[Gmp-commit] /var/hg/gmp: 2 new changesets
mercurial at gmplib.org
mercurial at gmplib.org
Sat Apr 15 20:57:07 UTC 2017
details: /var/hg/gmp/rev/5e99e1f25f87
changeset: 17344:5e99e1f25f87
user: Torbjorn Granlund <tg at gmplib.org>
date: Sat Apr 15 21:22:12 2017 +0200
description:
Add many AMD Zen "grabber" files.
details: /var/hg/gmp/rev/a13428bd4fd3
changeset: 17345:a13428bd4fd3
user: Torbjorn Granlund <tg at gmplib.org>
date: Sat Apr 15 22:56:07 2017 +0200
description:
New Zen parameter file.
diffstat:
mpn/x86_64/zen/com.asm | 37 +++++++
mpn/x86_64/zen/copyd.asm | 37 +++++++
mpn/x86_64/zen/copyi.asm | 37 +++++++
mpn/x86_64/zen/gcd_1.asm | 37 +++++++
mpn/x86_64/zen/gmp-mparam.h | 226 ++++++++++++++++++++++++++++++++++++++++++++
mpn/x86_64/zen/hamdist.asm | 38 +++++++
mpn/x86_64/zen/lshift.asm | 37 +++++++
mpn/x86_64/zen/lshiftc.asm | 37 +++++++
mpn/x86_64/zen/popcount.asm | 38 +++++++
mpn/x86_64/zen/rshift.asm | 37 +++++++
10 files changed, 561 insertions(+), 0 deletions(-)
diffs (truncated from 601 to 300 lines):
diff -r 2ce5c60f5372 -r a13428bd4fd3 mpn/x86_64/zen/com.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/x86_64/zen/com.asm Sat Apr 15 22:56:07 2017 +0200
@@ -0,0 +1,37 @@
+dnl X86-64 mpn_com optimised for AMD Zen.
+
+dnl Copyright 2012 Free Software Foundation, Inc.
+
+dnl This file is part of the GNU MP Library.
+dnl
+dnl The GNU MP Library is free software; you can redistribute it and/or modify
+dnl it under the terms of either:
+dnl
+dnl * the GNU Lesser General Public License as published by the Free
+dnl Software Foundation; either version 3 of the License, or (at your
+dnl option) any later version.
+dnl
+dnl or
+dnl
+dnl * the GNU General Public License as published by the Free Software
+dnl Foundation; either version 2 of the License, or (at your option) any
+dnl later version.
+dnl
+dnl or both in parallel, as here.
+dnl
+dnl The GNU MP Library is distributed in the hope that it will be useful, but
+dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+dnl for more details.
+dnl
+dnl You should have received copies of the GNU General Public License and the
+dnl GNU Lesser General Public License along with the GNU MP Library. If not,
+dnl see https://www.gnu.org/licenses/.
+
+include(`../config.m4')
+
+ABI_SUPPORT(DOS64)
+ABI_SUPPORT(STD64)
+
+MULFUNC_PROLOGUE(mpn_com)
+include_mpn(`x86_64/fastsse/com.asm')
diff -r 2ce5c60f5372 -r a13428bd4fd3 mpn/x86_64/zen/copyd.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/x86_64/zen/copyd.asm Sat Apr 15 22:56:07 2017 +0200
@@ -0,0 +1,37 @@
+dnl X86-64 mpn_copyd optimised for AMD Zen.
+
+dnl Copyright 2012 Free Software Foundation, Inc.
+
+dnl This file is part of the GNU MP Library.
+dnl
+dnl The GNU MP Library is free software; you can redistribute it and/or modify
+dnl it under the terms of either:
+dnl
+dnl * the GNU Lesser General Public License as published by the Free
+dnl Software Foundation; either version 3 of the License, or (at your
+dnl option) any later version.
+dnl
+dnl or
+dnl
+dnl * the GNU General Public License as published by the Free Software
+dnl Foundation; either version 2 of the License, or (at your option) any
+dnl later version.
+dnl
+dnl or both in parallel, as here.
+dnl
+dnl The GNU MP Library is distributed in the hope that it will be useful, but
+dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+dnl for more details.
+dnl
+dnl You should have received copies of the GNU General Public License and the
+dnl GNU Lesser General Public License along with the GNU MP Library. If not,
+dnl see https://www.gnu.org/licenses/.
+
+include(`../config.m4')
+
+ABI_SUPPORT(DOS64)
+ABI_SUPPORT(STD64)
+
+MULFUNC_PROLOGUE(mpn_copyd)
+include_mpn(`x86_64/fastsse/copyd.asm')
diff -r 2ce5c60f5372 -r a13428bd4fd3 mpn/x86_64/zen/copyi.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/x86_64/zen/copyi.asm Sat Apr 15 22:56:07 2017 +0200
@@ -0,0 +1,37 @@
+dnl X86-64 mpn_copyi optimised for AMD Zen.
+
+dnl Copyright 2012 Free Software Foundation, Inc.
+
+dnl This file is part of the GNU MP Library.
+dnl
+dnl The GNU MP Library is free software; you can redistribute it and/or modify
+dnl it under the terms of either:
+dnl
+dnl * the GNU Lesser General Public License as published by the Free
+dnl Software Foundation; either version 3 of the License, or (at your
+dnl option) any later version.
+dnl
+dnl or
+dnl
+dnl * the GNU General Public License as published by the Free Software
+dnl Foundation; either version 2 of the License, or (at your option) any
+dnl later version.
+dnl
+dnl or both in parallel, as here.
+dnl
+dnl The GNU MP Library is distributed in the hope that it will be useful, but
+dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+dnl for more details.
+dnl
+dnl You should have received copies of the GNU General Public License and the
+dnl GNU Lesser General Public License along with the GNU MP Library. If not,
+dnl see https://www.gnu.org/licenses/.
+
+include(`../config.m4')
+
+ABI_SUPPORT(DOS64)
+ABI_SUPPORT(STD64)
+
+MULFUNC_PROLOGUE(mpn_copyi)
+include_mpn(`x86_64/fastsse/copyi.asm')
diff -r 2ce5c60f5372 -r a13428bd4fd3 mpn/x86_64/zen/gcd_1.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/x86_64/zen/gcd_1.asm Sat Apr 15 22:56:07 2017 +0200
@@ -0,0 +1,37 @@
+dnl AMD64 mpn_gcd_1.
+
+dnl Copyright 2012 Free Software Foundation, Inc.
+
+dnl This file is part of the GNU MP Library.
+dnl
+dnl The GNU MP Library is free software; you can redistribute it and/or modify
+dnl it under the terms of either:
+dnl
+dnl * the GNU Lesser General Public License as published by the Free
+dnl Software Foundation; either version 3 of the License, or (at your
+dnl option) any later version.
+dnl
+dnl or
+dnl
+dnl * the GNU General Public License as published by the Free Software
+dnl Foundation; either version 2 of the License, or (at your option) any
+dnl later version.
+dnl
+dnl or both in parallel, as here.
+dnl
+dnl The GNU MP Library is distributed in the hope that it will be useful, but
+dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+dnl for more details.
+dnl
+dnl You should have received copies of the GNU General Public License and the
+dnl GNU Lesser General Public License along with the GNU MP Library. If not,
+dnl see https://www.gnu.org/licenses/.
+
+include(`../config.m4')
+
+ABI_SUPPORT(DOS64)
+ABI_SUPPORT(STD64)
+
+MULFUNC_PROLOGUE(mpn_gcd_1)
+include_mpn(`x86_64/core2/gcd_1.asm')
diff -r 2ce5c60f5372 -r a13428bd4fd3 mpn/x86_64/zen/gmp-mparam.h
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/x86_64/zen/gmp-mparam.h Sat Apr 15 22:56:07 2017 +0200
@@ -0,0 +1,226 @@
+/* AMD Zen 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
+
+/* 3500 MHz Zen */
+/* FFT tuning limit = 10 M */
+/* Generated by tuneup.c, 2017-04-15, gcc 4.9 */
+
+#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 13
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD 18
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 8
+#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 22
+
+#define DIV_1_VS_MUL_1_PERCENT 326
+
+#define MUL_TOOM22_THRESHOLD 29
+#define MUL_TOOM33_THRESHOLD 81
+#define MUL_TOOM44_THRESHOLD 121
+#define MUL_TOOM6H_THRESHOLD 262
+#define MUL_TOOM8H_THRESHOLD 296
+
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 81
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 90
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 81
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 103
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 118
+
+#define SQR_BASECASE_THRESHOLD 5
+#define SQR_TOOM2_THRESHOLD 44
+#define SQR_TOOM3_THRESHOLD 80
+#define SQR_TOOM4_THRESHOLD 208
+#define SQR_TOOM6_THRESHOLD 303
+#define SQR_TOOM8_THRESHOLD 406
+
+#define MULMID_TOOM42_THRESHOLD 40
+
+#define MULMOD_BNM1_THRESHOLD 14
+#define SQRMOD_BNM1_THRESHOLD 21
+
+#define MUL_FFT_MODF_THRESHOLD 460 /* k = 5 */
+#define MUL_FFT_TABLE3 \
+ { { 460, 5}, { 21, 6}, { 12, 5}, { 25, 6}, \
+ { 24, 7}, { 13, 6}, { 28, 7}, { 15, 6}, \
+ { 31, 7}, { 21, 8}, { 11, 7}, { 25, 8}, \
+ { 13, 7}, { 27, 8}, { 15, 7}, { 32, 8}, \
+ { 17, 7}, { 35, 8}, { 19, 7}, { 39, 8}, \
+ { 21, 9}, { 11, 8}, { 23, 7}, { 47, 8}, \
+ { 27, 9}, { 15, 8}, { 35, 9}, { 19, 8}, \
+ { 43, 9}, { 23, 8}, { 49, 9}, { 27,10}, \
+ { 15, 9}, { 31, 8}, { 63, 9}, { 43,10}, \
+ { 23, 9}, { 55,11}, { 15,10}, { 31, 9}, \
+ { 67,10}, { 39, 9}, { 79,10}, { 47, 9}, \
+ { 95,10}, { 55,11}, { 31,10}, { 63, 9}, \
+ { 127,10}, { 71, 9}, { 143,10}, { 79,11}, \
+ { 47,10}, { 95,12}, { 31,11}, { 63,10}, \
+ { 127, 9}, { 255,10}, { 135,11}, { 79,10}, \
+ { 159,11}, { 95,10}, { 191,11}, { 111,12}, \
+ { 63,11}, { 127, 9}, { 511,11}, { 143,10}, \
+ { 287,11}, { 159,12}, { 95,11}, { 191,10}, \
+ { 383,13}, { 63,12}, { 127,11}, { 255,10}, \
+ { 511,11}, { 271,10}, { 543,11}, { 287,10}, \
+ { 575,12}, { 159,11}, { 319,10}, { 639,11}, \
+ { 335,10}, { 671,11}, { 351,10}, { 703,12}, \
+ { 191,11}, { 383,10}, { 767,11}, { 415,10}, \
+ { 831, 9}, { 1663,11}, { 447,13}, { 127,12}, \
+ { 255,11}, { 511,10}, { 1023,11}, { 543,12}, \
+ { 287,11}, { 575,10}, { 1151,11}, { 607,10}, \
+ { 1215, 9}, { 2431,12}, { 319,11}, { 671,12}, \
+ { 351,11}, { 703,13}, { 191,12}, { 383,11}, \
+ { 767,10}, { 1535,12}, { 415,11}, { 831,10}, \
+ { 1663,12}, { 447,14}, { 127,13}, { 255,12}, \
+ { 511,11}, { 1023,12}, { 543,11}, { 1087,12}, \
+ { 575,11}, { 1151,12}, { 607,11}, { 1215,10}, \
+ { 2431,13}, { 319,12}, { 671,11}, { 1343,12}, \
+ { 703,11}, { 1407,12}, { 735,13}, { 383,12}, \
+ { 767,11}, { 1599,12}, { 831,11}, { 1663,13}, \
+ { 447,12}, { 959,11}, { 1919,14}, { 255,13}, \
+ { 511,12}, { 1023,11}, { 2047,12}, { 1087,11}, \
+ { 2175,13}, { 575,12}, { 1215,11}, { 2431,10}, \
+ { 4863,13}, { 639,12}, { 1343,11}, { 2687,13}, \
+ { 703,12}, { 1407,14}, { 383,13}, { 767,12}, \
+ { 1599,13}, { 831,12}, { 1727,11}, { 3455,13}, \
+ { 959,12}, { 1919,11}, { 3839,15}, { 255,14}, \
+ { 511,13}, { 1023,12}, { 2047,13}, { 1087,12}, \
+ { 2175,13}, { 1215,12}, { 2431,11}, { 4863,14}, \
+ { 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 186
+#define MUL_FFT_THRESHOLD 6272
+
+#define SQR_FFT_MODF_THRESHOLD 400 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 400, 5}, { 21, 6}, { 11, 5}, { 25, 6}, \
More information about the gmp-commit
mailing list