On Fri, Apr 16, 2021 at 12:24:13PM -0700, Eric Dumazet wrote:
> From: Eric Dumazet <eduma...@google.com>
>
> We have to loop only to copy u64 values.
> After this first loop, we copy at most one u32, one u16 and one byte.
Does it actually yield a better code?
FWIW, this
void bar(unsigned);
void foo(unsigned n)
{
while (n >= 8) {
bar(n);
n -= 8;
}
while (n >= 4) {
bar(n);
n -= 4;
}
while (n >= 2) {
bar(n);
n -= 2;
}
while (n >= 1) {
bar(n);
n -= 1;
}
}
will compile (with -O2) to
pushq %rbp
pushq %rbx
movl %edi, %ebx
subq $8, %rsp
cmpl $7, %edi
jbe .L2
movl %edi, %ebp
.L3:
movl %ebp, %edi
subl $8, %ebp
call bar@PLT
cmpl $7, %ebp
ja .L3
andl $7, %ebx
.L2:
cmpl $3, %ebx
jbe .L4
movl %ebx, %edi
andl $3, %ebx
call bar@PLT
.L4:
cmpl $1, %ebx
jbe .L5
movl %ebx, %edi
andl $1, %ebx
call bar@PLT
.L5:
testl %ebx, %ebx
je .L1
addq $8, %rsp
movl $1, %edi
popq %rbx
popq %rbp
jmp bar@PLT
.L1:
addq $8, %rsp
popq %rbx
popq %rbp
ret
i.e. loop + if + if + if...
