<html><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
Chihong,<div> I notice that IEEE-754-2008 does in fact define a 16-bit floating point standard now, </div><div>does your processor conform to that standard, if so there should be no objection to adding fp16 to LLVM</div><div>and you should have no problem using it, at least that's what I think Chris is trying to say (?).</div><div><br></div><div><br></div><div>IEEE-754-2008 fp16: 1-bit sign, 5-bit exponent, 10-bit fraction</div><div><br></div><div>largest ~~ 2^16 (65504), smallest ~~ 2^-14 (0.000,061).</div><div><br></div><div><br></div><div>uses the same exponent interpretation as other formats</div><div>0 --> +/-zero or denorm, MAX --> +/-infinity or not-a-number,</div><div><br></div><div>and (I presume) expects IEEE round-to-nearest-even to be the default rounding mode,</div><div><br></div><div><br></div><div>-Peter Lawrence.</div><div><br></div><div><br></div><div><br></div><div><div><div>On Mar 22, 2011, at 1:23 PM, <a href="mailto:llvmdev-request@cs.uiuc.edu">llvmdev-request@cs.uiuc.edu</a> wrote:</div><br class="Apple-interchange-newline"><blockquote type="cite"><p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Monaco" size="3" style="font: 12.0px Monaco">On Mar 21, 2011, at 1:59 PM, Zhang, Chihong wrote:</font></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px; font: 12.0px Monaco; min-height: 16.0px"><br></p> <blockquote type="cite"><p style="margin: 0.0px 0.0px 0.0px 10.0px"><font face="Monaco" size="3" style="font: 12.0px Monaco">Hi Chris,</font></p> <p style="margin: 0.0px 0.0px 0.0px 10.0px; font: 12.0px Monaco; min-height: 16.0px"><br></p> <p style="margin: 0.0px 0.0px 0.0px 10.0px"><font face="Monaco" size="3" style="font: 12.0px Monaco">It is important for embedded/mobile computation to have efficient fp16 support, otherwise those users will suffer from the merging problem with their local LLVM with native fp16 type they add (locally). So we should either add full fp16 support as a basic floating point type or enhance the LLVM infrastructure to make floating point type as scalable as int type.</font></p> </blockquote><p style="margin: 0.0px 0.0px 0.0px 0.0px; font: 12.0px Monaco; min-height: 16.0px"><br></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Monaco" size="3" style="font: 12.0px Monaco">As I've said several times now :), I'm ok with having fp16 as a native LLVM type so long as there is hardware that implements fp16 arithmetic operations like add and sub with correct fp16 rounding etc.</font></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px; font: 12.0px Monaco; min-height: 16.0px"><br></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Monaco" size="3" style="font: 12.0px Monaco">-Chris</font></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px; font: 12.0px Monaco; min-height: 16.0px"><br></p> <blockquote type="cite"><p style="margin: 0.0px 0.0px 0.0px 10.0px; font: 12.0px Monaco; min-height: 16.0px"><br></p> <p style="margin: 0.0px 0.0px 0.0px 10.0px; font: 12.0px Monaco; min-height: 16.0px"><br></p> <p style="margin: 0.0px 0.0px 0.0px 10.0px"><font face="Monaco" size="3" style="font: 12.0px Monaco">-Chihong</font></p> </blockquote></blockquote></div><br></div></body></html>