| ev67-strlen.S (e5451c8f8330e03ad3cfa16048b4daf961af434f) | ev67-strlen.S (00fc0e0dda6286407f3854cd71a125f519a5689c) |
|---|---|
| 1/* 2 * arch/alpha/lib/ev67-strlen.S 3 * 21264 version by Rick Gorton <rick.gorton@alpha-processor.com> 4 * 5 * Finds length of a 0-terminated string. Optimized for the 6 * Alpha architecture: 7 * 8 * - memory accessed as aligned quadwords only 9 * - uses bcmpge to compare 8 bytes in parallel 10 * 11 * Much of the information about 21264 scheduling/coding comes from: 12 * Compiler Writer's Guide for the Alpha 21264 13 * abbreviated as 'CWG' in other comments here 14 * ftp.digital.com/pub/Digital/info/semiconductor/literature/dsc-library.html 15 * Scheduling notation: 16 * E - either cluster 17 * U - upper subcluster; U0 - subcluster U0; U1 - subcluster U1 18 * L - lower subcluster; L0 - subcluster L0; L1 - subcluster L1 19 */ | 1/* 2 * arch/alpha/lib/ev67-strlen.S 3 * 21264 version by Rick Gorton <rick.gorton@alpha-processor.com> 4 * 5 * Finds length of a 0-terminated string. Optimized for the 6 * Alpha architecture: 7 * 8 * - memory accessed as aligned quadwords only 9 * - uses bcmpge to compare 8 bytes in parallel 10 * 11 * Much of the information about 21264 scheduling/coding comes from: 12 * Compiler Writer's Guide for the Alpha 21264 13 * abbreviated as 'CWG' in other comments here 14 * ftp.digital.com/pub/Digital/info/semiconductor/literature/dsc-library.html 15 * Scheduling notation: 16 * E - either cluster 17 * U - upper subcluster; U0 - subcluster U0; U1 - subcluster U1 18 * L - lower subcluster; L0 - subcluster L0; L1 - subcluster L1 19 */ |
| 20 | 20#include <asm/export.h> |
| 21 .set noreorder 22 .set noat 23 24 .globl strlen 25 .ent strlen 26 .align 4 27strlen: 28 ldq_u $1, 0($16) # L : load first quadword ($16 may be misaligned) --- 13 unchanged lines hidden (view full) --- 42 43$found: 44 cttz $2, $3 # U0 : 45 addq $0, $3, $0 # E : 46 subq $0, $16, $0 # E : 47 ret $31, ($26) # L0 : 48 49 .end strlen | 21 .set noreorder 22 .set noat 23 24 .globl strlen 25 .ent strlen 26 .align 4 27strlen: 28 ldq_u $1, 0($16) # L : load first quadword ($16 may be misaligned) --- 13 unchanged lines hidden (view full) --- 42 43$found: 44 cttz $2, $3 # U0 : 45 addq $0, $3, $0 # E : 46 subq $0, $16, $0 # E : 47 ret $31, ($26) # L0 : 48 49 .end strlen |
| 50 EXPORT_SYMBOL(strlen) |
|