1/* Alpha 21064 submul_1 -- Multiply a limb vector with a limb and 2 * subtract the result from a second limb vector. 3 * Copyright (C) 1992, 1994, 1995, 1998, 4 * 2001, 2002 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 23 24/******************* 25 * mpi_limb_t 26 * _gcry_mpih_submul_1( mpi_ptr_t res_ptr, (r16 ) 27 * mpi_ptr_t s1_ptr, (r17 ) 28 * mpi_size_t s1_size, (r18 ) 29 * mpi_limb_t s2_limb) (r19 ) 30 * 31 * This code runs at 42 cycles/limb on EV4 and 18 cycles/limb on EV5. 32 */ 33 34 .set noreorder 35 .set noat 36.text 37 .align 3 38 .globl _gcry_mpih_submul_1 39 .ent _gcry_mpih_submul_1 2 40_gcry_mpih_submul_1: 41 .frame $30,0,$26 42 43 ldq $2,0($17) # $2 = s1_limb 44 addq $17,8,$17 # s1_ptr++ 45 subq $18,1,$18 # size-- 46 mulq $2,$19,$3 # $3 = prod_low 47 ldq $5,0($16) # $5 = *res_ptr 48 umulh $2,$19,$0 # $0 = prod_high 49 beq $18,.Lend1 # jump if size was == 1 50 ldq $2,0($17) # $2 = s1_limb 51 addq $17,8,$17 # s1_ptr++ 52 subq $18,1,$18 # size-- 53 subq $5,$3,$3 54 cmpult $5,$3,$4 55 stq $3,0($16) 56 addq $16,8,$16 # res_ptr++ 57 beq $18,.Lend2 # jump if size was == 2 58 59 .align 3 60.Loop: mulq $2,$19,$3 # $3 = prod_low 61 ldq $5,0($16) # $5 = *res_ptr 62 addq $4,$0,$0 # cy_limb = cy_limb + 'cy' 63 subq $18,1,$18 # size-- 64 umulh $2,$19,$4 # $4 = cy_limb 65 ldq $2,0($17) # $2 = s1_limb 66 addq $17,8,$17 # s1_ptr++ 67 addq $3,$0,$3 # $3 = cy_limb + prod_low 68 cmpult $3,$0,$0 # $0 = carry from (cy_limb + prod_low) 69 subq $5,$3,$3 70 cmpult $5,$3,$5 71 stq $3,0($16) 72 addq $16,8,$16 # res_ptr++ 73 addq $5,$0,$0 # combine carries 74 bne $18,.Loop 75 76.Lend2: mulq $2,$19,$3 # $3 = prod_low 77 ldq $5,0($16) # $5 = *res_ptr 78 addq $4,$0,$0 # cy_limb = cy_limb + 'cy' 79 umulh $2,$19,$4 # $4 = cy_limb 80 addq $3,$0,$3 # $3 = cy_limb + prod_low 81 cmpult $3,$0,$0 # $0 = carry from (cy_limb + prod_low) 82 subq $5,$3,$3 83 cmpult $5,$3,$5 84 stq $3,0($16) 85 addq $5,$0,$0 # combine carries 86 addq $4,$0,$0 # cy_limb = prod_high + cy 87 ret $31,($26),1 88.Lend1: subq $5,$3,$3 89 cmpult $5,$3,$5 90 stq $3,0($16) 91 addq $0,$5,$0 92 ret $31,($26),1 93 94 .end _gcry_mpih_submul_1 95 96