diff options
Diffstat (limited to 'libc/string/x86_64/strcspn.S')
| -rw-r--r-- | libc/string/x86_64/strcspn.S | 12 |
1 files changed, 10 insertions, 2 deletions
diff --git a/libc/string/x86_64/strcspn.S b/libc/string/x86_64/strcspn.S index 9563de496..fd9b09c48 100644 --- a/libc/string/x86_64/strcspn.S +++ b/libc/string/x86_64/strcspn.S @@ -55,7 +55,9 @@ ENTRY (strcspn) Although all the following instruction only modify %cl we always have a correct zero-extended 64-bit value in %rcx. */ - .p2align 4 + /* Next 3 insns are 6 bytes total, make sure we decode them in one go */ + .p2align 3,,6 + L(2): movb (%rax), %cl /* get byte from skipset */ testb %cl, %cl /* is NUL char? */ jz L(1) /* yes => start compare loop */ @@ -88,7 +90,13 @@ L(1): leaq -4(%rdx), %rax /* prepare loop */ value in the table. But the value of NUL is NUL so the loop terminates for NUL in every case. */ - .p2align 4 + /* Next 3 insns are 9 bytes total. */ + /* .p2align 4,,9 would make sure we decode them in one go, */ + /* but it will also align entire function to 16 bytes, */ + /* potentially creating largish padding at link time. */ + /* We are aligning to 8 bytes instead: */ + .p2align 3,,8 + L(3): addq $4, %rax /* adjust pointer for full loop round */ movb (%rax), %cl /* get byte from string */ |