/* * include/asm-alpha/xor.h * * Optimized RAID-5 checksumming functions for alpha EV5 and EV6 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2, or (at your option) * any later version. * * You should have received a copy of the GNU General Public License * (for example /usr/src/linux/COPYING); if not, write to the Free * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ extern void xor_alpha_2(unsigned long, unsigned long *, unsigned long *); extern void xor_alpha_3(unsigned long, unsigned long *, unsigned long *, unsigned long *); extern void xor_alpha_4(unsigned long, unsigned long *, unsigned long *, unsigned long *, unsigned long *); extern void xor_alpha_5(unsigned long, unsigned long *, unsigned long *, unsigned long *, unsigned long *, unsigned long *); extern void xor_alpha_prefetch_2(unsigned long, unsigned long *, unsigned long *); extern void xor_alpha_prefetch_3(unsigned long, unsigned long *, unsigned long *, unsigned long *); extern void xor_alpha_prefetch_4(unsigned long, unsigned long *, unsigned long *, unsigned long *, unsigned long *); extern void xor_alpha_prefetch_5(unsigned long, unsigned long *, unsigned long *, unsigned long *, unsigned long *, unsigned long *); asm(" \n\ .text \n\ .align 3 \n\ .ent xor_alpha_2 \n\ xor_alpha_2: \n\ .prologue 0 \n\ srl $16, 6, $16 \n\ .align 4 \n\ 2: \n\ ldq $0,0($17) \n\ ldq $1,0($18) \n\ ldq $2,8($17) \n\ ldq $3,8($18) \n\ \n\ ldq $4,16($17) \n\ ldq $5,16($18) \n\ ldq $6,24($17) \n\ ldq $7,24($18) \n\ \n\ ldq $19,32($17) \n\ ldq $20,32($18) \n\ ldq $21,40($17) \n\ ldq $22,40($18) \n\ \n\ ldq $23,48($17) \n\ ldq $24,48($18) \n\ ldq $25,56($17) \n\ xor $0,$1,$0 # 7 cycles from $1 load \n\ \n\ ldq $27,56($18) \n\ xor $2,$3,$2 \n\ stq $0,0($17) \n\ xor $4,$5,$4 \n\ \n\ stq $2,8($17) \n\ xor $6,$7,$6 \n\ stq $4,16($17) \n\ xor $19,$20,$19 \n\ \n\ stq $6,24($17) \n\ xor $21,$22,$21 \n\ stq $19,32($17) \n\ xor $23,$24,$23 \n\ \n\ stq $21,40($17) \n\ xor $25,$27,$25 \n\ stq $23,48($17) \n\ subq $16,1,$16 \n\ \n\ stq $25,56($17) \n\ addq $17,64,$17 \n\ addq $18,64,$18 \n\ bgt $16,2b \n\ \n\ ret \n\ .end xor_alpha_2 \n\ \n\ .align 3 \n\ .ent xor_alpha_3 \n\ xor_alpha_3: \n\ .prologue 0 \n\ srl $16, 6, $16 \n\ .align 4 \n\ 3: \n\ ldq $0,0($17) \n\ ldq $1,0($18) \n\ ldq $2,0($19) \n\ ldq $3,8($17) \n\ \n\ ldq $4,8($18) \n\ ldq $6,16($17) \n\ ldq $7,16($18) \n\ ldq $21,24($17) \n\ \n\ ldq $22,24($18) \n\ ldq $24,32($17) \n\ ldq $25,32($18) \n\ ldq $5,8($19) \n\ \n\ ldq $20,16($19) \n\ ldq $23,24($19) \n\ ldq $27,32($19) \n\ nop \n\ \n\ xor $0,$1,$1 # 8 cycles from $0 load \n\ xor $3,$4,$4 # 6 cycles from $4 load \n\ xor $6,$7,$7 # 6 cycles from $7 load \n\ xor $21,$22,$22 # 5 cycles from $22 load \n\ \n\ xor $1,$2,$2 # 9 cycles from $2 load \n\ xor $24,$25,$25 # 5 cycles from $25 load \n\ stq $2,0($17) \n\ xor $4,$5,$5 # 6 cycles from $5 load \n\ \n\ stq $5,8($17) \n\ xor $7,$20,$20 # 7 cycles from $20 load \n\ stq $20,16($17) \n\ xor $22,$23,$23 # 7 cycles from $23 load \n\ \n\ stq $23,24($17) \n\ xor $25,$27,$27 # 7 cycles from $27 load \n\ stq $27,32($17) \n\ nop \n\ \n\ ldq $0,40($17) \n\ ldq $1,40($18) \n\ ldq $3,48($17) \n\ ldq $4,48($18) \n\ \n\ ldq $6,56($17) \n\ ldq $7,56($18) \n\ ldq $2,40($19) \n\ ldq $5,48($19) \n\ \n\ ldq $20,56($19) \n\ xor $0,$1,$1 # 4 cycles from $1 load \n\ xor $3,$4,$4 # 5 cycles from $4 load \n\ xor $6,$7,$7 # 5 cycles from $7 load \n\