From a89a14ef5da44684a16b204e7a70460cc8c4922a Mon Sep 17 00:00:00 2001 From: Thomas Voss Date: Fri, 21 Jun 2024 23:36:36 +0200 Subject: Basic constant folding implementation --- .../gmp-6.3.0/mpn/powerpc64/mode64/p8/gmp-mparam.h | 171 +++++++++++++++++++++ .../mpn/powerpc64/mode64/p8/invert_limb.asm | 53 +++++++ 2 files changed, 224 insertions(+) create mode 100644 vendor/gmp-6.3.0/mpn/powerpc64/mode64/p8/gmp-mparam.h create mode 100644 vendor/gmp-6.3.0/mpn/powerpc64/mode64/p8/invert_limb.asm (limited to 'vendor/gmp-6.3.0/mpn/powerpc64/mode64/p8') diff --git a/vendor/gmp-6.3.0/mpn/powerpc64/mode64/p8/gmp-mparam.h b/vendor/gmp-6.3.0/mpn/powerpc64/mode64/p8/gmp-mparam.h new file mode 100644 index 0000000..09348e0 --- /dev/null +++ b/vendor/gmp-6.3.0/mpn/powerpc64/mode64/p8/gmp-mparam.h @@ -0,0 +1,171 @@ +/* POWER8 gmp-mparam.h -- Compiler/machine parameter header file. + +Copyright 2017 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 64 +#define GMP_LIMB_BYTES 8 + +/* 4150 MHz POWER8/SMT4 */ +/* FFT tuning limit = 0.5 M */ +/* 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 22 +#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 10 +#define USE_PREINV_DIVREM_1 0 +/* From gcc112.osuosl.org, 2023-07-27 */ +#define DIV_QR_1N_PI1_METHOD 3 /* 13.00% faster than 4 */ +#define DIV_QR_1_NORM_THRESHOLD 2 +#define DIV_QR_1_UNNORM_THRESHOLD 1 +#define DIV_QR_2_PI2_THRESHOLD 9 +#define DIVEXACT_1_THRESHOLD 0 /* always (native) */ +#define BMOD_1_TO_MOD_1_THRESHOLD 34 + +#define DIV_1_VS_MUL_1_PERCENT 276 + +#define MUL_TOOM22_THRESHOLD 18 +#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 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 97 +#define SQR_TOOM4_THRESHOLD 178 +#define SQR_TOOM6_THRESHOLD 303 +#define SQR_TOOM8_THRESHOLD 454 + +#define MULMID_TOOM42_THRESHOLD 42 + +#define MULMOD_BNM1_THRESHOLD 15 +#define SQRMOD_BNM1_THRESHOLD 19 + +#define MUL_FFT_MODF_THRESHOLD 404 /* k = 5 */ +#define MUL_FFT_TABLE3 \ + { { 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}, { 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}, \ + { 47, 9}, { 27,10}, { 15, 9}, { 39,10}, \ + { 23, 9}, { 51,11}, { 15,10}, { 31, 9}, \ + { 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 340 /* k = 5 */ +#define SQR_FFT_TABLE3 \ + { { 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}, { 607,10}, \ + { 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 9174 +#define SQRLO_BASECASE_THRESHOLD 0 /* always */ +#define SQRLO_DC_THRESHOLD 114 +#define SQRLO_SQR_THRESHOLD 6461 + +#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 74 +#define INV_NEWTON_THRESHOLD 132 +#define INV_APPR_THRESHOLD 131 + +#define BINV_NEWTON_THRESHOLD 278 +#define REDC_1_TO_REDC_2_THRESHOLD 56 +#define REDC_2_TO_REDC_N_THRESHOLD 0 /* always */ + +#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 3,19,117,672,1867 + +#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 164 +#define FAC_ODD_THRESHOLD 0 /* always */ + +#define MATRIX22_STRASSEN_THRESHOLD 14 +#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/vendor/gmp-6.3.0/mpn/powerpc64/mode64/p8/invert_limb.asm b/vendor/gmp-6.3.0/mpn/powerpc64/mode64/p8/invert_limb.asm new file mode 100644 index 0000000..53ea0e0 --- /dev/null +++ b/vendor/gmp-6.3.0/mpn/powerpc64/mode64/p8/invert_limb.asm @@ -0,0 +1,53 @@ +dnl PowerPC-64 mpn_invert_limb -- Invert a normalized limb. + +dnl Copyright 2015, 2017 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +C cycles/limb (approximate) +C POWER3/PPC630 - +C POWER4/PPC970 - +C POWER5 - +C POWER6 - +C POWER7 ? +C POWER8 32 + +C This runs on POWER7 and later, but is faster only on later CPUs. +C We might want to inline this, considering its small footprint. + +ASM_START() +PROLOGUE(mpn_invert_limb) + sldi. r4, r3, 1 + neg r5, r3 + divdeu( r3, r5, r3) + beq- L(1) + blr +L(1): li r3, -1 + blr +EPILOGUE() -- cgit v1.2.3