<div dir="ltr">Hi Tim,<div><br></div><div>Thanks for your reply.</div><div class="gmail_extra"><br><div class="gmail_quote">On Mon, Nov 10, 2014 at 1:26 PM, Tim Northover <span dir="ltr"><<a href="mailto:t.p.northover@gmail.com" target="_blank">t.p.northover@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">Hi Ray,<br>
<div><div class="h5"><br>
On 10 November 2014 10:13, Alex S <<a href="mailto:alexmountain13@gmail.com">alexmountain13@gmail.com</a>> wrote:<br>
> Sorry for bothering those not interested. I found that ARM backend will<br>
> insert a modulo function<br>
> (like __modsi3) instead of the modulo instruction. I wonder how we can<br>
> inline the modulo function<br>
> into the program. Is there any OPTION we can use in the opt or llc?<br>
<br>
</div></div>It depends on whether the CPU actually supports integer division.<br>
Surprisingly modern CPUs don't (the Cortex-A9 for example), and LLVM<br>
doesn't synthesise an entire divide loop.<br></blockquote><div><br></div><div><br></div><div>I know this may degrade the performance. I wonder whether there is any easy</div><div>way to inline these functions into the callsite? Thanks again!</div><div><br></div><div><br></div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
<br>
Oddly, it also seems to call the library at -O0, because that's what<br>
the FastISel decides to do. That strikes me as a bug, or at least an<br>
oddity.<br>
<br>
Cheers.<br>
<span class=""><font color="#888888"><br>
Tim.<br></font></span></blockquote><div><br></div><div>Ray </div></div><br></div></div>