summaryrefslogtreecommitdiff
path: root/mpn/sparc64
diff options
context:
space:
mode:
authorTorbjorn Granlund <tege@gmplib.org>2010-01-25 00:43:54 +0100
committerTorbjorn Granlund <tege@gmplib.org>2010-01-25 00:43:54 +0100
commit1e04e04594c0335ec1289c4f87d87d290f56a5cc (patch)
tree9d4a85c4ebf96e84ebadece64605f26c5607b71f /mpn/sparc64
parent57a693b6f8862e6203566a8f72e7f576d2ec69e2 (diff)
downloadgmp-1e04e04594c0335ec1289c4f87d87d290f56a5cc.tar.gz
Add FFT_TABLE3 tables for more machines.
Diffstat (limited to 'mpn/sparc64')
-rw-r--r--mpn/sparc64/ultrasparc34/gmp-mparam.h103
1 files changed, 95 insertions, 8 deletions
diff --git a/mpn/sparc64/ultrasparc34/gmp-mparam.h b/mpn/sparc64/ultrasparc34/gmp-mparam.h
index 270e623c6..8c65d59e6 100644
--- a/mpn/sparc64/ultrasparc34/gmp-mparam.h
+++ b/mpn/sparc64/ultrasparc34/gmp-mparam.h
@@ -58,12 +58,103 @@ along with the GNU MP Library. If not, see http://www.gnu.org/licenses/. */
#define MULMOD_BNM1_THRESHOLD 14
#define SQRMOD_BNM1_THRESHOLD 9
-#define MUL_FFT_TABLE { 240, 480, 1344, 2304, 5120, 12288, 81920, 327680, 0 }
-#define MUL_FFT_MODF_THRESHOLD 256
+#define MUL_FFT_MODF_THRESHOLD 212 /* k = 5 */
+#define MUL_FFT_TABLE3 \
+ { { 212, 5}, { 13, 6}, { 17, 7}, { 9, 6}, \
+ { 19, 7}, { 17, 8}, { 9, 7}, { 20, 8}, \
+ { 11, 7}, { 24, 8}, { 13, 9}, { 7, 8}, \
+ { 19, 9}, { 11, 8}, { 25,10}, { 7, 9}, \
+ { 15, 8}, { 33, 9}, { 19, 8}, { 39, 9}, \
+ { 23, 8}, { 47, 9}, { 27,10}, { 15, 9}, \
+ { 39,10}, { 23, 9}, { 47,11}, { 15,10}, \
+ { 31, 9}, { 67,10}, { 39, 9}, { 79, 8}, \
+ { 159, 9}, { 83,10}, { 47, 9}, { 95, 8}, \
+ { 191, 7}, { 383, 9}, { 99,10}, { 55,11}, \
+ { 31,10}, { 63, 9}, { 127, 8}, { 255,10}, \
+ { 71, 9}, { 143, 8}, { 287,10}, { 79, 9}, \
+ { 159, 8}, { 319,11}, { 47,10}, { 95, 9}, \
+ { 191, 8}, { 383,10}, { 103, 9}, { 207, 8}, \
+ { 415,10}, { 111,12}, { 31,11}, { 63,10}, \
+ { 127, 9}, { 255,10}, { 143, 9}, { 287,11}, \
+ { 79,10}, { 159, 9}, { 319, 8}, { 639,10}, \
+ { 175, 9}, { 351,11}, { 95,10}, { 191, 9}, \
+ { 383,10}, { 207, 9}, { 415,11}, { 111,10}, \
+ { 223, 9}, { 447,12}, { 63,11}, { 127,10}, \
+ { 255,11}, { 143,10}, { 287, 9}, { 575,11}, \
+ { 159,10}, { 319,11}, { 175,10}, { 351,12}, \
+ { 95,11}, { 191,10}, { 383,11}, { 207,10}, \
+ { 415,11}, { 223,10}, { 447,13}, { 63,12}, \
+ { 127,11}, { 287,10}, { 575,12}, { 159,11}, \
+ { 351,10}, { 703,12}, { 191,11}, { 415,12}, \
+ { 223,11}, { 479,10}, { 959,13}, { 127,12}, \
+ { 287,11}, { 575,12}, { 351,13}, { 191,12}, \
+ { 479,14}, { 127,13}, { 255,12}, { 575,13}, \
+ { 319,12}, { 639,11}, { 1279,12}, { 703,13}, \
+ { 383,12}, { 831,13}, { 447,12}, { 895,14}, \
+ { 255,13}, { 511,12}, { 1087,13}, { 575,12}, \
+ { 1215,13}, { 639,12}, { 1279,13}, { 703,14}, \
+ { 383,13}, { 831,12}, { 1663,13}, { 895,15}, \
+ { 255,14}, { 511,13}, { 1151,14}, { 639,13}, \
+ { 1407,14}, { 767,13}, { 1663,14}, { 895,13}, \
+ { 1791,15}, { 511,14}, { 1023,13}, { 2047,14}, \
+ { 1151,13}, { 2303,14}, { 1407,15}, { 767,14}, \
+ { 1791,16}, { 511,15}, { 1023,14}, { 2303,15}, \
+ { 1279,14}, { 2815,15}, { 1535,14}, { 3199,15}, \
+ { 1791,14}, { 3583,16}, { 65536,17}, { 131072,18}, \
+ { 262144,19}, { 524288,20}, {1048576,21}, {2097152,22}, \
+ {4194304,23}, {8388608,24} }
+#define MUL_FFT_TABLE3_SIZE 170
#define MUL_FFT_THRESHOLD 2240
-#define SQR_FFT_TABLE { 304, 608, 1344, 2304, 7168, 12288, 81920, 327680, 0 }
-#define SQR_FFT_MODF_THRESHOLD 248
+#define SQR_FFT_MODF_THRESHOLD 244 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 244, 5}, { 8, 4}, { 17, 5}, { 17, 6}, \
+ { 17, 7}, { 9, 6}, { 19, 7}, { 17, 8}, \
+ { 9, 7}, { 20, 8}, { 11, 7}, { 23, 8}, \
+ { 21, 9}, { 11, 8}, { 25, 9}, { 15, 8}, \
+ { 31, 9}, { 19, 8}, { 39, 9}, { 27,10}, \
+ { 15, 9}, { 39,10}, { 23, 9}, { 47,11}, \
+ { 15,10}, { 31, 9}, { 67,10}, { 39, 9}, \
+ { 79,10}, { 55,11}, { 31,10}, { 63, 9}, \
+ { 127, 8}, { 255,10}, { 71, 9}, { 143, 8}, \
+ { 287,10}, { 79, 9}, { 159,11}, { 47,10}, \
+ { 95, 9}, { 191, 8}, { 383,12}, { 31,11}, \
+ { 63,10}, { 127, 9}, { 255, 8}, { 511,10}, \
+ { 135, 9}, { 271,10}, { 143, 9}, { 287,11}, \
+ { 79,10}, { 159, 9}, { 319, 8}, { 639,10}, \
+ { 175, 9}, { 351, 8}, { 703,11}, { 95,10}, \
+ { 191, 9}, { 383, 8}, { 767,10}, { 207, 9}, \
+ { 415, 8}, { 831,10}, { 223, 9}, { 447,12}, \
+ { 63,11}, { 127,10}, { 271, 9}, { 543,11}, \
+ { 143,10}, { 287, 9}, { 575, 8}, { 1151, 9}, \
+ { 607,11}, { 159,10}, { 319, 9}, { 639,11}, \
+ { 175,10}, { 351, 9}, { 703, 8}, { 1407,12}, \
+ { 95,11}, { 191,10}, { 383,11}, { 207,10}, \
+ { 415, 9}, { 831,11}, { 223,10}, { 447,13}, \
+ { 63,12}, { 127,11}, { 271,10}, { 543,11}, \
+ { 287,10}, { 575, 9}, { 1151,10}, { 607,12}, \
+ { 159,11}, { 319,10}, { 639,11}, { 351,10}, \
+ { 703,12}, { 191,11}, { 415,10}, { 831,12}, \
+ { 223,11}, { 479,13}, { 127,12}, { 255,11}, \
+ { 543,12}, { 287,11}, { 607,12}, { 319,11}, \
+ { 639,12}, { 351,11}, { 703,13}, { 191,12}, \
+ { 415,11}, { 831,12}, { 479,11}, { 959,14}, \
+ { 127,13}, { 255,12}, { 543,11}, { 1087,12}, \
+ { 575,13}, { 319,12}, { 639,11}, { 1279,12}, \
+ { 703,13}, { 383,12}, { 831,13}, { 447,12}, \
+ { 895,14}, { 255,13}, { 511,12}, { 1023,13}, \
+ { 575,12}, { 1151,13}, { 703,14}, { 383,13}, \
+ { 831,12}, { 1663,13}, { 959,15}, { 255,14}, \
+ { 511,13}, { 1087,12}, { 2175,13}, { 1151,14}, \
+ { 639,13}, { 1407,14}, { 767,13}, { 1663,14}, \
+ { 895,13}, { 1791,15}, { 511,14}, { 1023,13}, \
+ { 2047,14}, { 1151,13}, { 2431,14}, { 1407,15}, \
+ { 767,14}, { 1791,16}, { 511,15}, { 1023,14}, \
+ { 2303,15}, { 1279,14}, { 2815,15}, { 1535,14}, \
+ { 3199,15}, { 1791,16}, { 65536,17}, { 131072,18}, \
+ { 262144,19}, { 524288,20}, {1048576,21}, {2097152,22}, \
+ {4194304,23}, {8388608,24} }
+#define SQR_FFT_TABLE3_SIZE 182
#define SQR_FFT_THRESHOLD 1984
#define MULLO_BASECASE_THRESHOLD 26
@@ -99,7 +190,3 @@ along with the GNU MP Library. If not, see http://www.gnu.org/licenses/. */
#define GET_STR_PRECOMPUTE_THRESHOLD 27
#define SET_STR_DC_THRESHOLD 315
#define SET_STR_PRECOMPUTE_THRESHOLD 1037
-
-#define MUL_FFT_TABLE2 {{1,4}, {177,5}, {417,6}, {1089,7}, {2561,8}, {4865,9}, {5633,8}, {6401,10}, {7169,9}, {7681,8}, {8449,9}, {13825,10}, {15361,9}, {19969,10}, {23553,9}, {24065,11}, {30721,10}, {31745,9}, {34305,10}, {39937,9}, {42497,10}, {56321,11}, {63489,10}, {81921,11}, {96257,10}, {106241,12}, {126977,11}, {129025,10}, {146945,11}, {161793,10}, {179713,11}, {180737,9}, {181249,10}, {182273,11}, {194561,10}, {212993,11}, {228353,12}, {258049,11}, {359425,12}, {389121,11}, {456705,13}, {516097,12}, {520193,11}, {588801,12}, {651265,11}, {714753,12}, {782337,11}, {850945,12}, {913409,11}, {915457,13}, {1040385,12}, {1439745,13}, {1564673,12}, {1830913,14}, {1884161,12}, {1900545,14}, {1921025,12}, {1961985,14}, {MP_SIZE_T_MAX, 0}}
-
-#define SQR_FFT_TABLE2 {{1,4}, {241,5}, {481,6}, {1217,7}, {2561,8}, {6401,9}, {11777,10}, {15361,9}, {19969,10}, {23553,9}, {24065,11}, {30721,10}, {56321,11}, {63489,10}, {81665,11}, {96257,10}, {105473,9}, {114433,11}, {114689,12}, {126977,11}, {129025,10}, {130049,9}, {139009,10}, {146945,11}, {161793,10}, {179969,11}, {194561,10}, {228865,12}, {258049,11}, {260097,10}, {278017,11}, {458753,13}, {516097,12}, {520193,11}, {587777,10}, {589313,12}, {651265,11}, {719873,12}, {782337,11}, {850945,12}, {913409,11}, {982017,13}, {1040385,12}, {1044481,11}, {1113089,12}, {1187841,11}, {1191937,12}, {1196033,11}, {1212417,12}, {1220609,11}, {1224705,12}, {1439745,13}, {1564673,12}, {1961985,14}, {MP_SIZE_T_MAX, 0}}