[Gmp-commit] /var/hg/gmp: New tuneup files.
mercurial at gmplib.org
mercurial at gmplib.org
Sun Sep 29 20:48:49 UTC 2019
details: /var/hg/gmp/rev/44543bbf85d6
changeset: 17927:44543bbf85d6
user: Torbjorn Granlund <tg at gmplib.org>
date: Sun Sep 29 22:48:44 2019 +0200
description:
New tuneup files.
diffstat:
mpn/x86_64/atom/gmp-mparam.h | 167 ++++++++++++------------
mpn/x86_64/bt1/gmp-mparam.h | 216 +++++++++++++++---------------
mpn/x86_64/bt2/gmp-mparam.h | 175 +++++++++++++------------
mpn/x86_64/core2/gmp-mparam.h | 253 ++++++++++++++----------------------
mpn/x86_64/coreibwl/gmp-mparam.h | 180 +++++++++++++-------------
mpn/x86_64/coreihwl/gmp-mparam.h | 244 +++++++++++-----------------------
mpn/x86_64/coreinhm/gmp-mparam.h | 221 +++++++++++---------------------
mpn/x86_64/coreisbr/gmp-mparam.h | 217 +++++++++++--------------------
mpn/x86_64/goldmont/gmp-mparam.h | 197 ++++++++++++++--------------
mpn/x86_64/pentium4/gmp-mparam.h | 221 ++++++++++++-------------------
mpn/x86_64/silvermont/gmp-mparam.h | 185 +++++++++++++-------------
mpn/x86_64/skylake/gmp-mparam.h | 252 ++++++++++++++----------------------
12 files changed, 1076 insertions(+), 1452 deletions(-)
diffs (truncated from 3283 to 300 lines):
diff -r d204bf50b7b2 -r 44543bbf85d6 mpn/x86_64/atom/gmp-mparam.h
--- a/mpn/x86_64/atom/gmp-mparam.h Sun Sep 29 16:02:51 2019 +0200
+++ b/mpn/x86_64/atom/gmp-mparam.h Sun Sep 29 22:48:44 2019 +0200
@@ -1,6 +1,6 @@
/* Intel Atom/64 gmp-mparam.h -- Compiler/machine parameter header file.
-Copyright 2017 Free Software Foundation, Inc.
+Copyright 2019 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
@@ -36,44 +36,44 @@
/* 1600 MHz Diamondville (Atom 330) */
/* FFT tuning limit = 0.5 M */
-/* Generated by tuneup.c, 2017-02-21, gcc 4.9 */
+/* Generated by tuneup.c, 2019-09-25, gcc 8.3 */
#define MOD_1_NORM_THRESHOLD 0 /* always */
#define MOD_1_UNNORM_THRESHOLD 0 /* always */
#define MOD_1N_TO_MOD_1_1_THRESHOLD 5
-#define MOD_1U_TO_MOD_1_1_THRESHOLD 4
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 3
#define MOD_1_1_TO_MOD_1_2_THRESHOLD MP_SIZE_T_MAX
#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 11
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 12
#define USE_PREINV_DIVREM_1 1 /* native */
#define DIV_QR_1_NORM_THRESHOLD 1
#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 16
#define DIV_1_VS_MUL_1_PERCENT 201
#define MUL_TOOM22_THRESHOLD 12
-#define MUL_TOOM33_THRESHOLD 66
+#define MUL_TOOM33_THRESHOLD 74
#define MUL_TOOM44_THRESHOLD 106
-#define MUL_TOOM6H_THRESHOLD 157
+#define MUL_TOOM6H_THRESHOLD 156
#define MUL_TOOM8H_THRESHOLD 212
#define MUL_TOOM32_TO_TOOM43_THRESHOLD 73
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 91
-#define MUL_TOOM42_TO_TOOM53_THRESHOLD 81
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 74
-#define MUL_TOOM43_TO_TOOM54_THRESHOLD 64
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 78
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 73
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 72
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 55
#define SQR_BASECASE_THRESHOLD 5
-#define SQR_TOOM2_THRESHOLD 20
-#define SQR_TOOM3_THRESHOLD 73
-#define SQR_TOOM4_THRESHOLD 118
-#define SQR_TOOM6_THRESHOLD 157
-#define SQR_TOOM8_THRESHOLD 224
+#define SQR_TOOM2_THRESHOLD 22
+#define SQR_TOOM3_THRESHOLD 74
+#define SQR_TOOM4_THRESHOLD 130
+#define SQR_TOOM6_THRESHOLD 173
+#define SQR_TOOM8_THRESHOLD 248
-#define MULMID_TOOM42_THRESHOLD 16
+#define MULMID_TOOM42_THRESHOLD 18
#define MULMOD_BNM1_THRESHOLD 9
#define SQRMOD_BNM1_THRESHOLD 9
@@ -82,103 +82,104 @@
#define MUL_FFT_TABLE3 \
{ { 220, 5}, { 11, 6}, { 6, 5}, { 13, 6}, \
{ 13, 7}, { 7, 6}, { 15, 7}, { 8, 6}, \
- { 17, 7}, { 13, 8}, { 7, 7}, { 17, 8}, \
- { 9, 7}, { 19, 8}, { 11, 7}, { 23, 8}, \
- { 13, 9}, { 7, 8}, { 19, 9}, { 11, 8}, \
- { 25,10}, { 7, 9}, { 15, 8}, { 33, 9}, \
- { 19, 8}, { 39, 9}, { 23, 8}, { 47, 9}, \
- { 27,10}, { 15, 9}, { 35, 8}, { 71, 9}, \
- { 43,10}, { 23, 9}, { 47,11}, { 15,10}, \
- { 31, 9}, { 63, 8}, { 127, 9}, { 71,10}, \
- { 39, 9}, { 79,10}, { 47, 9}, { 95,11}, \
- { 31,10}, { 63, 9}, { 127, 8}, { 255,10}, \
- { 71, 9}, { 143, 8}, { 287,10}, { 79, 9}, \
- { 159, 8}, { 319,11}, { 47,10}, { 95, 9}, \
- { 191, 8}, { 383,12}, { 31,11}, { 63,10}, \
+ { 17, 7}, { 9, 6}, { 19, 7}, { 13, 8}, \
+ { 7, 7}, { 17, 8}, { 9, 7}, { 19, 8}, \
+ { 11, 7}, { 23, 8}, { 13, 9}, { 7, 8}, \
+ { 19, 9}, { 11, 8}, { 25,10}, { 7, 9}, \
+ { 15, 8}, { 33, 9}, { 19, 8}, { 39, 9}, \
+ { 23, 8}, { 47, 9}, { 27,10}, { 15, 9}, \
+ { 39,10}, { 23, 9}, { 47,11}, { 15,10}, \
+ { 31, 9}, { 67,10}, { 39, 9}, { 79,10}, \
+ { 47, 9}, { 95,11}, { 31,10}, { 63, 9}, \
+ { 127, 8}, { 255,10}, { 71, 9}, { 143, 8}, \
+ { 287,10}, { 79, 9}, { 159,11}, { 47,10}, \
+ { 95, 9}, { 191,12}, { 31,11}, { 63,10}, \
{ 127, 9}, { 255, 8}, { 511,10}, { 143, 9}, \
{ 287,11}, { 79,10}, { 159, 9}, { 319,10}, \
{ 175, 9}, { 351,11}, { 95,10}, { 191, 9}, \
{ 383,10}, { 207,11}, { 111,10}, { 223,12}, \
{ 63,11}, { 127,10}, { 255, 9}, { 511,11}, \
{ 143,10}, { 287, 9}, { 575,11}, { 159,10}, \
- { 319,11}, { 175,10}, { 351,11}, { 191,10}, \
- { 383,11}, { 207,10}, { 415,11}, { 223,13}, \
- { 8192,14}, { 16384,15}, { 32768,16}, { 65536,17}, \
- { 131072,18}, { 262144,19}, { 524288,20}, {1048576,21}, \
- {2097152,22}, {4194304,23}, {8388608,24} }
-#define MUL_FFT_TABLE3_SIZE 103
+ { 319,11}, { 175,10}, { 351,12}, { 95,11}, \
+ { 191,10}, { 383,11}, { 207,10}, { 415,11}, \
+ { 223,13}, { 8192,14}, { 16384,15}, { 32768,16}, \
+ { 65536,17}, { 131072,18}, { 262144,19}, { 524288,20}, \
+ {1048576,21}, {2097152,22}, {4194304,23}, {8388608,24} }
+#define MUL_FFT_TABLE3_SIZE 100
#define MUL_FFT_THRESHOLD 2240
#define SQR_FFT_MODF_THRESHOLD 184 /* k = 5 */
#define SQR_FFT_TABLE3 \
- { { 184, 5}, { 9, 6}, { 5, 5}, { 11, 6}, \
- { 13, 7}, { 7, 6}, { 15, 7}, { 8, 6}, \
- { 17, 7}, { 13, 8}, { 7, 7}, { 17, 8}, \
- { 9, 7}, { 19, 8}, { 11, 7}, { 23, 8}, \
- { 13, 9}, { 7, 8}, { 19, 9}, { 11, 8}, \
- { 25,10}, { 7, 9}, { 15, 8}, { 33, 9}, \
- { 19, 8}, { 39, 9}, { 23,10}, { 15, 9}, \
- { 39,10}, { 23, 9}, { 47,11}, { 15,10}, \
- { 31, 7}, { 255, 9}, { 67,10}, { 39, 8}, \
- { 159, 7}, { 319,10}, { 47, 9}, { 95, 8}, \
- { 191,11}, { 31,10}, { 63, 8}, { 255, 7}, \
- { 511, 8}, { 287, 7}, { 575, 9}, { 159, 8}, \
- { 319,11}, { 47, 9}, { 191, 8}, { 383,12}, \
- { 31,11}, { 63,10}, { 127, 9}, { 255, 8}, \
- { 511, 9}, { 287, 8}, { 575,10}, { 159, 9}, \
- { 319, 8}, { 639,10}, { 175, 9}, { 351,10}, \
- { 191, 9}, { 383, 8}, { 767,11}, { 111,10}, \
+ { { 184, 5}, { 11, 6}, { 13, 7}, { 7, 6}, \
+ { 15, 7}, { 8, 6}, { 17, 7}, { 13, 8}, \
+ { 7, 7}, { 16, 8}, { 9, 7}, { 19, 8}, \
+ { 11, 7}, { 23, 8}, { 13, 9}, { 7, 8}, \
+ { 19, 9}, { 11, 8}, { 25,10}, { 7, 9}, \
+ { 15, 8}, { 33, 9}, { 19, 8}, { 39, 9}, \
+ { 23,10}, { 15, 9}, { 39,10}, { 23, 9}, \
+ { 47,11}, { 15,10}, { 31, 9}, { 63, 8}, \
+ { 127, 7}, { 255,10}, { 39, 8}, { 159, 7}, \
+ { 319,10}, { 47, 9}, { 95, 8}, { 191,11}, \
+ { 31,10}, { 63, 9}, { 127, 8}, { 255, 7}, \
+ { 511,10}, { 71, 9}, { 143, 8}, { 287, 7}, \
+ { 575, 9}, { 159, 8}, { 319,11}, { 47,10}, \
+ { 95, 9}, { 191, 8}, { 383,12}, { 31,11}, \
+ { 63,10}, { 127, 9}, { 255, 8}, { 511,10}, \
+ { 143, 9}, { 287, 8}, { 575,10}, { 159, 9}, \
+ { 319, 8}, { 639,10}, { 175, 9}, { 351,11}, \
+ { 95,10}, { 191, 9}, { 383,11}, { 111,10}, \
{ 223, 9}, { 447,12}, { 63,11}, { 127,10}, \
{ 255, 9}, { 511,11}, { 143,10}, { 287, 9}, \
{ 575,11}, { 159,10}, { 319, 9}, { 639,11}, \
{ 175,10}, { 351,12}, { 95,11}, { 191,10}, \
- { 383, 9}, { 767,11}, { 223,10}, { 447,13}, \
- { 8192,14}, { 16384,15}, { 32768,16}, { 65536,17}, \
- { 131072,18}, { 262144,19}, { 524288,20}, {1048576,21}, \
- {2097152,22}, {4194304,23}, {8388608,24} }
-#define SQR_FFT_TABLE3_SIZE 99
+ { 383,11}, { 223,10}, { 447,13}, { 8192,14}, \
+ { 16384,15}, { 32768,16}, { 65536,17}, { 131072,18}, \
+ { 262144,19}, { 524288,20}, {1048576,21}, {2097152,22}, \
+ {4194304,23}, {8388608,24} }
+#define SQR_FFT_TABLE3_SIZE 102
#define SQR_FFT_THRESHOLD 1728
#define MULLO_BASECASE_THRESHOLD 0 /* always */
#define MULLO_DC_THRESHOLD 33
#define MULLO_MUL_N_THRESHOLD 4392
#define SQRLO_BASECASE_THRESHOLD 0 /* always */
-#define SQRLO_DC_THRESHOLD 85
-#define SQRLO_SQR_THRESHOLD 3176
+#define SQRLO_DC_THRESHOLD 90
+#define SQRLO_SQR_THRESHOLD 3199
-#define DC_DIV_QR_THRESHOLD 35
-#define DC_DIVAPPR_Q_THRESHOLD 119
-#define DC_BDIV_QR_THRESHOLD 31
-#define DC_BDIV_Q_THRESHOLD 75
+#define DC_DIV_QR_THRESHOLD 40
+#define DC_DIVAPPR_Q_THRESHOLD 118
+#define DC_BDIV_QR_THRESHOLD 39
+#define DC_BDIV_Q_THRESHOLD 78
#define INV_MULMOD_BNM1_THRESHOLD 22
-#define INV_NEWTON_THRESHOLD 147
-#define INV_APPR_THRESHOLD 123
+#define INV_NEWTON_THRESHOLD 149
+#define INV_APPR_THRESHOLD 124
-#define BINV_NEWTON_THRESHOLD 164
-#define REDC_1_TO_REDC_2_THRESHOLD 17
+#define BINV_NEWTON_THRESHOLD 179
+#define REDC_1_TO_REDC_2_THRESHOLD 24
#define REDC_2_TO_REDC_N_THRESHOLD 43
#define MU_DIV_QR_THRESHOLD 807
-#define MU_DIVAPPR_Q_THRESHOLD 855
-#define MUPI_DIV_QR_THRESHOLD 77
-#define MU_BDIV_QR_THRESHOLD 667
+#define MU_DIVAPPR_Q_THRESHOLD 807
+#define MUPI_DIV_QR_THRESHOLD 75
+#define MU_BDIV_QR_THRESHOLD 748
#define MU_BDIV_Q_THRESHOLD 807
-#define POWM_SEC_TABLE 1,22,114,452,2617
+#define POWM_SEC_TABLE 1,22,114,459,1486
-#define GET_STR_DC_THRESHOLD 15
-#define GET_STR_PRECOMPUTE_THRESHOLD 30
-#define SET_STR_DC_THRESHOLD 381
-#define SET_STR_PRECOMPUTE_THRESHOLD 1505
+#define GET_STR_DC_THRESHOLD 17
+#define GET_STR_PRECOMPUTE_THRESHOLD 33
+#define SET_STR_DC_THRESHOLD 686
+#define SET_STR_PRECOMPUTE_THRESHOLD 1570
-#define FAC_DSC_THRESHOLD 978
+#define FAC_DSC_THRESHOLD 969
#define FAC_ODD_THRESHOLD 0 /* always */
#define MATRIX22_STRASSEN_THRESHOLD 15
-#define HGCD_THRESHOLD 97
-#define HGCD_APPR_THRESHOLD 99
-#define HGCD_REDUCE_THRESHOLD 1137
-#define GCD_DC_THRESHOLD 249
-#define GCDEXT_DC_THRESHOLD 205
-#define JACOBI_BASE_METHOD 3
+#define HGCD2_DIV1_METHOD 3 /* 9.67% faster than 4 */
+#define HGCD_THRESHOLD 92
+#define HGCD_APPR_THRESHOLD 96
+#define HGCD_REDUCE_THRESHOLD 1182
+#define GCD_DC_THRESHOLD 245
+#define GCDEXT_DC_THRESHOLD 192
+#define JACOBI_BASE_METHOD 3 /* 9.54% faster than 2 */
diff -r d204bf50b7b2 -r 44543bbf85d6 mpn/x86_64/bt1/gmp-mparam.h
--- a/mpn/x86_64/bt1/gmp-mparam.h Sun Sep 29 16:02:51 2019 +0200
+++ b/mpn/x86_64/bt1/gmp-mparam.h Sun Sep 29 22:48:44 2019 +0200
@@ -1,6 +1,6 @@
/* AMD Bobcat gmp-mparam.h -- Compiler/machine parameter header file.
-Copyright 2017 Free Software Foundation, Inc.
+Copyright 2019 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
@@ -35,146 +35,146 @@
#undef HAVE_NATIVE_mpn_mul_2
#undef HAVE_NATIVE_mpn_addmul_2
-/* 2050 MHz AMD Jaguar */
+/* 1600 MHz AMD Bobcat/Zacate */
/* FFT tuning limit = 0.5 M */
-/* Generated by tuneup.c, 2017-02-21, gcc 6.2 */
+/* Generated by tuneup.c, 2019-09-29, gcc 8.3 */
-#define MOD_1_NORM_THRESHOLD 3
-#define MOD_1_UNNORM_THRESHOLD 4
-#define MOD_1N_TO_MOD_1_1_THRESHOLD 4
-#define MOD_1U_TO_MOD_1_1_THRESHOLD 4
-#define MOD_1_1_TO_MOD_1_2_THRESHOLD 65
-#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 9
+#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 3
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 32
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD 59
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 14
#define USE_PREINV_DIVREM_1 1 /* native */
-#define DIV_QR_1_NORM_THRESHOLD 3
+#define DIV_QR_1_NORM_THRESHOLD 1
#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 20
-#define DIV_1_VS_MUL_1_PERCENT 267
+#define DIV_1_VS_MUL_1_PERCENT 270
#define MUL_TOOM22_THRESHOLD 26
-#define MUL_TOOM33_THRESHOLD 35
-#define MUL_TOOM44_THRESHOLD 288
-#define MUL_TOOM6H_THRESHOLD 418
-#define MUL_TOOM8H_THRESHOLD 572
+#define MUL_TOOM33_THRESHOLD 73
+#define MUL_TOOM44_THRESHOLD 202
+#define MUL_TOOM6H_THRESHOLD 298
+#define MUL_TOOM8H_THRESHOLD 406
More information about the gmp-commit
mailing list