[Gmp-commit] /var/hg/gmp: Retune.
mercurial at gmplib.org
mercurial at gmplib.org
Thu Feb 23 13:14:47 UTC 2017
details: /var/hg/gmp/rev/65f365154912
changeset: 17296:65f365154912
user: Torbjorn Granlund <tg at gmplib.org>
date: Thu Feb 23 14:14:44 2017 +0100
description:
Retune.
diffstat:
mpn/arm/v7a/cora15/gmp-mparam.h | 199 +++++++++++--------------
mpn/arm/v7a/cora7/gmp-mparam.h | 167 ++++++++------------
mpn/arm64/cora57/gmp-mparam.h | 166 ++++++++++----------
mpn/arm64/gmp-mparam.h | 253 +++++++++++++++-----------------
mpn/arm64/xgene1/gmp-mparam.h | 244 ++++++++++++------------------
mpn/ia64/gmp-mparam.h | 229 +++++++++++-----------------
mpn/powerpc64/mode64/p7/gmp-mparam.h | 272 ++++++++++++----------------------
mpn/powerpc64/mode64/p8/gmp-mparam.h | 169 +++++++++++++++++++++
mpn/x86/k7/gmp-mparam.h | 11 +-
mpn/x86_64/atom/gmp-mparam.h | 220 +++++++++++----------------
mpn/x86_64/bobcat/gmp-mparam.h | 263 ++++++++++++++-------------------
mpn/x86_64/core2/gmp-mparam.h | 9 +-
mpn/x86_64/k10/gmp-mparam.h | 11 +-
mpn/x86_64/k8/gmp-mparam.h | 31 ++-
14 files changed, 1051 insertions(+), 1193 deletions(-)
diffs (truncated from 2850 to 300 lines):
diff -r bb7e1eae88ae -r 65f365154912 mpn/arm/v7a/cora15/gmp-mparam.h
--- a/mpn/arm/v7a/cora15/gmp-mparam.h Thu Feb 23 05:13:19 2017 +0100
+++ b/mpn/arm/v7a/cora15/gmp-mparam.h Thu Feb 23 14:14:44 2017 +0100
@@ -1,7 +1,6 @@
/* gmp-mparam.h -- Compiler/machine parameter header file.
-Copyright 1991, 1993, 1994, 1999-2003, 2009, 2010, 2012-2015 Free Software
-Foundation, Inc.
+Copyright 2017 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
@@ -32,16 +31,16 @@
#define GMP_LIMB_BITS 32
#define GMP_LIMB_BYTES 4
-/* 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 */
+/* 2000 MHz Cortex-A15 with Neon (in spite of file position) */
+/* FFT tuning limit = 0.5 M */
+/* Generated by tuneup.c, 2017-02-23, gcc 5.4 */
#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 2
-#define MOD_1_1_TO_MOD_1_2_THRESHOLD 9
-#define MOD_1_2_TO_MOD_1_4_THRESHOLD 102
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 3
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 10
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD MP_SIZE_T_MAX
#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 9
#define USE_PREINV_DIVREM_1 1 /* native */
#define DIV_QR_1N_PI1_METHOD 1
@@ -49,147 +48,125 @@
#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 15
+#define BMOD_1_TO_MOD_1_THRESHOLD 17
-#define DIV_1_VS_MUL_1_PERCENT 290
+#define DIV_1_VS_MUL_1_PERCENT 265
#define MUL_TOOM22_THRESHOLD 28
-#define MUL_TOOM33_THRESHOLD 116
-#define MUL_TOOM44_THRESHOLD 169
-#define MUL_TOOM6H_THRESHOLD 399
+#define MUL_TOOM33_THRESHOLD 114
+#define MUL_TOOM44_THRESHOLD 178
+#define MUL_TOOM6H_THRESHOLD 238
#define MUL_TOOM8H_THRESHOLD 597
#define MUL_TOOM32_TO_TOOM43_THRESHOLD 113
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 115
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 130
#define MUL_TOOM42_TO_TOOM53_THRESHOLD 115
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 115
-#define MUL_TOOM43_TO_TOOM54_THRESHOLD 160
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 120
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 170
#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
-#define SQR_TOOM2_THRESHOLD 38
+#define SQR_TOOM2_THRESHOLD 40
#define SQR_TOOM3_THRESHOLD 126
-#define SQR_TOOM4_THRESHOLD 345
-#define SQR_TOOM6_THRESHOLD 470
+#define SQR_TOOM4_THRESHOLD 342
+#define SQR_TOOM6_THRESHOLD 446
#define SQR_TOOM8_THRESHOLD 644
#define MULMID_TOOM42_THRESHOLD 52
-#define MULMOD_BNM1_THRESHOLD 17
-#define SQRMOD_BNM1_THRESHOLD 19
+#define MULMOD_BNM1_THRESHOLD 19
+#define SQRMOD_BNM1_THRESHOLD 20
-#define MUL_FFT_MODF_THRESHOLD 500 /* k = 5 */
+#define MUL_FFT_MODF_THRESHOLD 560 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 500, 5}, { 26, 6}, { 27, 7}, { 15, 6}, \
- { 31, 7}, { 19, 6}, { 39, 7}, { 25, 6}, \
- { 51, 7}, { 27, 8}, { 15, 7}, { 33, 8}, \
- { 19, 7}, { 41, 8}, { 23, 7}, { 51, 8}, \
- { 27, 9}, { 15, 8}, { 31, 7}, { 63, 8}, \
- { 39, 9}, { 23, 8}, { 51,10}, { 15, 9}, \
- { 31, 8}, { 67, 9}, { 47, 8}, { 99, 9}, \
- { 55,10}, { 31, 9}, { 79,10}, { 47, 9}, \
- { 95,11}, { 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, 8}, { 767,12}, { 63,11}, \
- { 127,10}, { 255, 9}, { 511,10}, { 271, 9}, \
- { 543,10}, { 287,11}, { 159,10}, { 319, 9}, \
- { 639,10}, { 335, 9}, { 671,10}, { 351,11}, \
- { 191,10}, { 383, 9}, { 767,10}, { 415,11}, \
- { 223,12}, { 127,11}, { 255,10}, { 543,11}, \
- { 287,10}, { 575,11}, { 319,10}, { 639,11}, \
- { 351,12}, { 191,11}, { 383,10}, { 767,11}, \
- { 447,13}, { 127,12}, { 255,11}, { 607,12}, \
- { 319,11}, { 735,12}, { 383,11}, { 831,12}, \
- { 447,11}, { 895,13}, { 255,12}, { 511,11}, \
- { 1023,12}, { 703,13}, { 383,12}, { 895,14}, \
- { 255,13}, { 511,12}, { 1151,13}, { 639,12}, \
- { 1471,13}, { 767,12}, { 1663,13}, { 895,14}, \
- { 511,13}, { 1023,12}, { 2111,13}, { 1151,12}, \
- { 2431,13}, { 1279,14}, { 767,13}, { 1535,12}, \
- { 3135,15}, { 511,14}, { 1023,13}, { 2303,14}, \
- { 1279,13}, { 2559,12}, { 5119,13}, { 2815,14}, \
- { 16384,15}, { 32768,16} }
-#define MUL_FFT_TABLE3_SIZE 122
-#define MUL_FFT_THRESHOLD 5312
-
-#define SQR_FFT_MODF_THRESHOLD 468 /* k = 5 */
-#define SQR_FFT_TABLE3 \
- { { 468, 5}, { 25, 6}, { 27, 7}, { 15, 6}, \
+ { { 560, 5}, { 25, 6}, { 27, 7}, { 15, 6}, \
{ 31, 7}, { 19, 6}, { 39, 7}, { 25, 6}, \
{ 51, 7}, { 27, 8}, { 15, 7}, { 33, 8}, \
{ 19, 7}, { 41, 8}, { 23, 7}, { 51, 8}, \
{ 27, 9}, { 15, 8}, { 31, 7}, { 63, 8}, \
- { 39, 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}, { 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}, \
+ { 39, 9}, { 23, 8}, { 55, 9}, { 31, 8}, \
+ { 67, 9}, { 39, 8}, { 83, 9}, { 47, 8}, \
+ { 99, 9}, { 55,10}, { 31, 9}, { 79,10}, \
+ { 47, 9}, { 95,11}, { 31,10}, { 63, 9}, \
+ { 135,10}, { 79, 9}, { 167,10}, { 95, 9}, \
+ { 191,10}, { 111,11}, { 63,10}, { 127, 9}, \
+ { 255,10}, { 143, 9}, { 287, 8}, { 575,10}, \
{ 159, 9}, { 319,11}, { 95,10}, { 191, 9}, \
- { 383, 8}, { 767,12}, { 63,11}, { 127,10}, \
- { 255, 9}, { 511,10}, { 271, 9}, { 543,10}, \
- { 287,11}, { 159,10}, { 319, 9}, { 639,10}, \
- { 335, 9}, { 671,10}, { 351, 9}, { 703,11}, \
- { 191,10}, { 383, 9}, { 767,10}, { 415,11}, \
- { 223,12}, { 127,11}, { 255,10}, { 511,11}, \
- { 287,10}, { 575,11}, { 319,10}, { 639,11}, \
- { 351,12}, { 191,11}, { 383,10}, { 767,11}, \
- { 447,13}, { 127,12}, { 255,11}, { 607,12}, \
- { 319,11}, { 735,12}, { 383,11}, { 831,12}, \
- { 447,13}, { 255,12}, { 511,11}, { 1023,12}, \
- { 575,11}, { 1151,12}, { 639,11}, { 1279,12}, \
- { 703,13}, { 383,12}, { 895,14}, { 255,13}, \
- { 511,12}, { 1151,13}, { 639,12}, { 1407,13}, \
- { 767,12}, { 1663,13}, { 895,14}, { 511,13}, \
- { 1023,12}, { 2047,13}, { 1151,12}, { 2431,13}, \
- { 1279,14}, { 767,13}, { 1535,12}, { 3135,15}, \
- { 511,14}, { 1023,13}, { 2175,14}, { 1279,13}, \
- { 2687,14}, { 16384,15}, { 32768,16} }
-#define SQR_FFT_TABLE3_SIZE 127
-#define SQR_FFT_THRESHOLD 4736
+ { 383, 8}, { 767,12}, { 63,11}, { 127, 9}, \
+ { 511,10}, { 271, 9}, { 543, 8}, { 1087,10}, \
+ { 287, 9}, { 575,10}, { 303,11}, { 159,10}, \
+ { 319, 9}, { 639,10}, { 335, 9}, { 671,10}, \
+ { 351, 9}, { 735,11}, { 191,10}, { 383, 9}, \
+ { 767,10}, { 399, 9}, { 799,10}, { 415, 9}, \
+ { 831,11}, { 223,10}, { 447,12}, { 4096,13}, \
+ { 8192,14}, { 16384,15}, { 32768,16} }
+#define MUL_FFT_TABLE3_SIZE 83
+#define MUL_FFT_THRESHOLD 5760
+
+#define SQR_FFT_MODF_THRESHOLD 525 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 525, 5}, { 25, 6}, { 13, 5}, { 27, 6}, \
+ { 27, 7}, { 15, 6}, { 32, 7}, { 19, 6}, \
+ { 39, 7}, { 25, 6}, { 51, 7}, { 27, 8}, \
+ { 15, 7}, { 33, 8}, { 19, 7}, { 41, 8}, \
+ { 23, 7}, { 51, 8}, { 27, 9}, { 15, 8}, \
+ { 31, 7}, { 63, 8}, { 39, 9}, { 23, 8}, \
+ { 55,10}, { 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}, { 191,10}, \
+ { 111,11}, { 63,10}, { 143, 9}, { 287,10}, \
+ { 159,11}, { 95,10}, { 191, 9}, { 383, 8}, \
+ { 767,12}, { 63,11}, { 127, 9}, { 511,10}, \
+ { 271, 9}, { 543,10}, { 287, 9}, { 575,11}, \
+ { 159,10}, { 319, 9}, { 639,10}, { 335, 9}, \
+ { 671,10}, { 351, 9}, { 735,11}, { 191,10}, \
+ { 383, 9}, { 767,10}, { 399, 9}, { 799,10}, \
+ { 415, 9}, { 831,11}, { 223,12}, { 4096,13}, \
+ { 8192,14}, { 16384,15}, { 32768,16} }
+#define SQR_FFT_TABLE3_SIZE 79
+#define SQR_FFT_THRESHOLD 5312
#define MULLO_BASECASE_THRESHOLD 0 /* always */
-#define MULLO_DC_THRESHOLD 38
+#define MULLO_DC_THRESHOLD 37
#define MULLO_MUL_N_THRESHOLD 8907
#define SQRLO_BASECASE_THRESHOLD 10
-#define SQRLO_DC_THRESHOLD 35
-#define SQRLO_SQR_THRESHOLD 8907
+#define SQRLO_DC_THRESHOLD 33
+#define SQRLO_SQR_THRESHOLD 10323
-#define DC_DIV_QR_THRESHOLD 54
-#define DC_DIVAPPR_Q_THRESHOLD 266
+#define DC_DIV_QR_THRESHOLD 57
+#define DC_DIVAPPR_Q_THRESHOLD 268
#define DC_BDIV_QR_THRESHOLD 48
#define DC_BDIV_Q_THRESHOLD 296
#define INV_MULMOD_BNM1_THRESHOLD 54
-#define INV_NEWTON_THRESHOLD 274
-#define INV_APPR_THRESHOLD 276
+#define INV_NEWTON_THRESHOLD 262
+#define INV_APPR_THRESHOLD 260
-#define BINV_NEWTON_THRESHOLD 348
-#define REDC_1_TO_REDC_2_THRESHOLD 59
+#define BINV_NEWTON_THRESHOLD 372
+#define REDC_1_TO_REDC_2_THRESHOLD 62
#define REDC_2_TO_REDC_N_THRESHOLD 0 /* always */
#define MU_DIV_QR_THRESHOLD 1787
-#define MU_DIVAPPR_Q_THRESHOLD 1787
-#define MUPI_DIV_QR_THRESHOLD 122
+#define MU_DIVAPPR_Q_THRESHOLD 1718
+#define MUPI_DIV_QR_THRESHOLD 99
#define MU_BDIV_QR_THRESHOLD 1528
-#define MU_BDIV_Q_THRESHOLD 1752
+#define MU_BDIV_Q_THRESHOLD 1836
-#define POWM_SEC_TABLE 1,32,224,398,2211
+#define POWM_SEC_TABLE 1,32,161,473,1509
#define GET_STR_DC_THRESHOLD 16
-#define GET_STR_PRECOMPUTE_THRESHOLD 30
+#define GET_STR_PRECOMPUTE_THRESHOLD 35
#define SET_STR_DC_THRESHOLD 100
-#define SET_STR_PRECOMPUTE_THRESHOLD 807
-
-#define FAC_DSC_THRESHOLD 309
-#define FAC_ODD_THRESHOLD 28
+#define SET_STR_PRECOMPUTE_THRESHOLD 1057
-#define MATRIX22_STRASSEN_THRESHOLD 25
-#define HGCD_THRESHOLD 153
-#define HGCD_APPR_THRESHOLD 176
-#define HGCD_REDUCE_THRESHOLD 3014
-#define GCD_DC_THRESHOLD 667
-#define GCDEXT_DC_THRESHOLD 483
+#define FAC_DSC_THRESHOLD 312
+#define FAC_ODD_THRESHOLD 27
+
+#define MATRIX22_STRASSEN_THRESHOLD 31
+#define HGCD_THRESHOLD 145
+#define HGCD_APPR_THRESHOLD 173
+#define HGCD_REDUCE_THRESHOLD 3389
+#define GCD_DC_THRESHOLD 684
+#define GCDEXT_DC_THRESHOLD 469
#define JACOBI_BASE_METHOD 4
diff -r bb7e1eae88ae -r 65f365154912 mpn/arm/v7a/cora7/gmp-mparam.h
--- a/mpn/arm/v7a/cora7/gmp-mparam.h Thu Feb 23 05:13:19 2017 +0100
+++ b/mpn/arm/v7a/cora7/gmp-mparam.h Thu Feb 23 14:14:44 2017 +0100
@@ -1,7 +1,6 @@
/* gmp-mparam.h -- Compiler/machine parameter header file.
-Copyright 1991, 1993, 1994, 1999-2003, 2009, 2010, 2012, 2015 Free Software
-Foundation, Inc.
+Copyright 2017 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
@@ -33,59 +32,59 @@
#define GMP_LIMB_BYTES 4
/* 900 MHz Cortex-A7 (raspberry pi2) */
-/* FFT tuning limit = 25 M */
-/* Generated by tuneup.c, 2015-05-15, gcc 4.6 */
+/* FFT tuning limit = 0.5 M */
+/* Generated by tuneup.c, 2017-02-23, gcc 4.9 */
#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_1_1_TO_MOD_1_2_THRESHOLD 7
+#define MOD_1N_TO_MOD_1_1_THRESHOLD 7
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 8
+#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 18
#define USE_PREINV_DIVREM_1 1 /* native */
#define DIV_QR_1N_PI1_METHOD 1
-#define DIV_QR_1_NORM_THRESHOLD 16
-#define DIV_QR_1_UNNORM_THRESHOLD 1
+#define DIV_QR_1_NORM_THRESHOLD MP_SIZE_T_MAX /* never */
More information about the gmp-commit
mailing list