[Gmp-commit] /var/hg/gmp: Regenerate most relevant gmp-mparam.h files for lar...
mercurial at gmplib.org
mercurial at gmplib.org
Sat Nov 2 15:17:46 UTC 2019
details: /var/hg/gmp/rev/71f136eea376
changeset: 17944:71f136eea376
user: Torbjorn Granlund <tg at gmplib.org>
date: Sat Nov 02 16:17:44 2019 +0100
description:
Regenerate most relevant gmp-mparam.h files for larger FFT limit.
diffstat:
mpn/arm/v6/gmp-mparam.h | 184 +++++++++++++-----------
mpn/arm/v7a/cora15/gmp-mparam.h | 195 +++++++++++++++----------
mpn/arm/v7a/cora17/gmp-mparam.h | 221 ++++++++++++++++++-----------
mpn/arm/v7a/cora5/gmp-mparam.h | 152 ++++++++++++-------
mpn/arm/v7a/cora7/gmp-mparam.h | 171 +++++++++++++---------
mpn/arm/v7a/cora8/gmp-mparam.h | 166 ++++++++++++---------
mpn/arm64/cora53/gmp-mparam.h | 242 ++++++++++++++++++++++++++++++++
mpn/arm64/cora72/gmp-mparam.h | 242 ++++++++++++++++++++++++++++++++
mpn/arm64/cora73/gmp-mparam.h | 225 +++++++++++++++++++++++++++++
mpn/ia64/gmp-mparam.h | 161 +++++++++++++-------
mpn/powerpc64/mode64/p9/gmp-mparam.h | 209 +++++++++++++++++++--------
mpn/x86/atom/gmp-mparam.h | 173 ++++++++++++++--------
mpn/x86/bd1/gmp-mparam.h | 197 ++++++++++++++++----------
mpn/x86/bd2/gmp-mparam.h | 202 ++++++++++++++++----------
mpn/x86/bd4/gmp-mparam.h | 225 +++++++++++++++++++++++++++++
mpn/x86/bt1/gmp-mparam.h | 216 +++++++++++++++++-----------
mpn/x86/bt2/gmp-mparam.h | 179 ++++++++++++++---------
mpn/x86/core2/gmp-mparam.h | 209 ++++++++++++++++----------
mpn/x86/coreibwl/gmp-mparam.h | 216 ++++++++++++++++++++++++++++
mpn/x86/coreihwl/gmp-mparam.h | 205 ++++++++++++++++----------
mpn/x86/coreinhm/gmp-mparam.h | 166 ++++++++++++++-------
mpn/x86/coreisbr/gmp-mparam.h | 226 ++++++++++++++++++-----------
mpn/x86/goldmont/gmp-mparam.h | 197 ++++++++++++++++----------
mpn/x86/k10/gmp-mparam.h | 209 +++++++++++++++++----------
mpn/x86/k8/gmp-mparam.h | 202 ++++++++++++++++----------
mpn/x86/silvermont/gmp-mparam.h | 175 ++++++++++++++--------
mpn/x86/skylake/gmp-mparam.h | 211 +++++++++++++++++++++++++++
mpn/x86/zn1/gmp-mparam.h | 220 +++++++++++++++++++++++++++++
mpn/x86/zn2/gmp-mparam.h | 226 +++++++++++++++++++++++++++++
mpn/x86_64/atom/gmp-mparam.h | 185 ++++++++++++++---------
mpn/x86_64/bd1/gmp-mparam.h | 251 +++++++++++++++++++++++----------
mpn/x86_64/bd2/gmp-mparam.h | 264 +++++++++++++++++++++++-----------
mpn/x86_64/bd4/gmp-mparam.h | 261 +++++++++++++++++++++++-----------
mpn/x86_64/bt1/gmp-mparam.h | 228 ++++++++++++++++++-----------
mpn/x86_64/bt2/gmp-mparam.h | 239 ++++++++++++++++++++-----------
mpn/x86_64/core2/gmp-mparam.h | 219 +++++++++++++++++-----------
mpn/x86_64/coreibwl/gmp-mparam.h | 229 ++++++++++++++++++++----------
mpn/x86_64/coreihwl/gmp-mparam.h | 239 +++++++++++++++++++++----------
mpn/x86_64/coreinhm/gmp-mparam.h | 186 ++++++++++++++++-------
mpn/x86_64/coreisbr/gmp-mparam.h | 201 ++++++++++++++++++--------
mpn/x86_64/goldmont/gmp-mparam.h | 210 +++++++++++++++++++-------
mpn/x86_64/k10/gmp-mparam.h | 221 +++++++++++++++++++---------
mpn/x86_64/k8/gmp-mparam.h | 220 ++++++++++++++++++-----------
mpn/x86_64/silvermont/gmp-mparam.h | 232 ++++++++++++++++++++----------
mpn/x86_64/skylake/gmp-mparam.h | 248 +++++++++++++++++++++-----------
mpn/x86_64/zen/gmp-mparam.h | 255 +++++++++++++++++++++++---------
mpn/x86_64/zen2/gmp-mparam.h | 257 ++++++++++++++++++++++++---------
47 files changed, 7043 insertions(+), 2924 deletions(-)
diffs (truncated from 12510 to 300 lines):
diff -r 688b91c9b765 -r 71f136eea376 mpn/arm/v6/gmp-mparam.h
--- a/mpn/arm/v6/gmp-mparam.h Sun Oct 06 11:34:04 2019 +0200
+++ b/mpn/arm/v6/gmp-mparam.h Sat Nov 02 16:17:44 2019 +0100
@@ -32,140 +32,156 @@
#define GMP_LIMB_BYTES 4
/* 700 MHz ARM11 (raspberry pi) */
-/* FFT tuning limit = 0.5 M */
-/* Generated by tuneup.c, 2019-10-01, gcc 8.3 */
+/* FFT tuning limit = 8,088,775 */
+/* Generated by tuneup.c, 2019-10-23, 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 8
+#define MOD_1N_TO_MOD_1_1_THRESHOLD 7
#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 23
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 19
#define USE_PREINV_DIVREM_1 1 /* preinv always */
-#define DIV_QR_1N_PI1_METHOD 1 /* 71.04% faster than 2 */
+#define DIV_QR_1N_PI1_METHOD 1 /* 71.61% 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 40
+#define BMOD_1_TO_MOD_1_THRESHOLD 38
-#define DIV_1_VS_MUL_1_PERCENT 253
+#define DIV_1_VS_MUL_1_PERCENT 251
#define MUL_TOOM22_THRESHOLD 38
-#define MUL_TOOM33_THRESHOLD 130
+#define MUL_TOOM33_THRESHOLD 134
#define MUL_TOOM44_THRESHOLD 512
#define MUL_TOOM6H_THRESHOLD 0 /* always */
#define MUL_TOOM8H_THRESHOLD 620
#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 MUL_TOOM32_TO_TOOM53_THRESHOLD 625
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 209
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 211
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 300
#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
#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 866
+#define SQR_TOOM3_THRESHOLD 200
+#define SQR_TOOM4_THRESHOLD 470
+#define SQR_TOOM6_THRESHOLD 614
+#define SQR_TOOM8_THRESHOLD 882
-#define MULMID_TOOM42_THRESHOLD 64
+#define MULMID_TOOM42_THRESHOLD 62
-#define MULMOD_BNM1_THRESHOLD 21
-#define SQRMOD_BNM1_THRESHOLD 27
+#define MULMOD_BNM1_THRESHOLD 23
+#define SQRMOD_BNM1_THRESHOLD 26
-#define MUL_FFT_MODF_THRESHOLD 560 /* k = 5 */
+#define MUL_FFT_MODF_THRESHOLD 565 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 560, 5}, { 25, 6}, { 13, 5}, { 28, 6}, \
- { 15, 5}, { 31, 6}, { 29, 7}, { 15, 6}, \
+ { { 565, 5}, { 25, 6}, { 13, 5}, { 27, 6}, \
+ { 15, 5}, { 31, 6}, { 28, 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}, { 35, 8}, \
+ { 47, 7}, { 27, 8}, { 15, 7}, { 35, 8}, \
{ 19, 7}, { 43, 8}, { 23, 7}, { 51, 8}, \
- { 27, 7}, { 55, 8}, { 31, 7}, { 65, 8}, \
- { 35, 7}, { 71, 8}, { 43, 9}, { 23, 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}, { 159,11}, \
+ { 95,10}, { 207,12}, { 63,11}, { 127,10}, \
+ { 255, 9}, { 511,10}, { 271,11}, { 159,10}, \
+ { 351,11}, { 191,10}, { 399,11}, { 223,12}, \
+ { 127,11}, { 255,10}, { 511,11}, { 287,10}, \
+ { 607,11}, { 319,10}, { 639,11}, { 351,12}, \
+ { 191,11}, { 415,13}, { 127,12}, { 255,11}, \
+ { 575,12}, { 319,11}, { 671,12}, { 383,11}, \
+ { 799,12}, { 447,13}, { 255,12}, { 511,11}, \
+ { 1023,12}, { 703,13}, { 383,12}, { 895,14}, \
+ { 255,13}, { 511,12}, { 1151,13}, { 639,12}, \
+ { 1343,13}, { 767,12}, { 1599,13}, { 895,14}, \
+ { 16384,15}, { 32768,16} }
+#define MUL_FFT_TABLE3_SIZE 98
+#define MUL_FFT_THRESHOLD 5760
+
+#define SQR_FFT_MODF_THRESHOLD 530 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 530, 5}, { 25, 6}, { 13, 5}, { 27, 6}, \
+ { 28, 7}, { 15, 6}, { 33, 7}, { 17, 6}, \
+ { 35, 7}, { 19, 6}, { 39, 7}, { 21, 6}, \
+ { 43, 7}, { 23, 6}, { 47, 7}, { 29, 8}, \
+ { 15, 7}, { 35, 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}, \
+ { 83, 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}, { 159,11}, { 95,10}, { 207,12}, \
- { 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 525 /* k = 5 */
-#define SQR_FFT_TABLE3 \
- { { 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
+ { 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}, { 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}, { 799,12}, { 447,11}, { 895,13}, \
+ { 255,12}, { 511,11}, { 1023,12}, { 703,13}, \
+ { 383,12}, { 895,14}, { 255,13}, { 511,12}, \
+ { 1151,13}, { 639,12}, { 1343,13}, { 767,12}, \
+ { 1599,13}, { 895,14}, { 16384,15}, { 32768,16} }
+#define SQR_FFT_TABLE3_SIZE 104
+#define SQR_FFT_THRESHOLD 4416
#define MULLO_BASECASE_THRESHOLD 0 /* always */
-#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 MULLO_DC_THRESHOLD 51
+#define MULLO_MUL_N_THRESHOLD 11278
+#define SQRLO_BASECASE_THRESHOLD 10
+#define SQRLO_DC_THRESHOLD 55
+#define SQRLO_SQR_THRESHOLD 8648
-#define DC_DIV_QR_THRESHOLD 41
-#define DC_DIVAPPR_Q_THRESHOLD 148
-#define DC_BDIV_QR_THRESHOLD 57
-#define DC_BDIV_Q_THRESHOLD 158
+#define DC_DIV_QR_THRESHOLD 36
+#define DC_DIVAPPR_Q_THRESHOLD 146
+#define DC_BDIV_QR_THRESHOLD 46
+#define DC_BDIV_Q_THRESHOLD 160
#define INV_MULMOD_BNM1_THRESHOLD 74
-#define INV_NEWTON_THRESHOLD 146
+#define INV_NEWTON_THRESHOLD 145
#define INV_APPR_THRESHOLD 147
#define BINV_NEWTON_THRESHOLD 372
#define REDC_1_TO_REDC_2_THRESHOLD 6
-#define REDC_2_TO_REDC_N_THRESHOLD 134
+#define REDC_2_TO_REDC_N_THRESHOLD 140
-#define MU_DIV_QR_THRESHOLD 2857
+#define MU_DIV_QR_THRESHOLD 2801
#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 MU_BDIV_Q_THRESHOLD 2764
-#define POWM_SEC_TABLE 7,19,133,473
+#define POWM_SEC_TABLE 3,20,139,734
-#define GET_STR_DC_THRESHOLD 29
-#define GET_STR_PRECOMPUTE_THRESHOLD 46
-#define SET_STR_DC_THRESHOLD 384
-#define SET_STR_PRECOMPUTE_THRESHOLD 1323
+#define GET_STR_DC_THRESHOLD 27
+#define GET_STR_PRECOMPUTE_THRESHOLD 45
+#define SET_STR_DC_THRESHOLD 342
+#define SET_STR_PRECOMPUTE_THRESHOLD 1290
-#define FAC_DSC_THRESHOLD 369
-#define FAC_ODD_THRESHOLD 450
+#define FAC_DSC_THRESHOLD 390
+#define FAC_ODD_THRESHOLD 438
-#define MATRIX22_STRASSEN_THRESHOLD 22
+#define MATRIX22_STRASSEN_THRESHOLD 25
#define HGCD2_DIV1_METHOD 5 /* 1.32% faster than 3 */
#define HGCD_THRESHOLD 82
-#define HGCD_APPR_THRESHOLD 97
-#define HGCD_REDUCE_THRESHOLD 3810
-#define GCD_DC_THRESHOLD 333
-#define GCDEXT_DC_THRESHOLD 253
-#define JACOBI_BASE_METHOD 1 /* 0.00% faster than 2 */
+#define HGCD_APPR_THRESHOLD 81
+#define HGCD_REDUCE_THRESHOLD 4633
+#define GCD_DC_THRESHOLD 345
+#define GCDEXT_DC_THRESHOLD 268
+#define JACOBI_BASE_METHOD 1 /* 3.30% faster than 2 */
+
+/* Tuneup completed successfully, took 45018 seconds */
diff -r 688b91c9b765 -r 71f136eea376 mpn/arm/v7a/cora15/gmp-mparam.h
--- a/mpn/arm/v7a/cora15/gmp-mparam.h Sun Oct 06 11:34:04 2019 +0200
+++ b/mpn/arm/v7a/cora15/gmp-mparam.h Sat Nov 02 16:17:44 2019 +0100
@@ -32,138 +32,181 @@
#define GMP_LIMB_BYTES 4
/* 2000 MHz Cortex-A15 with Neon (in spite of file position) */
-/* FFT tuning limit = 0.5 M */
-/* Generated by tuneup.c, 2019-10-01, gcc 5.4 */
+/* FFT tuning limit = 50,736,668 */
+/* Generated by tuneup.c, 2019-10-22, 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 11
+#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 8
#define USE_PREINV_DIVREM_1 1 /* native */
-#define DIV_QR_1N_PI1_METHOD 1 /* 44.35% faster than 2 */
+#define DIV_QR_1N_PI1_METHOD 1 /* 49.14% 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 17
-#define DIV_1_VS_MUL_1_PERCENT 284
+#define DIV_1_VS_MUL_1_PERCENT 267
#define MUL_TOOM22_THRESHOLD 28
-#define MUL_TOOM33_THRESHOLD 115
+#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 109
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 133
-#define MUL_TOOM42_TO_TOOM53_THRESHOLD 110
-#define MUL_TOOM42_TO_TOOM63_THRESHOLD 116
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 113
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 115
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 115
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 115
#define MUL_TOOM43_TO_TOOM54_THRESHOLD 154
#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
-#define SQR_TOOM2_THRESHOLD 41
-#define SQR_TOOM3_THRESHOLD 121
-#define SQR_TOOM4_THRESHOLD 345
+#define SQR_TOOM2_THRESHOLD 38
+#define SQR_TOOM3_THRESHOLD 126
+#define SQR_TOOM4_THRESHOLD 336
More information about the gmp-commit
mailing list