<html>
<head>
<base href="https://bugs.freedesktop.org/">
</head>
<body>
<p>
<div>
<b><a class="bz_bug_link
bz_status_NEW "
title="NEW - i965/fs: copy propagate should propagate bitwise not into logic operations"
href="https://bugs.freedesktop.org/show_bug.cgi?id=89970#c5">Comment # 5</a>
on <a class="bz_bug_link
bz_status_NEW "
title="NEW - i965/fs: copy propagate should propagate bitwise not into logic operations"
href="https://bugs.freedesktop.org/show_bug.cgi?id=89970">bug 89970</a>
from <span class="vcard"><a class="email" href="mailto:idr@freedesktop.org" title="Ian Romanick <idr@freedesktop.org>"> <span class="fn">Ian Romanick</span></a>
</span></b>
<pre>(In reply to Ian Romanick from <a href="show_bug.cgi?id=89970#c4">comment #4</a>)
<span class="quote">> At the time, we generated intBitsToFloat(b & floatBitsToInt(1.0)) to do b2f
> conversions. Since b could only be 0 or -1, ~b & 0x38f00000 produces the
> same possible values as -b & 0x37f00000. However, we now emit float(-b)
> instead, so I don't think this can occur anymore.
>
> Maybe generating ~b & 0x3f800000 (BDW+) or -b & 0x38f00000 (SNB - HSW) for
> float(!b) is better? Right now there's a late optimization in
> nir_opt_algebraic that does this:
>
> (('b2f(is_used_more_than_once)', ('inot', a)), ('bcsel', a, 0.0, 1.0)),
> (('fneg(is_used_more_than_once)', ('b2f', ('inot', a))), ('bcsel', a,
> -0.0, -1.0)),
>
> In at least some cases, this results in some extra load-immediate
> instructions
>
> mov(16) g16<1>D 1065353216D
> mov.nz.f0(16) null<1>D g8<8,8,1>D
> (-f0) sel(16) g126<1>UD g16<8,8,1>UD 0x00000000UD
>
> Which also seems dumb. This should be
>
> mov.z.f0(16) null<1>D g8<8,8,1>D
> (-f0) sel(16) g126<1>F g8<8,8,1>F 1.0F</span >
Ignore this last part. That's rubbish.</pre>
</div>
</p>
<hr>
<span>You are receiving this mail because:</span>
<ul>
<li>You are the QA Contact for the bug.</li>
</ul>
</body>
</html>