRESHOLD 90
-#define MU_BDIV_QR_THRESHOLD 855
-#define MU_BDIV_Q_THRESHOLD 1078
-
-#define POWM_SEC_TABLE 1,16,90,452,1221
+#define INV_MULMOD_BNM1_THRESHOLD 30
+#define INV_NEWTON_THRESHOLD 181
+#define INV_APPR_THRESHOLD 173
-#define MATRIX22_STRASSEN_THRESHOLD 11
-#define HGCD_THRESHOLD 99
-#define HGCD_APPR_THRESHOLD 103
-#define HGCD_REDUCE_THRESHOLD 2899
-#define GCD_DC_THRESHOLD 283
-#define GCDEXT_DC_THRESHOLD 201
-#define JACOBI_BASE_METHOD 3
+#define BINV_NEWTON_THRESHOLD 182
+#define REDC_1_TO_REDC_N_THRESHOLD 47
-#define GET_STR_DC_THRESHOLD 13
-#define GET_STR_PRECOMPUTE_THRESHOLD 28
-#define SET_STR_DC_THRESHOLD 426
-#define SET_STR_PRECOMPUTE_THRESHOLD 1505
+#define MU_DIV_QR_THRESHOLD 979
+#define MU_DIVAPPR_Q_THRESHOLD 1142
+#define MUPI_DIV_QR_THRESHOLD 90
+#define MU_BDIV_QR_THRESHOLD 748
+#define MU_BDIV_Q_THRESHOLD 979
-#define FAC_DSC_THRESHOLD 1404
+#define POWM_SEC_TABLE 1,16,90,386,2177
+
+#define GET_STR_DC_THRESHOLD 14
+#define GET_STR_PRECOMPUTE_THRESHOLD 26
+#define SET_STR_DC_THRESHOLD 363
+#define SET_STR_PRECOMPUTE_THRESHOLD 1201
+
+#define FAC_DSC_THRESHOLD 342
#define FAC_ODD_THRESHOLD 0 /* always */
+
+#define MATRIX22_STRASSEN_THRESHOLD 13
+#define HGCD_THRESHOLD 105
+#define HGCD_APPR_THRESHOLD 108
+#define HGCD_REDUCE_THRESHOLD 1679
+#define GCD_DC_THRESHOLD 238
+#define GCDEXT_DC_THRESHOLD 199
+#define JACOBI_BASE_METHOD 2
diff -r c23ab247bc13 -r e5173fed3ce9 mpn/x86/core2/gmp-mparam.h
--- a/mpn/x86/core2/gmp-mparam.h Sun Jan 29 23:36:58 2017 +0100
+++ b/mpn/x86/core2/gmp-mparam.h Fri Feb 03 14:29:31 2017 +0100
@@ -1,6 +1,6 @@
/* x86/core2 gmp-mparam.h -- Compiler/machine parameter header file.
-Copyright 1991, 1993, 1994, 2000-2011, 2014 Free Software Foundation, Inc.
+Copyright 1991-2017 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
@@ -31,95 +31,77 @@
#define GMP_LIMB_BITS 32
#define GMP_LIMB_BYTES 4
-/* 2133 MHz Core 2 (65nm) */
-/* FFT tuning limit = 25000000 */
-/* Generated by tuneup.c, 2014-03-14, gcc 4.5 */
+/* 3000 MHz Core 2 (45nm) */
+/* FFT tuning limit = 500000 */
+/* Generated by tuneup.c, 2017-01-15, gcc 6.2 */
-#define MOD_1_NORM_THRESHOLD 4
-#define MOD_1_UNNORM_THRESHOLD 4
-#define MOD_1N_TO_MOD_1_1_THRESHOLD 5
-#define MOD_1U_TO_MOD_1_1_THRESHOLD 4
-#define MOD_1_1_TO_MOD_1_2_THRESHOLD 10
+#define MOD_1_NORM_THRESHOLD MP_SIZE_T_MAX /* never */
+#define MOD_1_UNNORM_THRESHOLD MP_SIZE_T_MAX /* never */
+#define MOD_1N_TO_MOD_1_1_THRESHOLD 10
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 9
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 0 /* never mpn_mod_1_1p */
#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 10
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 3
#define USE_PREINV_DIVREM_1 1 /* native */
#define DIV_QR_1N_PI1_METHOD 1
-#define DIV_QR_1_NORM_THRESHOLD 3
+#define DIV_QR_1_NORM_THRESHOLD 17
#define DIV_QR_1_UNNORM_THRESHOLD MP_SIZE_T_MAX /* never */
#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 19
+#define BMOD_1_TO_MOD_1_THRESHOLD 16
-#define MUL_TOOM22_THRESHOLD 26
-#define MUL_TOOM33_THRESHOLD 90
-#define MUL_TOOM44_THRESHOLD 144
-#define MUL_TOOM6H_THRESHOLD 286
-#define MUL_TOOM8H_THRESHOLD 430
+#define DIV_1_VS_MUL_1_PERCENT 290
-#define MUL_TOOM32_TO_TOOM43_THRESHOLD 93
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 140
+#define MUL_TOOM22_THRESHOLD 24
+#define MUL_TOOM33_THRESHOLD 93
+#define MUL_TOOM44_THRESHOLD 214
+#define MUL_TOOM6H_THRESHOLD 300
+#define MUL_TOOM8H_THRESHOLD 462
+
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 91
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 145
#define MUL_TOOM42_TO_TOOM53_THRESHOLD 89
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 102
-#define MUL_TOOM43_TO_TOOM54_THRESHOLD 136
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 95
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 130
#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
-#define SQR_TOOM2_THRESHOLD 34
-#define SQR_TOOM3_THRESHOLD 114
-#define SQR_TOOM4_THRESHOLD 178
+#define SQR_TOOM2_THRESHOLD 36
+#define SQR_TOOM3_THRESHOLD 117
+#define SQR_TOOM4_THRESHOLD 176
#define SQR_TOOM6_THRESHOLD 262
-#define SQR_TOOM8_THRESHOLD 357
+#define SQR_TOOM8_THRESHOLD 597
-#define MULMID_TOOM42_THRESHOLD 66
+#define MULMID_TOOM42_THRESHOLD 64
#define MULMOD_BNM1_THRESHOLD 15
#define SQRMOD_BNM1_THRESHOLD 21
-#define MUL_FFT_MODF_THRESHOLD 600 /* k = 5 */
+#define MUL_FFT_MODF_THRESHOLD 570 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 600, 5}, { 25, 6}, { 13, 5}, { 28, 6}, \
- { 25, 7}, { 13, 6}, { 29, 7}, { 15, 6}, \
- { 33, 7}, { 17, 6}, { 36, 7}, { 19, 6}, \
- { 39, 7}, { 29, 8}, { 15, 7}, { 35, 8}, \
- { 19, 7}, { 43, 8}, { 23, 7}, { 47, 8}, \
- { 27, 9}, { 15, 8}, { 31, 7}, { 63, 8}, \
- { 43, 9}, { 23, 8}, { 51,10}, { 15, 9}, \
- { 31, 8}, { 67, 9}, { 39, 8}, { 79, 9}, \
- { 47, 8}, { 95, 9}, { 55,10}, { 31, 9}, \
- { 79,10}, { 47, 9}, { 95,11}, { 31,10}, \
- { 63, 9}, { 135,10}, { 79, 9}, { 159,10}, \
- { 95, 9}, { 191,11}, { 63,10}, { 159,11}, \
- { 95,10}, { 191,12}, { 63,11}, { 127,10}, \
- { 271, 9}, { 543, 8}, { 1087,11}, { 159,10}, \
- { 319, 9}, { 639,10}, { 335, 9}, { 671,10}, \
- { 351,11}, { 191,10}, { 383, 9}, { 767,10}, \
- { 399, 9}, { 799,11}, { 223,12}, { 127,11}, \
- { 255,10}, { 543, 9}, { 1087,11}, { 287,10}, \
- { 607, 9}, { 1215,11}, { 319,10}, { 671,11}, \
- { 351,12}, { 191,11}, { 383,10}, { 799, 9}, \
- { 1599,13}, { 127,12}, { 255,11}, { 543,10}, \
- { 1087,11}, { 607,10}, { 1215,12}, { 319,11}, \
- { 671,10}, { 1343,11}, { 735,12}, { 383,11}, \
- { 799,10}, { 1599,11}, { 863,10}, { 1727,12}, \
- { 447,11}, { 959,13}, { 255,12}, { 511,11}, \
- { 1087,12}, { 575,11}, { 1215,12}, { 639,11}, \
- { 1343,12}, { 703,13}, { 383,12}, { 767,11}, \
- { 1599,12}, { 831,11}, { 1727,12}, { 959,14}, \
- { 255,13}, { 511,12}, { 1087,11}, { 2239,10}, \
- { 4479,12}, { 1215,13}, { 639,12}, { 1471,11}, \
- { 2943,13}, { 767,12}, { 1727,13}, { 895,12}, \
- { 1983,14}, { 511,13}, { 1023,12}, { 2239,11}, \
- { 4479,13}, { 1151,12}, { 2495,13}, { 1279,12}, \
- { 2623,13}, { 1407,12}, { 2815,14}, { 767,13}, \
- { 1663,12}, { 3455,13}, { 1919,15}, { 511,14}, \
- { 1023,13}, { 2175,12}, { 4479,13}, { 2431,14}, \
- { 1279,13}, { 2943,12}, { 5887,14}, { 16384,15}, \
- { 32768,16} }
-#define MUL_FFT_TABLE3_SIZE 149
-#define MUL_FFT_THRESHOLD 6784
+ { { 570, 5}, { 28, 6}, { 15, 5}, { 31, 6}, \
+ { 28, 7}, { 15, 6}, { 33, 7}, { 17, 6}, \
+ { 35, 7}, { 19, 6}, { 39, 7}, { 27, 8}, \
+ { 15, 7}, { 35, 8}, { 19, 7}, { 41, 8}, \
+ { 23, 7}, { 47, 8}, { 27, 9}, { 15, 8}, \
+ { 31, 7}, { 63, 8}, { 43, 9}, { 23, 8}, \
+ { 55,10}, { 15, 9}, { 31, 8}, { 67, 9}, \
+ { 39, 8}, { 83, 9}, { 47, 8}, { 95, 9}, \
+ { 55,10}, { 31, 9}, { 79,10}, { 47, 9}, \
+ { 95,11}, { 31,10}, { 63, 9}, { 135,10}, \
+ { 79, 9}, { 159, 8}, { 319, 9}, { 175,10}, \
+ { 111,11}, { 63,10}, { 143, 9}, { 287,10}, \
+ { 159,11}, { 95,12}, { 63,11}, { 127,10}, \
+ { 255, 9}, { 543,10}, { 287,11}, { 159,10}, \
+ { 319, 9}, { 639,10}, { 335, 9}, { 671,11}, \
+ { 191,10}, { 383, 9}, { 767,10}, { 399, 9}, \
+ { 799,10}, { 415,11}, { 223,12}, { 4096,13}, \
+ { 8192,14}, { 16384,15}, { 32768,16} }
+#define MUL_FFT_TABLE3_SIZE 71
+#define MUL_FFT_THRESHOLD 5760
-#define SQR_FFT_MODF_THRESHOLD 500 /* k = 5 */
+#define SQR_FFT_MODF_THRESHOLD 472 /* k = 5 */
#define SQR_FFT_TABLE3 \
- { { 500, 5}, { 28, 6}, { 15, 5}, { 31, 6}, \
+ { { 472, 5}, { 28, 6}, { 15, 5}, { 31, 6}, \
More information about the gmp-commit
mailing list