gcc generates suboptimal code for tight loops

[Ondřej Bílka]

Consider following loop.

int recal(int *x){int i;
  for(i=0;;i+=4){
    if(__builtin_expect((x[i]|x[i+1])|(x[i+2]|x[i+3]),0))
      break;
  }
  return (x[i]|x[i+1])*(x[i+2]|x[i+3]);
}

On x64 orl instruction is destructive. Gcc saves intermediate result to
register instead recalculating it at end of loop, making loop run slower. 

Relevant assembly output is following
gcc-4.7 -O3 -S
	.file	"recal.c"
	.text
	.p2align 4,,15
	.globl	recal
	.type	recal, @function
recal:
.LFB0:
	.cfi_startproc
	movl	12(%rdi), %edx
	orl	8(%rdi), %edx
	movl	4(%rdi), %ecx
	orl	(%rdi), %ecx
	movl	%edx, %eax
	orl	%ecx, %eax
	jne	.L2
	leaq	16(%rdi), %rax
	.p2align 4,,10
	.p2align 3
.L3:
	movl	12(%rax), %edx
	orl	8(%rax), %edx
	movl	4(%rax), %ecx
	orl	(%rax), %ecx
	addq	$16, %rax
	movl	%edx, %esi
	orl	%ecx, %esi
	je	.L3
.L2:
	movl	%ecx, %eax
	imull	%edx, %eax
	ret
	.cfi_endproc
.LFE0:
	.size	recal, .-recal
	.ident	"GCC: (Debian 4.7.1-2) 4.7.1"
	.section	.note.GNU-stack,"",@progbits
-- 

Evil dogs hypnotised the night shift