[Gmp-commit] /var/hg/gmp: Provide AMD jaguar thresholds.
mercurial at gmplib.org
mercurial at gmplib.org
Mon Aug 5 09:07:32 UTC 2019
details: /var/hg/gmp/rev/4c6ae64fa612
changeset: 17788:4c6ae64fa612
user: Torbjorn Granlund <tg at gmplib.org>
date: Mon Aug 05 11:07:24 2019 +0200
description:
Provide AMD jaguar thresholds.
diffstat:
mpn/x86_64/bt2/gmp-mparam.h | 174 ++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 174 insertions(+), 0 deletions(-)
diffs (178 lines):
diff -r db3689d0a86f -r 4c6ae64fa612 mpn/x86_64/bt2/gmp-mparam.h
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/x86_64/bt2/gmp-mparam.h Mon Aug 05 11:07:24 2019 +0200
@@ -0,0 +1,174 @@
+/* AMD Bobcat gmp-mparam.h -- Compiler/machine parameter header file.
+
+Copyright 2017 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 64
+#define GMP_LIMB_BYTES 8
+
+/* Disable use of slow functions. FIXME: We should disable lib inclusion. */
+#undef HAVE_NATIVE_mpn_mul_2
+#undef HAVE_NATIVE_mpn_addmul_2
+
+/* 2050 MHz AMD Jaguar */
+/* FFT tuning limit = 0.5 M */
+/* Generated by tuneup.c, 2019-08-04, gcc 8.3 */
+
+#define MOD_1_NORM_THRESHOLD 4
+#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 69
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 10
+#define USE_PREINV_DIVREM_1 1 /* native */
+#define DIV_QR_1_NORM_THRESHOLD 3
+#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 DIV_1_VS_MUL_1_PERCENT 266
+
+#define MUL_TOOM22_THRESHOLD 25
+#define MUL_TOOM33_THRESHOLD 70
+#define MUL_TOOM44_THRESHOLD 103
+#define MUL_TOOM6H_THRESHOLD 298
+#define MUL_TOOM8H_THRESHOLD 387
+
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 69
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 143
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 133
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 137
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 95
+
+#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
+#define SQR_TOOM2_THRESHOLD 20
+#define SQR_TOOM3_THRESHOLD 98
+#define SQR_TOOM4_THRESHOLD 244
+#define SQR_TOOM6_THRESHOLD 327
+#define SQR_TOOM8_THRESHOLD 478
+
+#define MULMID_TOOM42_THRESHOLD 20
+
+#define MULMOD_BNM1_THRESHOLD 11
+#define SQRMOD_BNM1_THRESHOLD 13
+
+#define MUL_FFT_MODF_THRESHOLD 364 /* k = 5 */
+#define MUL_FFT_TABLE3 \
+ { { 364, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \
+ { 23, 7}, { 12, 6}, { 25, 7}, { 25, 8}, \
+ { 13, 7}, { 28, 8}, { 15, 7}, { 31, 8}, \
+ { 17, 7}, { 35, 8}, { 19, 7}, { 39, 8}, \
+ { 21, 9}, { 11, 8}, { 27, 9}, { 15, 8}, \
+ { 35, 9}, { 19, 8}, { 41, 9}, { 23, 8}, \
+ { 49, 9}, { 27,10}, { 15, 9}, { 31, 8}, \
+ { 63, 9}, { 43,10}, { 23, 9}, { 51,11}, \
+ { 15,10}, { 31, 9}, { 67,10}, { 39, 9}, \
+ { 79,10}, { 47, 9}, { 95,11}, { 31,10}, \
+ { 79,11}, { 47,10}, { 95,12}, { 31,11}, \
+ { 63,10}, { 127, 9}, { 255,11}, { 79,10}, \
+ { 159, 9}, { 319,10}, { 167,11}, { 95,10}, \
+ { 191, 9}, { 383,11}, { 111,12}, { 63,11}, \
+ { 127,10}, { 255, 9}, { 511,10}, { 271,11}, \
+ { 143,10}, { 287, 9}, { 575,10}, { 303,11}, \
+ { 159,10}, { 319,12}, { 95,11}, { 191,10}, \
+ { 383,11}, { 207,13}, { 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 81
+#define MUL_FFT_THRESHOLD 4224
+
+#define SQR_FFT_MODF_THRESHOLD 364 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 364, 5}, { 23, 6}, { 25, 7}, { 13, 6}, \
+ { 27, 7}, { 14, 6}, { 29, 7}, { 25, 8}, \
+ { 13, 7}, { 28, 8}, { 15, 7}, { 31, 8}, \
+ { 29, 9}, { 15, 8}, { 35, 9}, { 19, 8}, \
+ { 41, 9}, { 23, 8}, { 47, 9}, { 27,10}, \
+ { 15, 9}, { 39,10}, { 23, 9}, { 51,11}, \
+ { 15,10}, { 31, 9}, { 63,10}, { 39, 9}, \
+ { 79,10}, { 47,11}, { 31,10}, { 79,11}, \
+ { 47,10}, { 95,12}, { 31,11}, { 63,10}, \
+ { 127, 9}, { 255,10}, { 135, 9}, { 271,11}, \
+ { 79,10}, { 159, 9}, { 319,11}, { 95,10}, \
+ { 191, 9}, { 383,11}, { 111,12}, { 63,11}, \
+ { 127,10}, { 255, 9}, { 511,10}, { 271, 9}, \
+ { 543,11}, { 143,10}, { 287, 9}, { 575,10}, \
+ { 303, 9}, { 607,11}, { 159,10}, { 319,12}, \
+ { 95,11}, { 191,10}, { 383,11}, { 207,10}, \
+ { 415,13}, { 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 76
+#define SQR_FFT_THRESHOLD 3264
+
+#define MULLO_BASECASE_THRESHOLD 0 /* always */
+#define MULLO_DC_THRESHOLD 57
+#define MULLO_MUL_N_THRESHOLD 8397
+#define SQRLO_BASECASE_THRESHOLD 8
+#define SQRLO_DC_THRESHOLD 54
+#define SQRLO_SQR_THRESHOLD 6440
+
+#define DC_DIV_QR_THRESHOLD 76
+#define DC_DIVAPPR_Q_THRESHOLD 184
+#define DC_BDIV_QR_THRESHOLD 54
+#define DC_BDIV_Q_THRESHOLD 115
+
+#define INV_MULMOD_BNM1_THRESHOLD 49
+#define INV_NEWTON_THRESHOLD 214
+#define INV_APPR_THRESHOLD 187
+
+#define BINV_NEWTON_THRESHOLD 244
+#define REDC_1_TO_REDC_2_THRESHOLD 70
+#define REDC_2_TO_REDC_N_THRESHOLD 0 /* always */
+
+#define MU_DIV_QR_THRESHOLD 1334
+#define MU_DIVAPPR_Q_THRESHOLD 1334
+#define MUPI_DIV_QR_THRESHOLD 106
+#define MU_BDIV_QR_THRESHOLD 1120
+#define MU_BDIV_Q_THRESHOLD 1341
+
+#define POWM_SEC_TABLE 1,19,111,321,1167,2577
+
+#define GET_STR_DC_THRESHOLD 19
+#define GET_STR_PRECOMPUTE_THRESHOLD 29
+#define SET_STR_DC_THRESHOLD 248
+#define SET_STR_PRECOMPUTE_THRESHOLD 956
+
+#define FAC_DSC_THRESHOLD 210
+#define FAC_ODD_THRESHOLD 0 /* always */
+
+#define MATRIX22_STRASSEN_THRESHOLD 18
+#define HGCD_THRESHOLD 91
+#define HGCD_APPR_THRESHOLD 59
+#define HGCD_REDUCE_THRESHOLD 2121
+#define GCD_DC_THRESHOLD 440
+#define GCDEXT_DC_THRESHOLD 258
+#define JACOBI_BASE_METHOD 1
More information about the gmp-commit
mailing list