1/* Intel Pentium-4 mpn_mul_1 -- Multiply a limb vector with a limb and store 2 * the result in a second limb vector. 3 * 4 * Copyright 2001, 2002, 2003, 2005 Free Software Foundation, Inc. 5 * 6 * This file is part of Libgcrypt. 7 * 8 * Libgcrypt is free software; you can redistribute it and/or modify 9 * it under the terms of the GNU Lesser General Public License as 10 * published by the Free Software Foundation; either version 2.1 of 11 * the License, or (at your option) any later version. 12 * 13 * Libgcrypt is distributed in the hope that it will be useful, 14 * but WITHOUT ANY WARRANTY; without even the implied warranty of 15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 16 * GNU Lesser General Public License for more details. 17 * 18 * You should have received a copy of the GNU Lesser General Public 19 * License along with this program; if not, write to the Free Software 20 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA 21 * 22 * Note: This code is heavily based on the GNU MP Library. 23 * Actually it's the same code with only minor changes in the 24 * way the data is stored; this is to support the abstraction 25 * of an optional secure memory allocation which may be used 26 * to avoid revealing of sensitive data due to paging etc. 27 */ 28 29 30#include "sysdep.h" 31#include "asm-syntax.h" 32 33 34/******************* 35 * mpi_limb_t 36 * _gcry_mpih_mul_1( mpi_ptr_t res_ptr, (sp + 4) 37 * mpi_ptr_t s1_ptr, (sp + 8) 38 * mpi_size_t s1_size, (sp + 12) 39 * mpi_limb_t s2_limb) (sp + 16) 40 * 41 * src != dst src == dst 42 * P6 model 9 (Banias) ?.? 43 * P6 model 13 (Dothan) 4.75 4.75 44 * P4 model 0 (Willamette) 4.0 6.0 45 * P4 model 1 (?) 4.0 6.0 46 * P4 model 2 (Northwood) 4.0 6.0 47 * P4 model 3 (Prescott) ?.? ?.? 48 * P4 model 4 (Nocona) ?.? ?.? 49 * Unfortunately when src==dst the write-combining described in 50 * pentium4/README takes us up to 6 c/l. 51 * 52 */ 53 54 TEXT 55 ALIGN (3) 56 GLOBL C_SYMBOL_NAME(_gcry_mpih_mul_1) 57C_SYMBOL_NAME(_gcry_mpih_mul_1:); 58 59 pxor %mm0, %mm0 60 61.Lstart_1c: 62 movl 8(%esp), %eax 63 movd 16(%esp), %mm7 64 movl 4(%esp), %edx 65 movl 12(%esp), %ecx 66 67.Ltop: 68 69/* 70 C eax src, incrementing 71 C ebx 72 C ecx counter, size iterations 73 C edx dst, incrementing 74 C 75 C mm0 carry limb 76 C mm7 multiplier 77*/ 78 79 movd (%eax), %mm1 80 addl $4, %eax 81 pmuludq %mm7, %mm1 82 83 paddq %mm1, %mm0 84 movd %mm0, (%edx) 85 addl $4, %edx 86 87 psrlq $32, %mm0 88 89 subl $1, %ecx 90 jnz .Ltop 91 92 93 movd %mm0, %eax 94 emms 95 ret 96 97