| /* |
| * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu> |
| * Copyright (C) 2008-2009 PetaLogix |
| * Copyright (C) 2008 Jim Law - Iris LP All rights reserved. |
| * |
| * This file is subject to the terms and conditions of the GNU General |
| * Public License. See the file COPYING in the main directory of this |
| * archive for more details. |
| * |
| * Written by Jim Law <jlaw@irispower.com> |
| * |
| * intended to replace: |
| * memcpy in memcpy.c and |
| * memmove in memmove.c |
| * ... in arch/microblaze/lib |
| * |
| * |
| * assly_fastcopy.S |
| * |
| * Attempt at quicker memcpy and memmove for MicroBlaze |
| * Input : Operand1 in Reg r5 - destination address |
| * Operand2 in Reg r6 - source address |
| * Operand3 in Reg r7 - number of bytes to transfer |
| * Output: Result in Reg r3 - starting destinaition address |
| * |
| * |
| * Explanation: |
| * Perform (possibly unaligned) copy of a block of memory |
| * between mem locations with size of xfer spec'd in bytes |
| */ |
| |
| .text |
| .globl memcpy |
| .type memcpy, @function |
| .ent memcpy |
| |
| memcpy: |
| fast_memcpy_ascending: |
| /* move d to return register as value of function */ |
| addi r3, r5, 0 |
| |
| addi r4, r0, 4 /* n = 4 */ |
| cmpu r4, r4, r7 /* n = c - n (unsigned) */ |
| blti r4, a_xfer_end /* if n < 0, less than one word to transfer */ |
| |
| /* transfer first 0~3 bytes to get aligned dest address */ |
| andi r4, r5, 3 /* n = d & 3 */ |
| /* if zero, destination already aligned */ |
| beqi r4, a_dalign_done |
| /* n = 4 - n (yields 3, 2, 1 transfers for 1, 2, 3 addr offset) */ |
| rsubi r4, r4, 4 |
| rsub r7, r4, r7 /* c = c - n adjust c */ |
| |
| a_xfer_first_loop: |
| /* if no bytes left to transfer, transfer the bulk */ |
| beqi r4, a_dalign_done |
| lbui r11, r6, 0 /* h = *s */ |
| sbi r11, r5, 0 /* *d = h */ |
| addi r6, r6, 1 /* s++ */ |
| addi r5, r5, 1 /* d++ */ |
| brid a_xfer_first_loop /* loop */ |
| addi r4, r4, -1 /* n-- (IN DELAY SLOT) */ |
| |
| a_dalign_done: |
| addi r4, r0, 32 /* n = 32 */ |
| cmpu r4, r4, r7 /* n = c - n (unsigned) */ |
| /* if n < 0, less than one block to transfer */ |
| blti r4, a_block_done |
| |
| a_block_xfer: |
| andi r9, r6, 3 /* t1 = s & 3 */ |
| /* if temp == 0, everything is word-aligned */ |
| beqi r9, a_word_xfer |
| |
| a_block_unaligned: |
| andi r4, r7, 0xffffffe0 /* n = c & ~31 */ |
| rsub r7, r4, r7 /* c = c - n */ |
| andi r8, r6, 0xfffffffc /* as = s & ~3 */ |
| add r6, r6, r4 /* s = s + n */ |
| lwi r11, r8, 0 /* h = *(as + 0) */ |
| |
| addi r9, r9, -1 |
| beqi r9, a_block_u1 /* t1 was 1 => 1 byte offset */ |
| addi r9, r9, -1 |
| beqi r9, a_block_u2 /* t1 was 2 => 2 byte offset */ |
| |
| a_block_u3: |
| bslli r11, r11, 24 /* h = h << 24 */ |
| a_bu3_loop: |
| lwi r12, r8, 4 /* v = *(as + 4) */ |
| bsrli r9, r12, 8 /* t1 = v >> 8 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 0 /* *(d + 0) = t1 */ |
| bslli r11, r12, 24 /* h = v << 24 */ |
| lwi r12, r8, 8 /* v = *(as + 8) */ |
| bsrli r9, r12, 8 /* t1 = v >> 8 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 4 /* *(d + 4) = t1 */ |
| bslli r11, r12, 24 /* h = v << 24 */ |
| lwi r12, r8, 12 /* v = *(as + 12) */ |
| bsrli r9, r12, 8 /* t1 = v >> 8 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 8 /* *(d + 8) = t1 */ |
| bslli r11, r12, 24 /* h = v << 24 */ |
| lwi r12, r8, 16 /* v = *(as + 16) */ |
| bsrli r9, r12, 8 /* t1 = v >> 8 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 12 /* *(d + 12) = t1 */ |
| bslli r11, r12, 24 /* h = v << 24 */ |
| lwi r12, r8, 20 /* v = *(as + 20) */ |
| bsrli r9, r12, 8 /* t1 = v >> 8 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 16 /* *(d + 16) = t1 */ |
| bslli r11, r12, 24 /* h = v << 24 */ |
| lwi r12, r8, 24 /* v = *(as + 24) */ |
| bsrli r9, r12, 8 /* t1 = v >> 8 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 20 /* *(d + 20) = t1 */ |
| bslli r11, r12, 24 /* h = v << 24 */ |
| lwi r12, r8, 28 /* v = *(as + 28) */ |
| bsrli r9, r12, 8 /* t1 = v >> 8 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 24 /* *(d + 24) = t1 */ |
| bslli r11, r12, 24 /* h = v << 24 */ |
| lwi r12, r8, 32 /* v = *(as + 32) */ |
| bsrli r9, r12, 8 /* t1 = v >> 8 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 28 /* *(d + 28) = t1 */ |
| bslli r11, r12, 24 /* h = v << 24 */ |
| addi r8, r8, 32 /* as = as + 32 */ |
| addi r4, r4, -32 /* n = n - 32 */ |
| bneid r4, a_bu3_loop /* while (n) loop */ |
| addi r5, r5, 32 /* d = d + 32 (IN DELAY SLOT) */ |
| bri a_block_done |
| |
| a_block_u1: |
| bslli r11, r11, 8 /* h = h << 8 */ |
| a_bu1_loop: |
| lwi r12, r8, 4 /* v = *(as + 4) */ |
| bsrli r9, r12, 24 /* t1 = v >> 24 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 0 /* *(d + 0) = t1 */ |
| bslli r11, r12, 8 /* h = v << 8 */ |
| lwi r12, r8, 8 /* v = *(as + 8) */ |
| bsrli r9, r12, 24 /* t1 = v >> 24 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 4 /* *(d + 4) = t1 */ |
| bslli r11, r12, 8 /* h = v << 8 */ |
| lwi r12, r8, 12 /* v = *(as + 12) */ |
| bsrli r9, r12, 24 /* t1 = v >> 24 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 8 /* *(d + 8) = t1 */ |
| bslli r11, r12, 8 /* h = v << 8 */ |
| lwi r12, r8, 16 /* v = *(as + 16) */ |
| bsrli r9, r12, 24 /* t1 = v >> 24 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 12 /* *(d + 12) = t1 */ |
| bslli r11, r12, 8 /* h = v << 8 */ |
| lwi r12, r8, 20 /* v = *(as + 20) */ |
| bsrli r9, r12, 24 /* t1 = v >> 24 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 16 /* *(d + 16) = t1 */ |
| bslli r11, r12, 8 /* h = v << 8 */ |
| lwi r12, r8, 24 /* v = *(as + 24) */ |
| bsrli r9, r12, 24 /* t1 = v >> 24 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 20 /* *(d + 20) = t1 */ |
| bslli r11, r12, 8 /* h = v << 8 */ |
| lwi r12, r8, 28 /* v = *(as + 28) */ |
| bsrli r9, r12, 24 /* t1 = v >> 24 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 24 /* *(d + 24) = t1 */ |
| bslli r11, r12, 8 /* h = v << 8 */ |
| lwi r12, r8, 32 /* v = *(as + 32) */ |
| bsrli r9, r12, 24 /* t1 = v >> 24 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 28 /* *(d + 28) = t1 */ |
| bslli r11, r12, 8 /* h = v << 8 */ |
| addi r8, r8, 32 /* as = as + 32 */ |
| addi r4, r4, -32 /* n = n - 32 */ |
| bneid r4, a_bu1_loop /* while (n) loop */ |
| addi r5, r5, 32 /* d = d + 32 (IN DELAY SLOT) */ |
| bri a_block_done |
| |
| a_block_u2: |
| bslli r11, r11, 16 /* h = h << 16 */ |
| a_bu2_loop: |
| lwi r12, r8, 4 /* v = *(as + 4) */ |
| bsrli r9, r12, 16 /* t1 = v >> 16 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 0 /* *(d + 0) = t1 */ |
| bslli r11, r12, 16 /* h = v << 16 */ |
| lwi r12, r8, 8 /* v = *(as + 8) */ |
| bsrli r9, r12, 16 /* t1 = v >> 16 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 4 /* *(d + 4) = t1 */ |
| bslli r11, r12, 16 /* h = v << 16 */ |
| lwi r12, r8, 12 /* v = *(as + 12) */ |
| bsrli r9, r12, 16 /* t1 = v >> 16 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 8 /* *(d + 8) = t1 */ |
| bslli r11, r12, 16 /* h = v << 16 */ |
| lwi r12, r8, 16 /* v = *(as + 16) */ |
| bsrli r9, r12, 16 /* t1 = v >> 16 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 12 /* *(d + 12) = t1 */ |
| bslli r11, r12, 16 /* h = v << 16 */ |
| lwi r12, r8, 20 /* v = *(as + 20) */ |
| bsrli r9, r12, 16 /* t1 = v >> 16 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 16 /* *(d + 16) = t1 */ |
| bslli r11, r12, 16 /* h = v << 16 */ |
| lwi r12, r8, 24 /* v = *(as + 24) */ |
| bsrli r9, r12, 16 /* t1 = v >> 16 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 20 /* *(d + 20) = t1 */ |
| bslli r11, r12, 16 /* h = v << 16 */ |
| lwi r12, r8, 28 /* v = *(as + 28) */ |
| bsrli r9, r12, 16 /* t1 = v >> 16 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 24 /* *(d + 24) = t1 */ |
| bslli r11, r12, 16 /* h = v << 16 */ |
| lwi r12, r8, 32 /* v = *(as + 32) */ |
| bsrli r9, r12, 16 /* t1 = v >> 16 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| swi r9, r5, 28 /* *(d + 28) = t1 */ |
| bslli r11, r12, 16 /* h = v << 16 */ |
| addi r8, r8, 32 /* as = as + 32 */ |
| addi r4, r4, -32 /* n = n - 32 */ |
| bneid r4, a_bu2_loop /* while (n) loop */ |
| addi r5, r5, 32 /* d = d + 32 (IN DELAY SLOT) */ |
| |
| a_block_done: |
| addi r4, r0, 4 /* n = 4 */ |
| cmpu r4, r4, r7 /* n = c - n (unsigned) */ |
| blti r4, a_xfer_end /* if n < 0, less than one word to transfer */ |
| |
| a_word_xfer: |
| andi r4, r7, 0xfffffffc /* n = c & ~3 */ |
| addi r10, r0, 0 /* offset = 0 */ |
| |
| andi r9, r6, 3 /* t1 = s & 3 */ |
| /* if temp != 0, unaligned transfers needed */ |
| bnei r9, a_word_unaligned |
| |
| a_word_aligned: |
| lw r9, r6, r10 /* t1 = *(s+offset) */ |
| sw r9, r5, r10 /* *(d+offset) = t1 */ |
| addi r4, r4,-4 /* n-- */ |
| bneid r4, a_word_aligned /* loop */ |
| addi r10, r10, 4 /* offset++ (IN DELAY SLOT) */ |
| |
| bri a_word_done |
| |
| a_word_unaligned: |
| andi r8, r6, 0xfffffffc /* as = s & ~3 */ |
| lwi r11, r8, 0 /* h = *(as + 0) */ |
| addi r8, r8, 4 /* as = as + 4 */ |
| |
| addi r9, r9, -1 |
| beqi r9, a_word_u1 /* t1 was 1 => 1 byte offset */ |
| addi r9, r9, -1 |
| beqi r9, a_word_u2 /* t1 was 2 => 2 byte offset */ |
| |
| a_word_u3: |
| bslli r11, r11, 24 /* h = h << 24 */ |
| a_wu3_loop: |
| lw r12, r8, r10 /* v = *(as + offset) */ |
| bsrli r9, r12, 8 /* t1 = v >> 8 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| sw r9, r5, r10 /* *(d + offset) = t1 */ |
| bslli r11, r12, 24 /* h = v << 24 */ |
| addi r4, r4,-4 /* n = n - 4 */ |
| bneid r4, a_wu3_loop /* while (n) loop */ |
| addi r10, r10, 4 /* offset = ofset + 4 (IN DELAY SLOT) */ |
| |
| bri a_word_done |
| |
| a_word_u1: |
| bslli r11, r11, 8 /* h = h << 8 */ |
| a_wu1_loop: |
| lw r12, r8, r10 /* v = *(as + offset) */ |
| bsrli r9, r12, 24 /* t1 = v >> 24 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| sw r9, r5, r10 /* *(d + offset) = t1 */ |
| bslli r11, r12, 8 /* h = v << 8 */ |
| addi r4, r4,-4 /* n = n - 4 */ |
| bneid r4, a_wu1_loop /* while (n) loop */ |
| addi r10, r10, 4 /* offset = ofset + 4 (IN DELAY SLOT) */ |
| |
| bri a_word_done |
| |
| a_word_u2: |
| bslli r11, r11, 16 /* h = h << 16 */ |
| a_wu2_loop: |
| lw r12, r8, r10 /* v = *(as + offset) */ |
| bsrli r9, r12, 16 /* t1 = v >> 16 */ |
| or r9, r11, r9 /* t1 = h | t1 */ |
| sw r9, r5, r10 /* *(d + offset) = t1 */ |
| bslli r11, r12, 16 /* h = v << 16 */ |
| addi r4, r4,-4 /* n = n - 4 */ |
| bneid r4, a_wu2_loop /* while (n) loop */ |
| addi r10, r10, 4 /* offset = ofset + 4 (IN DELAY SLOT) */ |
| |
| a_word_done: |
| add r5, r5, r10 /* d = d + offset */ |
| add r6, r6, r10 /* s = s + offset */ |
| rsub r7, r10, r7 /* c = c - offset */ |
| |
| a_xfer_end: |
| a_xfer_end_loop: |
| beqi r7, a_done /* while (c) */ |
| lbui r9, r6, 0 /* t1 = *s */ |
| addi r6, r6, 1 /* s++ */ |
| sbi r9, r5, 0 /* *d = t1 */ |
| addi r7, r7, -1 /* c-- */ |
| brid a_xfer_end_loop /* loop */ |
| addi r5, r5, 1 /* d++ (IN DELAY SLOT) */ |
| |
| a_done: |
| rtsd r15, 8 |
| nop |
| |
| .size memcpy, . - memcpy |
| .end memcpy |
| libc_hidden_def(memcpy) |