[Gmp-commit] /home/hgfiles/gmp: Retune atom-32 (with FFT_TABLE3).
mercurial at gmplib.org
mercurial at gmplib.org
Tue Jan 26 12:26:54 CET 2010
details: /home/hgfiles/gmp/rev/24e8cb9950c5
changeset: 13399:24e8cb9950c5
user: Marco Bodrato <bodrato at mail.dm.unipi.it>
date: Tue Jan 26 12:26:32 2010 +0100
description:
Retune atom-32 (with FFT_TABLE3).
diffstat:
mpn/x86/atom/gmp-mparam.h | 144 ++++++++++++++++++++++++++++++++++++---------
1 files changed, 113 insertions(+), 31 deletions(-)
diffs (196 lines):
diff -r 77f525d9039a -r 24e8cb9950c5 mpn/x86/atom/gmp-mparam.h
--- a/mpn/x86/atom/gmp-mparam.h Mon Jan 25 14:31:26 2010 +0100
+++ b/mpn/x86/atom/gmp-mparam.h Tue Jan 26 12:26:32 2010 +0100
@@ -1,7 +1,7 @@
/* Intel Atom/32 gmp-mparam.h -- Compiler/machine parameter header file.
Copyright 1991, 1993, 1994, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007,
-2008, 2009 Free Software Foundation, Inc.
+2008, 2009, 2010 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
@@ -21,18 +21,18 @@
#define GMP_LIMB_BITS 32
#define BYTES_PER_MP_LIMB 4
-/* Generated by tuneup.c, 2009-12-28, gcc 4.4 */
+/* Generated by tuneup.c */
#define MOD_1_NORM_THRESHOLD 3
#define MOD_1_UNNORM_THRESHOLD 7
#define MOD_1N_TO_MOD_1_1_THRESHOLD 19
#define MOD_1U_TO_MOD_1_1_THRESHOLD 7
-#define MOD_1_1_TO_MOD_1_2_THRESHOLD 11
-#define MOD_1_2_TO_MOD_1_4_THRESHOLD 18
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 38
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD MP_SIZE_T_MAX
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD MP_SIZE_T_MAX
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 31
#define USE_PREINV_DIVREM_1 1
#define DIVEXACT_1_THRESHOLD 0 /* always (native) */
-#define BMOD_1_TO_MOD_1_THRESHOLD 144
+#define BMOD_1_TO_MOD_1_THRESHOLD MP_SIZE_T_MAX /* never */
#define MUL_TOOM22_THRESHOLD 16
#define MUL_TOOM33_THRESHOLD 66
@@ -41,8 +41,8 @@
#define MUL_TOOM8H_THRESHOLD 357
#define MUL_TOOM32_TO_TOOM43_THRESHOLD 113
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 124
-#define MUL_TOOM42_TO_TOOM53_THRESHOLD 113
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 129
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 115
#define MUL_TOOM42_TO_TOOM63_THRESHOLD 129
#define SQR_BASECASE_THRESHOLD 0 /* always (native) */
@@ -55,43 +55,125 @@
#define MULMOD_BNM1_THRESHOLD 13
#define SQRMOD_BNM1_THRESHOLD 11
-#define MUL_FFT_TABLE { 336, 672, 896, 2560, 10240, 24576, 98304, 393216, 0 }
-#define MUL_FFT_MODF_THRESHOLD 352
-#define MUL_FFT_THRESHOLD 7168
+#define MUL_FFT_MODF_THRESHOLD 332 /* k = 5 */
+#define MUL_FFT_TABLE3 \
+ { { 332, 5}, { 17, 6}, { 9, 5}, { 19, 6}, \
+ { 11, 5}, { 23, 6}, { 17, 7}, { 9, 6}, \
+ { 19, 7}, { 11, 6}, { 25, 7}, { 15, 6}, \
+ { 31, 7}, { 19, 8}, { 11, 7}, { 27, 8}, \
+ { 15, 7}, { 33, 8}, { 19, 7}, { 39, 8}, \
+ { 23, 7}, { 47, 8}, { 27, 9}, { 15, 8}, \
+ { 35, 7}, { 71, 8}, { 39, 9}, { 23, 8}, \
+ { 51,10}, { 15, 9}, { 31, 8}, { 67, 9}, \
+ { 39, 8}, { 79, 9}, { 55,10}, { 31, 9}, \
+ { 79,10}, { 47, 9}, { 95,11}, { 31,10}, \
+ { 63, 9}, { 127, 8}, { 255, 9}, { 135,10}, \
+ { 79, 9}, { 159,10}, { 95, 9}, { 191, 8}, \
+ { 383,11}, { 63,10}, { 127, 9}, { 255, 8}, \
+ { 511, 9}, { 271,10}, { 143, 9}, { 287, 8}, \
+ { 607,10}, { 159, 9}, { 319,11}, { 95,10}, \
+ { 191, 9}, { 383,12}, { 63,11}, { 127,10}, \
+ { 255, 9}, { 511,10}, { 271, 9}, { 543, 8}, \
+ { 1087,10}, { 287, 9}, { 607,11}, { 159,10}, \
+ { 351, 9}, { 703, 8}, { 1407,11}, { 191,10}, \
+ { 415, 9}, { 831,11}, { 223,10}, { 479, 9}, \
+ { 959,12}, { 127,11}, { 255,10}, { 543, 9}, \
+ { 1087,11}, { 287,10}, { 607, 9}, { 1215,11}, \
+ { 351,10}, { 703, 9}, { 1407,12}, { 191,11}, \
+ { 383,10}, { 767,11}, { 415,10}, { 831,11}, \
+ { 479,10}, { 959,13}, { 127,12}, { 255,11}, \
+ { 543,10}, { 1087,11}, { 607,10}, { 1215,12}, \
+ { 319,11}, { 703,10}, { 1407,11}, { 735,10}, \
+ { 1471,12}, { 383,11}, { 831,12}, { 447,11}, \
+ { 959,10}, { 1919,13}, { 255,12}, { 511,11}, \
+ { 1087,12}, { 575,11}, { 1215,10}, { 2431,12}, \
+ { 703,11}, { 1471,13}, { 383,12}, { 959,11}, \
+ { 1919,14}, { 255,13}, { 511,12}, { 1215,11}, \
+ { 2431,13}, { 639,12}, { 1471,11}, { 2943,10}, \
+ { 5887,13}, { 767,12}, { 1599,13}, { 895,12}, \
+ { 1919,11}, { 3839,14}, { 511,13}, { 1023,12}, \
+ { 2111,13}, { 1151,12}, { 2431,13}, { 1407,12}, \
+ { 2943,11}, { 5887,14}, { 767,13}, { 1919,12}, \
+ { 3839,15}, { 511,14}, { 1023,13}, { 2431,14}, \
+ { 1279,13}, { 2943,12}, { 5887,14}, { 1535,13}, \
+ { 3199,14}, { 1791,13}, { 3839,12}, { 7679,15}, \
+ { 1023,14}, { 16384,15}, { 32768,16} }
+#define MUL_FFT_TABLE3_SIZE 163
+#define MUL_FFT_THRESHOLD 3456
-#define SQR_FFT_TABLE { 336, 672, 896, 2560, 6144, 24576, 98304, 393216, 0 }
-#define SQR_FFT_MODF_THRESHOLD 296
-#define SQR_FFT_THRESHOLD 3840
+#define SQR_FFT_MODF_THRESHOLD 308 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 308, 5}, { 13, 6}, { 7, 5}, { 17, 6}, \
+ { 9, 5}, { 19, 6}, { 13, 7}, { 7, 6}, \
+ { 17, 7}, { 9, 6}, { 19, 7}, { 11, 6}, \
+ { 24, 7}, { 15, 6}, { 31, 7}, { 21, 8}, \
+ { 11, 7}, { 25, 8}, { 15, 7}, { 31, 8}, \
+ { 19, 7}, { 39, 8}, { 23, 7}, { 47, 8}, \
+ { 27, 9}, { 15, 8}, { 31, 4}, { 607, 5}, \
+ { 319, 7}, { 95, 8}, { 55, 9}, { 31, 8}, \
+ { 63, 9}, { 39, 8}, { 79, 9}, { 47,10}, \
+ { 31, 9}, { 79,10}, { 47,11}, { 31,10}, \
+ { 63, 9}, { 127, 8}, { 255, 7}, { 511,10}, \
+ { 79, 9}, { 159, 8}, { 319,10}, { 95, 9}, \
+ { 191, 8}, { 383,11}, { 63,10}, { 127, 9}, \
+ { 255, 8}, { 543, 7}, { 1087, 9}, { 287, 8}, \
+ { 607,10}, { 159, 9}, { 319,11}, { 95,10}, \
+ { 191, 9}, { 383,12}, { 63,11}, { 127,10}, \
+ { 255, 9}, { 543, 8}, { 1087,10}, { 287, 9}, \
+ { 607,11}, { 159,10}, { 351, 9}, { 703, 8}, \
+ { 1407, 9}, { 735,11}, { 191,10}, { 415, 9}, \
+ { 831,11}, { 223,10}, { 479, 9}, { 959, 8}, \
+ { 1919,12}, { 127,11}, { 255,10}, { 543, 9}, \
+ { 1087,11}, { 287,10}, { 607, 9}, { 1215,11}, \
+ { 351,10}, { 703, 9}, { 1407,12}, { 191,11}, \
+ { 415,10}, { 831,11}, { 479,10}, { 959, 9}, \
+ { 1919,13}, { 127,12}, { 255,11}, { 543,10}, \
+ { 1087,11}, { 607,10}, { 1215,12}, { 319,11}, \
+ { 703,10}, { 1407,11}, { 735,12}, { 383,11}, \
+ { 831,12}, { 447,11}, { 959,10}, { 1919, 9}, \
+ { 3839,13}, { 255,12}, { 511,11}, { 1087,12}, \
+ { 575,11}, { 1215,10}, { 2431,12}, { 703,11}, \
+ { 1407,13}, { 383,12}, { 959,11}, { 1919,10}, \
+ { 3839,14}, { 255,13}, { 511,12}, { 1215,11}, \
+ { 2431,13}, { 639,12}, { 1471,11}, { 2943,13}, \
+ { 767,12}, { 1599,13}, { 895,12}, { 1919,11}, \
+ { 3839,14}, { 511,13}, { 1151,12}, { 2431,13}, \
+ { 1407,12}, { 2943,14}, { 767,13}, { 1919,12}, \
+ { 3839,15}, { 511,14}, { 1023,13}, { 2431,14}, \
+ { 1279,13}, { 2943,14}, { 1791,13}, { 3839,15}, \
+ { 1023,14}, { 16384,15}, { 32768,16} }
+#define SQR_FFT_TABLE3_SIZE 155
+#define SQR_FFT_THRESHOLD 2368
#define MULLO_BASECASE_THRESHOLD 0 /* always */
#define MULLO_DC_THRESHOLD 56
-#define MULLO_MUL_N_THRESHOLD 8648
+#define MULLO_MUL_N_THRESHOLD 6633
-#define DC_DIV_QR_THRESHOLD 58
-#define DC_DIVAPPR_Q_THRESHOLD 220
+#define DC_DIV_QR_THRESHOLD 59
+#define DC_DIVAPPR_Q_THRESHOLD 216
#define DC_BDIV_QR_THRESHOLD 56
#define DC_BDIV_Q_THRESHOLD 136
-#define INV_MULMOD_BNM1_THRESHOLD 30
+#define INV_MULMOD_BNM1_THRESHOLD 59
#define INV_NEWTON_THRESHOLD 260
#define INV_APPR_THRESHOLD 244
-#define BINV_NEWTON_THRESHOLD 264
-#define REDC_1_TO_REDC_N_THRESHOLD 63
+#define BINV_NEWTON_THRESHOLD 266
+#define REDC_1_TO_REDC_N_THRESHOLD 62
-#define MU_DIV_QR_THRESHOLD 1607
-#define MU_DIVAPPR_Q_THRESHOLD 1607
-#define MUPI_DIV_QR_THRESHOLD 293
-#define MU_BDIV_QR_THRESHOLD 1547
-#define MU_BDIV_Q_THRESHOLD 1577
+#define MU_DIV_QR_THRESHOLD 1308
+#define MU_DIVAPPR_Q_THRESHOLD 1334
+#define MUPI_DIV_QR_THRESHOLD 130
+#define MU_BDIV_QR_THRESHOLD 1017
+#define MU_BDIV_Q_THRESHOLD 1308
-#define MATRIX22_STRASSEN_THRESHOLD 17
-#define HGCD_THRESHOLD 109
-#define GCD_DC_THRESHOLD 372
-#define GCDEXT_DC_THRESHOLD 275
-#define JACOBI_BASE_METHOD 2
+#define MATRIX22_STRASSEN_THRESHOLD 15
+#define HGCD_THRESHOLD 111
+#define GCD_DC_THRESHOLD 375
+#define GCDEXT_DC_THRESHOLD 273
+#define JACOBI_BASE_METHOD 3
#define GET_STR_DC_THRESHOLD 14
-#define GET_STR_PRECOMPUTE_THRESHOLD 27
+#define GET_STR_PRECOMPUTE_THRESHOLD 26
#define SET_STR_DC_THRESHOLD 270
#define SET_STR_PRECOMPUTE_THRESHOLD 860
More information about the gmp-commit
mailing list