<div>Hi,</div>
<div> </div>
<div>I don't have any real numbers right now, but it takes roughly a minute on a 10MHz OpenRISC CPU, so it seems something is up</div>
<div> </div>
<div>//Olof<br><br></div>
<div class="gmail_quote">2011/3/15 Matt Johnston <span dir="ltr"><<a href="mailto:matt@ucc.asn.au">matt@ucc.asn.au</a>></span><br>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">
<div class="im">On Tue, Mar 15, 2011 at 02:02:54PM +0100, Magnus Nilsson wrote:<br>> Sorry, I was unclear - it's only 100% busy during those 45s.<br></div>
<div class="im">> My question is:<br>> Is 45s reasonable on a 192MHz cpu, or do you think I might have some<br>> issue with my compilation options (see my first post,<br>> <a href="http://hi.baidu.com/kkernel/blog/item/ff919681141beddebc3e1e23.html" target="_blank">http://hi.baidu.com/kkernel/blog/item/ff919681141beddebc3e1e23.html</a><br>
> but with --disable-shadow) or something?<br>> Anyone who has similar experiences? Or the opposite, someone who's<br>> running it on a low-end system without this issue?<br><br></div>I haven't tried anything quite that low-end, but the couple<br>
of MIPS routers I've tried at ~400mhz take about 1 second<br>for that step. I guess there could be something odd about<br>the architecture that interacts badly with what libtommath<br>is doing, or perhaps the compiler. The binary was built with<br>
optimisation enabled?<br><br>Cheers,<br><font color="#888888">Matt<br></font></blockquote></div><br>