[Gmp-commit] /var/hg/gmp: 3 new changesets
mercurial at gmplib.org
mercurial at gmplib.org
Mon Apr 27 20:47:33 UTC 2015
details: /var/hg/gmp/rev/c56d03f411fa
changeset: 16601:c56d03f411fa
user: Torbjorn Granlund <torbjorng at google.com>
date: Mon Apr 27 22:45:24 2015 +0200
description:
Provide broadwell gmp-mparam.h.
details: /var/hg/gmp/rev/8a542115a649
changeset: 16602:8a542115a649
user: Torbjorn Granlund <torbjorng at google.com>
date: Mon Apr 27 22:46:14 2015 +0200
description:
Remove a stale comment.
details: /var/hg/gmp/rev/6e11cd70e19e
changeset: 16603:6e11cd70e19e
user: Torbjorn Granlund <torbjorng at google.com>
date: Mon Apr 27 22:46:53 2015 +0200
description:
ChangeLog
diffstat:
ChangeLog | 4 +
mpn/x86_64/coreibwl/gmp-mparam.h | 166 +++++++++++++++++++++++++++++++++++
mpn/x86_64/coreisbr/mul_basecase.asm | 2 +-
3 files changed, 171 insertions(+), 1 deletions(-)
diffs (193 lines):
diff -r c679b9059102 -r 6e11cd70e19e ChangeLog
--- a/ChangeLog Mon Apr 27 22:44:13 2015 +0200
+++ b/ChangeLog Mon Apr 27 22:46:53 2015 +0200
@@ -1,3 +1,7 @@
+2015-04-27 <torbjorng at google.com>
+
+ * mpn/x86_64/coreibwl/gmp-mparam.h: New file.
+
2015-04-26 <torbjorng at google.com>
* mpn/x86_64/coreibwl/mul_basecase.asm: New file.
diff -r c679b9059102 -r 6e11cd70e19e mpn/x86_64/coreibwl/gmp-mparam.h
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/x86_64/coreibwl/gmp-mparam.h Mon Apr 27 22:46:53 2015 +0200
@@ -0,0 +1,166 @@
+/* Broadwell gmp-mparam.h -- Compiler/machine parameter header file.
+
+Copyright 1991, 1993, 1994, 2000-2015 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
+
+/* 1297 MHz Intel 5Y70 */
+/* Generated by tuneup.c, 2015-04-23, 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 4
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 3
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 14
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD 28
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 9
+#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 20
+
+#define MUL_TOOM22_THRESHOLD 28
+#define MUL_TOOM33_THRESHOLD 77
+#define MUL_TOOM44_THRESHOLD 218
+#define MUL_TOOM6H_THRESHOLD 321
+#define MUL_TOOM8H_THRESHOLD 430
+
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 81
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 160
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 145
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 160
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 121
+
+#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
+#define SQR_TOOM2_THRESHOLD 38
+#define SQR_TOOM3_THRESHOLD 117
+#define SQR_TOOM4_THRESHOLD 458
+#define SQR_TOOM6_THRESHOLD 517
+#define SQR_TOOM8_THRESHOLD 597
+
+#define MULMID_TOOM42_THRESHOLD 48
+
+#define MULMOD_BNM1_THRESHOLD 16
+#define SQRMOD_BNM1_THRESHOLD 18
+
+#define MUL_FFT_MODF_THRESHOLD 404 /* k = 5 */
+#define MUL_FFT_TABLE3 \
+ { { 404, 5}, { 21, 6}, { 11, 5}, { 23, 6}, \
+ { 25, 7}, { 13, 6}, { 27, 7}, { 15, 6}, \
+ { 31, 7}, { 25, 8}, { 13, 7}, { 28, 8}, \
+ { 15, 7}, { 31, 8}, { 17, 7}, { 35, 8}, \
+ { 21, 9}, { 11, 8}, { 27, 9}, { 15, 8}, \
+ { 35, 9}, { 19, 8}, { 41, 9}, { 23, 8}, \
+ { 47, 9}, { 27,10}, { 15, 9}, { 43,10}, \
+ { 23, 9}, { 55,11}, { 15,10}, { 31, 9}, \
+ { 67,10}, { 39, 9}, { 83,10}, { 47, 9}, \
+ { 95,10}, { 55,11}, { 31,10}, { 79,11}, \
+ { 47,10}, { 95,12}, { 31,11}, { 63,10}, \
+ { 135,11}, { 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}, \
+ { 95,10}, { 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 78
+#define MUL_FFT_THRESHOLD 4736
+
+#define SQR_FFT_MODF_THRESHOLD 376 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 376, 5}, { 21, 6}, { 11, 5}, { 23, 6}, \
+ { 29, 7}, { 28, 8}, { 15, 7}, { 32, 8}, \
+ { 21, 9}, { 11, 8}, { 27, 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}, \
+ { 67,10}, { 39, 9}, { 83,10}, { 55,11}, \
+ { 31,10}, { 79,11}, { 47,10}, { 95,12}, \
+ { 31,11}, { 63,10}, { 127, 9}, { 255,10}, \
+ { 135,11}, { 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}, { 159,12}, \
+ { 95,11}, { 191,10}, { 383, 9}, { 767,13}, \
+ { 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 71
+#define SQR_FFT_THRESHOLD 3712
+
+#define MULLO_BASECASE_THRESHOLD 0 /* always */
+#define MULLO_DC_THRESHOLD 35
+#define MULLO_MUL_N_THRESHOLD 8648
+
+#define DC_DIV_QR_THRESHOLD 63
+#define DC_DIVAPPR_Q_THRESHOLD 195
+#define DC_BDIV_QR_THRESHOLD 99
+#define DC_BDIV_Q_THRESHOLD 200
+
+#define INV_MULMOD_BNM1_THRESHOLD 58
+#define INV_NEWTON_THRESHOLD 197
+#define INV_APPR_THRESHOLD 182
+
+#define BINV_NEWTON_THRESHOLD 327
+#define REDC_1_TO_REDC_2_THRESHOLD 66
+#define REDC_2_TO_REDC_N_THRESHOLD 0 /* always */
+
+#define MU_DIV_QR_THRESHOLD 1620
+#define MU_DIVAPPR_Q_THRESHOLD 1858
+#define MUPI_DIV_QR_THRESHOLD 78
+#define MU_BDIV_QR_THRESHOLD 1620
+#define MU_BDIV_Q_THRESHOLD 1752
+
+#define POWM_SEC_TABLE 1,22,194,257,1099
+
+#define MATRIX22_STRASSEN_THRESHOLD 15
+#define HGCD_THRESHOLD 143 /* old measurement */
+#define HGCD_APPR_THRESHOLD 113 /* old measurement */
+#define HGCD_REDUCE_THRESHOLD 2899 /* old measurement */
+#define GCD_DC_THRESHOLD 812 /* old measurement */
+#define GCDEXT_DC_THRESHOLD 478 /* old measurement */
+#define JACOBI_BASE_METHOD 4 /* old measurement */
+
+#define GET_STR_DC_THRESHOLD 13 /* old measurement */
+#define GET_STR_PRECOMPUTE_THRESHOLD 21 /* old measurement */
+#define SET_STR_DC_THRESHOLD 1446 /* old measurement */
+#define SET_STR_PRECOMPUTE_THRESHOLD 2266 /* old measurement */
+
+#define FAC_DSC_THRESHOLD 692 /* old measurement */
+#define FAC_ODD_THRESHOLD 28 /* old measurement */
diff -r c679b9059102 -r 6e11cd70e19e mpn/x86_64/coreisbr/mul_basecase.asm
--- a/mpn/x86_64/coreisbr/mul_basecase.asm Mon Apr 27 22:44:13 2015 +0200
+++ b/mpn/x86_64/coreisbr/mul_basecase.asm Mon Apr 27 22:46:53 2015 +0200
@@ -287,7 +287,7 @@
adc $0, w1
mov (up,un,8), %rax
mul v1
- mov 8(rp,un,8), X1 C FIXME: Use un
+ mov 8(rp,un,8), X1
jmp L(lo0)
L(a110):lea (un), n C un = 2, 6, 10, ...
More information about the gmp-commit
mailing list