<html><head><meta http-equiv="Content-Type" content="text/html charset=windows-1252"><base href="x-msg://321/"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><div>We want functions with integral-valued results (floor, ceil, round, rint, nearbyint, trunc) to get these transformations universally; because the result is always exactly representable, this transformation does not change the resulting values.</div><div><br></div><div>For functions that can return inexact results (cos, sin, pow, exp, log, etc), this should be defeatable. There are platforms with "skanky" math libraries that may have 10+ ulps of error in these single-precision routines; using the double-precision versions instead is a common idiom for developers to get better quality results.</div><div><br></div><div>The transform that I'm especially concerned about, is where the result is not casted back to float:</div><div><br></div><div><span class="Apple-tab-span" style="white-space:pre"> </span>func(floatval) --> (double)funcf(floatval)</div><div><br></div><div>this should simply not done for the inexact operations (it discards 29 bits of precision!), but is fine for the functions that produce integral results.</div><div><br></div><div>Someone who knows the guts here may have a better idea, but it seems to me that we should have two distinct optimizations (one for floor/ceil/round/etc, and one for cos/sin/pow/etc).</div><div><br></div><div>- Steve</div><br><div><div>On Aug 15, 2012, at 4:37 PM, Weiming Zhao <<a href="mailto:weimingz@codeaurora.org">weimingz@codeaurora.org</a>> wrote:</div><br class="Apple-interchange-newline"><blockquote type="cite"><div lang="EN-US" link="blue" vlink="purple" style="font-family: Helvetica; font-size: medium; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; "><div class="WordSection1" style="page: WordSection1; "><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; color: rgb(31, 73, 125); ">Hi Steve,<o:p></o:p></span></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; color: rgb(31, 73, 125); "> </span></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; color: rgb(31, 73, 125); ">Yes, it transforms (float)func((double) val) to funcf(v), which saves 2 conversions and possibly cheaper math function.<o:p></o:p></span></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; color: rgb(31, 73, 125); "> </span></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; color: rgb(31, 73, 125); ">GCC O1 does the same transformation. For LLVM, we can guard the transformations by flags like fast-math or a separate flag.<o:p></o:p></span></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; color: rgb(31, 73, 125); ">Furthermore, such transformation can be disabled by default. So it also solves the performance issue of double/single FP on some platforms.<o:p></o:p></span></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; color: rgb(31, 73, 125); "> </span></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; color: rgb(31, 73, 125); ">Thanks,<o:p></o:p></span></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; color: rgb(31, 73, 125); ">Weiming<o:p></o:p></span></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; color: rgb(31, 73, 125); "> </span></div><div><div style="border-style: solid none none; border-top-width: 1pt; border-top-color: rgb(181, 196, 223); padding: 3pt 0in 0in; "><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><b><span style="font-size: 10pt; font-family: Tahoma, sans-serif; ">From:</span></b><span style="font-size: 10pt; font-family: Tahoma, sans-serif; "><span class="Apple-converted-space"> </span>Stephen Canon [mailto:scanon@<a href="http://apple.com" style="color: purple; text-decoration: underline; ">apple.com</a>]<span class="Apple-converted-space"> </span><br><b>Sent:</b><span class="Apple-converted-space"> </span>Wednesday, August 15, 2012 11:54 AM<br><b>To:</b><span class="Apple-converted-space"> </span>Weiming Zhao<br><b>Cc:</b><span class="Apple-converted-space"> </span><a href="mailto:llvm-commits@cs.uiuc.edu" style="color: purple; text-decoration: underline; ">llvm-commits@cs.uiuc.edu</a><br><b>Subject:</b><span class="Apple-converted-space"> </span>Re: [llvm-commits] Fix Bug 13574: Add more double float shrinking optimizations<o:p></o:p></span></div></div></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><o:p> </o:p></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; ">Do I understand correctly that this optimization would transform cos((double)floatval) --> (double)cosf(floatval)? That's not a acceptable transformation, numerically.<o:p></o:p></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><o:p> </o:p></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; ">One should also consider that there are a number of platforms supported by LLVM (not naming names) on which the float variants of libm functions are significantly *slower* than the double-precision variants.<o:p></o:p></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><o:p> </o:p></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; ">- Steve<o:p></o:p></div></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><o:p> </o:p></div><div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; ">On Aug 15, 2012, at 2:33 PM, Weiming Zhao <<a href="mailto:weimingz@codeaurora.org" style="color: purple; text-decoration: underline; ">weimingz@codeaurora.org</a>> wrote:<o:p></o:p></div></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><br><br><o:p></o:p></div><div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; ">Hi,<o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; "> <o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; ">This patch fixes<span class="apple-converted-space"> </span><a href="http://llvm.org/bugs/show_bug.cgi?id=13574" style="color: purple; text-decoration: underline; "><span style="color: purple; ">http://llvm.org/bugs/show_bug.cgi?id=13574</span></a><o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; "> <o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 9pt; font-family: Arial, sans-serif; ">Current LLVM only supports 5 double->float shrinking optimizations (floor->floorf, ceil->ceilf,round->roundf, rint->rintf() and nearbyint->nearbyintf).</span><span style="font-size: 11pt; font-family: Calibri, sans-serif; "><o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 9pt; font-family: Arial, sans-serif; "> </span><span style="font-size: 11pt; font-family: Calibri, sans-serif; "><o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 9pt; font-family: Arial, sans-serif; ">This patch adds more math functions, for example, pow->powf, sin->sinf, cos->cosf, etc.</span><span style="font-size: 11pt; font-family: Calibri, sans-serif; "><o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 9pt; font-family: Arial, sans-serif; "> </span><span style="font-size: 11pt; font-family: Calibri, sans-serif; "><o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 9pt; font-family: Arial, sans-serif; ">In this patch:</span><span style="font-size: 11pt; font-family: Calibri, sans-serif; "><o:p></o:p></span></div></div><div style="margin-left: 0.5in; "><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; text-indent: -0.25in; "><span style="font-size: 9pt; font-family: Arial, sans-serif; ">1.</span><span style="font-size: 7pt; "> <span class="apple-converted-space"> </span></span><span style="font-size: 9pt; font-family: Arial, sans-serif; ">Since cos(), pow() and exp2() already have their own optimizers: CosPot, PowOpt and Exp2Opt, respectively, I let them inherit from UnaryDoubleFPOpt and in their CallOptimizer(), I let them to call the base class’s CallOptimizer() first.</span><span style="font-size: 11pt; font-family: Calibri, sans-serif; "><o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 9pt; font-family: Arial, sans-serif; ">For this change, I have to hoist the definition of UnaryDoubleFPOpt ahead of CosOpt.</span><span style="font-size: 11pt; font-family: Calibri, sans-serif; "><o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 9pt; font-family: Arial, sans-serif; "> </span><span style="font-size: 11pt; font-family: Calibri, sans-serif; "><o:p></o:p></span></div></div><div style="margin-left: 0.5in; "><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; text-indent: -0.25in; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; ">2.</span><span style="font-size: 7pt; "> <span class="apple-converted-space"> </span></span><span style="font-size: 11pt; font-family: Calibri, sans-serif; ">Since some functions are not available on Windows, I updated TargetLibraryInfo to mark them as unavailable.<o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; "> <o:p></o:p></span></div></div><div style="margin-left: 0.5in; "><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; text-indent: -0.25in; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; ">3.</span><span style="font-size: 7pt; "> <span class="apple-converted-space"> </span></span><span style="font-size: 11pt; font-family: Calibri, sans-serif; ">A unit test case is updated to test this patch.<o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; "> <o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; ">Please help to review them.<o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; "> <o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; ">Thanks,<o:p></o:p></span></div></div><div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 11pt; font-family: Calibri, sans-serif; ">Weiming<o:p></o:p></span></div></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><span style="font-size: 13.5pt; font-family: Helvetica, sans-serif; "><0001-Bug-13574-More-double-float-shrinking-optimizations-f.patch>_______________________________________________<br>llvm-commits mailing list<br><a href="mailto:llvm-commits@cs.uiuc.edu" style="color: purple; text-decoration: underline; "><span style="color: purple; ">llvm-commits@cs.uiuc.edu</span></a><br><a href="http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits" style="color: purple; text-decoration: underline; "><span style="color: purple; ">http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits</span></a><o:p></o:p></span></div></div></div><div style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: 'Times New Roman', serif; "><o:p> </o:p></div></div></div></blockquote></div><br></body></html>