[Gmp-commit] /var/hg/gmp: Retune.
mercurial at gmplib.org
mercurial at gmplib.org
Mon Oct 12 22:59:56 UTC 2015
details: /var/hg/gmp/rev/9f8c7c1e4dbe
changeset: 16846:9f8c7c1e4dbe
user: Torbjorn Granlund <torbjorng at google.com>
date: Tue Oct 13 00:59:54 2015 +0200
description:
Retune.
diffstat:
mpn/arm/v6/gmp-mparam.h | 201 +++++++++++--------
mpn/arm/v7a/cora15/gmp-mparam.h | 234 +++++++++++------------
mpn/arm/v7a/cora7/gmp-mparam.h | 127 +++++++----
mpn/arm/v7a/cora8/gmp-mparam.h | 213 ++++++++++++---------
mpn/arm/v7a/cora9/gmp-mparam.h | 220 +++++++++++-----------
mpn/ia64/gmp-mparam.h | 202 ++++++++++----------
mpn/powerpc32/gmp-mparam.h | 205 ++++++++++----------
mpn/powerpc64/mode64/p4/gmp-mparam.h | 220 +++++++++++----------
mpn/powerpc64/mode64/p7/gmp-mparam.h | 346 +++++++++++++++++-----------------
mpn/s390_64/z10/gmp-mparam.h | 296 +++++++++++++++--------------
mpn/x86/atom/gmp-mparam.h | 207 ++++++++++----------
mpn/x86/k7/gmp-mparam.h | 342 +++++++++++++++++----------------
mpn/x86_64/atom/gmp-mparam.h | 234 +++++++++++------------
mpn/x86_64/bd2/gmp-mparam.h | 306 ++++++++++++++++--------------
mpn/x86_64/bobcat/gmp-mparam.h | 222 +++++++++++----------
mpn/x86_64/core2/gmp-mparam.h | 216 +++++++++++----------
mpn/x86_64/coreibwl/gmp-mparam.h | 223 ++++++++++++++--------
mpn/x86_64/coreihwl/gmp-mparam.h | 207 ++++++++++----------
mpn/x86_64/coreinhm/gmp-mparam.h | 260 +++++++++++++-------------
mpn/x86_64/coreisbr/gmp-mparam.h | 272 +++++++++++++-------------
mpn/x86_64/k10/gmp-mparam.h | 273 ++++++++++++++-------------
mpn/x86_64/skylake/gmp-mparam.h | 210 ++++++++++++--------
22 files changed, 2756 insertions(+), 2480 deletions(-)
diffs (truncated from 6729 to 300 lines):
diff -r dde8d3201906 -r 9f8c7c1e4dbe mpn/arm/v6/gmp-mparam.h
--- a/mpn/arm/v6/gmp-mparam.h Mon Oct 12 22:33:11 2015 +0200
+++ b/mpn/arm/v6/gmp-mparam.h Tue Oct 13 00:59:54 2015 +0200
@@ -1,6 +1,6 @@
/* gmp-mparam.h -- Compiler/machine parameter header file.
-Copyright 1991, 1993, 1994, 1999-2003, 2009, 2010, 2012 Free Software
+Copyright 1991, 1993, 1994, 1999-2003, 2009, 2010, 2012, 2015 Free Software
Foundation, Inc.
This file is part of the GNU MP Library.
@@ -32,126 +32,157 @@
#define GMP_LIMB_BITS 32
#define GMP_LIMB_BYTES 4
-/* 700MHz ARM11 (raspberry pi) */
+/* 700 MHz ARM11 (raspberry pi) */
+/* FFT tuning limit = 10 M */
+/* Generated by tuneup.c, 2015-10-05, gcc 4.6 */
#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 7
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 6
#define MOD_1_1_TO_MOD_1_2_THRESHOLD 0 /* never mpn_mod_1_1p */
#define MOD_1_2_TO_MOD_1_4_THRESHOLD MP_SIZE_T_MAX
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 29
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 19
#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 33
+#define DIVEXACT_1_THRESHOLD 0 /* always (native) */
+#define BMOD_1_TO_MOD_1_THRESHOLD 39
-#define MUL_TOOM22_THRESHOLD 36
-#define MUL_TOOM33_THRESHOLD 117
-#define MUL_TOOM44_THRESHOLD 462
+#define MUL_TOOM22_THRESHOLD 44
+#define MUL_TOOM33_THRESHOLD 138
+#define MUL_TOOM44_THRESHOLD 517
#define MUL_TOOM6H_THRESHOLD 0 /* always */
-#define MUL_TOOM8H_THRESHOLD 620
+#define MUL_TOOM8H_THRESHOLD 692
-#define MUL_TOOM32_TO_TOOM43_THRESHOLD 130
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 573
-#define MUL_TOOM42_TO_TOOM53_THRESHOLD 209
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 209
-#define MUL_TOOM43_TO_TOOM54_THRESHOLD 305
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 141
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 407
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 132
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 211
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 225
#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
-#define SQR_TOOM2_THRESHOLD 50
-#define SQR_TOOM3_THRESHOLD 181
-#define SQR_TOOM4_THRESHOLD 686
+#define SQR_TOOM2_THRESHOLD 56
+#define SQR_TOOM3_THRESHOLD 173
+#define SQR_TOOM4_THRESHOLD 711
#define SQR_TOOM6_THRESHOLD 0 /* always */
#define SQR_TOOM8_THRESHOLD 915
-#define MULMID_TOOM42_THRESHOLD 72
+#define MULMID_TOOM42_THRESHOLD 70
-#define MULMOD_BNM1_THRESHOLD 25
-#define SQRMOD_BNM1_THRESHOLD 30
+#define MULMOD_BNM1_THRESHOLD 24
+#define SQRMOD_BNM1_THRESHOLD 28
-#define MUL_FFT_MODF_THRESHOLD 476 /* k = 5 */
+#define MUL_FFT_MODF_THRESHOLD 560 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 476, 5}, { 21, 6}, { 11, 5}, { 25, 6}, \
- { 13, 5}, { 27, 6}, { 25, 7}, { 13, 6}, \
- { 28, 7}, { 15, 6}, { 32, 7}, { 17, 6}, \
- { 35, 7}, { 19, 6}, { 39, 7}, { 23, 6}, \
- { 47, 7}, { 29, 8}, { 15, 7}, { 35, 8}, \
+ { { 560, 5}, { 27, 6}, { 15, 5}, { 31, 6}, \
+ { 28, 7}, { 15, 6}, { 33, 7}, { 17, 6}, \
+ { 36, 7}, { 19, 6}, { 39, 7}, { 23, 6}, \
+ { 47, 7}, { 25, 6}, { 51, 7}, { 27, 6}, \
+ { 55, 7}, { 29, 8}, { 15, 7}, { 37, 8}, \
{ 19, 7}, { 43, 8}, { 23, 7}, { 51, 8}, \
{ 27, 7}, { 55, 8}, { 31, 7}, { 63, 8}, \
+ { 35, 7}, { 71, 8}, { 43, 9}, { 23, 8}, \
+ { 55, 9}, { 31, 8}, { 71, 9}, { 39, 8}, \
+ { 83, 9}, { 47, 8}, { 99, 9}, { 55,10}, \
+ { 31, 9}, { 79,10}, { 47, 9}, { 103,11}, \
+ { 31,10}, { 63, 9}, { 135,10}, { 79, 9}, \
+ { 159,10}, { 95, 9}, { 191,10}, { 111,11}, \
+ { 63,10}, { 159,11}, { 95,10}, { 207,12}, \
+ { 63,11}, { 127,10}, { 255, 9}, { 511,10}, \
+ { 271,11}, { 159,10}, { 335,11}, { 191,10}, \
+ { 399,11}, { 223,12}, { 127,11}, { 255,10}, \
+ { 511,11}, { 287,10}, { 575,11}, { 319,10}, \
+ { 639,11}, { 351,12}, { 191,11}, { 383,10}, \
+ { 767,11}, { 415,13}, { 127,12}, { 255,11}, \
+ { 575,12}, { 319,11}, { 703,12}, { 383,11}, \
+ { 799,12}, { 447,13}, { 255,12}, { 511,11}, \
+ { 1023,12}, { 575,11}, { 1151,12}, { 703,13}, \
+ { 383,12}, { 831,14}, { 255,13}, { 511,12}, \
+ { 1151,13}, { 639,12}, { 1343,13}, { 767,12}, \
+ { 1599,13}, { 895,14}, { 511,13}, { 1023,12}, \
+ { 2111,13}, { 1151,12}, { 2367,13}, { 8192,14}, \
+ { 16384,15}, { 32768,16} }
+#define MUL_FFT_TABLE3_SIZE 110
+#define MUL_FFT_THRESHOLD 5760
+
+#define SQR_FFT_MODF_THRESHOLD 505 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 505, 5}, { 27, 6}, { 15, 5}, { 31, 6}, \
+ { 29, 7}, { 15, 6}, { 33, 7}, { 17, 6}, \
+ { 35, 7}, { 19, 6}, { 40, 7}, { 23, 6}, \
+ { 47, 7}, { 29, 8}, { 15, 7}, { 37, 8}, \
+ { 19, 7}, { 43, 8}, { 23, 7}, { 49, 8}, \
+ { 27, 7}, { 55, 8}, { 31, 7}, { 63, 8}, \
{ 43, 9}, { 23, 8}, { 55, 9}, { 31, 8}, \
{ 71, 9}, { 39, 8}, { 83, 9}, { 47, 8}, \
- { 95, 9}, { 55,10}, { 31, 9}, { 79,10}, \
+ { 99, 9}, { 55,10}, { 31, 9}, { 79,10}, \
{ 47, 9}, { 103,11}, { 31,10}, { 63, 9}, \
{ 135,10}, { 79, 9}, { 159,10}, { 95, 9}, \
{ 191,10}, { 111,11}, { 63,10}, { 127, 9}, \
{ 255,10}, { 143, 9}, { 287,10}, { 159,11}, \
- { 95,10}, { 191, 9}, { 383,12}, { 4096,13}, \
- { 8192,14}, { 16384,15}, { 32768,16} }
-#define MUL_FFT_TABLE3_SIZE 63
-#define MUL_FFT_THRESHOLD 4736
-
-#define SQR_FFT_MODF_THRESHOLD 464 /* k = 5 */
-#define SQR_FFT_TABLE3 \
- { { 464, 5}, { 25, 6}, { 13, 5}, { 27, 6}, \
- { 29, 7}, { 15, 6}, { 33, 7}, { 17, 6}, \
- { 36, 7}, { 19, 6}, { 39, 7}, { 23, 6}, \
- { 47, 7}, { 29, 8}, { 15, 7}, { 35, 8}, \
- { 19, 7}, { 43, 8}, { 23, 7}, { 49, 8}, \
- { 27, 7}, { 55, 8}, { 31, 7}, { 63, 8}, \
- { 35, 7}, { 71, 8}, { 43, 9}, { 23, 8}, \
- { 55, 9}, { 31, 8}, { 71, 9}, { 39, 8}, \
- { 83, 9}, { 47, 8}, { 95, 9}, { 55,10}, \
- { 31, 9}, { 79,10}, { 47, 9}, { 103,11}, \
- { 31,10}, { 63, 9}, { 135,10}, { 79, 9}, \
- { 159,10}, { 95, 9}, { 191,10}, { 111,11}, \
- { 63,10}, { 127, 9}, { 255,10}, { 143, 9}, \
- { 287,10}, { 159,11}, { 95,10}, { 191, 9}, \
- { 383,12}, { 4096,13}, { 8192,14}, { 16384,15}, \
+ { 95,10}, { 191, 9}, { 383,12}, { 63,11}, \
+ { 127,10}, { 255, 9}, { 511,10}, { 271, 9}, \
+ { 543,10}, { 287,11}, { 159,10}, { 351,11}, \
+ { 191,10}, { 415,11}, { 223,12}, { 127,11}, \
+ { 255,10}, { 543,11}, { 287,10}, { 607,11}, \
+ { 319,10}, { 639,11}, { 351,12}, { 191,11}, \
+ { 383,10}, { 767,11}, { 415,13}, { 127,12}, \
+ { 255,11}, { 607,12}, { 319,11}, { 703,12}, \
+ { 383,11}, { 831,12}, { 447,13}, { 255,12}, \
+ { 511,11}, { 1023,12}, { 703,13}, { 383,12}, \
+ { 831,14}, { 255,13}, { 511,12}, { 1087,13}, \
+ { 639,12}, { 1343,13}, { 767,12}, { 1599,13}, \
+ { 895,14}, { 511,13}, { 1023,12}, { 2111,13}, \
+ { 1151,12}, { 2431,13}, { 8192,14}, { 16384,15}, \
{ 32768,16} }
-#define SQR_FFT_TABLE3_SIZE 61
-#define SQR_FFT_THRESHOLD 3776
+#define SQR_FFT_TABLE3_SIZE 109
+#define SQR_FFT_THRESHOLD 4672
#define MULLO_BASECASE_THRESHOLD 0 /* always */
-#define MULLO_DC_THRESHOLD 67
-#define MULLO_MUL_N_THRESHOLD 8907
+#define MULLO_DC_THRESHOLD 55
+#define MULLO_MUL_N_THRESHOLD 11278
+#define SQRLO_BASECASE_THRESHOLD 8
+#define SQRLO_DC_THRESHOLD 51
+#define SQRLO_SQR_THRESHOLD 8907
-#define DC_DIV_QR_THRESHOLD 40
-#define DC_DIVAPPR_Q_THRESHOLD 156
-#define DC_BDIV_QR_THRESHOLD 71
-#define DC_BDIV_Q_THRESHOLD 208
+#define DC_DIV_QR_THRESHOLD 46
+#define DC_DIVAPPR_Q_THRESHOLD 148
+#define DC_BDIV_QR_THRESHOLD 57
+#define DC_BDIV_Q_THRESHOLD 160
-#define INV_MULMOD_BNM1_THRESHOLD 70
-#define INV_NEWTON_THRESHOLD 151
-#define INV_APPR_THRESHOLD 150
+#define INV_MULMOD_BNM1_THRESHOLD 86
+#define INV_NEWTON_THRESHOLD 138
+#define INV_APPR_THRESHOLD 139
-#define BINV_NEWTON_THRESHOLD 375
-#define REDC_1_TO_REDC_2_THRESHOLD 5
-#define REDC_2_TO_REDC_N_THRESHOLD 134
+#define BINV_NEWTON_THRESHOLD 216
+#define REDC_1_TO_REDC_2_THRESHOLD 6
+#define REDC_2_TO_REDC_N_THRESHOLD 124
-#define MU_DIV_QR_THRESHOLD 2130
-#define MU_DIVAPPR_Q_THRESHOLD 2130
-#define MUPI_DIV_QR_THRESHOLD 80
-#define MU_BDIV_QR_THRESHOLD 1787
-#define MU_BDIV_Q_THRESHOLD 2130
+#define MU_DIV_QR_THRESHOLD 2642
+#define MU_DIVAPPR_Q_THRESHOLD 2492
+#define MUPI_DIV_QR_THRESHOLD 74
+#define MU_BDIV_QR_THRESHOLD 2130
+#define MU_BDIV_Q_THRESHOLD 2541
-#define POWM_SEC_TABLE 7,32,460,1705
+#define POWM_SEC_TABLE 5,26,143,446
-#define MATRIX22_STRASSEN_THRESHOLD 19
-#define HGCD_THRESHOLD 85
-#define HGCD_APPR_THRESHOLD 119
-#define HGCD_REDUCE_THRESHOLD 3389
-#define GCD_DC_THRESHOLD 333
-#define GCDEXT_DC_THRESHOLD 309
+#define GET_STR_DC_THRESHOLD 20
+#define GET_STR_PRECOMPUTE_THRESHOLD 39
+#define SET_STR_DC_THRESHOLD 527
+#define SET_STR_PRECOMPUTE_THRESHOLD 1069
+
+#define FAC_DSC_THRESHOLD 430
+#define FAC_ODD_THRESHOLD 55
+
+#define MATRIX22_STRASSEN_THRESHOLD 23
+#define HGCD_THRESHOLD 79
+#define HGCD_APPR_THRESHOLD 71
+#define HGCD_REDUCE_THRESHOLD 3810
+#define GCD_DC_THRESHOLD 283
+#define GCDEXT_DC_THRESHOLD 253
#define JACOBI_BASE_METHOD 1
-
-#define GET_STR_DC_THRESHOLD 21
-#define GET_STR_PRECOMPUTE_THRESHOLD 41
-#define SET_STR_DC_THRESHOLD 527
-#define SET_STR_PRECOMPUTE_THRESHOLD 1323
-
-#define FAC_DSC_THRESHOLD 414
-#define FAC_ODD_THRESHOLD 154
diff -r dde8d3201906 -r 9f8c7c1e4dbe mpn/arm/v7a/cora15/gmp-mparam.h
--- a/mpn/arm/v7a/cora15/gmp-mparam.h Mon Oct 12 22:33:11 2015 +0200
+++ b/mpn/arm/v7a/cora15/gmp-mparam.h Tue Oct 13 00:59:54 2015 +0200
@@ -1,6 +1,6 @@
/* gmp-mparam.h -- Compiler/machine parameter header file.
-Copyright 1991, 1993, 1994, 1999-2003, 2009, 2010, 2012-2014 Free Software
+ Copyright 1991, 1993, 1994, 1999-2003, 2009, 2010, 2012-2015 Free Software
Foundation, Inc.
This file is part of the GNU MP Library.
@@ -32,17 +32,17 @@
#define GMP_LIMB_BITS 32
#define GMP_LIMB_BYTES 4
-/* 1700MHz Cortex-A15 with Neon (in spite of file position) */
-/* FFT tuning limit = 25000000 */
-/* Generated by tuneup.c, 2014-03-12, gcc 4.6 */
+/* 1700 MHz Cortex-A15 with Neon (in spite of file position) */
+/* FFT tuning limit = 25 M */
+/* Generated by tuneup.c, 2015-10-06, 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 3
-#define MOD_1U_TO_MOD_1_1_THRESHOLD 3
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 2
#define MOD_1_1_TO_MOD_1_2_THRESHOLD 9
-#define MOD_1_2_TO_MOD_1_4_THRESHOLD MP_SIZE_T_MAX
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 8
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD 102
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 9
#define USE_PREINV_DIVREM_1 1 /* native */
#define DIV_QR_1N_PI1_METHOD 1
#define DIV_QR_1_NORM_THRESHOLD MP_SIZE_T_MAX /* never */
@@ -51,147 +51,143 @@
#define DIVEXACT_1_THRESHOLD 0 /* always (native) */
#define BMOD_1_TO_MOD_1_THRESHOLD 15
-#define MUL_TOOM22_THRESHOLD 23
-#define MUL_TOOM33_THRESHOLD 90
-#define MUL_TOOM44_THRESHOLD 262
-#define MUL_TOOM6H_THRESHOLD 351
-#define MUL_TOOM8H_THRESHOLD 557
+#define MUL_TOOM22_THRESHOLD 28
+#define MUL_TOOM33_THRESHOLD 116
+#define MUL_TOOM44_THRESHOLD 169
More information about the gmp-commit
mailing list