summaryrefslogtreecommitdiff
path: root/mpn/x86_64
diff options
context:
space:
mode:
authorTorbjorn Granlund <tg@gmplib.org>2019-11-17 23:42:56 +0100
committerTorbjorn Granlund <tg@gmplib.org>2019-11-17 23:42:56 +0100
commit33fdd0ad3c05366fa7431418f6ba0da52a2c5091 (patch)
tree5c7212997b43a06812d9b4e4da6b18fe321e19a5 /mpn/x86_64
parent9f4b2946b5690a9391349d5cf469f19524d870d8 (diff)
downloadgmp-33fdd0ad3c05366fa7431418f6ba0da52a2c5091.tar.gz
Regenerate more gmp-mparam.h files for larger FFT limit.
Diffstat (limited to 'mpn/x86_64')
-rw-r--r--mpn/x86_64/pentium4/gmp-mparam.h207
1 files changed, 139 insertions, 68 deletions
diff --git a/mpn/x86_64/pentium4/gmp-mparam.h b/mpn/x86_64/pentium4/gmp-mparam.h
index df2b65675..9c79310e5 100644
--- a/mpn/x86_64/pentium4/gmp-mparam.h
+++ b/mpn/x86_64/pentium4/gmp-mparam.h
@@ -39,8 +39,8 @@ see https://www.gnu.org/licenses/. */
#undef HAVE_NATIVE_mpn_rsblsh_n
/* 3400 MHz Pentium4 Nocona / 1024 Kibyte L2 cache */
-/* FFT tuning limit = 0.5 M */
-/* Generated by tuneup.c, 2019-09-27, gcc 8.3 */
+/* FFT tuning limit = 107,095,964 */
+/* Generated by tuneup.c, 2019-11-09, gcc 8.3 */
#define MOD_1_NORM_THRESHOLD 0 /* always */
#define MOD_1_UNNORM_THRESHOLD 0 /* always */
@@ -48,7 +48,7 @@ see https://www.gnu.org/licenses/. */
#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 32
-#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 12
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 11
#define USE_PREINV_DIVREM_1 1 /* native */
#define DIV_QR_1_NORM_THRESHOLD 2
#define DIV_QR_1_UNNORM_THRESHOLD MP_SIZE_T_MAX /* never */
@@ -60,13 +60,13 @@ see https://www.gnu.org/licenses/. */
#define MUL_TOOM22_THRESHOLD 12
#define MUL_TOOM33_THRESHOLD 81
-#define MUL_TOOM44_THRESHOLD 178
-#define MUL_TOOM6H_THRESHOLD 0 /* always */
+#define MUL_TOOM44_THRESHOLD 130
+#define MUL_TOOM6H_THRESHOLD 173
#define MUL_TOOM8H_THRESHOLD 430
#define MUL_TOOM32_TO_TOOM43_THRESHOLD 81
-#define MUL_TOOM32_TO_TOOM53_THRESHOLD 138
-#define MUL_TOOM42_TO_TOOM53_THRESHOLD 82
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 91
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 89
#define MUL_TOOM42_TO_TOOM63_THRESHOLD 88
#define MUL_TOOM43_TO_TOOM54_THRESHOLD 112
@@ -77,50 +77,84 @@ see https://www.gnu.org/licenses/. */
#define SQR_TOOM6_THRESHOLD 238
#define SQR_TOOM8_THRESHOLD 430
-#define MULMID_TOOM42_THRESHOLD 24
+#define MULMID_TOOM42_THRESHOLD 20
#define MULMOD_BNM1_THRESHOLD 9
#define SQRMOD_BNM1_THRESHOLD 11
-#define MUL_FFT_MODF_THRESHOLD 244 /* k = 5 */
+#define MUL_FFT_MODF_THRESHOLD 236 /* k = 5 */
#define MUL_FFT_TABLE3 \
- { { 244, 5}, { 11, 6}, { 6, 5}, { 13, 6}, \
- { 21, 7}, { 11, 6}, { 23, 7}, { 13, 8}, \
- { 7, 7}, { 17, 8}, { 9, 7}, { 21, 8}, \
- { 11, 7}, { 23, 8}, { 13, 9}, { 7, 8}, \
- { 15, 7}, { 31, 8}, { 21, 9}, { 11, 8}, \
- { 27,10}, { 7, 9}, { 15, 8}, { 33, 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}, \
- { 47, 9}, { 95,10}, { 55,11}, { 31,10}, \
- { 63, 9}, { 127, 8}, { 255,10}, { 71, 9}, \
- { 143, 8}, { 287,10}, { 79,11}, { 47,10}, \
- { 95,12}, { 31,11}, { 63,10}, { 127, 9}, \
- { 255,10}, { 143, 9}, { 287,11}, { 79,10}, \
- { 159, 9}, { 319,10}, { 175,11}, { 95,10}, \
- { 191, 9}, { 383,10}, { 207, 9}, { 415,10}, \
- { 223,12}, { 63,11}, { 127,10}, { 255,11}, \
- { 143,10}, { 287,11}, { 159,10}, { 319,11}, \
- { 175,12}, { 95,11}, { 191,10}, { 383,11}, \
- { 207,10}, { 415,11}, { 223,13}, { 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 90
-#define MUL_FFT_THRESHOLD 3200
-
-#define SQR_FFT_MODF_THRESHOLD 244 /* k = 5 */
-#define SQR_FFT_TABLE3 \
- { { 244, 5}, { 11, 6}, { 6, 5}, { 13, 6}, \
- { 7, 5}, { 15, 6}, { 9, 5}, { 19, 6}, \
- { 17, 7}, { 9, 6}, { 21, 7}, { 11, 6}, \
+ { { 236, 5}, { 11, 6}, { 6, 5}, { 13, 6}, \
+ { 9, 5}, { 19, 6}, { 17, 7}, { 9, 6}, \
+ { 19, 7}, { 10, 6}, { 21, 7}, { 11, 6}, \
{ 23, 7}, { 13, 8}, { 7, 7}, { 17, 8}, \
- { 9, 7}, { 21, 8}, { 11, 7}, { 24, 8}, \
+ { 9, 7}, { 21, 8}, { 11, 7}, { 23, 8}, \
{ 13, 9}, { 7, 8}, { 15, 7}, { 31, 8}, \
{ 21, 9}, { 11, 8}, { 27,10}, { 7, 9}, \
{ 15, 8}, { 33, 9}, { 19, 8}, { 39, 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}, \
+ { 47, 9}, { 95,10}, { 55,11}, { 31,10}, \
+ { 63, 9}, { 127, 8}, { 255,10}, { 71, 9}, \
+ { 143, 8}, { 287,10}, { 79,11}, { 47,10}, \
+ { 95, 9}, { 191,12}, { 31,11}, { 63,10}, \
+ { 127, 9}, { 255,10}, { 143, 9}, { 287,11}, \
+ { 79,10}, { 159, 9}, { 319,10}, { 175,11}, \
+ { 95,10}, { 191, 9}, { 383,10}, { 223,12}, \
+ { 63,11}, { 127,10}, { 255,11}, { 143,10}, \
+ { 287,11}, { 159,10}, { 319,11}, { 175,12}, \
+ { 95,11}, { 191,10}, { 383,11}, { 223,13}, \
+ { 63,12}, { 127,11}, { 255,10}, { 511,11}, \
+ { 287,10}, { 575,12}, { 159,11}, { 351,12}, \
+ { 191,11}, { 383,12}, { 223,11}, { 447,13}, \
+ { 127,12}, { 255,11}, { 511,12}, { 287,11}, \
+ { 575,10}, { 1151,12}, { 351,13}, { 191,12}, \
+ { 415,11}, { 831,10}, { 1663,12}, { 447,14}, \
+ { 127,13}, { 255,12}, { 511,11}, { 1023,12}, \
+ { 543,11}, { 1087,10}, { 2175,12}, { 575,11}, \
+ { 1151,13}, { 319,12}, { 639,11}, { 1279,12}, \
+ { 671,11}, { 1343,12}, { 703,13}, { 383,12}, \
+ { 767,11}, { 1535,12}, { 831,11}, { 1663,13}, \
+ { 447,14}, { 255,13}, { 511,12}, { 1023,11}, \
+ { 2047,12}, { 1087,11}, { 2175,13}, { 575,12}, \
+ { 1151,11}, { 2303,12}, { 1215,11}, { 2431,10}, \
+ { 4863,13}, { 639,12}, { 1279,11}, { 2559,12}, \
+ { 1343,13}, { 703,14}, { 383,13}, { 767,12}, \
+ { 1535,13}, { 831,12}, { 1663,15}, { 255,14}, \
+ { 511,13}, { 1023,12}, { 2047,13}, { 1087,12}, \
+ { 2175,13}, { 1151,12}, { 2303,13}, { 1215,12}, \
+ { 2431,11}, { 4863,14}, { 639,13}, { 1279,12}, \
+ { 2559,13}, { 1343,12}, { 2687,13}, { 1407,12}, \
+ { 2815,13}, { 1471,14}, { 767,13}, { 1663,14}, \
+ { 895,13}, { 1791,12}, { 3583,13}, { 1919,12}, \
+ { 3839,15}, { 511,14}, { 1023,13}, { 2175,14}, \
+ { 1151,13}, { 2303,12}, { 4607,13}, { 2431,12}, \
+ { 4863,14}, { 1279,13}, { 2687,14}, { 1407,13}, \
+ { 2815,15}, { 767,14}, { 1791,13}, { 3583,14}, \
+ { 1919,13}, { 3839,16}, { 511,15}, { 1023,14}, \
+ { 2175,13}, { 4351,14}, { 2303,13}, { 4607,14}, \
+ { 2431,13}, { 4863,15}, { 1279,14}, { 2943,13}, \
+ { 5887,15}, { 1535,14}, { 3199,15}, { 1791,14}, \
+ { 3839,13}, { 7679,16}, { 1023,15}, { 2047,14}, \
+ { 4351,15}, { 2303,14}, { 4863,15}, { 2815,14}, \
+ { 5887,16}, { 1535,15}, { 3071,14}, { 6143,15}, \
+ { 32768,16}, { 65536,17}, { 131072,18}, { 262144,19}, \
+ { 524288,20}, {1048576,21}, {2097152,22}, {4194304,23}, \
+ {8388608,24} }
+#define MUL_FFT_TABLE3_SIZE 229
+#define MUL_FFT_THRESHOLD 2752
+
+#define SQR_FFT_MODF_THRESHOLD 240 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 240, 5}, { 11, 6}, { 6, 5}, { 13, 6}, \
+ { 9, 5}, { 19, 6}, { 17, 7}, { 9, 6}, \
+ { 23, 7}, { 12, 6}, { 25, 7}, { 13, 8}, \
+ { 7, 7}, { 17, 8}, { 9, 7}, { 21, 8}, \
+ { 11, 7}, { 24, 8}, { 13, 9}, { 7, 8}, \
+ { 15, 7}, { 31, 8}, { 21, 9}, { 11, 8}, \
+ { 27,10}, { 7, 9}, { 15, 8}, { 33, 9}, \
+ { 19, 8}, { 39, 9}, { 27,10}, { 15, 9}, \
{ 39,10}, { 23, 9}, { 47,11}, { 15,10}, \
{ 31, 9}, { 63,10}, { 39, 9}, { 79,10}, \
{ 55,11}, { 31,10}, { 63, 9}, { 127, 8}, \
@@ -134,53 +168,90 @@ see https://www.gnu.org/licenses/. */
{ 143,10}, { 287,11}, { 159,10}, { 319,11}, \
{ 175,10}, { 351,12}, { 95,11}, { 191,10}, \
{ 383,11}, { 207,10}, { 415,11}, { 223,13}, \
- { 8192,14}, { 16384,15}, { 32768,16}, { 65536,17}, \
+ { 63,12}, { 127,11}, { 255,10}, { 511,11}, \
+ { 287,10}, { 575,12}, { 159,11}, { 319,10}, \
+ { 639,11}, { 351,12}, { 191,11}, { 383,10}, \
+ { 767,12}, { 223,11}, { 447,13}, { 127,12}, \
+ { 255,11}, { 511,12}, { 287,11}, { 575,10}, \
+ { 1151,12}, { 319,11}, { 639,12}, { 351,13}, \
+ { 191,12}, { 383,11}, { 767,12}, { 415,11}, \
+ { 831,12}, { 447,14}, { 127,13}, { 255,12}, \
+ { 511,11}, { 1023,12}, { 543,11}, { 1087,12}, \
+ { 575,11}, { 1151,13}, { 319,12}, { 639,11}, \
+ { 1279,12}, { 671,11}, { 1343,13}, { 383,12}, \
+ { 767,11}, { 1535,12}, { 831,13}, { 447,14}, \
+ { 255,13}, { 511,12}, { 1023,11}, { 2047,12}, \
+ { 1087,13}, { 575,12}, { 1151,11}, { 2303,12}, \
+ { 1215,11}, { 2431,10}, { 4863,13}, { 639,12}, \
+ { 1279,11}, { 2559,12}, { 1343,11}, { 2687,14}, \
+ { 383,13}, { 767,12}, { 1535,13}, { 831,12}, \
+ { 1663,15}, { 255,14}, { 511,13}, { 1023,12}, \
+ { 2047,13}, { 1087,12}, { 2175,13}, { 1151,12}, \
+ { 2303,13}, { 1215,12}, { 2431,11}, { 4863,14}, \
+ { 639,13}, { 1279,12}, { 2559,13}, { 1343,12}, \
+ { 2687,13}, { 1407,12}, { 2815,13}, { 1471,14}, \
+ { 767,13}, { 1663,14}, { 895,13}, { 1791,12}, \
+ { 3583,13}, { 1919,12}, { 3839,15}, { 511,14}, \
+ { 1023,13}, { 2175,14}, { 1151,13}, { 2303,12}, \
+ { 4607,13}, { 2431,12}, { 4863,14}, { 1279,13}, \
+ { 2687,14}, { 1407,13}, { 2943,15}, { 767,14}, \
+ { 1663,13}, { 3327,14}, { 1791,13}, { 3583,14}, \
+ { 1919,13}, { 3839,16}, { 511,15}, { 1023,14}, \
+ { 2175,13}, { 4351,14}, { 2303,13}, { 4607,14}, \
+ { 2431,13}, { 4863,15}, { 1279,14}, { 2815,13}, \
+ { 5631,14}, { 2943,13}, { 5887,15}, { 1535,14}, \
+ { 3327,15}, { 1791,14}, { 3839,13}, { 7679,16}, \
+ { 1023,15}, { 2047,14}, { 4351,15}, { 2303,14}, \
+ { 4863,15}, { 2815,14}, { 5887,16}, { 1535,15}, \
+ { 3071,14}, { 6143,15}, { 32768,16}, { 65536,17}, \
{ 131072,18}, { 262144,19}, { 524288,20}, {1048576,21}, \
{2097152,22}, {4194304,23}, {8388608,24} }
-#define SQR_FFT_TABLE3_SIZE 99
+#define SQR_FFT_TABLE3_SIZE 235
#define SQR_FFT_THRESHOLD 2368
#define MULLO_BASECASE_THRESHOLD 0 /* always */
-#define MULLO_DC_THRESHOLD 49
-#define MULLO_MUL_N_THRESHOLD 6253
+#define MULLO_DC_THRESHOLD 45
+#define MULLO_MUL_N_THRESHOLD 5397
#define SQRLO_BASECASE_THRESHOLD 6
-#define SQRLO_DC_THRESHOLD 57
+#define SQRLO_DC_THRESHOLD 46
#define SQRLO_SQR_THRESHOLD 4658
-#define DC_DIV_QR_THRESHOLD 40
+#define DC_DIV_QR_THRESHOLD 36
#define DC_DIVAPPR_Q_THRESHOLD 95
-#define DC_BDIV_QR_THRESHOLD 43
-#define DC_BDIV_Q_THRESHOLD 60
+#define DC_BDIV_QR_THRESHOLD 35
+#define DC_BDIV_Q_THRESHOLD 47
#define INV_MULMOD_BNM1_THRESHOLD 22
-#define INV_NEWTON_THRESHOLD 179
-#define INV_APPR_THRESHOLD 118
+#define INV_NEWTON_THRESHOLD 178
+#define INV_APPR_THRESHOLD 116
-#define BINV_NEWTON_THRESHOLD 199
+#define BINV_NEWTON_THRESHOLD 206
#define REDC_1_TO_REDC_2_THRESHOLD 24
-#define REDC_2_TO_REDC_N_THRESHOLD 55
+#define REDC_2_TO_REDC_N_THRESHOLD 50
#define MU_DIV_QR_THRESHOLD 979
#define MU_DIVAPPR_Q_THRESHOLD 979
#define MUPI_DIV_QR_THRESHOLD 97
-#define MU_BDIV_QR_THRESHOLD 807
-#define MU_BDIV_Q_THRESHOLD 979
+#define MU_BDIV_QR_THRESHOLD 762
+#define MU_BDIV_Q_THRESHOLD 942
-#define POWM_SEC_TABLE 7,34,122,531,1486
+#define POWM_SEC_TABLE 7,34,114,523,1486
-#define GET_STR_DC_THRESHOLD 15
-#define GET_STR_PRECOMPUTE_THRESHOLD 30
-#define SET_STR_DC_THRESHOLD 1035
-#define SET_STR_PRECOMPUTE_THRESHOLD 1618
+#define GET_STR_DC_THRESHOLD 13
+#define GET_STR_PRECOMPUTE_THRESHOLD 25
+#define SET_STR_DC_THRESHOLD 381
+#define SET_STR_PRECOMPUTE_THRESHOLD 1659
-#define FAC_DSC_THRESHOLD 978
+#define FAC_DSC_THRESHOLD 969
#define FAC_ODD_THRESHOLD 0 /* always */
-#define MATRIX22_STRASSEN_THRESHOLD 27
-#define HGCD2_DIV1_METHOD 3 /* 2.00% faster than 5 */
-#define HGCD_THRESHOLD 91
-#define HGCD_APPR_THRESHOLD 107
-#define HGCD_REDUCE_THRESHOLD 1679
-#define GCD_DC_THRESHOLD 229
+#define MATRIX22_STRASSEN_THRESHOLD 29
+#define HGCD2_DIV1_METHOD 3 /* 2.03% faster than 5 */
+#define HGCD_THRESHOLD 92
+#define HGCD_APPR_THRESHOLD 95
+#define HGCD_REDUCE_THRESHOLD 1815
+#define GCD_DC_THRESHOLD 195
#define GCDEXT_DC_THRESHOLD 233
-#define JACOBI_BASE_METHOD 4 /* 17.83% faster than 1 */
+#define JACOBI_BASE_METHOD 4 /* 17.06% faster than 1 */
+
+/* Tuneup completed successfully, took 297016 seconds */