[Gmp-commit] /var/hg/gmp: 4 new changesets
mercurial at gmplib.org
mercurial at gmplib.org
Tue Oct 1 21:05:43 UTC 2019
details: /var/hg/gmp/rev/0cf7b9b8aa4a
changeset: 17931:0cf7b9b8aa4a
user: Torbjorn Granlund <tg at gmplib.org>
date: Tue Oct 01 22:45:21 2019 +0200
description:
Let cortex-a7x look in a57 folder.
details: /var/hg/gmp/rev/527e61368705
changeset: 17932:527e61368705
user: Torbjorn Granlund <tg at gmplib.org>
date: Tue Oct 01 22:47:59 2019 +0200
description:
New tuneup files.
details: /var/hg/gmp/rev/3afc9e22897e
changeset: 17933:3afc9e22897e
user: Torbjorn Granlund <tg at gmplib.org>
date: Tue Oct 01 23:04:11 2019 +0200
description:
New tuneup files.
details: /var/hg/gmp/rev/2ced5e1c4a4e
changeset: 17934:2ced5e1c4a4e
user: Torbjorn Granlund <tg at gmplib.org>
date: Tue Oct 01 23:05:40 2019 +0200
description:
Trivial merge.
diffstat:
ChangeLog | 9 +
configure.ac | 4 +-
mini-gmp/ChangeLog | 5 +
mini-gmp/tests/t-gcd.c | 10 +-
mpn/arm/v6/gmp-mparam.h | 193 ++++++++++++++++--------------------
mpn/arm/v7a/cora15/gmp-mparam.h | 157 ++++++++++++++---------------
mpn/arm/v7a/cora17/gmp-mparam.h | 159 +++++++++++++++---------------
mpn/arm/v7a/cora5/gmp-mparam.h | 156 ++++++++++++++---------------
mpn/arm/v7a/cora7/gmp-mparam.h | 164 ++++++++++++++++---------------
mpn/arm/v7a/cora8/gmp-mparam.h | 192 +++++++++++++++---------------------
mpn/arm64/gmp-mparam.h | 206 ++++++++++++++++++++-------------------
mpn/arm64/xgene1/gmp-mparam.h | 123 ++++++++++++-----------
mpn/generic/gcdext_1.c | 7 +-
tests/mpn/Makefile.am | 2 +-
tests/mpn/t-gcdext_1.c | 131 +++++++++++++++++++++++++
15 files changed, 811 insertions(+), 707 deletions(-)
diffs (truncated from 2140 to 300 lines):
diff -r 44543bbf85d6 -r 2ced5e1c4a4e ChangeLog
--- a/ChangeLog Sun Sep 29 22:48:44 2019 +0200
+++ b/ChangeLog Tue Oct 01 23:05:40 2019 +0200
@@ -1,3 +1,12 @@
+2019-10-01 Niels Möller <nisse at lysator.liu.se>
+
+ * mpn/generic/gcdext_1.c (mpn_gcdext_1) [GCDEXT_1_USE_BINARY]: Fix
+ canonicalization condition.
+
+2019-09-30 Niels Möller <nisse at lysator.liu.se>
+
+ * tests/mpn/t-gcdext_1.c: New test.
+
2019-09-23 Niels Möller <nisse at lysator.liu.se>
* gmp-impl.h (hgcd2_func_t) [TUNE_PROGRAM_BUILD]: New typedef.
diff -r 44543bbf85d6 -r 2ced5e1c4a4e configure.ac
--- a/configure.ac Sun Sep 29 22:48:44 2019 +0200
+++ b/configure.ac Tue Oct 01 23:05:40 2019 +0200
@@ -741,10 +741,10 @@
[armcortexa7[2-9] | armcortexa7[2-9]neon])
abilist="64 32"
path="arm/v7a/cora15/neon arm/neon arm/v7a/cora15 arm/v6t2 arm/v6 arm/v5 arm"
- path_64="arm64/cora72 arm64"
+ path_64="arm64/cora57 arm64"
gcc_cflags_arch="-march=armv8-a"
gcc_cflags_neon="-mfpu=neon"
- gcc_cflags_tune="-mtune=cortex-a72"
+ gcc_cflags_tune="-mtune=cortex-a72 -mtune=cortex-a57"
;;
armexynosm1)
abilist="64 32"
diff -r 44543bbf85d6 -r 2ced5e1c4a4e mini-gmp/ChangeLog
--- a/mini-gmp/ChangeLog Sun Sep 29 22:48:44 2019 +0200
+++ b/mini-gmp/ChangeLog Tue Oct 01 23:05:40 2019 +0200
@@ -1,3 +1,8 @@
+2019-09-30 Niels Möller <nisse at lysator.liu.se>
+
+ * tests/t-gcd.c (gcdext_valid_p): Stricter checks for gcdext
+ corner cases.
+
2018-11-07 Marco Bodrato <bodrato at mail.dm.unipi.it>
* mini-gmp/mini-gmp.c: Silence a couple of warnings.
diff -r 44543bbf85d6 -r 2ced5e1c4a4e mini-gmp/tests/t-gcd.c
--- a/mini-gmp/tests/t-gcd.c Sun Sep 29 22:48:44 2019 +0200
+++ b/mini-gmp/tests/t-gcd.c Tue Oct 01 23:05:40 2019 +0200
@@ -41,13 +41,15 @@
if (mpz_sgn (a) == 0)
{
/* Must have g == abs (b). Any value for s is in some sense "correct",
- but it makes sense to require that s == 0. */
- return mpz_cmpabs (g, b) == 0 && mpz_sgn (s) == 0;
+ but it makes sense to require that s == 0, t = sgn (b)*/
+ return mpz_cmpabs (g, b) == 0
+ && mpz_sgn (s) == 0 && mpz_cmp_si (t, mpz_sgn (b)) == 0;
}
else if (mpz_sgn (b) == 0)
{
- /* Must have g == abs (a), s == sign (a) */
- return mpz_cmpabs (g, a) == 0 && mpz_cmp_si (s, mpz_sgn (a)) == 0;
+ /* Must have g == abs (a), s == sign (a), t = 0 */
+ return mpz_cmpabs (g, a) == 0
+ && mpz_cmp_si (s, mpz_sgn (a)) == 0 && mpz_sgn (t) == 0;
}
if (mpz_sgn (g) <= 0)
diff -r 44543bbf85d6 -r 2ced5e1c4a4e mpn/arm/v6/gmp-mparam.h
--- a/mpn/arm/v6/gmp-mparam.h Sun Sep 29 22:48:44 2019 +0200
+++ b/mpn/arm/v6/gmp-mparam.h Tue Oct 01 23:05:40 2019 +0200
@@ -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 2019 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
@@ -33,61 +32,62 @@
#define GMP_LIMB_BYTES 4
/* 700 MHz ARM11 (raspberry pi) */
-/* FFT tuning limit = 10 M */
-/* Generated by tuneup.c, 2015-10-05, gcc 4.6 */
+/* FFT tuning limit = 0.5 M */
+/* Generated by tuneup.c, 2019-10-01, gcc 8.3 */
#define DIVREM_1_NORM_THRESHOLD 0 /* preinv always */
#define DIVREM_1_UNNORM_THRESHOLD 0 /* always */
#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_1N_TO_MOD_1_1_THRESHOLD 8
#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 19
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 23
#define USE_PREINV_DIVREM_1 1 /* preinv always */
-#define DIV_QR_1N_PI1_METHOD 1
+#define DIV_QR_1N_PI1_METHOD 1 /* 71.04% faster than 2 */
#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 (native) */
-#define BMOD_1_TO_MOD_1_THRESHOLD 39
+#define BMOD_1_TO_MOD_1_THRESHOLD 40
-#define DIV_1_VS_MUL_1_PERCENT 178
+#define DIV_1_VS_MUL_1_PERCENT 253
-#define MUL_TOOM22_THRESHOLD 44
-#define MUL_TOOM33_THRESHOLD 138
-#define MUL_TOOM44_THRESHOLD 517
+#define MUL_TOOM22_THRESHOLD 38
+#define MUL_TOOM33_THRESHOLD 130
+#define MUL_TOOM44_THRESHOLD 512
#define MUL_TOOM6H_THRESHOLD 0 /* always */
-#define MUL_TOOM8H_THRESHOLD 692
+#define MUL_TOOM8H_THRESHOLD 620
-#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 MUL_TOOM32_TO_TOOM43_THRESHOLD 209
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 608
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 211
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 186
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 295
#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
-#define SQR_TOOM2_THRESHOLD 56
-#define SQR_TOOM3_THRESHOLD 173
-#define SQR_TOOM4_THRESHOLD 711
+#define SQR_TOOM2_THRESHOLD 55
+#define SQR_TOOM3_THRESHOLD 194
+#define SQR_TOOM4_THRESHOLD 507
#define SQR_TOOM6_THRESHOLD 0 /* always */
-#define SQR_TOOM8_THRESHOLD 915
+#define SQR_TOOM8_THRESHOLD 866
-#define MULMID_TOOM42_THRESHOLD 70
+#define MULMID_TOOM42_THRESHOLD 64
-#define MULMOD_BNM1_THRESHOLD 24
-#define SQRMOD_BNM1_THRESHOLD 28
+#define MULMOD_BNM1_THRESHOLD 21
+#define SQRMOD_BNM1_THRESHOLD 27
#define MUL_FFT_MODF_THRESHOLD 560 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 560, 5}, { 27, 6}, { 15, 5}, { 31, 6}, \
- { 28, 7}, { 15, 6}, { 33, 7}, { 17, 6}, \
- { 36, 7}, { 19, 6}, { 39, 7}, { 23, 6}, \
+ { { 560, 5}, { 25, 6}, { 13, 5}, { 28, 6}, \
+ { 15, 5}, { 31, 6}, { 29, 7}, { 15, 6}, \
+ { 33, 7}, { 17, 6}, { 35, 7}, { 19, 6}, \
+ { 39, 7}, { 21, 6}, { 43, 7}, { 23, 6}, \
{ 47, 7}, { 25, 6}, { 51, 7}, { 27, 6}, \
- { 55, 7}, { 29, 8}, { 15, 7}, { 37, 8}, \
+ { 55, 7}, { 29, 8}, { 15, 7}, { 35, 8}, \
{ 19, 7}, { 43, 8}, { 23, 7}, { 51, 8}, \
- { 27, 7}, { 55, 8}, { 31, 7}, { 63, 8}, \
+ { 27, 7}, { 55, 8}, { 31, 7}, { 65, 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}, \
@@ -95,96 +95,77 @@
{ 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
+ { 63,11}, { 127,10}, { 287,11}, { 159,10}, \
+ { 351,11}, { 191,10}, { 399,11}, { 223,12}, \
+ { 4096,13}, { 8192,14}, { 16384,15}, { 32768,16} }
+#define MUL_FFT_TABLE3_SIZE 72
+#define MUL_FFT_THRESHOLD 6592
-#define SQR_FFT_MODF_THRESHOLD 505 /* k = 5 */
+#define SQR_FFT_MODF_THRESHOLD 525 /* 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}, \
- { 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}, { 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 109
-#define SQR_FFT_THRESHOLD 4672
+ { { 525, 5}, { 25, 6}, { 13, 5}, { 27, 6}, \
+ { 15, 5}, { 31, 6}, { 29, 7}, { 15, 6}, \
+ { 33, 7}, { 17, 6}, { 35, 7}, { 19, 6}, \
+ { 39, 7}, { 23, 6}, { 47, 7}, { 29, 8}, \
+ { 15, 7}, { 37, 8}, { 19, 7}, { 43, 8}, \
+ { 23, 7}, { 49, 8}, { 27, 7}, { 55, 9}, \
+ { 15, 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}, { 167,10}, \
+ { 95, 9}, { 191,10}, { 111,11}, { 63,10}, \
+ { 143, 9}, { 287,10}, { 159,11}, { 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}, { 4096,13}, { 8192,14}, \
+ { 16384,15}, { 32768,16} }
+#define SQR_FFT_TABLE3_SIZE 74
+#define SQR_FFT_THRESHOLD 4736
#define MULLO_BASECASE_THRESHOLD 0 /* always */
-#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 MULLO_DC_THRESHOLD 54
+#define MULLO_MUL_N_THRESHOLD 13071
+#define SQRLO_BASECASE_THRESHOLD 12
+#define SQRLO_DC_THRESHOLD 108
+#define SQRLO_SQR_THRESHOLD 8937
-#define DC_DIV_QR_THRESHOLD 46
+#define DC_DIV_QR_THRESHOLD 41
#define DC_DIVAPPR_Q_THRESHOLD 148
#define DC_BDIV_QR_THRESHOLD 57
-#define DC_BDIV_Q_THRESHOLD 160
+#define DC_BDIV_Q_THRESHOLD 158
-#define INV_MULMOD_BNM1_THRESHOLD 86
-#define INV_NEWTON_THRESHOLD 138
-#define INV_APPR_THRESHOLD 139
+#define INV_MULMOD_BNM1_THRESHOLD 74
+#define INV_NEWTON_THRESHOLD 146
+#define INV_APPR_THRESHOLD 147
-#define BINV_NEWTON_THRESHOLD 216
+#define BINV_NEWTON_THRESHOLD 372
#define REDC_1_TO_REDC_2_THRESHOLD 6
-#define REDC_2_TO_REDC_N_THRESHOLD 124
+#define REDC_2_TO_REDC_N_THRESHOLD 134
-#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 MU_DIV_QR_THRESHOLD 2857
+#define MU_DIVAPPR_Q_THRESHOLD 2801
+#define MUPI_DIV_QR_THRESHOLD 79
+#define MU_BDIV_QR_THRESHOLD 2541
+#define MU_BDIV_Q_THRESHOLD 2686
-#define POWM_SEC_TABLE 5,26,143,446
+#define POWM_SEC_TABLE 7,19,133,473
-#define GET_STR_DC_THRESHOLD 20
-#define GET_STR_PRECOMPUTE_THRESHOLD 39
-#define SET_STR_DC_THRESHOLD 527
More information about the gmp-commit
mailing list