Source-Changes-HG archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

[src/trunk]: src/external/lgpl3/gmp/lib/libgmp/arch re-run native-gmp for gmp...



details:   https://anonhg.NetBSD.org/src/rev/65a83fd3491a
branches:  trunk
changeset: 944397:65a83fd3491a
user:      mrg <mrg%NetBSD.org@localhost>
date:      Sun Sep 27 21:19:36 2020 +0000

description:
re-run native-gmp for gmp 6.2.0 and arm:  run with a v4 toolchain
instead of a v7 toolchain, so it works on all.

should fix latest build mess.

future: test the speed of this vs armv[567] specific on armv[567].

diffstat:

 external/lgpl3/gmp/lib/libgmp/arch/arm/config.h       |   28 +-
 external/lgpl3/gmp/lib/libgmp/arch/arm/config.m4      |    7 +-
 external/lgpl3/gmp/lib/libgmp/arch/arm/gmp-mparam.h   |  228 +++++------------
 external/lgpl3/gmp/lib/libgmp/arch/arm/gmp.h          |   11 +-
 external/lgpl3/gmp/lib/libgmp/arch/arm/srcs.mk        |   36 +-
 external/lgpl3/gmp/lib/libgmp/arch/armeb/config.h     |   28 +-
 external/lgpl3/gmp/lib/libgmp/arch/armeb/config.m4    |    7 +-
 external/lgpl3/gmp/lib/libgmp/arch/armeb/gmp-mparam.h |  228 +++++------------
 external/lgpl3/gmp/lib/libgmp/arch/armeb/gmp.h        |   11 +-
 external/lgpl3/gmp/lib/libgmp/arch/armeb/srcs.mk      |   36 +-
 10 files changed, 232 insertions(+), 388 deletions(-)

diffs (truncated from 1110 to 300 lines):

diff -r bb616c8f46eb -r 65a83fd3491a external/lgpl3/gmp/lib/libgmp/arch/arm/config.h
--- a/external/lgpl3/gmp/lib/libgmp/arch/arm/config.h   Sun Sep 27 20:13:44 2020 +0000
+++ b/external/lgpl3/gmp/lib/libgmp/arch/arm/config.h   Sun Sep 27 21:19:36 2020 +0000
@@ -37,7 +37,7 @@
 
 /* The gmp-mparam.h file (a string) the tune program should suggest updating.
    */
-#define GMP_MPARAM_H_SUGGEST "./mpn/arm/v7a/cora5/gmp-mparam.h"
+#define GMP_MPARAM_H_SUGGEST "./mpn/arm/gmp-mparam.h"
 
 /* Define to 1 if you have the `alarm' function. */
 #define HAVE_ALARM 1
@@ -278,8 +278,8 @@
 /* #undef HAVE_NATIVE_mpn_addlsh2_nc_ip2 */
 /* #undef HAVE_NATIVE_mpn_addlsh_nc_ip2 */
 /* #undef HAVE_NATIVE_mpn_addmul_1c */
-#define HAVE_NATIVE_mpn_addmul_2 1
-#define HAVE_NATIVE_mpn_addmul_3 1
+/* #undef HAVE_NATIVE_mpn_addmul_2 */
+/* #undef HAVE_NATIVE_mpn_addmul_3 */
 /* #undef HAVE_NATIVE_mpn_addmul_4 */
 /* #undef HAVE_NATIVE_mpn_addmul_5 */
 /* #undef HAVE_NATIVE_mpn_addmul_6 */
@@ -300,13 +300,13 @@
 /* #undef HAVE_NATIVE_mpn_div_qr_2 */
 #define HAVE_NATIVE_mpn_divexact_1 1
 /* #undef HAVE_NATIVE_mpn_divexact_by3c */
-#define HAVE_NATIVE_mpn_divrem_1 1
+/* #undef HAVE_NATIVE_mpn_divrem_1 */
 /* #undef HAVE_NATIVE_mpn_divrem_1c */
 /* #undef HAVE_NATIVE_mpn_divrem_2 */
 /* #undef HAVE_NATIVE_mpn_gcd_1 */
-#define HAVE_NATIVE_mpn_gcd_11 1
-#define HAVE_NATIVE_mpn_gcd_22 1
-#define HAVE_NATIVE_mpn_hamdist 1
+/* #undef HAVE_NATIVE_mpn_gcd_11 */
+/* #undef HAVE_NATIVE_mpn_gcd_22 */
+/* #undef HAVE_NATIVE_mpn_hamdist */
 #define HAVE_NATIVE_mpn_invert_limb 1
 #define HAVE_NATIVE_mpn_ior_n 1
 #define HAVE_NATIVE_mpn_iorn_n 1
@@ -314,16 +314,16 @@
 #define HAVE_NATIVE_mpn_lshiftc 1
 /* #undef HAVE_NATIVE_mpn_lshsub_n */
 /* #undef HAVE_NATIVE_mpn_mod_1 */
-#define HAVE_NATIVE_mpn_mod_1_1p 1
+/* #undef HAVE_NATIVE_mpn_mod_1_1p */
 /* #undef HAVE_NATIVE_mpn_mod_1c */
-#define HAVE_NATIVE_mpn_mod_1s_2p 1
+/* #undef HAVE_NATIVE_mpn_mod_1s_2p */
 /* #undef HAVE_NATIVE_mpn_mod_1s_4p */
 #define HAVE_NATIVE_mpn_mod_34lsub1 1
 /* #undef HAVE_NATIVE_mpn_modexact_1_odd */
 #define HAVE_NATIVE_mpn_modexact_1c_odd 1
 #define HAVE_NATIVE_mpn_mul_1 1
 /* #undef HAVE_NATIVE_mpn_mul_1c */
-#define HAVE_NATIVE_mpn_mul_2 1
+/* #undef HAVE_NATIVE_mpn_mul_2 */
 /* #undef HAVE_NATIVE_mpn_mul_3 */
 /* #undef HAVE_NATIVE_mpn_mul_4 */
 /* #undef HAVE_NATIVE_mpn_mul_5 */
@@ -332,8 +332,8 @@
 /* #undef HAVE_NATIVE_mpn_mullo_basecase */
 #define HAVE_NATIVE_mpn_nand_n 1
 #define HAVE_NATIVE_mpn_nior_n 1
-#define HAVE_NATIVE_mpn_popcount 1
-#define HAVE_NATIVE_mpn_preinv_divrem_1 1
+/* #undef HAVE_NATIVE_mpn_popcount */
+/* #undef HAVE_NATIVE_mpn_preinv_divrem_1 */
 /* #undef HAVE_NATIVE_mpn_preinv_mod_1 */
 /* #undef HAVE_NATIVE_mpn_redc_1 */
 /* #undef HAVE_NATIVE_mpn_redc_2 */
@@ -349,7 +349,7 @@
 /* #undef HAVE_NATIVE_mpn_rsh1sub_nc */
 #define HAVE_NATIVE_mpn_rshift 1
 /* #undef HAVE_NATIVE_mpn_sbpi1_bdiv_r */
-#define HAVE_NATIVE_mpn_sqr_basecase 1
+/* #undef HAVE_NATIVE_mpn_sqr_basecase */
 /* #undef HAVE_NATIVE_mpn_sqr_diagonal */
 /* #undef HAVE_NATIVE_mpn_sqr_diag_addlsh1 */
 #define HAVE_NATIVE_mpn_sub_n 1
@@ -587,7 +587,7 @@
 #define TIME_WITH_SYS_TIME 1
 
 /* Maximum size the tune program can test for SQR_TOOM2_THRESHOLD */
-/* #undef TUNE_SQR_TOOM2_MAX */
+#define TUNE_SQR_TOOM2_MAX SQR_TOOM2_MAX_GENERIC
 
 /* Version number of package */
 #define VERSION "6.2.0"
diff -r bb616c8f46eb -r 65a83fd3491a external/lgpl3/gmp/lib/libgmp/arch/arm/config.m4
--- a/external/lgpl3/gmp/lib/libgmp/arch/arm/config.m4  Sun Sep 27 20:13:44 2020 +0000
+++ b/external/lgpl3/gmp/lib/libgmp/arch/arm/config.m4  Sun Sep 27 21:19:36 2020 +0000
@@ -4,6 +4,7 @@
 
 define(<WANT_ASSERT>,0)
 define(<WANT_PROFILING>,<`no'>)
+define(<NOTHUMB>,1)
 define(<M4WRAP_SPURIOUS>,<no>)
 define(<TEXT>, <.text>)
 define(<DATA>, <.data>)
@@ -17,8 +18,8 @@
 define(<LSYM_PREFIX>, <.L>)
 define(<W32>, <.long>)
 define(<ALIGN_LOGARITHMIC>,<yes>)
-define(<SQR_TOOM2_THRESHOLD>,<66>)
-define(<BMOD_1_TO_MOD_1_THRESHOLD>,<52>)
+define(<SQR_TOOM2_THRESHOLD>,<78>)
+define(<BMOD_1_TO_MOD_1_THRESHOLD>,<41>)
 define(<SIZEOF_UNSIGNED>,<4>)
 define(<GMP_LIMB_BITS>,32)
 define(<GMP_NAIL_BITS>,0)
@@ -28,7 +29,7 @@
 ifdef(`__CONFIG_M4_INCLUDED__',,`
 include(CONFIG_TOP_SRCDIR`/mpn/asm-defs.m4')
 include_mpn(`arm/arm-defs.m4')
-define_not_for_expansion(`HAVE_HOST_CPU_armv7')
+define_not_for_expansion(`HAVE_HOST_CPU_armv4')
 define_not_for_expansion(`HAVE_ABI_32')
 define_not_for_expansion(`HAVE_LIMB_LITTLE_ENDIAN')
 define_not_for_expansion(`HAVE_DOUBLE_IEEE_LITTLE_ENDIAN')
diff -r bb616c8f46eb -r 65a83fd3491a external/lgpl3/gmp/lib/libgmp/arch/arm/gmp-mparam.h
--- a/external/lgpl3/gmp/lib/libgmp/arch/arm/gmp-mparam.h       Sun Sep 27 20:13:44 2020 +0000
+++ b/external/lgpl3/gmp/lib/libgmp/arch/arm/gmp-mparam.h       Sun Sep 27 21:19:36 2020 +0000
@@ -1,6 +1,7 @@
 /* gmp-mparam.h -- Compiler/machine parameter header file.
 
-Copyright 2019 Free Software Foundation, Inc.
+Copyright 1991, 1993, 1994, 1999-2003, 2009, 2010 Free Software Foundation,
+Inc.
 
 This file is part of the GNU MP Library.
 
@@ -31,175 +32,96 @@
 #define GMP_LIMB_BITS 32
 #define GMP_LIMB_BYTES 4
 
-/* 1500 MHz Cortex-A5 (odroid c1) */
-/* FFT tuning limit = 18,235,562 */
-/* Generated by tuneup.c, 2019-10-22, gcc 4.9 */
+/* 1193MHz ARM (gcc55.fsffrance.org) */
 
+#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          7
-#define MOD_1U_TO_MOD_1_1_THRESHOLD          7
-#define MOD_1_1_TO_MOD_1_2_THRESHOLD         8
+#define MOD_1N_TO_MOD_1_1_THRESHOLD         56
+#define MOD_1U_TO_MOD_1_1_THRESHOLD         11
+#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     23
-#define USE_PREINV_DIVREM_1                  1  /* native */
-#define DIV_QR_1N_PI1_METHOD                 1  /* 132.79% 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           52
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD     71
+#define USE_PREINV_DIVREM_1                  1  /* preinv always */
+#define DIVREM_2_THRESHOLD                   0  /* preinv always */
+#define DIVEXACT_1_THRESHOLD                 0  /* always */
+#define BMOD_1_TO_MOD_1_THRESHOLD           41
 
-#define DIV_1_VS_MUL_1_PERCENT             213
+#define MUL_TOOM22_THRESHOLD                36
+#define MUL_TOOM33_THRESHOLD               125
+#define MUL_TOOM44_THRESHOLD               193
+#define MUL_TOOM6H_THRESHOLD               303
+#define MUL_TOOM8H_THRESHOLD               418
 
-#define MUL_TOOM22_THRESHOLD                48
-#define MUL_TOOM33_THRESHOLD               143
-#define MUL_TOOM44_THRESHOLD               262
-#define MUL_TOOM6H_THRESHOLD               414
-#define MUL_TOOM8H_THRESHOLD               527
-
-#define MUL_TOOM32_TO_TOOM43_THRESHOLD     153
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD     168
-#define MUL_TOOM42_TO_TOOM53_THRESHOLD     152
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD     180
-#define MUL_TOOM43_TO_TOOM54_THRESHOLD     226
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD     125
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD     176
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD     114
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD     129
 
-#define SQR_BASECASE_THRESHOLD               0  /* always (native) */
-#define SQR_TOOM2_THRESHOLD                 66
-#define SQR_TOOM3_THRESHOLD                149
-#define SQR_TOOM4_THRESHOLD                348
-#define SQR_TOOM6_THRESHOLD                517
-#define SQR_TOOM8_THRESHOLD                608
+#define SQR_BASECASE_THRESHOLD              12
+#define SQR_TOOM2_THRESHOLD                 78
+#define SQR_TOOM3_THRESHOLD                137
+#define SQR_TOOM4_THRESHOLD                212
+#define SQR_TOOM6_THRESHOLD                306
+#define SQR_TOOM8_THRESHOLD                422
 
-#define MULMID_TOOM42_THRESHOLD             70
+#define MULMOD_BNM1_THRESHOLD               20
+#define SQRMOD_BNM1_THRESHOLD               26
 
-#define MULMOD_BNM1_THRESHOLD               26
-#define SQRMOD_BNM1_THRESHOLD               28
-
-#define MUL_FFT_MODF_THRESHOLD             660  /* k = 5 */
+#define MUL_FFT_MODF_THRESHOLD             436  /* k = 5 */
 #define MUL_FFT_TABLE3                                      \
-  { {    660, 5}, {     29, 6}, {     15, 5}, {     33, 6}, \
-    {     17, 5}, {     35, 6}, {     29, 7}, {     15, 6}, \
-    {     37, 7}, {     19, 6}, {     40, 7}, {     21, 6}, \
-    {     43, 7}, {     37, 8}, {     19, 7}, {     43, 8}, \
-    {     23, 7}, {     51, 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}, {     63, 8}, {    127, 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}, {    159,11}, \
-    {     95,10}, {    191, 9}, {    383,12}, {     63,11}, \
-    {    127,10}, {    255, 9}, {    511,10}, {    271,11}, \
-    {    159,10}, {    319, 9}, {    639,10}, {    335, 9}, \
-    {    671,11}, {    191,10}, {    383, 9}, {    767,10}, \
-    {    399, 9}, {    799,10}, {    415,11}, {    223,12}, \
-    {    127,11}, {    255,10}, {    511, 9}, {   1023,10}, \
-    {    543,11}, {    287,10}, {    607,11}, {    319,10}, \
-    {    671,11}, {    351,12}, {    191,11}, {    383,10}, \
-    {    799,11}, {    415,10}, {    831,13}, {    127,12}, \
-    {    255,11}, {    511,10}, {   1023,11}, {    543,10}, \
-    {   1087,11}, {    575,10}, {   1151,11}, {    607,12}, \
-    {    319,11}, {    703,12}, {    383,11}, {    831,12}, \
-    {    447,11}, {    895,13}, {    255,12}, {    511,11}, \
-    {   1087,12}, {    575,11}, {   1183,12}, {    639,11}, \
-    {   1279,12}, {    703,13}, {    383,12}, {    767,11}, \
-    {   1535,12}, {    895,14}, {    255,13}, {    511,12}, \
-    {   1151,13}, {    639,12}, {   1407,13}, {    767,12}, \
-    {   1599,13}, {    895,12}, {   1791,14}, {    511,13}, \
-    {   1023,12}, {   2111,13}, {   1151,12}, {   2367,13}, \
-    {   1279,12}, {   2559,13}, {   1407,14}, {    767,13}, \
-    {   1535,12}, {   3071,13}, {   1663,12}, {   3327,13}, \
-    {   1791,15}, {    511,14}, {   1023,13}, {   2175,12}, \
-    {   4351,13}, {   8192,14}, {  16384,15}, {  32768,16} }
-#define MUL_FFT_TABLE3_SIZE 140
-#define MUL_FFT_THRESHOLD                 7552
+  { {    436, 5}, {     27, 6}, {     28, 7}, {     15, 6}, \
+    {     32, 7}, {     17, 6}, {     35, 7}, {     19, 6}, \
+    {     39, 7}, {     29, 8}, {     15, 7}, {     35, 8}, \
+    {     19, 7}, {     41, 8}, {     23, 7}, {     49, 8}, \
+    {     27, 9}, {     15, 8}, {     31, 7}, {     63, 8}, \
+    {    256, 9}, {    512,10}, {   1024,11}, {   2048,12}, \
+    {   4096,13}, {   8192,14}, {  16384,15}, {  32768,16} }
+#define MUL_FFT_TABLE3_SIZE 28
+#define MUL_FFT_THRESHOLD                 5760
 
-#define SQR_FFT_MODF_THRESHOLD             590  /* k = 5 */
+#define SQR_FFT_MODF_THRESHOLD             404  /* k = 5 */
 #define SQR_FFT_TABLE3                                      \
-  { {    590, 5}, {     33, 6}, {     17, 5}, {     35, 6}, \
-    {     36, 7}, {     19, 6}, {     40, 7}, {     21, 6}, \
-    {     43, 7}, {     23, 6}, {     47, 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}, \
-    {     67, 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}, {    159,11}, \
-    {     95,10}, {    191, 9}, {    383,12}, {     63,11}, \
-    {    127,10}, {    255, 9}, {    511,10}, {    271, 9}, \
-    {    543,11}, {    159,10}, {    319, 9}, {    639,10}, \
-    {    335, 9}, {    671,10}, {    351,11}, {    191,10}, \
-    {    383, 9}, {    767,10}, {    415,12}, {    127,11}, \
-    {    255,10}, {    511, 9}, {   1023,10}, {    543, 9}, \
-    {   1087,11}, {    287,10}, {    575, 9}, {   1151,10}, \
-    {    607,11}, {    319,10}, {    671,11}, {    351,12}, \
-    {    191,11}, {    383,10}, {    799,11}, {    415,10}, \
-    {    831,13}, {    127,12}, {    255,11}, {    511,10}, \
-    {   1023,11}, {    543,10}, {   1087,11}, {    575,10}, \
-    {   1151,11}, {    607,12}, {    319,11}, {    735,12}, \
-    {    383,11}, {    831,12}, {    447,11}, {    927,13}, \
-    {    255,12}, {    511,11}, {   1087,12}, {    575,11}, \
-    {   1151,12}, {    639,11}, {   1279,12}, {    703,13}, \
-    {    383,12}, {    767,11}, {   1535,12}, {    831,11}, \
-    {   1663,12}, {    895,11}, {   1791,12}, {    959,14}, \
-    {    255,13}, {    511,12}, {   1023,11}, {   2047,12}, \
-    {   1151,13}, {    639,12}, {   1407,13}, {    767,12}, \
-    {   1599,13}, {    895,12}, {   1791,14}, {    511,13}, \
-    {   1023,12}, {   2111,13}, {   1151,12}, {   2367,13}, \
-    {   1279,12}, {   2559,13}, {   1407,14}, {    767,13}, \
-    {   1535,12}, {   3071,13}, {   1663,12}, {   3327,13}, \
-    {   1791,15}, {    511,14}, {   1023,13}, {   2175,12}, \
-    {   4351,13}, {   8192,14}, {  16384,15}, {  32768,16} }
-#define SQR_FFT_TABLE3_SIZE 144



Home | Main Index | Thread Index | Old Index