[Gmp-commit] /var/hg/gmp: 6 new changesets
mercurial at gmplib.org
mercurial at gmplib.org
Sun Jun 4 01:07:37 UTC 2017
details: /var/hg/gmp/rev/71296a4c885e
changeset: 17421:71296a4c885e
user: Torbjorn Granlund <tg at gmplib.org>
date: Sat Jun 03 23:55:10 2017 +0200
description:
Fix comment typo.
details: /var/hg/gmp/rev/fc8f8817aa99
changeset: 17422:fc8f8817aa99
user: Torbjorn Granlund <tg at gmplib.org>
date: Sat Jun 03 23:57:45 2017 +0200
description:
Expand some instructions as .byte sequences.
details: /var/hg/gmp/rev/5a4f82a2d81b
changeset: 17423:5a4f82a2d81b
user: Torbjorn Granlund <tg at gmplib.org>
date: Sun Jun 04 00:23:03 2017 +0200
description:
Amend comments and c/l tables.
details: /var/hg/gmp/rev/eb9bcde939e8
changeset: 17424:eb9bcde939e8
user: Torbjorn Granlund <tg at gmplib.org>
date: Sun Jun 04 03:05:43 2017 +0200
description:
Rename bobcat -> bt1.
details: /var/hg/gmp/rev/ffce31edae41
changeset: 17425:ffce31edae41
user: Torbjorn Granlund <tg at gmplib.org>
date: Sun Jun 04 03:06:28 2017 +0200
description:
Add bt2 grabbers for copyi, copyd, com.
details: /var/hg/gmp/rev/330407782736
changeset: 17426:330407782736
user: Torbjorn Granlund <tg at gmplib.org>
date: Sun Jun 04 03:06:58 2017 +0200
description:
Use bt1/bt2 for bobcat and jaguar dirs.
diffstat:
configure.ac | 12 +-
mpn/x86/bobcat/gmp-mparam.h | 202 -------------
mpn/x86/bt1/gmp-mparam.h | 202 +++++++++++++
mpn/x86_64/aors_n.asm | 13 +-
mpn/x86_64/bd1/hamdist.asm | 22 +-
mpn/x86_64/bd1/popcount.asm | 22 +-
mpn/x86_64/bobcat/aors_n.asm | 158 ----------
mpn/x86_64/bobcat/aorsmul_1.asm | 192 ------------
mpn/x86_64/bobcat/copyd.asm | 91 -----
mpn/x86_64/bobcat/copyi.asm | 94 ------
mpn/x86_64/bobcat/gmp-mparam.h | 180 -----------
mpn/x86_64/bobcat/mul_1.asm | 196 ------------
mpn/x86_64/bobcat/mul_basecase.asm | 486 -------------------------------
mpn/x86_64/bobcat/redc_1.asm | 507 ---------------------------------
mpn/x86_64/bobcat/sqr_basecase.asm | 565 -------------------------------------
mpn/x86_64/bt1/aors_n.asm | 158 ++++++++++
mpn/x86_64/bt1/aorsmul_1.asm | 192 ++++++++++++
mpn/x86_64/bt1/copyd.asm | 91 +++++
mpn/x86_64/bt1/copyi.asm | 94 ++++++
mpn/x86_64/bt1/gmp-mparam.h | 180 +++++++++++
mpn/x86_64/bt1/mul_1.asm | 196 ++++++++++++
mpn/x86_64/bt1/mul_basecase.asm | 486 +++++++++++++++++++++++++++++++
mpn/x86_64/bt1/redc_1.asm | 507 +++++++++++++++++++++++++++++++++
mpn/x86_64/bt1/sqr_basecase.asm | 565 +++++++++++++++++++++++++++++++++++++
mpn/x86_64/bt2/com.asm | 37 ++
mpn/x86_64/bt2/copyd.asm | 37 ++
mpn/x86_64/bt2/copyi.asm | 37 ++
mpn/x86_64/core2/popcount.asm | 6 +-
mpn/x86_64/coreinhm/hamdist.asm | 3 +
mpn/x86_64/coreisbr/aors_n.asm | 21 +-
mpn/x86_64/darwin.m4 | 2 +-
31 files changed, 2835 insertions(+), 2719 deletions(-)
diffs (truncated from 5795 to 300 lines):
diff -r 616afdb45cb6 -r 330407782736 configure.ac
--- a/configure.ac Fri Jun 02 13:02:20 2017 +0200
+++ b/configure.ac Sun Jun 04 03:06:58 2017 +0200
@@ -1796,14 +1796,14 @@
bobcat)
gcc_cflags_cpu="-mtune=btver1 -mtune=amdfam10 -mtune=k8"
gcc_cflags_arch="-march=btver1 -march=amdfam10 -march=k8 -march=k8~-mno-sse2"
- path="x86/bobcat x86/k7/mmx x86/k7 x86/mmx x86"
- path_64="x86_64/bobcat x86_64/k10 x86_64/k8 x86_64"
+ path="x86/bt1 x86/k7/mmx x86/k7 x86/mmx x86"
+ path_64="x86_64/bt1 x86_64/k10 x86_64/k8 x86_64"
;;
jaguar | jaguarnoavx)
gcc_cflags_cpu="-mtune=btver2 -mtune=btver1 -mtune=amdfam10 -mtune=k8"
gcc_cflags_arch="-march=btver2 -march=btver1 -march=amdfam10 -march=k8 -march=k8~-mno-sse2"
- path="x86/jaguar x86/bobcat x86/k7/mmx x86/k7 x86/mmx x86"
- path_64="x86_64/jaguar x86_64/bobcat x86_64/k10 x86_64/k8 x86_64"
+ path="x86/bt2 x86/bt1 x86/k7/mmx x86/k7 x86/mmx x86"
+ path_64="x86_64/bt2 x86_64/bt1 x86_64/k10 x86_64/k8 x86_64"
;;
bulldozer | bd1 | bulldozernoavx | bd1noavx)
gcc_cflags_cpu="-mtune=bdver1 -mtune=amdfam10 -mtune=k8"
@@ -2221,7 +2221,7 @@
fat_path="x86 x86/fat x86/i486
x86/k6 x86/k6/mmx x86/k6/k62mmx
x86/k7 x86/k7/mmx
- x86/k8 x86/k10 x86/bobcat
+ x86/k8 x86/k10 x86/bt1
x86/pentium x86/pentium/mmx
x86/p6 x86/p6/mmx x86/p6/p3mmx x86/p6/sse2
x86/pentium4 x86/pentium4/mmx x86/pentium4/sse2
@@ -2234,7 +2234,7 @@
extra_functions_64="$extra_functions_64 fat fat_entry"
path_64="x86_64/fat x86_64"
fat_path="x86_64 x86_64/fat
- x86_64/k8 x86_64/k10 x86_64/bd1 x86_64/bobcat x86_64/zen
+ x86_64/k8 x86_64/k10 x86_64/bd1 x86_64/bt1 x86_64/zen
x86_64/pentium4 x86_64/core2 x86_64/coreinhm x86_64/coreisbr
x86_64/coreihwl x86_64/coreibwl x86_64/skylake x86_64/atom
x86_64/silvermont x86_64/nano"
diff -r 616afdb45cb6 -r 330407782736 mpn/x86/bobcat/gmp-mparam.h
--- a/mpn/x86/bobcat/gmp-mparam.h Fri Jun 02 13:02:20 2017 +0200
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,202 +0,0 @@
-/* x86/bobcat gmp-mparam.h -- Compiler/machine parameter header file.
-
-Copyright 1991, 1993, 1994, 2000-2011, 2014 Free Software Foundation, Inc.
-
-This file is part of the GNU MP Library.
-
-The GNU MP Library is free software; you can redistribute it and/or modify
-it under the terms of either:
-
- * the GNU Lesser General Public License as published by the Free
- Software Foundation; either version 3 of the License, or (at your
- option) any later version.
-
-or
-
- * the GNU General Public License as published by the Free Software
- Foundation; either version 2 of the License, or (at your option) any
- later version.
-
-or both in parallel, as here.
-
-The GNU MP Library is distributed in the hope that it will be useful, but
-WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
-or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
-for more details.
-
-You should have received copies of the GNU General Public License and the
-GNU Lesser General Public License along with the GNU MP Library. If not,
-see https://www.gnu.org/licenses/. */
-
-#define GMP_LIMB_BITS 32
-#define GMP_LIMB_BYTES 4
-
-/* 1600 MHz AMD Bobcat Zacate E-350 */
-/* FFT tuning limit = 25000000 */
-/* Generated by tuneup.c, 2014-03-12, gcc 4.5 */
-
-#define MOD_1_NORM_THRESHOLD 0 /* always */
-#define MOD_1_UNNORM_THRESHOLD 0 /* always */
-#define MOD_1N_TO_MOD_1_1_THRESHOLD 12
-#define MOD_1U_TO_MOD_1_1_THRESHOLD 5
-#define MOD_1_1_TO_MOD_1_2_THRESHOLD 16
-#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 16
-#define USE_PREINV_DIVREM_1 1 /* native */
-#define DIV_QR_1N_PI1_METHOD 1
-#define DIV_QR_1_NORM_THRESHOLD 2
-#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 40
-
-#define DIV_1_VS_MUL_1_PERCENT 231
-
-#define MUL_TOOM22_THRESHOLD 28
-#define MUL_TOOM33_THRESHOLD 90
-#define MUL_TOOM44_THRESHOLD 154
-#define MUL_TOOM6H_THRESHOLD 270
-#define MUL_TOOM8H_THRESHOLD 490
-
-#define MUL_TOOM32_TO_TOOM43_THRESHOLD 89
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 107
-#define MUL_TOOM42_TO_TOOM53_THRESHOLD 95
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 110
-#define MUL_TOOM43_TO_TOOM54_THRESHOLD 130
-
-#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
-#define SQR_TOOM2_THRESHOLD 38
-#define SQR_TOOM3_THRESHOLD 121
-#define SQR_TOOM4_THRESHOLD 212
-#define SQR_TOOM6_THRESHOLD 303
-#define SQR_TOOM8_THRESHOLD 454
-
-#define MULMID_TOOM42_THRESHOLD 74
-
-#define MULMOD_BNM1_THRESHOLD 18
-#define SQRMOD_BNM1_THRESHOLD 23
-
-#define MUL_FFT_MODF_THRESHOLD 660 /* k = 5 */
-#define MUL_FFT_TABLE3 \
- { { 660, 5}, { 25, 6}, { 13, 5}, { 27, 6}, \
- { 27, 7}, { 15, 6}, { 33, 7}, { 17, 6}, \
- { 35, 7}, { 19, 6}, { 39, 7}, { 23, 6}, \
- { 47, 7}, { 27, 8}, { 15, 7}, { 35, 8}, \
- { 19, 7}, { 41, 8}, { 23, 7}, { 49, 8}, \
- { 31, 7}, { 63, 8}, { 39, 9}, { 23, 8}, \
- { 55, 9}, { 31, 8}, { 67, 9}, { 39, 8}, \
- { 79, 9}, { 47, 8}, { 95, 9}, { 55,10}, \
- { 31, 9}, { 63, 8}, { 127, 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}, { 191,12}, { 63,11}, { 127,10}, \
- { 255, 9}, { 511,10}, { 271, 9}, { 543,11}, \
- { 159, 9}, { 639,10}, { 335, 9}, { 671,11}, \
- { 191,10}, { 383, 9}, { 767,10}, { 399, 9}, \
- { 799,11}, { 223,12}, { 127,11}, { 255,10}, \
- { 543, 9}, { 1087,11}, { 287,10}, { 607, 9}, \
- { 1215,10}, { 671,12}, { 191,11}, { 383,10}, \
- { 799, 9}, { 1599,11}, { 415,13}, { 127,12}, \
- { 255,11}, { 543,10}, { 1087,11}, { 607,10}, \
- { 1215,11}, { 671,10}, { 1343,11}, { 735,10}, \
- { 1471,12}, { 383,11}, { 799,10}, { 1599,11}, \
- { 863,12}, { 447,11}, { 991,13}, { 255,12}, \
- { 511,11}, { 1087,12}, { 575,11}, { 1215,12}, \
- { 639,11}, { 1343,12}, { 703,11}, { 1471,13}, \
- { 383,12}, { 767,11}, { 1599,12}, { 831,11}, \
- { 1727,12}, { 959,14}, { 255,13}, { 511,12}, \
- { 1215,13}, { 639,12}, { 1471,13}, { 767,12}, \
- { 1727,13}, { 895,12}, { 1919,14}, { 511,13}, \
- { 1023,12}, { 2111,13}, { 1151,12}, { 2431,13}, \
- { 1407,14}, { 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 139
-#define MUL_FFT_THRESHOLD 7552
-
-#define SQR_FFT_MODF_THRESHOLD 606 /* k = 5 */
-#define SQR_FFT_TABLE3 \
- { { 606, 5}, { 28, 6}, { 15, 5}, { 31, 6}, \
- { 28, 7}, { 15, 6}, { 33, 7}, { 17, 6}, \
- { 35, 7}, { 19, 6}, { 39, 7}, { 23, 6}, \
- { 47, 7}, { 29, 8}, { 15, 7}, { 35, 8}, \
- { 19, 7}, { 41, 8}, { 23, 7}, { 49, 8}, \
- { 31, 7}, { 63, 8}, { 43, 9}, { 23, 8}, \
- { 55, 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}, { 191,11}, { 63,10}, \
- { 159,11}, { 95,10}, { 191,12}, { 63,11}, \
- { 127,10}, { 255, 9}, { 511,10}, { 271, 9}, \
- { 543, 8}, { 1087,11}, { 159,10}, { 319, 9}, \
- { 639,10}, { 335, 9}, { 671, 8}, { 1343,10}, \
- { 351,11}, { 191,10}, { 383, 9}, { 767,10}, \
- { 399, 9}, { 799,10}, { 415, 9}, { 831,12}, \
- { 127,11}, { 255,10}, { 511, 9}, { 1023,10}, \
- { 543, 9}, { 1087,11}, { 287,10}, { 607, 9}, \
- { 1215,11}, { 319,10}, { 671, 9}, { 1343,12}, \
- { 191,11}, { 383,10}, { 799,11}, { 415,10}, \
- { 831,13}, { 127,12}, { 255,11}, { 511,10}, \
- { 1023,11}, { 543,10}, { 1087,11}, { 607,10}, \
- { 1215,12}, { 319,11}, { 671,10}, { 1343,11}, \
- { 735,10}, { 1471,12}, { 383,11}, { 799,10}, \
- { 1599,11}, { 863,12}, { 447,11}, { 991,13}, \
- { 255,12}, { 511,11}, { 1087,12}, { 575,11}, \
- { 1215,12}, { 639,11}, { 1343,12}, { 703,11}, \
- { 1471,13}, { 383,12}, { 767,11}, { 1599,12}, \
- { 831,11}, { 1727,12}, { 959,14}, { 255,13}, \
- { 511,12}, { 1215,13}, { 639,12}, { 1471,13}, \
- { 767,12}, { 1727,13}, { 895,12}, { 1983,14}, \
- { 511,13}, { 1023,12}, { 2111,13}, { 1151,12}, \
- { 2431,13}, { 1407,14}, { 767,13}, { 1663,12}, \
- { 3455,13}, { 1919,15}, { 511,14}, { 1023,13}, \
- { 2175,12}, { 4479,13}, { 2431,14}, { 1279,13}, \
- { 2943,14}, { 16384,15}, { 32768,16} }
-#define SQR_FFT_TABLE3_SIZE 147
-#define SQR_FFT_THRESHOLD 5760
-
-#define MULLO_BASECASE_THRESHOLD 5
-#define MULLO_DC_THRESHOLD 45
-#define MULLO_MUL_N_THRESHOLD 14281
-#define SQRLO_BASECASE_THRESHOLD 7
-#define SQRLO_DC_THRESHOLD 71
-#define SQRLO_SQR_THRESHOLD 10323
-
-#define DC_DIV_QR_THRESHOLD 71
-#define DC_DIVAPPR_Q_THRESHOLD 238
-#define DC_BDIV_QR_THRESHOLD 67
-#define DC_BDIV_Q_THRESHOLD 151
-
-#define INV_MULMOD_BNM1_THRESHOLD 66
-#define INV_NEWTON_THRESHOLD 228
-#define INV_APPR_THRESHOLD 222
-
-#define BINV_NEWTON_THRESHOLD 270
-#define REDC_1_TO_REDC_N_THRESHOLD 71
-
-#define MU_DIV_QR_THRESHOLD 1718
-#define MU_DIVAPPR_Q_THRESHOLD 1718
-#define MUPI_DIV_QR_THRESHOLD 91
-#define MU_BDIV_QR_THRESHOLD 1589
-#define MU_BDIV_Q_THRESHOLD 1718
-
-#define POWM_SEC_TABLE 1,16,96,416,1185
-
-#define GET_STR_DC_THRESHOLD 15
-#define GET_STR_PRECOMPUTE_THRESHOLD 29
-#define SET_STR_DC_THRESHOLD 290
-#define SET_STR_PRECOMPUTE_THRESHOLD 860
-
-#define FAC_DSC_THRESHOLD 141
-#define FAC_ODD_THRESHOLD 50
-
-#define MATRIX22_STRASSEN_THRESHOLD 17
-#define HGCD_THRESHOLD 88
-#define HGCD_APPR_THRESHOLD 137
-#define HGCD_REDUCE_THRESHOLD 3664
-#define GCD_DC_THRESHOLD 465
-#define GCDEXT_DC_THRESHOLD 345
-#define JACOBI_BASE_METHOD 4
diff -r 616afdb45cb6 -r 330407782736 mpn/x86/bt1/gmp-mparam.h
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/x86/bt1/gmp-mparam.h Sun Jun 04 03:06:58 2017 +0200
@@ -0,0 +1,202 @@
+/* x86/bobcat gmp-mparam.h -- Compiler/machine parameter header file.
+
+Copyright 1991, 1993, 1994, 2000-2011, 2014 Free Software Foundation, Inc.
+
+This file is part of the GNU MP Library.
+
+The GNU MP Library is free software; you can redistribute it and/or modify
+it under the terms of either:
+
+ * the GNU Lesser General Public License as published by the Free
+ Software Foundation; either version 3 of the License, or (at your
+ option) any later version.
+
+or
+
+ * the GNU General Public License as published by the Free Software
+ Foundation; either version 2 of the License, or (at your option) any
+ later version.
+
+or both in parallel, as here.
+
+The GNU MP Library is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+for more details.
+
+You should have received copies of the GNU General Public License and the
+GNU Lesser General Public License along with the GNU MP Library. If not,
+see https://www.gnu.org/licenses/. */
+
+#define GMP_LIMB_BITS 32
+#define GMP_LIMB_BYTES 4
+
+/* 1600 MHz AMD Bobcat Zacate E-350 */
+/* FFT tuning limit = 25000000 */
+/* Generated by tuneup.c, 2014-03-12, gcc 4.5 */
+
+#define MOD_1_NORM_THRESHOLD 0 /* always */
+#define MOD_1_UNNORM_THRESHOLD 0 /* always */
+#define MOD_1N_TO_MOD_1_1_THRESHOLD 12
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 5
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 16
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 16
+#define USE_PREINV_DIVREM_1 1 /* native */
+#define DIV_QR_1N_PI1_METHOD 1
+#define DIV_QR_1_NORM_THRESHOLD 2
+#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) */
More information about the gmp-commit
mailing list