| /* SPDX-License-Identifier: GPL-2.0 */ |
| /* |
| * arch/alpha/lib/ev67-strlen.S |
| * 21264 version by Rick Gorton <rick.gorton@alpha-processor.com> |
| * |
| * Finds length of a 0-terminated string. Optimized for the |
| * Alpha architecture: |
| * |
| * - memory accessed as aligned quadwords only |
| * - uses bcmpge to compare 8 bytes in parallel |
| * |
| * Much of the information about 21264 scheduling/coding comes from: |
| * Compiler Writer's Guide for the Alpha 21264 |
| * abbreviated as 'CWG' in other comments here |
| * ftp.digital.com/pub/Digital/info/semiconductor/literature/dsc-library.html |
| * Scheduling notation: |
| * E - either cluster |
| * U - upper subcluster; U0 - subcluster U0; U1 - subcluster U1 |
| * L - lower subcluster; L0 - subcluster L0; L1 - subcluster L1 |
| */ |
| #include <asm/export.h> |
| .set noreorder |
| .set noat |
| |
| .globl strlen |
| .ent strlen |
| .align 4 |
| strlen: |
| ldq_u $1, 0($16) # L : load first quadword ($16 may be misaligned) |
| lda $2, -1($31) # E : |
| insqh $2, $16, $2 # U : |
| andnot $16, 7, $0 # E : |
| |
| or $2, $1, $1 # E : |
| cmpbge $31, $1, $2 # E : $2 <- bitmask: bit i == 1 <==> i-th byte == 0 |
| nop # E : |
| bne $2, $found # U : |
| |
| $loop: ldq $1, 8($0) # L : |
| addq $0, 8, $0 # E : addr += 8 |
| cmpbge $31, $1, $2 # E : |
| beq $2, $loop # U : |
| |
| $found: |
| cttz $2, $3 # U0 : |
| addq $0, $3, $0 # E : |
| subq $0, $16, $0 # E : |
| ret $31, ($26) # L0 : |
| |
| .end strlen |
| EXPORT_SYMBOL(strlen) |