/* Optimized strncmp implementation for PowerPC64/POWER10. Copyright (C) 2025 Free Software Foundation, Inc. This file is part of the GNU C Library. The GNU C Library is free software; you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License as published by the Free Software Foundation; either version 2.1 of the License, or (at your option) any later version. The GNU C 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 Lesser General Public License for more details. You should have received a copy of the GNU Lesser General Public License along with the GNU C Library; if not, see . */ #include /* Implements the function int [r3] strncmp (const char *s1 [r3], const char *s2 [r4], size_t [r5] n) The implementation uses unaligned doubleword access to avoid specialized code paths depending of data alignment for first 32 bytes and uses vectorised loops after that. */ #ifndef STRNCMP # define STRNCMP strncmp #endif #define COMPARE_16(vreg1,vreg2,offset) \ lxv vreg1+32,offset(r3); \ lxv vreg2+32,offset(r4); \ vcmpnezb. v7,vreg1,vreg2; \ bne cr6,L(different); \ cmpldi cr7,r5,16; \ ble cr7,L(ret0); \ addi r5,r5,-16; #define COMPARE_32(vreg1,vreg2,offset,label1,label2) \ lxvp vreg1+32,offset(r3); \ lxvp vreg2+32,offset(r4); \ vcmpnezb. v7,vreg1+1,vreg2+1; \ bne cr6,L(label1); \ vcmpnezb. v7,vreg1,vreg2; \ bne cr6,L(label2); \ cmpldi cr7,r5,32; \ ble cr7,L(ret0); \ addi r5,r5,-32; #define TAIL_FIRST_16B(vreg1,vreg2) \ vctzlsbb r6,v7; \ cmpld cr7,r5,r6; \ ble cr7,L(ret0); \ vextubrx r5,r6,vreg1; \ vextubrx r4,r6,vreg2; \ subf r3,r4,r5; \ blr; #define TAIL_SECOND_16B(vreg1,vreg2) \ vctzlsbb r6,v7; \ addi r0,r6,16; \ cmpld cr7,r5,r0; \ ble cr7,L(ret0); \ vextubrx r5,r6,vreg1; \ vextubrx r4,r6,vreg2; \ subf r3,r4,r5; \ blr; #define CHECK_N_BYTES(reg1,reg2,len_reg) \ sldi r6,len_reg,56; \ lxvl 32+v4,reg1,r6; \ lxvl 32+v5,reg2,r6; \ add reg1,reg1,len_reg; \ add reg2,reg2,len_reg; \ vcmpnezb v7,v4,v5; \ vctzlsbb r6,v7; \ cmpld cr7,r6,len_reg; \ blt cr7,L(different); \ cmpld cr7,r5,len_reg; \ ble cr7,L(ret0); \ sub r5,r5,len_reg; \ .machine power10 ENTRY_TOCLESS (STRNCMP, 4) /* Check if size is 0. */ cmpdi cr0,r5,0 beq cr0,L(ret0) andi. r7,r3,4095 andi. r8,r4,4095 cmpldi cr0,r7,4096-16 cmpldi cr1,r8,4096-16 bgt cr0,L(crosses) bgt cr1,L(crosses) COMPARE_16(v4,v5,0) addi r3,r3,16 addi r4,r4,16 L(crosses): andi. r7,r3,15 subfic r7,r7,16 /* r7(nalign1) = 16 - (str1 & 15). */ andi. r9,r4,15 subfic r8,r9,16 /* r8(nalign2) = 16 - (str2 & 15). */ cmpld cr7,r7,r8 beq cr7,L(same_aligned) blt cr7,L(nalign1_min) /* nalign2 is minimum and s2 pointer is aligned. */ CHECK_N_BYTES(r3,r4,r8) /* Are we on the 64B hunk which crosses a page? */ andi. r10,r3,63 /* Determine offset into 64B hunk. */ andi. r8,r3,15 /* The offset into the 16B hunk. */ neg r7,r3 andi. r9,r7,15 /* Number of bytes after a 16B cross. */ rlwinm. r7,r7,26,0x3F /* ((r4-4096))>>6&63. */ beq L(compare_64_pagecross) mtctr r7 b L(compare_64B_unaligned) /* nalign1 is minimum and s1 pointer is aligned. */ L(nalign1_min): CHECK_N_BYTES(r3,r4,r7) /* Are we on the 64B hunk which crosses a page? */ andi. r10,r4,63 /* Determine offset into 64B hunk. */ andi. r8,r4,15 /* The offset into the 16B hunk. */ neg r7,r4 andi. r9,r7,15 /* Number of bytes after a 16B cross. */ rlwinm. r7,r7,26,0x3F /* ((r4-4096))>>6&63. */ beq L(compare_64_pagecross) mtctr r7 .p2align 5 L(compare_64B_unaligned): COMPARE_16(v4,v5,0) COMPARE_16(v4,v5,16) COMPARE_16(v4,v5,32) COMPARE_16(v4,v5,48) addi r3,r3,64 addi r4,r4,64 bdnz L(compare_64B_unaligned) /* Cross the page boundary of s2, carefully. Only for first iteration we have to get the count of 64B blocks to be checked. From second iteration and beyond, loop counter is always 63. */ L(compare_64_pagecross): li r11, 63 mtctr r11 cmpldi r10,16 ble L(cross_4) cmpldi r10,32 ble L(cross_3) cmpldi r10,48 ble L(cross_2) L(cross_1): CHECK_N_BYTES(r3,r4,r9) CHECK_N_BYTES(r3,r4,r8) COMPARE_16(v4,v5,0) COMPARE_16(v4,v5,16) COMPARE_16(v4,v5,32) addi r3,r3,48 addi r4,r4,48 b L(compare_64B_unaligned) L(cross_2): COMPARE_16(v4,v5,0) addi r3,r3,16 addi r4,r4,16 CHECK_N_BYTES(r3,r4,r9) CHECK_N_BYTES(r3,r4,r8) COMPARE_16(v4,v5,0) COMPARE_16(v4,v5,16) addi r3,r3,32 addi r4,r4,32 b L(compare_64B_unaligned) L(cross_3): COMPARE_16(v4,v5,0) COMPARE_16(v4,v5,16) addi r3,r3,32 addi r4,r4,32 CHECK_N_BYTES(r3,r4,r9) CHECK_N_BYTES(r3,r4,r8) COMPARE_16(v4,v5,0) addi r3,r3,16 addi r4,r4,16 b L(compare_64B_unaligned) L(cross_4): COMPARE_16(v4,v5,0) COMPARE_16(v4,v5,16) COMPARE_16(v4,v5,32) addi r3,r3,48 addi r4,r4,48 CHECK_N_BYTES(r3,r4,r9) CHECK_N_BYTES(r3,r4,r8) b L(compare_64B_unaligned) L(same_aligned): CHECK_N_BYTES(r3,r4,r7) /* Align s1 to 32B and adjust s2 address. Use lxvp only if both s1 and s2 are 32B aligned. */ COMPARE_16(v4,v5,0) COMPARE_16(v4,v5,16) COMPARE_16(v4,v5,32) COMPARE_16(v4,v5,48) addi r3,r3,64 addi r4,r4,64 COMPARE_16(v4,v5,0) COMPARE_16(v4,v5,16) addi r5,r5,32 clrldi r6,r3,59 subfic r7,r6,32 add r3,r3,r7 add r4,r4,r7 subf r5,r7,r5 andi. r7,r4,0x1F beq cr0,L(32B_aligned_loop) .p2align 5 L(16B_aligned_loop): COMPARE_16(v4,v5,0) COMPARE_16(v4,v5,16) COMPARE_16(v4,v5,32) COMPARE_16(v4,v5,48) addi r3,r3,64 addi r4,r4,64 b L(16B_aligned_loop) /* Calculate and return the difference. */ L(different): TAIL_FIRST_16B(v4,v5) .p2align 5 L(32B_aligned_loop): COMPARE_32(v14,v16,0,tail1,tail2) COMPARE_32(v14,v16,32,tail1,tail2) COMPARE_32(v14,v16,64,tail1,tail2) COMPARE_32(v14,v16,96,tail1,tail2) addi r3,r3,128 addi r4,r4,128 b L(32B_aligned_loop) L(tail1): TAIL_FIRST_16B(v15,v17) L(tail2): TAIL_SECOND_16B(v14,v16) .p2align 5 L(ret0): li r3,0 blr END(STRNCMP) libc_hidden_builtin_def(strncmp)