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 --- vendor/gmp-6.3.0/mpn/alpha/ev5/diveby3.asm | 332 ++++++++++++++++++++++++++++ vendor/gmp-6.3.0/mpn/alpha/ev5/gmp-mparam.h | 191 ++++++++++++++++ 2 files changed, 523 insertions(+) create mode 100644 vendor/gmp-6.3.0/mpn/alpha/ev5/diveby3.asm create mode 100644 vendor/gmp-6.3.0/mpn/alpha/ev5/gmp-mparam.h (limited to 'vendor/gmp-6.3.0/mpn/alpha/ev5') diff --git a/vendor/gmp-6.3.0/mpn/alpha/ev5/diveby3.asm b/vendor/gmp-6.3.0/mpn/alpha/ev5/diveby3.asm new file mode 100644 index 0000000..3758188 --- /dev/null +++ b/vendor/gmp-6.3.0/mpn/alpha/ev5/diveby3.asm @@ -0,0 +1,332 @@ +dnl Alpha mpn_divexact_by3c -- mpn division by 3, expecting no remainder. + +dnl Copyright 2004, 2005, 2009 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 +C EV4: 22 +C EV5: 11.5 +C EV6: 6.3 Note that mpn_bdiv_dbm1c is faster + +C TODO +C * Remove the unops, they benefit just ev6, which no longer uses this file. +C * Try prefetch for destination, using lds. +C * Improve feed-in code, by moving initial mulq earlier; make initial load +C to u0/u0 to save some copying. +C * Combine u0 and u2, u1 and u3. + +C INPUT PARAMETERS +define(`rp', `r16') +define(`up', `r17') +define(`n', `r18') +define(`cy', `r19') + +ASM_START() + +DATASTART(L(LC),8) + .quad 0xAAAAAAAAAAAAAAAB + .quad 0x5555555555555555 + .quad 0xAAAAAAAAAAAAAAAA +DATAEND() + +define(`xAAAAAAAAAAAAAAAB', `r20') +define(`x5555555555555555', `r21') +define(`xAAAAAAAAAAAAAAAA', `r22') +define(`u0', `r0') define(`u1', `r1') +define(`u2', `r2') define(`u3', `r3') +define(`l0', `r25') define(`x', `r8') +define(`q0', `r4') define(`q1', `r5') +define(`p6', `r6') define(`p7', `r7') +define(`t0', `r23') define(`t1', `r24') +define(`cymask',`r28') + + +PROLOGUE(mpn_divexact_by3c,gp) + + ldq r28, 0(up) C load first limb early + +C Put magic constants in registers + lda r0, L(LC) + ldq xAAAAAAAAAAAAAAAB, 0(r0) + ldq x5555555555555555, 8(r0) + ldq xAAAAAAAAAAAAAAAA, 16(r0) + +C Compute initial l0 value + cmpeq cy, 1, p6 + cmpeq cy, 2, p7 + negq p6, p6 + and p6, x5555555555555555, l0 + cmovne p7, xAAAAAAAAAAAAAAAA, l0 + +C Feed-in depending on (n mod 4) + and n, 3, r8 + lda n, -3(n) + cmpeq r8, 1, r4 + cmpeq r8, 2, r5 + bne r4, $Lb01 + bne r5, $Lb10 + beq r8, $Lb00 + +$Lb11: ldq u3, 8(up) + lda up, -24(up) + lda rp, -24(rp) + mulq r28, xAAAAAAAAAAAAAAAB, q0 + mov r28, u2 + br r31, $L11 + +$Lb00: ldq u2, 8(up) + lda up, -16(up) + lda rp, -16(rp) + mulq r28, xAAAAAAAAAAAAAAAB, q1 + mov r28, u1 + br r31, $L00 + +$Lb01: lda rp, -8(rp) + mulq r28, xAAAAAAAAAAAAAAAB, q0 + mov r28, u0 + blt n, $Lcj1 + ldq u1, 8(up) + lda up, -8(up) + br r31, $L01 + +$Lb10: ldq u0, 8(up) + mulq r28, xAAAAAAAAAAAAAAAB, q1 + mov r28, u3 + blt n, $Lend + + ALIGN(16) +$Ltop: +C 0 + cmpult u3, cy, cy C L0 + mulq u0, xAAAAAAAAAAAAAAAB, q0 C U1 + ldq u1, 16(up) C L1 + addq q1, l0, x C U0 +C 1 + negq cy, cymask C L0 + unop C U1 + unop C L1 + cmpult x5555555555555555, x, p6 C U0 +C 2 + cmpult xAAAAAAAAAAAAAAAA, x, p7 C U1 + unop + unop + negq p6, t0 C L0 +C 3 + negq p7, t1 C L0 + and cymask, x5555555555555555, l0 C U1 + addq p6, cy, cy + and t0, x5555555555555555, t0 +C 4 + and t1, x5555555555555555, t1 + addq p7, cy, cy + unop + addq t0, l0, l0 +C 5 + addq t1, l0, l0 + unop + stq x, 0(rp) C L1 + unop +$L01: +C 0 + cmpult u0, cy, cy C L0 + mulq u1, xAAAAAAAAAAAAAAAB, q1 C U1 + ldq u2, 24(up) C L1 + addq q0, l0, x C U0 +C 1 + negq cy, cymask C L0 + unop C U1 + unop C L1 + cmpult x5555555555555555, x, p6 C U0 +C 2 + cmpult xAAAAAAAAAAAAAAAA, x, p7 C U1 + unop + unop + negq p6, t0 C L0 +C 3 + negq p7, t1 C L0 + and cymask, x5555555555555555, l0 C U1 + addq p6, cy, cy + and t0, x5555555555555555, t0 +C 4 + and t1, x5555555555555555, t1 + addq p7, cy, cy + unop + addq t0, l0, l0 +C 5 + addq t1, l0, l0 + unop + stq x, 8(rp) C L1 + unop +$L00: +C 0 + cmpult u1, cy, cy C L0 + mulq u2, xAAAAAAAAAAAAAAAB, q0 C U1 + ldq u3, 32(up) C L1 + addq q1, l0, x C U0 +C 1 + negq cy, cymask C L0 + unop C U1 + unop C L1 + cmpult x5555555555555555, x, p6 C U0 +C 2 + cmpult xAAAAAAAAAAAAAAAA, x, p7 C U1 + unop + unop + negq p6, t0 C L0 +C 3 + negq p7, t1 C L0 + and cymask, x5555555555555555, l0 C U1 + addq p6, cy, cy + and t0, x5555555555555555, t0 +C 4 + and t1, x5555555555555555, t1 + addq p7, cy, cy + unop + addq t0, l0, l0 +C 5 + addq t1, l0, l0 + unop + stq x, 16(rp) C L1 + unop +$L11: +C 0 + cmpult u2, cy, cy C L0 + mulq u3, xAAAAAAAAAAAAAAAB, q1 C U1 + ldq u0, 40(up) C L1 + addq q0, l0, x C U0 +C 1 + negq cy, cymask C L0 + unop C U1 + unop C L1 + cmpult x5555555555555555, x, p6 C U0 +C 2 + cmpult xAAAAAAAAAAAAAAAA, x, p7 C U1 + lda n, -4(n) C L1 bookkeeping + unop + negq p6, t0 C L0 +C 3 + negq p7, t1 C L0 + and cymask, x5555555555555555, l0 C U1 + addq p6, cy, cy + and t0, x5555555555555555, t0 +C 4 + and t1, x5555555555555555, t1 + addq p7, cy, cy + unop + addq t0, l0, l0 +C 5 + addq t1, l0, l0 + unop + stq x, 24(rp) C L1 + lda up, 32(up) +C + ldl r31, 256(up) C prefetch + unop + lda rp, 32(rp) + bge n, $Ltop C U1 +C *** MAIN LOOP END *** +$Lend: + + cmpult u3, cy, cy C L0 + mulq u0, xAAAAAAAAAAAAAAAB, q0 C U1 + unop + addq q1, l0, x C U0 +C 1 + negq cy, cymask C L0 + unop C U1 + unop C L1 + cmpult x5555555555555555, x, p6 C U0 +C 2 + cmpult xAAAAAAAAAAAAAAAA, x, p7 C U1 + unop + unop + negq p6, t0 C L0 +C 3 + negq p7, t1 C L0 + and cymask, x5555555555555555, l0 C U1 + addq p6, cy, cy + and t0, x5555555555555555, t0 +C 4 + and t1, x5555555555555555, t1 + addq p7, cy, cy + unop + addq t0, l0, l0 +C 5 + addq t1, l0, l0 + unop + stq x, 0(rp) C L1 + unop +$Lcj1: + cmpult u0, cy, cy C L0 + addq q0, l0, x C U0 + cmpult x5555555555555555, x, p6 C U0 + cmpult xAAAAAAAAAAAAAAAA, x, p7 C U1 + addq p6, cy, cy + addq p7, cy, r0 + stq x, 8(rp) C L1 + + ret r31,(r26),1 +EPILOGUE() +ASM_END() + +C This is useful for playing with various schedules. +C Expand as: one(0)one(1)one(2)one(3) +define(`one',` +C 0 + cmpult `$'eval(($1+3)%4), cy, cy C L0 + mulq `$'$1, xAAAAAAAAAAAAAAAB, `$'eval(4+$1%2) C U1 + ldq `$'eval(($1+1)%4), eval($1*8+16)(up) C L1 + addq `$'eval(4+($1+1)%2), l0, x C U0 +C 1 + negq cy, cymask C L0 + unop C U1 + unop C L1 + cmpult x5555555555555555, x, p6 C U0 +C 2 + cmpult xAAAAAAAAAAAAAAAA, x, p7 C U1 + unop + unop + negq p6, t0 C L0 +C 3 + negq p7, t1 C L0 + and cymask, x5555555555555555, l0 C U1 + addq p6, cy, cy + and t0, x5555555555555555, t0 +C 4 + and t1, x5555555555555555, t1 + addq p7, cy, cy + unop + addq t0, l0, l0 +C 5 + addq t1, l0, l0 + unop + stq x, eval($1*8)(rp) C L1 + unop +') diff --git a/vendor/gmp-6.3.0/mpn/alpha/ev5/gmp-mparam.h b/vendor/gmp-6.3.0/mpn/alpha/ev5/gmp-mparam.h new file mode 100644 index 0000000..1575a28 --- /dev/null +++ b/vendor/gmp-6.3.0/mpn/alpha/ev5/gmp-mparam.h @@ -0,0 +1,191 @@ +/* Alpha EV5 gmp-mparam.h -- Compiler/machine parameter header file. + +Copyright 1991-2017 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 + +/* 600 MHz 21164A */ +/* FFT tuning limit = 5000000 */ +/* Generated by tuneup.c, 2017-02-02, gcc 4.9 */ + +#define DIVREM_1_NORM_THRESHOLD 0 /* preinv always */ +#define DIVREM_1_UNNORM_THRESHOLD 0 /* always */ +#define MOD_1_1P_METHOD 2 +#define MOD_1_NORM_THRESHOLD 0 /* always */ +#define MOD_1_UNNORM_THRESHOLD 0 /* always */ +#define MOD_1N_TO_MOD_1_1_THRESHOLD 10 +#define MOD_1U_TO_MOD_1_1_THRESHOLD 7 +#define MOD_1_1_TO_MOD_1_2_THRESHOLD 22 +#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */ +#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 20 +#define USE_PREINV_DIVREM_1 1 /* preinv always */ +#define DIV_QR_1N_PI1_METHOD 1 +#define DIV_QR_1_NORM_THRESHOLD MP_SIZE_T_MAX /* never */ +#define DIV_QR_1_UNNORM_THRESHOLD MP_SIZE_T_MAX /* never */ +#define DIV_QR_2_PI2_THRESHOLD MP_SIZE_T_MAX /* never */ +#define DIVEXACT_1_THRESHOLD 0 /* always */ +#define BMOD_1_TO_MOD_1_THRESHOLD 69 + +#define DIV_1_VS_MUL_1_PERCENT 181 + +#define MUL_TOOM22_THRESHOLD 16 +#define MUL_TOOM33_THRESHOLD 50 +#define MUL_TOOM44_THRESHOLD 118 +#define MUL_TOOM6H_THRESHOLD 173 +#define MUL_TOOM8H_THRESHOLD 236 + +#define MUL_TOOM32_TO_TOOM43_THRESHOLD 49 +#define MUL_TOOM32_TO_TOOM53_THRESHOLD 84 +#define MUL_TOOM42_TO_TOOM53_THRESHOLD 81 +#define MUL_TOOM42_TO_TOOM63_THRESHOLD 53 +#define MUL_TOOM43_TO_TOOM54_THRESHOLD 70 + +#define SQR_BASECASE_THRESHOLD 0 /* always */ +#define SQR_TOOM2_THRESHOLD 22 +#define SQR_TOOM3_THRESHOLD 69 +#define SQR_TOOM4_THRESHOLD 178 +#define SQR_TOOM6_THRESHOLD 189 +#define SQR_TOOM8_THRESHOLD 357 + +#define MULMID_TOOM42_THRESHOLD 18 + +#define MULMOD_BNM1_THRESHOLD 9 +#define SQRMOD_BNM1_THRESHOLD 12 + +#define MUL_FFT_MODF_THRESHOLD 284 /* k = 5 */ +#define MUL_FFT_TABLE3 \ + { { 284, 5}, { 11, 6}, { 6, 5}, { 13, 6}, \ + { 7, 5}, { 15, 6}, { 13, 7}, { 7, 6}, \ + { 15, 7}, { 8, 6}, { 17, 7}, { 13, 8}, \ + { 7, 7}, { 17, 8}, { 9, 7}, { 20, 8}, \ + { 11, 7}, { 23, 8}, { 13, 9}, { 7, 8}, \ + { 19, 9}, { 11, 8}, { 25,10}, { 7, 9}, \ + { 15, 8}, { 33, 9}, { 19, 8}, { 39, 9}, \ + { 23, 8}, { 47,10}, { 15, 9}, { 39,10}, \ + { 23, 9}, { 47,11}, { 15,10}, { 31, 9}, \ + { 67,10}, { 39, 9}, { 79,10}, { 47, 9}, \ + { 95,10}, { 55,11}, { 31,10}, { 63, 8}, \ + { 255, 7}, { 511,10}, { 71, 9}, { 143, 8}, \ + { 287, 7}, { 575, 9}, { 159, 8}, { 319,11}, \ + { 47,12}, { 31,11}, { 63, 9}, { 255, 8}, \ + { 511,10}, { 143, 9}, { 287,11}, { 79,10}, \ + { 159, 9}, { 319,10}, { 175, 9}, { 351, 8}, \ + { 703,10}, { 191, 9}, { 383,10}, { 207, 9}, \ + { 415,12}, { 63,10}, { 255,11}, { 143,10}, \ + { 287, 9}, { 575,11}, { 159,10}, { 319, 9}, \ + { 639,11}, { 175,12}, { 95,11}, { 191,10}, \ + { 383,11}, { 207,10}, { 415,11}, { 223,13}, \ + { 63,11}, { 287,10}, { 575,12}, { 159,11}, \ + { 319,10}, { 639,11}, { 351,12}, { 191,11}, \ + { 415,12}, { 223,11}, { 447,10}, { 895,11}, \ + { 479,12}, { 287,11}, { 575,12}, { 351,13}, \ + { 191,12}, { 479,13}, { 255,12}, { 575,13}, \ + { 319,12}, { 703,13}, { 383,12}, { 831,13}, \ + { 447,14}, { 255,13}, { 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 121 +#define MUL_FFT_THRESHOLD 4224 + +#define SQR_FFT_MODF_THRESHOLD 240 /* k = 5 */ +#define SQR_FFT_TABLE3 \ + { { 240, 5}, { 13, 6}, { 7, 5}, { 15, 6}, \ + { 14, 5}, { 29, 7}, { 9, 6}, { 19, 7}, \ + { 13, 6}, { 27, 8}, { 7, 7}, { 21, 8}, \ + { 11, 7}, { 29, 8}, { 19, 9}, { 11, 8}, \ + { 27,10}, { 7, 9}, { 15, 8}, { 33, 9}, \ + { 19, 8}, { 39, 9}, { 23, 8}, { 47,10}, \ + { 15, 9}, { 39,10}, { 23, 9}, { 47,11}, \ + { 15,10}, { 31, 9}, { 67,10}, { 39, 9}, \ + { 79,10}, { 47,11}, { 31,10}, { 63, 9}, \ + { 127, 8}, { 255,10}, { 71, 9}, { 143, 8}, \ + { 287,10}, { 79,11}, { 47,12}, { 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}, { 415,11}, { 111,10}, { 223,12}, \ + { 63,11}, { 175,12}, { 95,11}, { 207,13}, \ + { 63,12}, { 127,11}, { 287,12}, { 159,11}, \ + { 351,12}, { 191,11}, { 415,12}, { 223,11}, \ + { 447,13}, { 127,12}, { 351,13}, { 191,12}, \ + { 383,11}, { 767,12}, { 415,11}, { 831,12}, \ + { 447,14}, { 127,13}, { 255,12}, { 511,11}, \ + { 1087,12}, { 575,13}, { 319,12}, { 703,13}, \ + { 383,12}, { 831,13}, { 447,14}, { 255,13}, \ + { 511,12}, { 1023,13}, { 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 105 +#define SQR_FFT_THRESHOLD 3968 + +#define MULLO_BASECASE_THRESHOLD 0 /* always */ +#define MULLO_DC_THRESHOLD 50 +#define MULLO_MUL_N_THRESHOLD 5558 +#define SQRLO_BASECASE_THRESHOLD 0 /* always */ +#define SQRLO_DC_THRESHOLD 78 +#define SQRLO_SQR_THRESHOLD 3597 + +#define DC_DIV_QR_THRESHOLD 47 +#define DC_DIVAPPR_Q_THRESHOLD 167 +#define DC_BDIV_QR_THRESHOLD 47 +#define DC_BDIV_Q_THRESHOLD 110 + +#define INV_MULMOD_BNM1_THRESHOLD 30 +#define INV_NEWTON_THRESHOLD 181 +#define INV_APPR_THRESHOLD 173 + +#define BINV_NEWTON_THRESHOLD 182 +#define REDC_1_TO_REDC_N_THRESHOLD 47 + +#define MU_DIV_QR_THRESHOLD 979 +#define MU_DIVAPPR_Q_THRESHOLD 1142 +#define MUPI_DIV_QR_THRESHOLD 90 +#define MU_BDIV_QR_THRESHOLD 748 +#define MU_BDIV_Q_THRESHOLD 979 + +#define POWM_SEC_TABLE 1,16,90,386,2177 + +#define GET_STR_DC_THRESHOLD 14 +#define GET_STR_PRECOMPUTE_THRESHOLD 26 +#define SET_STR_DC_THRESHOLD 363 +#define SET_STR_PRECOMPUTE_THRESHOLD 1201 + +#define FAC_DSC_THRESHOLD 342 +#define FAC_ODD_THRESHOLD 0 /* always */ + +#define MATRIX22_STRASSEN_THRESHOLD 13 +#define HGCD_THRESHOLD 105 +#define HGCD_APPR_THRESHOLD 108 +#define HGCD_REDUCE_THRESHOLD 1679 +#define GCD_DC_THRESHOLD 238 +#define GCDEXT_DC_THRESHOLD 199 +#define JACOBI_BASE_METHOD 2 -- cgit v1.2.3