The following has always proven to be fairly efficient for me:
return (a < b) ? -1 : (a > b);
With gcc -O2 -S
, this compiles down to the following five instructions:
xorl %edx, %edx
cmpl %esi, %edi
movl $-1, %eax
setg %dl
cmovge %edx, %eax
As a follow-up to Ambroz Bizjak's excellent companion answer, I was not convinced that his program tested the same assembly code what was posted above. And, when I was studying the compiler output more closely, I noticed that the compiler was not generating the same instructions as was posted in either of our answers. So, I took his test program, hand modified the assembly output to match what we posted, and compared the resulting times. It seems the two versions compare roughly identically.
./opt_cmp_branchless: 0m1.070s
./opt_cmp_branch: 0m1.037s
I am posting the assembly of each program in full so that others may attempt the same experiment, and confirm or contradict my observation.
The following is the version with the cmovge
instruction ((a < b) ? -1 : (a > b)
):
.file "cmp.c"
.text
.section .rodata.str1.1,"aMS",@progbits,1
.LC0:
.string "%d=0\n"
.text
.p2align 4,,15
.globl main
.type main, @function
main:
.LFB20:
.cfi_startproc
pushq %rbp
.cfi_def_cfa_offset 16
.cfi_offset 6, -16
pushq %rbx
.cfi_def_cfa_offset 24
.cfi_offset 3, -24
movl $arr.2789, %ebx
subq $8, %rsp
.cfi_def_cfa_offset 32
.L9:
leaq 4(%rbx), %rbp
.L10:
call rand
movb %al, (%rbx)
addq $1, %rbx
cmpq %rbx, %rbp
jne .L10
cmpq $arr.2789+4096, %rbp
jne .L9
xorl %r8d, %r8d
xorl %esi, %esi
orl $-1, %edi
.L12:
xorl %ebp, %ebp
.p2align 4,,10
.p2align 3
.L18:
movl arr.2789(%rbp), %ecx
xorl %eax, %eax
.p2align 4,,10
.p2align 3
.L15:
movl arr.2789(%rax), %edx
xorl %ebx, %ebx
cmpl %ecx, %edx
movl $-1, %edx
setg %bl
cmovge %ebx, %edx
addq $4, %rax
addl %edx, %esi
cmpq $4096, %rax
jne .L15
addq $4, %rbp
cmpq $4096, %rbp
jne .L18
addl $1, %r8d
cmpl $500, %r8d
jne .L12
movl $.LC0, %edi
xorl %eax, %eax
call printf
addq $8, %rsp
.cfi_def_cfa_offset 24
xorl %eax, %eax
popq %rbx
.cfi_def_cfa_offset 16
popq %rbp
.cfi_def_cfa_offset 8
ret
.cfi_endproc
.LFE20:
.size main, .-main
.local arr.2789
.comm arr.2789,4096,32
.section .note.GNU-stack,"",@progbits
The version below uses the branchless method ((a > b) - (a < b)
):
.file "cmp.c"
.text
.section .rodata.str1.1,"aMS",@progbits,1
.LC0:
.string "%d=0\n"
.text
.p2align 4,,15
.globl main
.type main, @function
main:
.LFB20:
.cfi_startproc
pushq %rbp
.cfi_def_cfa_offset 16
.cfi_offset 6, -16
pushq %rbx
.cfi_def_cfa_offset 24
.cfi_offset 3, -24
movl $arr.2789, %ebx
subq $8, %rsp
.cfi_def_cfa_offset 32
.L9:
leaq 4(%rbx), %rbp
.L10:
call rand
movb %al, (%rbx)
addq $1, %rbx
cmpq %rbx, %rbp
jne .L10
cmpq $arr.2789+4096, %rbp
jne .L9
xorl %r8d, %r8d
xorl %esi, %esi
.L19:
movl %ebp, %ebx
xorl %edi, %edi
.p2align 4,,10
.p2align 3
.L24:
movl %ebp, %ecx
xorl %eax, %eax
jmp .L22
.p2align 4,,10
.p2align 3
.L20:
movl arr.2789(%rax), %ecx
.L22:
xorl %edx, %edx
cmpl %ebx, %ecx
setg %cl
setl %dl
movzbl %cl, %ecx
subl %ecx, %edx
addl %edx, %esi
addq $4, %rax
cmpq $4096, %rax
jne .L20
addq $4, %rdi
cmpq $4096, %rdi
je .L21
movl arr.2789(%rdi), %ebx
jmp .L24
.L21:
addl $1, %r8d
cmpl $500, %r8d
jne .L19
movl $.LC0, %edi
xorl %eax, %eax
call printf
addq $8, %rsp
.cfi_def_cfa_offset 24
xorl %eax, %eax
popq %rbx
.cfi_def_cfa_offset 16
popq %rbp
.cfi_def_cfa_offset 8
ret
.cfi_endproc
.LFE20:
.size main, .-main
.local arr.2789
.comm arr.2789,4096,32
.section .note.GNU-stack,"",@progbits