Handle negative strides much more optimally. This compiles X86/lsr-negative-stride.ll

into:

_t:
        movl 8(%esp), %ecx
        movl 4(%esp), %eax
        cmpl %ecx, %eax
        je LBB1_3       #bb17
LBB1_1: #bb
        cmpl %ecx, %eax
        jg LBB1_4       #cond_true
LBB1_2: #cond_false
        subl %eax, %ecx
        cmpl %ecx, %eax
        jne LBB1_1      #bb
LBB1_3: #bb17
        ret
LBB1_4: #cond_true
        subl %ecx, %eax
        cmpl %ecx, %eax
        jne LBB1_1      #bb
        jmp LBB1_3      #bb17

instead of:

_t:
        subl $4, %esp
        movl %esi, (%esp)
        movl 12(%esp), %ecx
        movl 8(%esp), %eax
        cmpl %ecx, %eax
        je LBB1_4       #bb17
LBB1_1: #bb.outer
        movl %ecx, %edx
        negl %edx
LBB1_2: #bb
        cmpl %ecx, %eax
        jle LBB1_5      #cond_false
LBB1_3: #cond_true
        addl %edx, %eax
        cmpl %ecx, %eax
        jne LBB1_2      #bb
LBB1_4: #bb17
        movl (%esp), %esi
        addl $4, %esp
        ret
LBB1_5: #cond_false
        movl %ecx, %edx
        subl %eax, %edx
        movl %eax, %esi
        addl %esi, %esi
        cmpl %ecx, %esi
        je LBB1_4       #bb17
LBB1_6: #cond_false.bb.outer_crit_edge
        movl %edx, %ecx
        jmp LBB1_1      #bb.outer

llvm-svn: 37252