[Gmp-commit] /var/hg/gmp: 3 new changesets
mercurial at gmplib.org
mercurial at gmplib.org
Fri May 15 19:42:23 UTC 2015
details: /var/hg/gmp/rev/5da577b7e3cd
changeset: 16630:5da577b7e3cd
user: Torbjorn Granlund <torbjorng at google.com>
date: Fri May 15 21:34:55 2015 +0200
description:
Provide cortex-a7/a8 tuning files.
details: /var/hg/gmp/rev/bf96186ea824
changeset: 16631:bf96186ea824
user: Torbjorn Granlund <torbjorng at google.com>
date: Fri May 15 21:41:32 2015 +0200
description:
Provide more arm cycle numbers.
details: /var/hg/gmp/rev/d2482eadb2c7
changeset: 16632:d2482eadb2c7
user: Torbjorn Granlund <torbjorng at google.com>
date: Fri May 15 21:42:17 2015 +0200
description:
ChangeLog
diffstat:
ChangeLog | 6 +
configure.ac | 8 +-
mpn/arm/v6/addmul_1.asm | 5 +-
mpn/arm/v6/addmul_2.asm | 5 +-
mpn/arm/v6/addmul_3.asm | 5 +-
mpn/arm/v6/mul_1.asm | 5 +-
mpn/arm/v6/mul_2.asm | 5 +-
mpn/arm/v7a/cora7/gmp-mparam.h | 163 ++++++++++++++++++++++++++++++++++++++
mpn/arm/v7a/cora8/gmp-mparam.h | 172 +++++++++++++++++++++++++++++++++++++++++
9 files changed, 360 insertions(+), 14 deletions(-)
diffs (truncated from 462 to 300 lines):
diff -r 5736ed67a208 -r d2482eadb2c7 ChangeLog
--- a/ChangeLog Fri May 15 08:26:10 2015 +0200
+++ b/ChangeLog Fri May 15 21:42:17 2015 +0200
@@ -1,3 +1,9 @@
+2015-05-15 Torbjörn Granlund <torbjorng at google.com>
+
+ * mpn/arm/v7a/cora7/gmp-mparam.h: New file.
+ * mpn/arm/v7a/cora8/gmp-mparam.h: New file.
+ * configure.ac (arm): Point to new directories.
+
2015-05-15 Marco Bodrato <bodrato at mail.dm.unipi.it>
* mpn/generic/invertappr.c: Reduce memory usage.
diff -r 5736ed67a208 -r d2482eadb2c7 configure.ac
--- a/configure.ac Fri May 15 08:26:10 2015 +0200
+++ b/configure.ac Fri May 15 21:42:17 2015 +0200
@@ -659,23 +659,23 @@
gcc_cflags_arch="-march=armv7-a"
;;
armcortexa7)
- path="arm/v6t2 arm/v6 arm/v5 arm"
+ path="arm/v7a/cora7 arm/v6t2 arm/v6 arm/v5 arm"
gcc_cflags_arch="-march=armv7-a"
gcc_cflags_tune="-mtune=cortex-a7"
;;
armcortexa7neon)
- path="arm/neon arm/v6t2 arm/v6 arm/v5 arm"
+ path="arm/neon arm/v7a/cora7 arm/v6t2 arm/v6 arm/v5 arm"
gcc_cflags_arch="-march=armv7-a"
gcc_cflags_neon="-mfpu=neon"
gcc_cflags_tune="-mtune=cortex-a7"
;;
armcortexa8)
- path="arm/v6t2 arm/v6 arm/v5 arm"
+ path="arm/v7a/cora8 arm/v6t2 arm/v6 arm/v5 arm"
gcc_cflags_arch="-march=armv7-a"
gcc_cflags_tune="-mtune=cortex-a8"
;;
armcortexa8neon)
- path="arm/neon arm/v6t2 arm/v6 arm/v5 arm"
+ path="arm/neon arm/v7a/cora8 arm/v6t2 arm/v6 arm/v5 arm"
gcc_cflags_arch="-march=armv7-a"
gcc_cflags_neon="-mfpu=neon"
gcc_cflags_tune="-mtune=cortex-a8"
diff -r 5736ed67a208 -r d2482eadb2c7 mpn/arm/v6/addmul_1.asm
--- a/mpn/arm/v6/addmul_1.asm Fri May 15 08:26:10 2015 +0200
+++ b/mpn/arm/v6/addmul_1.asm Fri May 15 21:42:17 2015 +0200
@@ -33,8 +33,9 @@
C cycles/limb
C StrongARM: -
C XScale -
-C Cortex-A7 ?
-C Cortex-A8 ?
+C ARM11 6.4
+C Cortex-A7 5.25
+C Cortex-A8 7
C Cortex-A9 3.25
C Cortex-A15 4
diff -r 5736ed67a208 -r d2482eadb2c7 mpn/arm/v6/addmul_2.asm
--- a/mpn/arm/v6/addmul_2.asm Fri May 15 08:26:10 2015 +0200
+++ b/mpn/arm/v6/addmul_2.asm Fri May 15 21:42:17 2015 +0200
@@ -35,8 +35,9 @@
C cycles/limb
C StrongARM: -
C XScale -
-C Cortex-A7 ?
-C Cortex-A8 ?
+C ARM11 5.5
+C Cortex-A7 3.88
+C Cortex-A8 5.5
C Cortex-A9 2.25
C Cortex-A15 2.5
diff -r 5736ed67a208 -r d2482eadb2c7 mpn/arm/v6/addmul_3.asm
--- a/mpn/arm/v6/addmul_3.asm Fri May 15 08:26:10 2015 +0200
+++ b/mpn/arm/v6/addmul_3.asm Fri May 15 21:42:17 2015 +0200
@@ -35,8 +35,9 @@
C cycles/limb
C StrongARM: -
C XScale -
-C Cortex-A7 ?
-C Cortex-A8 ?
+C ARM11 4.33
+C Cortex-A7 3.23
+C Cortex-A8 3.19
C Cortex-A9 2.125
C Cortex-A15 2
diff -r 5736ed67a208 -r d2482eadb2c7 mpn/arm/v6/mul_1.asm
--- a/mpn/arm/v6/mul_1.asm Fri May 15 08:26:10 2015 +0200
+++ b/mpn/arm/v6/mul_1.asm Fri May 15 21:42:17 2015 +0200
@@ -33,8 +33,9 @@
C cycles/limb
C StrongARM: -
C XScale -
-C Cortex-A7 ?
-C Cortex-A8 ?
+C ARM11 6.4
+C Cortex-A7 5.25
+C Cortex-A8 7
C Cortex-A9 3.25
C Cortex-A15 4
diff -r 5736ed67a208 -r d2482eadb2c7 mpn/arm/v6/mul_2.asm
--- a/mpn/arm/v6/mul_2.asm Fri May 15 08:26:10 2015 +0200
+++ b/mpn/arm/v6/mul_2.asm Fri May 15 21:42:17 2015 +0200
@@ -35,8 +35,9 @@
C cycles/limb
C StrongARM: -
C XScale -
-C Cortex-A7 ?
-C Cortex-A8 ?
+C ARM11 5.25
+C Cortex-A7 3.13
+C Cortex-A8 5
C Cortex-A9 2.25
C Cortex-A15 2.5
diff -r 5736ed67a208 -r d2482eadb2c7 mpn/arm/v7a/cora7/gmp-mparam.h
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/arm/v7a/cora7/gmp-mparam.h Fri May 15 21:42:17 2015 +0200
@@ -0,0 +1,163 @@
+/* gmp-mparam.h -- Compiler/machine parameter header file.
+
+Copyright 1991, 1993, 1994, 1999-2003, 2009, 2010, 2012, 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 32
+#define GMP_LIMB_BYTES 4
+
+/* 900MHz Cortex-A7 (raspberry pi2) */
+/* Generated by tuneup.c, 2015-05-15, gcc 4.6 */
+
+#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 6
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 7
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD MP_SIZE_T_MAX
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 18
+#define USE_PREINV_DIVREM_1 1 /* native */
+#define DIV_QR_1N_PI1_METHOD 1
+#define DIV_QR_1_NORM_THRESHOLD 16
+#define DIV_QR_1_UNNORM_THRESHOLD 1
+#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 48
+
+#define MUL_TOOM22_THRESHOLD 39
+#define MUL_TOOM33_THRESHOLD 129
+#define MUL_TOOM44_THRESHOLD 195
+#define MUL_TOOM6H_THRESHOLD 414
+#define MUL_TOOM8H_THRESHOLD 478
+
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 129
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 153
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 122
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 144
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 193
+
+#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
+#define SQR_TOOM2_THRESHOLD 54
+#define SQR_TOOM3_THRESHOLD 162
+#define SQR_TOOM4_THRESHOLD 274
+#define SQR_TOOM6_THRESHOLD 390
+#define SQR_TOOM8_THRESHOLD 547
+
+#define MULMID_TOOM42_THRESHOLD 58
+
+#define MULMOD_BNM1_THRESHOLD 22
+#define SQRMOD_BNM1_THRESHOLD 27
+
+#define MUL_FFT_MODF_THRESHOLD 636 /* k = 5 */
+#define MUL_FFT_TABLE3 \
+ { { 636, 5}, { 28, 6}, { 15, 5}, { 31, 6}, \
+ { 29, 7}, { 15, 6}, { 33, 7}, { 17, 6}, \
+ { 35, 7}, { 19, 6}, { 39, 7}, { 29, 8}, \
+ { 15, 7}, { 35, 8}, { 19, 7}, { 41, 8}, \
+ { 23, 7}, { 49, 8}, { 27, 7}, { 55, 8}, \
+ { 31, 7}, { 63, 8}, { 43, 9}, { 23, 8}, \
+ { 55, 9}, { 31, 8}, { 67, 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}, \
+ { 159,10}, { 95, 9}, { 191,10}, { 111,11}, \
+ { 63,10}, { 159,11}, { 95,10}, { 191,12}, \
+ { 63,11}, { 127,10}, { 255, 9}, { 511,10}, \
+ { 271, 9}, { 543,11}, { 159,10}, { 319, 9}, \
+ { 639,10}, { 335, 9}, { 671,11}, { 191,10}, \
+ { 383, 9}, { 767,10}, { 399, 9}, { 799,10}, \
+ { 415,11}, { 223,12}, { 4096,13}, { 8192,14}, \
+ { 16384,15}, { 32768,16} }
+#define MUL_FFT_TABLE3_SIZE 70
+#define MUL_FFT_THRESHOLD 6784
+
+#define SQR_FFT_MODF_THRESHOLD 555 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 555, 5}, { 28, 6}, { 15, 5}, { 31, 6}, \
+ { 29, 7}, { 15, 6}, { 33, 7}, { 17, 6}, \
+ { 36, 7}, { 19, 6}, { 39, 7}, { 29, 8}, \
+ { 15, 7}, { 37, 8}, { 19, 7}, { 41, 8}, \
+ { 23, 7}, { 49, 8}, { 27, 7}, { 55, 9}, \
+ { 15, 8}, { 31, 7}, { 63, 8}, { 43, 9}, \
+ { 23, 8}, { 55, 9}, { 31, 8}, { 67, 9}, \
+ { 39, 8}, { 79, 9}, { 47, 8}, { 95, 9}, \
+ { 55,10}, { 31, 9}, { 79,10}, { 47, 9}, \
+ { 95,11}, { 31,10}, { 63, 9}, { 135,10}, \
+ { 79, 9}, { 159,10}, { 95, 9}, { 191,10}, \
+ { 111,11}, { 63,10}, { 143, 9}, { 287,10}, \
+ { 159,11}, { 95,10}, { 191,12}, { 63,11}, \
+ { 127,10}, { 255, 9}, { 511, 8}, { 1023, 9}, \
+ { 543,10}, { 287,11}, { 159,10}, { 319, 9}, \
+ { 639,10}, { 335, 9}, { 671,10}, { 351,11}, \
+ { 191,10}, { 383, 9}, { 767,10}, { 399, 9}, \
+ { 799,10}, { 415,11}, { 223,12}, { 4096,13}, \
+ { 8192,14}, { 16384,15}, { 32768,16} }
+#define SQR_FFT_TABLE3_SIZE 75
+#define SQR_FFT_THRESHOLD 4736
+
+#define MULLO_BASECASE_THRESHOLD 0 /* always */
+#define MULLO_DC_THRESHOLD 27
+#define MULLO_MUL_N_THRESHOLD 13463
+
+#define DC_DIV_QR_THRESHOLD 28
+#define DC_DIVAPPR_Q_THRESHOLD 88
+#define DC_BDIV_QR_THRESHOLD 39
+#define DC_BDIV_Q_THRESHOLD 112
+
+#define INV_MULMOD_BNM1_THRESHOLD 76
+#define INV_NEWTON_THRESHOLD 117
+#define INV_APPR_THRESHOLD 98
+
+#define BINV_NEWTON_THRESHOLD 240
+#define REDC_1_TO_REDC_2_THRESHOLD 4
+#define REDC_2_TO_REDC_N_THRESHOLD 106
+
+#define MU_DIV_QR_THRESHOLD 1718
+#define MU_DIVAPPR_Q_THRESHOLD 1652
+#define MUPI_DIV_QR_THRESHOLD 54
+#define MU_BDIV_QR_THRESHOLD 1470
+#define MU_BDIV_Q_THRESHOLD 1685
+
+#define POWM_SEC_TABLE 1,10,102,615,2016
+
+#define GET_STR_DC_THRESHOLD 28
+#define GET_STR_PRECOMPUTE_THRESHOLD 57
+#define SET_STR_DC_THRESHOLD 270
+#define SET_STR_PRECOMPUTE_THRESHOLD 752
+
+#define FAC_DSC_THRESHOLD 348
+#define FAC_ODD_THRESHOLD 55
+
+#define MATRIX22_STRASSEN_THRESHOLD 27
+#define HGCD_THRESHOLD 55
+#define HGCD_APPR_THRESHOLD 50
+#define HGCD_REDUCE_THRESHOLD 3389
+#define GCD_DC_THRESHOLD 174
+#define GCDEXT_DC_THRESHOLD 183
+#define JACOBI_BASE_METHOD 1
diff -r 5736ed67a208 -r d2482eadb2c7 mpn/arm/v7a/cora8/gmp-mparam.h
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/arm/v7a/cora8/gmp-mparam.h Fri May 15 21:42:17 2015 +0200
@@ -0,0 +1,172 @@
+/* gmp-mparam.h -- Compiler/machine parameter header file.
+
+Copyright 1991, 1993, 1994, 1999-2003, 2009, 2010, 2012, 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:
+
More information about the gmp-commit
mailing list