diff options
author | Torbjorn Granlund <tg@gmplib.org> | 2019-10-02 21:06:48 +0200 |
---|---|---|
committer | Torbjorn Granlund <tg@gmplib.org> | 2019-10-02 21:06:48 +0200 |
commit | a52b2338c910ffe6027b7ecbe953ff60bcdcc56a (patch) | |
tree | bac4b207d8a9bf3de69c16bbce76b3c47e8eb993 /mpn/powerpc64 | |
parent | 3469ff8feea233875097a5de0b2a342347b08066 (diff) | |
download | gmp-a52b2338c910ffe6027b7ecbe953ff60bcdcc56a.tar.gz |
New tuneup files.
Diffstat (limited to 'mpn/powerpc64')
-rw-r--r-- | mpn/powerpc64/mode64/p7/gmp-mparam.h | 163 | ||||
-rw-r--r-- | mpn/powerpc64/mode64/p8/gmp-mparam.h | 157 | ||||
-rw-r--r-- | mpn/powerpc64/mode64/p9/gmp-mparam.h | 172 |
3 files changed, 249 insertions, 243 deletions
diff --git a/mpn/powerpc64/mode64/p7/gmp-mparam.h b/mpn/powerpc64/mode64/p7/gmp-mparam.h index a0a85bfe4..5fa62cfb1 100644 --- a/mpn/powerpc64/mode64/p7/gmp-mparam.h +++ b/mpn/powerpc64/mode64/p7/gmp-mparam.h @@ -1,6 +1,6 @@ /* POWER7 gmp-mparam.h -- Compiler/machine parameter header file. -Copyright 2017 Free Software Foundation, Inc. +Copyright 2019 Free Software Foundation, Inc. This file is part of the GNU MP Library. @@ -31,83 +31,84 @@ see https://www.gnu.org/licenses/. */ #define GMP_LIMB_BITS 64 #define GMP_LIMB_BYTES 8 -/* 3425 MHz POWER8/SMT4 (gcc112.fsffrance.org) */ +/* 3720 MHz POWER7/SMT4 */ /* FFT tuning limit = 0.5 M */ -/* Generated by tuneup.c, 2017-02-20, gcc 4.8 */ +/* Generated by tuneup.c, 2019-10-02, gcc 4.8 */ #define MOD_1_NORM_THRESHOLD 0 /* always */ #define MOD_1_UNNORM_THRESHOLD 0 /* always */ -#define MOD_1N_TO_MOD_1_1_THRESHOLD 5 -#define MOD_1U_TO_MOD_1_1_THRESHOLD 5 -#define MOD_1_1_TO_MOD_1_2_THRESHOLD 7 +#define MOD_1N_TO_MOD_1_1_THRESHOLD 6 +#define MOD_1U_TO_MOD_1_1_THRESHOLD 4 +#define MOD_1_1_TO_MOD_1_2_THRESHOLD 8 #define MOD_1_2_TO_MOD_1_4_THRESHOLD 16 -#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 12 +#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 13 #define USE_PREINV_DIVREM_1 0 -#define DIV_QR_1N_PI1_METHOD 1 +#define DIV_QR_1N_PI1_METHOD 1 /* 3.47% faster than 2 */ #define DIV_QR_1_NORM_THRESHOLD 1 #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 22 +#define BMOD_1_TO_MOD_1_THRESHOLD 27 -#define DIV_1_VS_MUL_1_PERCENT 346 +#define DIV_1_VS_MUL_1_PERCENT 341 -#define MUL_TOOM22_THRESHOLD 24 +#define MUL_TOOM22_THRESHOLD 22 #define MUL_TOOM33_THRESHOLD 71 #define MUL_TOOM44_THRESHOLD 196 #define MUL_TOOM6H_THRESHOLD 298 #define MUL_TOOM8H_THRESHOLD 406 -#define MUL_TOOM32_TO_TOOM43_THRESHOLD 69 -#define MUL_TOOM32_TO_TOOM53_THRESHOLD 131 -#define MUL_TOOM42_TO_TOOM53_THRESHOLD 64 -#define MUL_TOOM42_TO_TOOM63_THRESHOLD 137 -#define MUL_TOOM43_TO_TOOM54_THRESHOLD 112 +#define MUL_TOOM32_TO_TOOM43_THRESHOLD 81 +#define MUL_TOOM32_TO_TOOM53_THRESHOLD 140 +#define MUL_TOOM42_TO_TOOM53_THRESHOLD 132 +#define MUL_TOOM42_TO_TOOM63_THRESHOLD 139 +#define MUL_TOOM43_TO_TOOM54_THRESHOLD 120 #define SQR_BASECASE_THRESHOLD 0 /* always (native) */ -#define SQR_TOOM2_THRESHOLD 38 +#define SQR_TOOM2_THRESHOLD 32 #define SQR_TOOM3_THRESHOLD 105 -#define SQR_TOOM4_THRESHOLD 191 -#define SQR_TOOM6_THRESHOLD 286 -#define SQR_TOOM8_THRESHOLD 406 +#define SQR_TOOM4_THRESHOLD 190 +#define SQR_TOOM6_THRESHOLD 318 +#define SQR_TOOM8_THRESHOLD 547 -#define MULMID_TOOM42_THRESHOLD 50 +#define MULMID_TOOM42_THRESHOLD 56 -#define MULMOD_BNM1_THRESHOLD 16 +#define MULMOD_BNM1_THRESHOLD 18 #define SQRMOD_BNM1_THRESHOLD 20 -#define MUL_FFT_MODF_THRESHOLD 468 /* k = 5 */ +#define MUL_FFT_MODF_THRESHOLD 436 /* k = 5 */ #define MUL_FFT_TABLE3 \ - { { 468, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \ - { 21, 7}, { 11, 6}, { 23, 7}, { 12, 6}, \ - { 25, 7}, { 15, 6}, { 31, 7}, { 21, 8}, \ + { { 436, 5}, { 21, 6}, { 21, 7}, { 11, 6}, \ + { 23, 7}, { 12, 6}, { 25, 7}, { 21, 8}, \ { 11, 7}, { 25, 8}, { 13, 7}, { 28, 8}, \ - { 15, 7}, { 32, 8}, { 17, 7}, { 35, 8}, \ - { 19, 7}, { 39, 8}, { 21, 9}, { 11, 7}, \ - { 45, 8}, { 29, 9}, { 15, 8}, { 35, 9}, \ - { 19, 8}, { 41, 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}, \ - { 79,11}, { 47,10}, { 95,12}, { 31,11}, \ - { 63,10}, { 135,11}, { 79,10}, { 167,11}, \ - { 95,10}, { 191,11}, { 111,12}, { 63,11}, \ - { 127,10}, { 255, 9}, { 511,11}, { 143,10}, \ - { 287, 9}, { 575,11}, { 159,12}, { 95,11}, \ - { 191,10}, { 383,13}, { 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 81 + { 15, 7}, { 33, 8}, { 17, 7}, { 35, 8}, \ + { 19, 7}, { 39, 8}, { 21, 9}, { 11, 8}, \ + { 29, 9}, { 15, 8}, { 35, 9}, { 19, 8}, \ + { 41, 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}, { 79,11}, { 47,10}, { 103,12}, \ + { 31,11}, { 63,10}, { 135,11}, { 79,10}, \ + { 159,11}, { 95,10}, { 191, 9}, { 383,11}, \ + { 111,12}, { 63,11}, { 127,10}, { 255, 9}, \ + { 511,11}, { 143,10}, { 287, 9}, { 575,11}, \ + { 159,10}, { 319,12}, { 95,11}, { 191,10}, \ + { 383, 9}, { 767,11}, { 207,10}, { 415,13}, \ + { 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 83 #define MUL_FFT_THRESHOLD 4736 -#define SQR_FFT_MODF_THRESHOLD 380 /* k = 5 */ +#define SQR_FFT_MODF_THRESHOLD 368 /* k = 5 */ #define SQR_FFT_TABLE3 \ - { { 380, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \ + { { 368, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \ { 21, 7}, { 11, 6}, { 23, 7}, { 12, 6}, \ - { 25, 7}, { 25, 8}, { 13, 7}, { 28, 8}, \ - { 15, 7}, { 32, 8}, { 17, 7}, { 35, 8}, \ + { 25, 7}, { 13, 6}, { 27, 7}, { 25, 8}, \ + { 13, 7}, { 28, 8}, { 15, 7}, { 32, 8}, \ + { 17, 7}, { 35, 8}, { 19, 7}, { 39, 8}, \ { 21, 9}, { 11, 8}, { 29, 9}, { 15, 8}, \ { 35, 9}, { 19, 8}, { 41, 9}, { 23, 8}, \ { 47, 9}, { 27,10}, { 15, 9}, { 31, 8}, \ @@ -116,56 +117,58 @@ see https://www.gnu.org/licenses/. */ { 79,10}, { 47, 9}, { 95,10}, { 55,11}, \ { 31,10}, { 79,11}, { 47,10}, { 95,12}, \ { 31,11}, { 63,10}, { 135,11}, { 79,10}, \ - { 159, 9}, { 319,11}, { 95,10}, { 191,12}, \ - { 63,11}, { 127,10}, { 255, 9}, { 511,11}, \ - { 143,10}, { 287, 9}, { 575,10}, { 303,11}, \ - { 159,10}, { 319,12}, { 95,11}, { 191,10}, \ - { 383,13}, { 8192,14}, { 16384,15}, { 32768,16}, \ + { 159, 9}, { 319,11}, { 95,10}, { 191, 9}, \ + { 383,11}, { 111,12}, { 63,11}, { 127,10}, \ + { 255, 9}, { 511,11}, { 143,10}, { 287, 9}, \ + { 575,10}, { 303,11}, { 159,10}, { 319, 9}, \ + { 639,12}, { 95,11}, { 191,10}, { 383, 9}, \ + { 767,13}, { 8192,14}, { 16384,15}, { 32768,16}, \ { 65536,17}, { 131072,18}, { 262144,19}, { 524288,20}, \ {1048576,21}, {2097152,22}, {4194304,23}, {8388608,24} } -#define SQR_FFT_TABLE3_SIZE 76 +#define SQR_FFT_TABLE3_SIZE 84 #define SQR_FFT_THRESHOLD 3264 #define MULLO_BASECASE_THRESHOLD 3 -#define MULLO_DC_THRESHOLD 28 +#define MULLO_DC_THRESHOLD 35 #define MULLO_MUL_N_THRESHOLD 9449 #define SQRLO_BASECASE_THRESHOLD 3 -#define SQRLO_DC_THRESHOLD 124 -#define SQRLO_SQR_THRESHOLD 6481 +#define SQRLO_DC_THRESHOLD 119 +#define SQRLO_SQR_THRESHOLD 6440 #define DC_DIV_QR_THRESHOLD 33 #define DC_DIVAPPR_Q_THRESHOLD 124 -#define DC_BDIV_QR_THRESHOLD 63 +#define DC_BDIV_QR_THRESHOLD 62 #define DC_BDIV_Q_THRESHOLD 144 -#define INV_MULMOD_BNM1_THRESHOLD 69 -#define INV_NEWTON_THRESHOLD 131 -#define INV_APPR_THRESHOLD 125 +#define INV_MULMOD_BNM1_THRESHOLD 67 +#define INV_NEWTON_THRESHOLD 123 +#define INV_APPR_THRESHOLD 123 -#define BINV_NEWTON_THRESHOLD 280 -#define REDC_1_TO_REDC_2_THRESHOLD 16 -#define REDC_2_TO_REDC_N_THRESHOLD 108 +#define BINV_NEWTON_THRESHOLD 284 +#define REDC_1_TO_REDC_2_THRESHOLD 18 +#define REDC_2_TO_REDC_N_THRESHOLD 109 -#define MU_DIV_QR_THRESHOLD 1334 +#define MU_DIV_QR_THRESHOLD 1387 #define MU_DIVAPPR_Q_THRESHOLD 1334 -#define MUPI_DIV_QR_THRESHOLD 54 +#define MUPI_DIV_QR_THRESHOLD 50 #define MU_BDIV_QR_THRESHOLD 1308 -#define MU_BDIV_Q_THRESHOLD 1470 +#define MU_BDIV_Q_THRESHOLD 1499 -#define POWM_SEC_TABLE 1,16,194,712,1357 +#define POWM_SEC_TABLE 1,23,121,579,642 -#define GET_STR_DC_THRESHOLD 10 -#define GET_STR_PRECOMPUTE_THRESHOLD 20 -#define SET_STR_DC_THRESHOLD 1193 -#define SET_STR_PRECOMPUTE_THRESHOLD 3048 +#define GET_STR_DC_THRESHOLD 11 +#define GET_STR_PRECOMPUTE_THRESHOLD 18 +#define SET_STR_DC_THRESHOLD 1562 +#define SET_STR_PRECOMPUTE_THRESHOLD 3100 -#define FAC_DSC_THRESHOLD 680 -#define FAC_ODD_THRESHOLD 26 +#define FAC_DSC_THRESHOLD 774 +#define FAC_ODD_THRESHOLD 25 -#define MATRIX22_STRASSEN_THRESHOLD 16 -#define HGCD_THRESHOLD 128 -#define HGCD_APPR_THRESHOLD 159 +#define MATRIX22_STRASSEN_THRESHOLD 18 +#define HGCD2_DIV1_METHOD 5 /* 3.27% faster than 3 */ +#define HGCD_THRESHOLD 118 +#define HGCD_APPR_THRESHOLD 150 #define HGCD_REDUCE_THRESHOLD 3014 -#define GCD_DC_THRESHOLD 416 -#define GCDEXT_DC_THRESHOLD 379 -#define JACOBI_BASE_METHOD 4 +#define GCD_DC_THRESHOLD 386 +#define GCDEXT_DC_THRESHOLD 365 +#define JACOBI_BASE_METHOD 4 /* 27.64% faster than 1 */ diff --git a/mpn/powerpc64/mode64/p8/gmp-mparam.h b/mpn/powerpc64/mode64/p8/gmp-mparam.h index b1a5c6dfd..ed4db28a9 100644 --- a/mpn/powerpc64/mode64/p8/gmp-mparam.h +++ b/mpn/powerpc64/mode64/p8/gmp-mparam.h @@ -31,139 +31,140 @@ see https://www.gnu.org/licenses/. */ #define GMP_LIMB_BITS 64 #define GMP_LIMB_BYTES 8 -/* 3425 MHz POWER8/SMT4 (gcc112.fsffrance.org) */ +/* 4150 MHz POWER8/SMT4 */ /* FFT tuning limit = 0.5 M */ -/* Generated by tuneup.c, 2017-02-23, gcc 4.9 */ +/* Generated by tuneup.c, 2019-09-24, gcc 7.2 */ #define MOD_1_NORM_THRESHOLD 0 /* always */ #define MOD_1_UNNORM_THRESHOLD 0 /* always */ #define MOD_1N_TO_MOD_1_1_THRESHOLD 7 #define MOD_1U_TO_MOD_1_1_THRESHOLD 6 #define MOD_1_1_TO_MOD_1_2_THRESHOLD 11 -#define MOD_1_2_TO_MOD_1_4_THRESHOLD 32 +#define MOD_1_2_TO_MOD_1_4_THRESHOLD 22 #define PREINV_MOD_1_TO_MOD_1_THRESHOLD 10 #define USE_PREINV_DIVREM_1 0 -#define DIV_QR_1N_PI1_METHOD 1 +#define DIV_QR_1N_PI1_METHOD 2 /* 16.97% faster than 1 */ #define DIV_QR_1_NORM_THRESHOLD 2 #define DIV_QR_1_UNNORM_THRESHOLD 1 -#define DIV_QR_2_PI2_THRESHOLD MP_SIZE_T_MAX /* never */ +#define DIV_QR_2_PI2_THRESHOLD 9 #define DIVEXACT_1_THRESHOLD 0 /* always (native) */ -#define BMOD_1_TO_MOD_1_THRESHOLD 30 +#define BMOD_1_TO_MOD_1_THRESHOLD 34 -#define DIV_1_VS_MUL_1_PERCENT 285 +#define DIV_1_VS_MUL_1_PERCENT 276 #define MUL_TOOM22_THRESHOLD 18 -#define MUL_TOOM33_THRESHOLD 72 -#define MUL_TOOM44_THRESHOLD 196 +#define MUL_TOOM33_THRESHOLD 73 +#define MUL_TOOM44_THRESHOLD 195 #define MUL_TOOM6H_THRESHOLD 278 #define MUL_TOOM8H_THRESHOLD 406 #define MUL_TOOM32_TO_TOOM43_THRESHOLD 73 #define MUL_TOOM32_TO_TOOM53_THRESHOLD 131 -#define MUL_TOOM42_TO_TOOM53_THRESHOLD 125 -#define MUL_TOOM42_TO_TOOM63_THRESHOLD 74 +#define MUL_TOOM42_TO_TOOM53_THRESHOLD 121 +#define MUL_TOOM42_TO_TOOM63_THRESHOLD 138 #define MUL_TOOM43_TO_TOOM54_THRESHOLD 106 #define SQR_BASECASE_THRESHOLD 0 /* always (native) */ #define SQR_TOOM2_THRESHOLD 32 -#define SQR_TOOM3_THRESHOLD 101 +#define SQR_TOOM3_THRESHOLD 97 #define SQR_TOOM4_THRESHOLD 178 -#define SQR_TOOM6_THRESHOLD 270 -#define SQR_TOOM8_THRESHOLD 357 +#define SQR_TOOM6_THRESHOLD 303 +#define SQR_TOOM8_THRESHOLD 454 #define MULMID_TOOM42_THRESHOLD 42 -#define MULMOD_BNM1_THRESHOLD 16 +#define MULMOD_BNM1_THRESHOLD 15 #define SQRMOD_BNM1_THRESHOLD 19 -#define MUL_FFT_MODF_THRESHOLD 432 /* k = 5 */ +#define MUL_FFT_MODF_THRESHOLD 404 /* k = 5 */ #define MUL_FFT_TABLE3 \ - { { 432, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \ + { { 404, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \ { 21, 7}, { 11, 6}, { 23, 7}, { 12, 6}, \ { 25, 7}, { 21, 8}, { 11, 7}, { 25, 8}, \ - { 13, 7}, { 27, 8}, { 15, 7}, { 32, 8}, \ + { 13, 7}, { 27, 8}, { 15, 7}, { 31, 8}, \ { 17, 7}, { 35, 8}, { 19, 7}, { 39, 8}, \ { 21, 9}, { 11, 8}, { 27, 9}, { 15, 8}, \ { 35, 9}, { 19, 8}, { 41, 9}, { 23, 8}, \ - { 49, 9}, { 27,10}, { 15, 9}, { 39,10}, \ + { 47, 9}, { 27,10}, { 15, 9}, { 39,10}, \ { 23, 9}, { 51,11}, { 15,10}, { 31, 9}, \ - { 67,10}, { 39, 9}, { 79,10}, { 47, 9}, \ - { 95,11}, { 31,10}, { 79,11}, { 47,10}, \ - { 95,12}, { 31,11}, { 63,10}, { 135,11}, \ - { 79,10}, { 159,11}, { 95,10}, { 191,11}, \ - { 111,12}, { 63,11}, { 127,10}, { 255, 9}, \ - { 511,11}, { 143,10}, { 287, 9}, { 575,11}, \ - { 159,12}, { 95,11}, { 191,10}, { 383,13}, \ - { 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 75 + { 63,10}, { 39, 9}, { 79,10}, { 47, 9}, \ + { 95,11}, { 31,10}, { 63, 9}, { 131,10}, \ + { 79,11}, { 47,10}, { 95,12}, { 31,11}, \ + { 63,10}, { 127, 9}, { 255,10}, { 135,11}, \ + { 79,10}, { 159,11}, { 95, 8}, { 767, 7}, \ + { 1599,11}, { 111,12}, { 63,11}, { 127,10}, \ + { 255, 9}, { 511,11}, { 143,10}, { 287, 9}, \ + { 575,11}, { 159,12}, { 95,11}, { 191,10}, \ + { 383,13}, { 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 80 #define MUL_FFT_THRESHOLD 4736 -#define SQR_FFT_MODF_THRESHOLD 368 /* k = 5 */ +#define SQR_FFT_MODF_THRESHOLD 340 /* k = 5 */ #define SQR_FFT_TABLE3 \ - { { 368, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \ - { 21, 7}, { 11, 6}, { 23, 7}, { 12, 6}, \ - { 25, 7}, { 21, 8}, { 11, 7}, { 25, 8}, \ - { 13, 7}, { 27, 8}, { 15, 7}, { 31, 8}, \ - { 21, 9}, { 11, 8}, { 27, 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}, { 39, 9}, { 79,10}, { 47, 9}, \ - { 95,11}, { 31,10}, { 79,11}, { 47,10}, \ - { 95,12}, { 31,11}, { 63,10}, { 127, 9}, \ - { 255,11}, { 79,10}, { 159, 9}, { 319,11}, \ + { { 340, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \ + { 21, 7}, { 11, 6}, { 23, 7}, { 21, 8}, \ + { 11, 7}, { 25, 8}, { 13, 7}, { 27, 8}, \ + { 15, 7}, { 31, 8}, { 21, 9}, { 11, 8}, \ + { 27, 9}, { 15, 8}, { 33, 9}, { 19, 8}, \ + { 41, 9}, { 23, 8}, { 47, 9}, { 27,10}, \ + { 15, 9}, { 39,10}, { 23, 9}, { 47,11}, \ + { 15,10}, { 31, 9}, { 67,10}, { 39, 9}, \ + { 79,10}, { 47,11}, { 31,10}, { 79,11}, \ + { 47,10}, { 95,12}, { 31,11}, { 63,10}, \ + { 127, 9}, { 255,11}, { 79, 9}, { 319,11}, \ { 95,10}, { 191,12}, { 63,11}, { 127,10}, \ { 255, 9}, { 511,10}, { 271,11}, { 143,10}, \ - { 287, 9}, { 575,10}, { 303, 9}, { 607,11}, \ - { 159,10}, { 319,12}, { 95,11}, { 191,10}, \ - { 383,13}, { 8192,14}, { 16384,15}, { 32768,16}, \ - { 65536,17}, { 131072,18}, { 262144,19}, { 524288,20}, \ - {1048576,21}, {2097152,22}, {4194304,23}, {8388608,24} } -#define SQR_FFT_TABLE3_SIZE 76 + { 287, 9}, { 575,10}, { 303, 9}, { 607,10}, \ + { 319,12}, { 95,11}, { 191,10}, { 383,13}, \ + { 8192,14}, { 16384,15}, { 32768,16}, { 65536,17}, \ + { 131072,18}, { 262144,19}, { 524288,20}, {1048576,21}, \ + {2097152,22}, {4194304,23}, {8388608,24} } +#define SQR_FFT_TABLE3_SIZE 71 #define SQR_FFT_THRESHOLD 3264 #define MULLO_BASECASE_THRESHOLD 3 #define MULLO_DC_THRESHOLD 33 -#define MULLO_MUL_N_THRESHOLD 9449 -#define SQRLO_BASECASE_THRESHOLD 3 -#define SQRLO_DC_THRESHOLD 115 -#define SQRLO_SQR_THRESHOLD 6481 +#define MULLO_MUL_N_THRESHOLD 9174 +#define SQRLO_BASECASE_THRESHOLD 0 /* always */ +#define SQRLO_DC_THRESHOLD 114 +#define SQRLO_SQR_THRESHOLD 6461 -#define DC_DIV_QR_THRESHOLD 32 -#define DC_DIVAPPR_Q_THRESHOLD 156 -#define DC_BDIV_QR_THRESHOLD 46 -#define DC_BDIV_Q_THRESHOLD 96 +#define DC_DIV_QR_THRESHOLD 38 +#define DC_DIVAPPR_Q_THRESHOLD 158 +#define DC_BDIV_QR_THRESHOLD 48 +#define DC_BDIV_Q_THRESHOLD 112 -#define INV_MULMOD_BNM1_THRESHOLD 36 -#define INV_NEWTON_THRESHOLD 141 -#define INV_APPR_THRESHOLD 140 +#define INV_MULMOD_BNM1_THRESHOLD 74 +#define INV_NEWTON_THRESHOLD 132 +#define INV_APPR_THRESHOLD 131 #define BINV_NEWTON_THRESHOLD 278 -#define REDC_1_TO_REDC_2_THRESHOLD 59 +#define REDC_1_TO_REDC_2_THRESHOLD 56 #define REDC_2_TO_REDC_N_THRESHOLD 0 /* always */ -#define MU_DIV_QR_THRESHOLD 1187 -#define MU_DIVAPPR_Q_THRESHOLD 1187 -#define MUPI_DIV_QR_THRESHOLD 47 -#define MU_BDIV_QR_THRESHOLD 1187 +#define MU_DIV_QR_THRESHOLD 1142 +#define MU_DIVAPPR_Q_THRESHOLD 1142 +#define MUPI_DIV_QR_THRESHOLD 46 +#define MU_BDIV_QR_THRESHOLD 1142 #define MU_BDIV_Q_THRESHOLD 1470 -#define POWM_SEC_TABLE 1,26,194,712,2144 +#define POWM_SEC_TABLE 3,19,117,672,1867 -#define GET_STR_DC_THRESHOLD 8 -#define GET_STR_PRECOMPUTE_THRESHOLD 17 -#define SET_STR_DC_THRESHOLD 426 -#define SET_STR_PRECOMPUTE_THRESHOLD 2503 +#define GET_STR_DC_THRESHOLD 11 +#define GET_STR_PRECOMPUTE_THRESHOLD 18 +#define SET_STR_DC_THRESHOLD 608 +#define SET_STR_PRECOMPUTE_THRESHOLD 2405 -#define FAC_DSC_THRESHOLD 228 -#define FAC_ODD_THRESHOLD 25 +#define FAC_DSC_THRESHOLD 164 +#define FAC_ODD_THRESHOLD 0 /* always */ #define MATRIX22_STRASSEN_THRESHOLD 14 -#define HGCD_THRESHOLD 106 -#define HGCD_APPR_THRESHOLD 167 -#define HGCD_REDUCE_THRESHOLD 2681 -#define GCD_DC_THRESHOLD 393 -#define GCDEXT_DC_THRESHOLD 379 -#define JACOBI_BASE_METHOD 4 +#define HGCD2_DIV1_METHOD 1 /* 6.88% faster than 3 */ +#define HGCD_THRESHOLD 114 +#define HGCD_APPR_THRESHOLD 118 +#define HGCD_REDUCE_THRESHOLD 2205 +#define GCD_DC_THRESHOLD 440 +#define GCDEXT_DC_THRESHOLD 345 +#define JACOBI_BASE_METHOD 1 /* 0.74% faster than 4 */ diff --git a/mpn/powerpc64/mode64/p9/gmp-mparam.h b/mpn/powerpc64/mode64/p9/gmp-mparam.h index f66099ca6..d11001fb5 100644 --- a/mpn/powerpc64/mode64/p9/gmp-mparam.h +++ b/mpn/powerpc64/mode64/p9/gmp-mparam.h @@ -1,6 +1,6 @@ /* POWER9 gmp-mparam.h -- Compiler/machine parameter header file. -Copyright 2018 Free Software Foundation, Inc. +Copyright 2019 Free Software Foundation, Inc. This file is part of the GNU MP Library. @@ -32,8 +32,8 @@ see https://www.gnu.org/licenses/. */ #define GMP_LIMB_BYTES 8 /* 3700MHz POWER9 */ - -/* Generated by tuneup.c, 2018-11-30, gcc 4.8 */ +/* FFT tuning limit = 0.5 M */ +/* Generated by tuneup.c, 2019-09-30, gcc 4.8 */ #define MOD_1_NORM_THRESHOLD 0 /* always */ #define MOD_1_UNNORM_THRESHOLD 0 /* always */ @@ -43,124 +43,126 @@ see https://www.gnu.org/licenses/. */ #define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */ #define PREINV_MOD_1_TO_MOD_1_THRESHOLD 12 #define USE_PREINV_DIVREM_1 0 -#define DIV_QR_1N_PI1_METHOD 2 +#define DIV_QR_1N_PI1_METHOD 2 /* 4.04% faster than 1 */ #define DIV_QR_1_NORM_THRESHOLD 3 #define DIV_QR_1_UNNORM_THRESHOLD 2 -#define DIV_QR_2_PI2_THRESHOLD 13 +#define DIV_QR_2_PI2_THRESHOLD 10 #define DIVEXACT_1_THRESHOLD 0 /* always (native) */ -#define BMOD_1_TO_MOD_1_THRESHOLD 21 +#define BMOD_1_TO_MOD_1_THRESHOLD 22 -#define DIV_1_VS_MUL_1_PERCENT 359 +#define DIV_1_VS_MUL_1_PERCENT 357 #define MUL_TOOM22_THRESHOLD 34 -#define MUL_TOOM33_THRESHOLD 105 -#define MUL_TOOM44_THRESHOLD 450 -#define MUL_TOOM6H_THRESHOLD 517 +#define MUL_TOOM33_THRESHOLD 108 +#define MUL_TOOM44_THRESHOLD 458 +#define MUL_TOOM6H_THRESHOLD 0 /* always */ #define MUL_TOOM8H_THRESHOLD 608 -#define MUL_TOOM32_TO_TOOM43_THRESHOLD 114 -#define MUL_TOOM32_TO_TOOM53_THRESHOLD 279 -#define MUL_TOOM42_TO_TOOM53_THRESHOLD 204 +#define MUL_TOOM32_TO_TOOM43_THRESHOLD 113 +#define MUL_TOOM32_TO_TOOM53_THRESHOLD 297 +#define MUL_TOOM42_TO_TOOM53_THRESHOLD 193 #define MUL_TOOM42_TO_TOOM63_THRESHOLD 211 -#define MUL_TOOM43_TO_TOOM54_THRESHOLD 185 +#define MUL_TOOM43_TO_TOOM54_THRESHOLD 178 #define SQR_BASECASE_THRESHOLD 0 /* always (native) */ #define SQR_TOOM2_THRESHOLD 46 -#define SQR_TOOM3_THRESHOLD 158 -#define SQR_TOOM4_THRESHOLD 686 +#define SQR_TOOM3_THRESHOLD 157 +#define SQR_TOOM4_THRESHOLD 674 #define SQR_TOOM6_THRESHOLD 0 /* always */ #define SQR_TOOM8_THRESHOLD 866 #define MULMID_TOOM42_THRESHOLD 66 -#define MULMOD_BNM1_THRESHOLD 19 -#define SQRMOD_BNM1_THRESHOLD 26 +#define MULMOD_BNM1_THRESHOLD 20 +#define SQRMOD_BNM1_THRESHOLD 25 -#define MUL_FFT_MODF_THRESHOLD 530 /* k = 5 */ +#define MUL_FFT_MODF_THRESHOLD 436 /* k = 5 */ #define MUL_FFT_TABLE3 \ - { { 530, 5}, { 25, 6}, { 13, 5}, { 27, 6}, \ - { 27, 7}, { 14, 6}, { 29, 7}, { 15, 6}, \ - { 31, 7}, { 25, 8}, { 13, 7}, { 28, 8}, \ - { 15, 7}, { 32, 8}, { 17, 7}, { 36, 8}, \ - { 19, 7}, { 39, 8}, { 27, 9}, { 15, 8}, \ - { 35, 9}, { 19, 8}, { 41, 9}, { 23, 8}, \ - { 49, 9}, { 27,10}, { 15, 9}, { 31, 8}, \ - { 63, 9}, { 39,10}, { 23, 9}, { 51,11}, \ - { 15,10}, { 31, 9}, { 67,10}, { 39, 9}, \ - { 79,10}, { 47, 9}, { 95,10}, { 55,11}, \ - { 31,10}, { 79,11}, { 47,10}, { 95,12}, \ - { 31,11}, { 63,10}, { 135,11}, { 79,10}, \ - { 159,11}, { 95,10}, { 191,12}, { 63,11}, \ - { 143,10}, { 287,11}, { 159,12}, { 95,11}, \ - { 191,13}, { 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 68 -#define MUL_FFT_THRESHOLD 5248 - -#define SQR_FFT_MODF_THRESHOLD 496 /* k = 5 */ -#define SQR_FFT_TABLE3 \ - { { 496, 5}, { 23, 6}, { 12, 5}, { 25, 6}, \ - { 13, 5}, { 27, 6}, { 29, 7}, { 15, 6}, \ - { 31, 7}, { 16, 6}, { 33, 7}, { 28, 8}, \ - { 15, 7}, { 32, 8}, { 17, 7}, { 36, 8}, \ - { 19, 7}, { 39, 8}, { 29, 9}, { 15, 8}, \ - { 35, 9}, { 19, 8}, { 41, 9}, { 23, 8}, \ + { { 436, 5}, { 25, 6}, { 13, 5}, { 27, 6}, \ + { 27, 7}, { 15, 6}, { 31, 7}, { 25, 8}, \ + { 13, 7}, { 28, 8}, { 15, 7}, { 32, 8}, \ + { 17, 7}, { 35, 8}, { 27, 9}, { 15, 8}, \ + { 35, 9}, { 19, 8}, { 39, 9}, { 23, 8}, \ { 47, 9}, { 27,10}, { 15, 9}, { 31, 8}, \ - { 63, 9}, { 39,10}, { 23, 9}, { 51,11}, \ - { 15,10}, { 31, 9}, { 67,10}, { 39, 9}, \ - { 79,10}, { 47, 9}, { 95,10}, { 55,11}, \ - { 31,10}, { 79,11}, { 47,10}, { 95,12}, \ - { 31,11}, { 63,10}, { 135,11}, { 79,10}, \ + { 63, 9}, { 35, 8}, { 71, 9}, { 39,10}, \ + { 23, 9}, { 51,11}, { 15,10}, { 31, 9}, \ + { 71,10}, { 39, 9}, { 83,10}, { 47, 9}, \ + { 95,10}, { 55,11}, { 31,10}, { 79,11}, \ + { 47,10}, { 95,12}, { 31,11}, { 63,10}, \ + { 135,11}, { 79,10}, { 159,11}, { 95,12}, \ + { 63,11}, { 127,10}, { 255, 9}, { 511,11}, \ + { 143,10}, { 287, 9}, { 575,10}, { 303,11}, \ + { 159,12}, { 95,11}, { 191,13}, { 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 70 +#define MUL_FFT_THRESHOLD 3712 + +#define SQR_FFT_MODF_THRESHOLD 436 /* k = 5 */ +#define SQR_FFT_TABLE3 \ + { { 436, 5}, { 25, 6}, { 13, 5}, { 27, 6}, \ + { 14, 5}, { 29, 6}, { 29, 7}, { 15, 6}, \ + { 33, 7}, { 17, 6}, { 35, 7}, { 25, 8}, \ + { 13, 7}, { 28, 8}, { 15, 7}, { 32, 8}, \ + { 17, 7}, { 35, 8}, { 27, 9}, { 15, 8}, \ + { 35, 9}, { 19, 8}, { 39, 9}, { 23, 8}, \ + { 47, 9}, { 27,10}, { 15, 9}, { 39,10}, \ + { 23, 9}, { 51,11}, { 15,10}, { 31, 9}, \ + { 71,10}, { 39, 9}, { 83,10}, { 47, 9}, \ + { 95,10}, { 55,11}, { 31,10}, { 79,11}, \ + { 47,10}, { 95,12}, { 31,11}, { 63,10}, \ + { 127, 9}, { 255,10}, { 135,11}, { 79,10}, \ { 159,11}, { 95,12}, { 63,11}, { 127,10}, \ - { 255,11}, { 143,10}, { 287,11}, { 159,12}, \ - { 95,11}, { 191,13}, { 8192,14}, { 16384,15}, \ - { 32768,16}, { 65536,17}, { 131072,18}, { 262144,19}, \ - { 524288,20}, {1048576,21}, {2097152,22}, {4194304,23}, \ - {8388608,24} } -#define SQR_FFT_TABLE3_SIZE 69 -#define SQR_FFT_THRESHOLD 4224 + { 255, 9}, { 511,10}, { 271,11}, { 143,10}, \ + { 287, 9}, { 575,10}, { 303,11}, { 159,12}, \ + { 95,13}, { 8192,14}, { 16384,15}, { 32768,16}, \ + { 65536,17}, { 131072,18}, { 262144,19}, { 524288,20}, \ + {1048576,21}, {2097152,22}, {4194304,23}, {8388608,24} } +#define SQR_FFT_TABLE3_SIZE 72 +#define SQR_FFT_THRESHOLD 3392 #define MULLO_BASECASE_THRESHOLD 3 -#define MULLO_DC_THRESHOLD 40 -#define MULLO_MUL_N_THRESHOLD 10323 +#define MULLO_DC_THRESHOLD 41 +#define MULLO_MUL_N_THRESHOLD 7246 #define SQRLO_BASECASE_THRESHOLD 6 -#define SQRLO_DC_THRESHOLD 40 -#define SQRLO_SQR_THRESHOLD 8397 +#define SQRLO_DC_THRESHOLD 41 +#define SQRLO_SQR_THRESHOLD 6633 -#define DC_DIV_QR_THRESHOLD 30 -#define DC_DIVAPPR_Q_THRESHOLD 91 +#define DC_DIV_QR_THRESHOLD 29 +#define DC_DIVAPPR_Q_THRESHOLD 88 #define DC_BDIV_QR_THRESHOLD 36 -#define DC_BDIV_Q_THRESHOLD 63 +#define DC_BDIV_Q_THRESHOLD 62 -#define INV_MULMOD_BNM1_THRESHOLD 78 -#define INV_NEWTON_THRESHOLD 11 +#define INV_MULMOD_BNM1_THRESHOLD 95 +#define INV_NEWTON_THRESHOLD 13 #define INV_APPR_THRESHOLD 13 -#define BINV_NEWTON_THRESHOLD 272 +#define BINV_NEWTON_THRESHOLD 270 #define REDC_1_TO_REDC_2_THRESHOLD 8 #define REDC_2_TO_REDC_N_THRESHOLD 79 -#define MU_DIV_QR_THRESHOLD 1589 -#define MU_DIVAPPR_Q_THRESHOLD 1589 +#define MU_DIV_QR_THRESHOLD 1470 +#define MU_DIVAPPR_Q_THRESHOLD 1528 #define MUPI_DIV_QR_THRESHOLD 0 /* always */ -#define MU_BDIV_QR_THRESHOLD 1652 -#define MU_BDIV_Q_THRESHOLD 2089 +#define MU_BDIV_QR_THRESHOLD 1470 +#define MU_BDIV_Q_THRESHOLD 1718 -#define POWM_SEC_TABLE 3,16,139,852 +#define POWM_SEC_TABLE 1,16,147,852 -#define GET_STR_DC_THRESHOLD 9 -#define GET_STR_PRECOMPUTE_THRESHOLD 17 +#define GET_STR_DC_THRESHOLD 7 +#define GET_STR_PRECOMPUTE_THRESHOLD 16 #define SET_STR_DC_THRESHOLD 406 -#define SET_STR_PRECOMPUTE_THRESHOLD 956 +#define SET_STR_PRECOMPUTE_THRESHOLD 938 -#define FAC_DSC_THRESHOLD 181 -#define FAC_ODD_THRESHOLD 44 +#define FAC_DSC_THRESHOLD 266 +#define FAC_ODD_THRESHOLD 26 -#define MATRIX22_STRASSEN_THRESHOLD 21 -#define HGCD_THRESHOLD 41 +#define MATRIX22_STRASSEN_THRESHOLD 22 +#define HGCD2_DIV1_METHOD 1 /* 8.31% faster than 3 */ +#define HGCD_THRESHOLD 46 #define HGCD_APPR_THRESHOLD 50 -#define HGCD_REDUCE_THRESHOLD 3389 -#define GCD_DC_THRESHOLD 379 -#define GCDEXT_DC_THRESHOLD 293 -#define JACOBI_BASE_METHOD 4 +#define HGCD_REDUCE_THRESHOLD 2681 +#define GCD_DC_THRESHOLD 333 +#define GCDEXT_DC_THRESHOLD 268 +#define JACOBI_BASE_METHOD 4 /* 23.09% faster than 1 */ |